aboutsummaryrefslogtreecommitdiff
path: root/tests/test-aes-key-wrap.c
blob: cebdcc7c18440b0022c8505e2a42e4de40d48f48 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
/*
 * test-aes-key-wrap.c
 * -------------------
 * Test code for AES Key Wrap.
 *
 * Authors: Rob Austein
 * Copyright (c) 2015, SUNET
 *
 * Redistribution and use in source and binary forms, with or
 * without modification, are permitted provided that the following
 * conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
 * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <assert.h>

#include <cryptech.h>

#ifndef TC_BUFSIZE
#define TC_BUFSIZE      4096
#endif

/*
 * Test cases from RFC 5649 all use a 192-bit key, which our AES
 * implementation doesn't support, so had to write our own.
 */

static const uint8_t Q[] = { /* Plaintext, 81 bytes */
  0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x21, 0x20, 0x20, 0x4d, 0x79, 0x20, 0x6e,
  0x61, 0x6d, 0x65, 0x20, 0x69, 0x73, 0x20, 0x49, 0x6e, 0x69, 0x67, 0x6f,
  0x20, 0x4d, 0x6f, 0x6e, 0x74, 0x6f, 0x79, 0x61, 0x2e, 0x20, 0x20, 0x59,
  0x6f, 0x75, 0x20, 0x62, 0x72, 0x6f, 0x6b, 0x65, 0x20, 0x6d, 0x79, 0x20,
  0x41, 0x45, 0x53, 0x20, 0x6b, 0x65, 0x79, 0x20, 0x77, 0x72, 0x61, 0x70,
  0x70, 0x65, 0x72, 0x2e, 0x20, 0x20, 0x50, 0x72, 0x65, 0x70, 0x61, 0x72,
  0x65, 0x20, 0x74, 0x6f, 0x20, 0x64, 0x69, 0x65, 0x2e
};

static const uint8_t K_128[] = { /* 128-bit KEK, 16 bytes */
  0xbc, 0x2a, 0xd8, 0x90, 0xd8, 0x91, 0x10, 0x65, 0xf0, 0x42, 0x10, 0x1b,
  0x4a, 0x6b, 0xaf, 0x99
};

static const uint8_t K_256[] = { /* 256-bit KEK, 32 bytes */
  0xe3, 0x97, 0x52, 0x81, 0x2b, 0x7e, 0xc2, 0xa4, 0x6a, 0xac, 0x50, 0x18,
  0x0d, 0x10, 0xc6, 0x85, 0x2c, 0xcf, 0x86, 0x0a, 0xa9, 0x4f, 0x69, 0xab,
  0x16, 0xa6, 0x4f, 0x3e, 0x96, 0xa0, 0xbd, 0x9e
};

static const uint8_t C_128[] = { /* Plaintext wrapped by 128-bit KEK, 96 bytes */
  0xb0, 0x10, 0x91, 0x7b, 0xe7, 0x67, 0x9c, 0x10, 0x16, 0x64, 0xe7, 0x73,
  0xd2, 0x68, 0xba, 0xed, 0x8c, 0x50, 0x49, 0x80, 0x16, 0x2f, 0x4e, 0x97,
  0xe8, 0x45, 0x5c, 0x2f, 0x2b, 0x7a, 0x88, 0x0e, 0xd8, 0xef, 0xaa, 0x40,
  0xb0, 0x2e, 0xb4, 0x50, 0xe7, 0x60, 0xf7, 0xbb, 0xed, 0x56, 0x79, 0x16,
  0x65, 0xb7, 0x13, 0x9b, 0x4c, 0x66, 0x86, 0x5f, 0x4d, 0x53, 0x2d, 0xcd,
  0x83, 0x41, 0x01, 0x35, 0x0d, 0x06, 0x39, 0x4e, 0x9e, 0xfe, 0x68, 0xc5,
  0x2f, 0x37, 0x33, 0x99, 0xbb, 0x88, 0xf7, 0x76, 0x1e, 0x82, 0x48, 0xd6,
  0xa2, 0xf3, 0x9b, 0x92, 0x01, 0x65, 0xcb, 0x48, 0x36, 0xf5, 0x42, 0xd3
};

static const uint8_t C_256[] = { /* Plaintext wrapped by 256-bit KEK, 96 bytes */
  0x08, 0x00, 0xbc, 0x1b, 0x35, 0xe4, 0x2a, 0x69, 0x3f, 0x43, 0x07, 0x54,
  0x31, 0xba, 0xb6, 0x89, 0x7c, 0x64, 0x9f, 0x03, 0x84, 0xc4, 0x4a, 0x71,
  0xdb, 0xcb, 0xae, 0x55, 0x30, 0xdf, 0xb0, 0x2b, 0xc3, 0x91, 0x5d, 0x07,
  0xa9, 0x24, 0xdb, 0xe7, 0xbe, 0x4d, 0x0d, 0x62, 0xd4, 0xf8, 0xb1, 0x94,
  0xf1, 0xb9, 0x22, 0xb5, 0x94, 0xab, 0x7e, 0x0b, 0x15, 0x6a, 0xd9, 0x5f,
  0x6c, 0x20, 0xb7, 0x7e, 0x13, 0x19, 0xfa, 0xc4, 0x70, 0xec, 0x0d, 0xbd,
  0xf7, 0x01, 0xc6, 0xb3, 0x9a, 0x19, 0xaf, 0xf2, 0x47, 0x68, 0xea, 0x7e,
  0x97, 0x7e, 0x52, 0x2e, 0xd4, 0x03, 0x31, 0xcb, 0x22, 0xb6, 0xfe, 0xf5
};

static const char *format_hex(const uint8_t *bin, const size_t len, char *hex, const size_t max)
{
  size_t i;

  assert(bin != NULL && hex != NULL && len * 3 < max);

  if (len == 0)
    return "";

  for (i = 0; i < len; i++)
    sprintf(hex + 3 * i, "%02x:", bin[i]);

  hex[len * 3 - 1] = '\0';
  return hex;
}

static int run_test(const uint8_t * const K, const size_t K_len,
                    const uint8_t * const C, const size_t C_len)
{
  const size_t Q_len = sizeof(Q);
  uint8_t q[TC_BUFSIZE], c[TC_BUFSIZE];
  size_t q_len = sizeof(q), c_len = sizeof(c);
  char h1[TC_BUFSIZE * 3 + 1],  h2[TC_BUFSIZE * 3 + 1];
  hal_error_t err;
  int ok1 = 1, ok2 = 1;

  /*
   * Wrap and compare results.
   */

  printf("Wrapping with %lu-bit KEK...\n", (unsigned long) K_len * 8);
  if ((err = hal_aes_keywrap(K, K_len, Q, Q_len, c, &c_len)) != HAL_OK) {
    printf("Couldn't wrap with %lu-bit KEK: %s\n",
           (unsigned long) K_len * 8, hal_error_string(err));
    ok1 = 0;
  }
  else if (C_len != c_len || memcmp(C, c, C_len) != 0) {
    printf("Ciphertext mismatch:\n  Want: %s\n  Got:  %s\n",
           format_hex(C, C_len, h1, sizeof(h1)),
           format_hex(c, c_len, h2, sizeof(h2)));
    ok1 = 0;
  }
  else {
    printf("OK\n");
  }

  /*
   * Unwrap and compare results.
   */

  printf("Unwrapping with %lu-bit KEK...\n", (unsigned long) K_len * 8);
  if ((err = hal_aes_keyunwrap(K, K_len, C, C_len, q, &q_len)) != HAL_OK) {
    printf("Couldn't unwrap with %lu-bit KEK: %s\n",
           (unsigned long) K_len * 8, hal_error_string(err));
    ok2 = 0;
  }
  else if (Q_len != q_len || memcmp(Q, q, Q_len) != 0) {
    printf("Plaintext mismatch:\n  Want: %s\n  Got:  %s\n",
           format_hex(Q, Q_len, h1, sizeof(h1)),
           format_hex(q, q_len, h2, sizeof(h2)));
    ok2 = 0;
  }
  else {
    printf("OK\n");
  }

  return ok1 && ok2;
}

int main (int argc, char *argv[])
{
  int failures = 0;

  printf("Testing whether AES core reports present...");
  if (hal_io_expected(AES_ADDR_NAME0, (const uint8_t *) (AES_CORE_NAME0 AES_CORE_NAME1), 8) != HAL_OK) {
    printf("no, skipping keywrap tests\n");
  }

  else {
    printf("yes\n");
    if (!run_test(K_128, sizeof(K_128), C_128, sizeof(C_128)))
      failures++;
    if (!run_test(K_256, sizeof(K_256), C_256, sizeof(C_256)))
      failures++;
  }

  return failures;
}

/*
 * "Any programmer who fails to comply with the standard naming, formatting,
 *  or commenting conventions should be shot.  If it so happens that it is
 *  inconvenient to shoot him, then he is to be politely requested to recode
 *  his program in adherence to the above standard."
 *                      -- Michael Spier, Digital Equipment Corporation
 *
 * Local variables:
 * indent-tabs-mode: nil
 * End:
 */
1'>1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556
/* ----------------------------------------------------------------------
* Copyright (C) 2010-2015 ARM Limited. All rights reserved.
*
* $Date:        19. March 2015
* $Revision: 	V.1.4.5
*
* Project: 	    CMSIS DSP Library
* Title:	    arm_math.h
*
* Description:	Public header file for CMSIS DSP Library
*
* Target Processor: Cortex-M7/Cortex-M4/Cortex-M3/Cortex-M0
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*   - Redistributions of source code must retain the above copyright
*     notice, this list of conditions and the following disclaimer.
*   - Redistributions in binary form must reproduce the above copyright
*     notice, this list of conditions and the following disclaimer in
*     the documentation and/or other materials provided with the
*     distribution.
*   - Neither the name of ARM LIMITED nor the names of its contributors
*     may be used to endorse or promote products derived from this
*     software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
 * -------------------------------------------------------------------- */

/**
   \mainpage CMSIS DSP Software Library
   *
   * Introduction
   * ------------
   *
   * This user manual describes the CMSIS DSP software library,
   * a suite of common signal processing functions for use on Cortex-M processor based devices.
   *
   * The library is divided into a number of functions each covering a specific category:
   * - Basic math functions
   * - Fast math functions
   * - Complex math functions
   * - Filters
   * - Matrix functions
   * - Transforms
   * - Motor control functions
   * - Statistical functions
   * - Support functions
   * - Interpolation functions
   *
   * The library has separate functions for operating on 8-bit integers, 16-bit integers,
   * 32-bit integer and 32-bit floating-point values.
   *
   * Using the Library
   * ------------
   *
   * The library installer contains prebuilt versions of the libraries in the <code>Lib</code> folder.
   * - arm_cortexM7lfdp_math.lib (Little endian and Double Precision Floating Point Unit on Cortex-M7)
   * - arm_cortexM7bfdp_math.lib (Big endian and Double Precision Floating Point Unit on Cortex-M7)
   * - arm_cortexM7lfsp_math.lib (Little endian and Single Precision Floating Point Unit on Cortex-M7)
   * - arm_cortexM7bfsp_math.lib (Big endian and Single Precision Floating Point Unit on Cortex-M7)
   * - arm_cortexM7l_math.lib (Little endian on Cortex-M7)
   * - arm_cortexM7b_math.lib (Big endian on Cortex-M7)
   * - arm_cortexM4lf_math.lib (Little endian and Floating Point Unit on Cortex-M4)
   * - arm_cortexM4bf_math.lib (Big endian and Floating Point Unit on Cortex-M4)
   * - arm_cortexM4l_math.lib (Little endian on Cortex-M4)
   * - arm_cortexM4b_math.lib (Big endian on Cortex-M4)
   * - arm_cortexM3l_math.lib (Little endian on Cortex-M3)
   * - arm_cortexM3b_math.lib (Big endian on Cortex-M3)
   * - arm_cortexM0l_math.lib (Little endian on Cortex-M0 / CortexM0+)
   * - arm_cortexM0b_math.lib (Big endian on Cortex-M0 / CortexM0+)
   *
   * The library functions are declared in the public file <code>arm_math.h</code> which is placed in the <code>Include</code> folder.
   * Simply include this file and link the appropriate library in the application and begin calling the library functions. The Library supports single
   * public header file <code> arm_math.h</code> for Cortex-M7/M4/M3/M0/M0+ with little endian and big endian. Same header file will be used for floating point unit(FPU) variants.
   * Define the appropriate pre processor MACRO ARM_MATH_CM7 or ARM_MATH_CM4 or  ARM_MATH_CM3 or
   * ARM_MATH_CM0 or ARM_MATH_CM0PLUS depending on the target processor in the application.
   *
   * Examples
   * --------
   *
   * The library ships with a number of examples which demonstrate how to use the library functions.
   *
   * Toolchain Support
   * ------------
   *
   * The library has been developed and tested with MDK-ARM version 5.14.0.0
   * The library is being tested in GCC and IAR toolchains and updates on this activity will be made available shortly.
   *
   * Building the Library
   * ------------
   *
   * The library installer contains a project file to re build libraries on MDK-ARM Tool chain in the <code>CMSIS\\DSP_Lib\\Source\\ARM</code> folder.
   * - arm_cortexM_math.uvprojx
   *
   *
   * The libraries can be built by opening the arm_cortexM_math.uvprojx project in MDK-ARM, selecting a specific target, and defining the optional pre processor MACROs detailed above.
   *
   * Pre-processor Macros
   * ------------
   *
   * Each library project have differant pre-processor macros.
   *
   * - UNALIGNED_SUPPORT_DISABLE:
   *
   * Define macro UNALIGNED_SUPPORT_DISABLE, If the silicon does not support unaligned memory access
   *
   * - ARM_MATH_BIG_ENDIAN:
   *
   * Define macro ARM_MATH_BIG_ENDIAN to build the library for big endian targets. By default library builds for little endian targets.
   *
   * - ARM_MATH_MATRIX_CHECK:
   *
   * Define macro ARM_MATH_MATRIX_CHECK for checking on the input and output sizes of matrices
   *
   * - ARM_MATH_ROUNDING:
   *
   * Define macro ARM_MATH_ROUNDING for rounding on support functions
   *
   * - ARM_MATH_CMx:
   *
   * Define macro ARM_MATH_CM4 for building the library on Cortex-M4 target, ARM_MATH_CM3 for building library on Cortex-M3 target
   * and ARM_MATH_CM0 for building library on Cortex-M0 target, ARM_MATH_CM0PLUS for building library on Cortex-M0+ target, and
   * ARM_MATH_CM7 for building the library on cortex-M7.
   *
   * - __FPU_PRESENT:
   *
   * Initialize macro __FPU_PRESENT = 1 when building on FPU supported Targets. Enable this macro for M4bf and M4lf libraries
   *
   * <hr>
   * CMSIS-DSP in ARM::CMSIS Pack
   * -----------------------------
   * 
   * The following files relevant to CMSIS-DSP are present in the <b>ARM::CMSIS</b> Pack directories:
   * |File/Folder                   |Content                                                                 |
   * |------------------------------|------------------------------------------------------------------------|
   * |\b CMSIS\\Documentation\\DSP  | This documentation                                                     |
   * |\b CMSIS\\DSP_Lib             | Software license agreement (license.txt)                               |
   * |\b CMSIS\\DSP_Lib\\Examples   | Example projects demonstrating the usage of the library functions      |
   * |\b CMSIS\\DSP_Lib\\Source     | Source files for rebuilding the library                                |
   * 
   * <hr>
   * Revision History of CMSIS-DSP
   * ------------
   * Please refer to \ref ChangeLog_pg.
   *
   * Copyright Notice
   * ------------
   *
   * Copyright (C) 2010-2015 ARM Limited. All rights reserved.
   */


/**
 * @defgroup groupMath Basic Math Functions
 */

/**
 * @defgroup groupFastMath Fast Math Functions
 * This set of functions provides a fast approximation to sine, cosine, and square root.
 * As compared to most of the other functions in the CMSIS math library, the fast math functions
 * operate on individual values and not arrays.
 * There are separate functions for Q15, Q31, and floating-point data.
 *
 */

/**
 * @defgroup groupCmplxMath Complex Math Functions
 * This set of functions operates on complex data vectors.
 * The data in the complex arrays is stored in an interleaved fashion
 * (real, imag, real, imag, ...).
 * In the API functions, the number of samples in a complex array refers
 * to the number of complex values; the array contains twice this number of
 * real values.
 */

/**
 * @defgroup groupFilters Filtering Functions
 */

/**
 * @defgroup groupMatrix Matrix Functions
 *
 * This set of functions provides basic matrix math operations.
 * The functions operate on matrix data structures.  For example,
 * the type
 * definition for the floating-point matrix structure is shown
 * below:
 * <pre>
 *     typedef struct
 *     {
 *       uint16_t numRows;     // number of rows of the matrix.
 *       uint16_t numCols;     // number of columns of the matrix.
 *       float32_t *pData;     // points to the data of the matrix.
 *     } arm_matrix_instance_f32;
 * </pre>
 * There are similar definitions for Q15 and Q31 data types.
 *
 * The structure specifies the size of the matrix and then points to
 * an array of data.  The array is of size <code>numRows X numCols</code>
 * and the values are arranged in row order.  That is, the
 * matrix element (i, j) is stored at:
 * <pre>
 *     pData[i*numCols + j]
 * </pre>
 *
 * \par Init Functions
 * There is an associated initialization function for each type of matrix
 * data structure.
 * The initialization function sets the values of the internal structure fields.
 * Refer to the function <code>arm_mat_init_f32()</code>, <code>arm_mat_init_q31()</code>
 * and <code>arm_mat_init_q15()</code> for floating-point, Q31 and Q15 types,  respectively.
 *
 * \par
 * Use of the initialization function is optional. However, if initialization function is used
 * then the instance structure cannot be placed into a const data section.
 * To place the instance structure in a const data
 * section, manually initialize the data structure.  For example:
 * <pre>
 * <code>arm_matrix_instance_f32 S = {nRows, nColumns, pData};</code>
 * <code>arm_matrix_instance_q31 S = {nRows, nColumns, pData};</code>
 * <code>arm_matrix_instance_q15 S = {nRows, nColumns, pData};</code>
 * </pre>
 * where <code>nRows</code> specifies the number of rows, <code>nColumns</code>
 * specifies the number of columns, and <code>pData</code> points to the
 * data array.
 *
 * \par Size Checking
 * By default all of the matrix functions perform size checking on the input and
 * output matrices.  For example, the matrix addition function verifies that the
 * two input matrices and the output matrix all have the same number of rows and
 * columns.  If the size check fails the functions return:
 * <pre>
 *     ARM_MATH_SIZE_MISMATCH
 * </pre>
 * Otherwise the functions return
 * <pre>
 *     ARM_MATH_SUCCESS
 * </pre>
 * There is some overhead associated with this matrix size checking.
 * The matrix size checking is enabled via the \#define
 * <pre>
 *     ARM_MATH_MATRIX_CHECK
 * </pre>
 * within the library project settings.  By default this macro is defined
 * and size checking is enabled.  By changing the project settings and
 * undefining this macro size checking is eliminated and the functions
 * run a bit faster.  With size checking disabled the functions always
 * return <code>ARM_MATH_SUCCESS</code>.
 */

/**
 * @defgroup groupTransforms Transform Functions
 */

/**
 * @defgroup groupController Controller Functions
 */

/**
 * @defgroup groupStats Statistics Functions
 */
/**
 * @defgroup groupSupport Support Functions
 */

/**
 * @defgroup groupInterpolation Interpolation Functions
 * These functions perform 1- and 2-dimensional interpolation of data.
 * Linear interpolation is used for 1-dimensional data and
 * bilinear interpolation is used for 2-dimensional data.
 */

/**
 * @defgroup groupExamples Examples
 */
#ifndef _ARM_MATH_H
#define _ARM_MATH_H

#define __CMSIS_GENERIC         /* disable NVIC and Systick functions */

#if defined(ARM_MATH_CM7)
  #include "core_cm7.h"
#elif defined (ARM_MATH_CM4)
  #include "core_cm4.h"
#elif defined (ARM_MATH_CM3)
  #include "core_cm3.h"
#elif defined (ARM_MATH_CM0)
  #include "core_cm0.h"
#define ARM_MATH_CM0_FAMILY
  #elif defined (ARM_MATH_CM0PLUS)
#include "core_cm0plus.h"
  #define ARM_MATH_CM0_FAMILY
#else
  #error "Define according the used Cortex core ARM_MATH_CM7, ARM_MATH_CM4, ARM_MATH_CM3, ARM_MATH_CM0PLUS or ARM_MATH_CM0"
#endif

#undef  __CMSIS_GENERIC         /* enable NVIC and Systick functions */
#include "string.h"
#include "math.h"
#ifdef	__cplusplus
extern "C"
{
#endif


  /**
   * @brief Macros required for reciprocal calculation in Normalized LMS
   */

#define DELTA_Q31 			(0x100)
#define DELTA_Q15 			0x5
#define INDEX_MASK 			0x0000003F
#ifndef PI
#define PI					3.14159265358979f
#endif

  /**
   * @brief Macros required for SINE and COSINE Fast math approximations
   */

#define FAST_MATH_TABLE_SIZE  512
#define FAST_MATH_Q31_SHIFT   (32 - 10)
#define FAST_MATH_Q15_SHIFT   (16 - 10)
#define CONTROLLER_Q31_SHIFT  (32 - 9)
#define TABLE_SIZE  256
#define TABLE_SPACING_Q31	   0x400000
#define TABLE_SPACING_Q15	   0x80

  /**
   * @brief Macros required for SINE and COSINE Controller functions
   */
  /* 1.31(q31) Fixed value of 2/360 */
  /* -1 to +1 is divided into 360 values so total spacing is (2/360) */
#define INPUT_SPACING			0xB60B61

  /**
   * @brief Macro for Unaligned Support
   */
#ifndef UNALIGNED_SUPPORT_DISABLE
    #define ALIGN4
#else
  #if defined  (__GNUC__)
    #define ALIGN4 __attribute__((aligned(4)))
  #else
    #define ALIGN4 __align(4)
  #endif
#endif	/*	#ifndef UNALIGNED_SUPPORT_DISABLE	*/

  /**
   * @brief Error status returned by some functions in the library.
   */

  typedef enum
  {
    ARM_MATH_SUCCESS = 0,                /**< No error */
    ARM_MATH_ARGUMENT_ERROR = -1,        /**< One or more arguments are incorrect */
    ARM_MATH_LENGTH_ERROR = -2,          /**< Length of data buffer is incorrect */
    ARM_MATH_SIZE_MISMATCH = -3,         /**< Size of matrices is not compatible with the operation. */
    ARM_MATH_NANINF = -4,                /**< Not-a-number (NaN) or infinity is generated */
    ARM_MATH_SINGULAR = -5,              /**< Generated by matrix inversion if the input matrix is singular and cannot be inverted. */
    ARM_MATH_TEST_FAILURE = -6           /**< Test Failed  */
  } arm_status;

  /**
   * @brief 8-bit fractional data type in 1.7 format.
   */
  typedef int8_t q7_t;

  /**
   * @brief 16-bit fractional data type in 1.15 format.
   */
  typedef int16_t q15_t;

  /**
   * @brief 32-bit fractional data type in 1.31 format.
   */
  typedef int32_t q31_t;

  /**
   * @brief 64-bit fractional data type in 1.63 format.
   */
  typedef int64_t q63_t;

  /**
   * @brief 32-bit floating-point type definition.
   */
  typedef float float32_t;

  /**
   * @brief 64-bit floating-point type definition.
   */
  typedef double float64_t;

  /**
   * @brief definition to read/write two 16 bit values.
   */
#if defined __CC_ARM
  #define __SIMD32_TYPE int32_t __packed
  #define CMSIS_UNUSED __attribute__((unused))
#elif defined __ICCARM__
  #define __SIMD32_TYPE int32_t __packed
  #define CMSIS_UNUSED
#elif defined __GNUC__
  #define __SIMD32_TYPE int32_t
  #define CMSIS_UNUSED __attribute__((unused))
#elif defined __CSMC__			/* Cosmic */
  #define __SIMD32_TYPE int32_t
  #define CMSIS_UNUSED
#elif defined __TASKING__
  #define __SIMD32_TYPE __unaligned int32_t
  #define CMSIS_UNUSED
#else
  #error Unknown compiler
#endif

#define __SIMD32(addr)  (*(__SIMD32_TYPE **) & (addr))
#define __SIMD32_CONST(addr)  ((__SIMD32_TYPE *)(addr))

#define _SIMD32_OFFSET(addr)  (*(__SIMD32_TYPE *)  (addr))

#define __SIMD64(addr)  (*(int64_t **) & (addr))

#if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY)
  /**
   * @brief definition to pack two 16 bit values.
   */
#define __PKHBT(ARG1, ARG2, ARG3)      ( (((int32_t)(ARG1) <<  0) & (int32_t)0x0000FFFF) | \
                                         (((int32_t)(ARG2) << ARG3) & (int32_t)0xFFFF0000)  )
#define __PKHTB(ARG1, ARG2, ARG3)      ( (((int32_t)(ARG1) <<  0) & (int32_t)0xFFFF0000) | \
                                         (((int32_t)(ARG2) >> ARG3) & (int32_t)0x0000FFFF)  )

#endif


   /**
   * @brief definition to pack four 8 bit values.
   */
#ifndef ARM_MATH_BIG_ENDIAN

#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v0) <<  0) & (int32_t)0x000000FF) |	\
                                (((int32_t)(v1) <<  8) & (int32_t)0x0000FF00) |	\
							    (((int32_t)(v2) << 16) & (int32_t)0x00FF0000) |	\
							    (((int32_t)(v3) << 24) & (int32_t)0xFF000000)  )
#else

#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v3) <<  0) & (int32_t)0x000000FF) |	\
                                (((int32_t)(v2) <<  8) & (int32_t)0x0000FF00) |	\
							    (((int32_t)(v1) << 16) & (int32_t)0x00FF0000) |	\
							    (((int32_t)(v0) << 24) & (int32_t)0xFF000000)  )

#endif


  /**
   * @brief Clips Q63 to Q31 values.
   */
  static __INLINE q31_t clip_q63_to_q31(
  q63_t x)
  {
    return ((q31_t) (x >> 32) != ((q31_t) x >> 31)) ?
      ((0x7FFFFFFF ^ ((q31_t) (x >> 63)))) : (q31_t) x;
  }

  /**
   * @brief Clips Q63 to Q15 values.
   */
  static __INLINE q15_t clip_q63_to_q15(
  q63_t x)
  {
    return ((q31_t) (x >> 32) != ((q31_t) x >> 31)) ?
      ((0x7FFF ^ ((q15_t) (x >> 63)))) : (q15_t) (x >> 15);
  }

  /**
   * @brief Clips Q31 to Q7 values.
   */
  static __INLINE q7_t clip_q31_to_q7(
  q31_t x)
  {
    return ((q31_t) (x >> 24) != ((q31_t) x >> 23)) ?
      ((0x7F ^ ((q7_t) (x >> 31)))) : (q7_t) x;
  }

  /**
   * @brief Clips Q31 to Q15 values.
   */
  static __INLINE q15_t clip_q31_to_q15(
  q31_t x)
  {
    return ((q31_t) (x >> 16) != ((q31_t) x >> 15)) ?
      ((0x7FFF ^ ((q15_t) (x >> 31)))) : (q15_t) x;
  }

  /**
   * @brief Multiplies 32 X 64 and returns 32 bit result in 2.30 format.
   */

  static __INLINE q63_t mult32x64(
  q63_t x,
  q31_t y)
  {
    return ((((q63_t) (x & 0x00000000FFFFFFFF) * y) >> 32) +
            (((q63_t) (x >> 32) * y)));
  }


//#if defined (ARM_MATH_CM0_FAMILY) && defined ( __CC_ARM   )
//#define __CLZ __clz
//#endif

//note: function can be removed when all toolchain support __CLZ for Cortex-M0
#if defined (ARM_MATH_CM0_FAMILY) && ((defined (__ICCARM__))  )

  static __INLINE uint32_t __CLZ(
  q31_t data);


  static __INLINE uint32_t __CLZ(
  q31_t data)
  {
    uint32_t count = 0;
    uint32_t mask = 0x80000000;

    while((data & mask) == 0)
    {
      count += 1u;
      mask = mask >> 1u;
    }

    return (count);

  }

#endif

  /**
   * @brief Function to Calculates 1/in (reciprocal) value of Q31 Data type.
   */

  static __INLINE uint32_t arm_recip_q31(
  q31_t in,
  q31_t * dst,
  q31_t * pRecipTable)
  {

    uint32_t out, tempVal;
    uint32_t index, i;
    uint32_t signBits;

    if(in > 0)
    {
      signBits = __CLZ(in) - 1;
    }
    else
    {
      signBits = __CLZ(-in) - 1;
    }

    /* Convert input sample to 1.31 format */
    in = in << signBits;

    /* calculation of index for initial approximated Val */
    index = (uint32_t) (in >> 24u);
    index = (index & INDEX_MASK);

    /* 1.31 with exp 1 */
    out = pRecipTable[index];

    /* calculation of reciprocal value */
    /* running approximation for two iterations */
    for (i = 0u; i < 2u; i++)
    {
      tempVal = (q31_t) (((q63_t) in * out) >> 31u);
      tempVal = 0x7FFFFFFF - tempVal;
      /*      1.31 with exp 1 */
      //out = (q31_t) (((q63_t) out * tempVal) >> 30u);
      out = (q31_t) clip_q63_to_q31(((q63_t) out * tempVal) >> 30u);
    }

    /* write output */
    *dst = out;

    /* return num of signbits of out = 1/in value */
    return (signBits + 1u);

  }

  /**
   * @brief Function to Calculates 1/in (reciprocal) value of Q15 Data type.
   */
  static __INLINE uint32_t arm_recip_q15(
  q15_t in,
  q15_t * dst,
  q15_t * pRecipTable)
  {

    uint32_t out = 0, tempVal = 0;
    uint32_t index = 0, i = 0;
    uint32_t signBits = 0;

    if(in > 0)
    {
      signBits = __CLZ(in) - 17;
    }
    else
    {
      signBits = __CLZ(-in) - 17;
    }

    /* Convert input sample to 1.15 format */
    in = in << signBits;

    /* calculation of index for initial approximated Val */
    index = in >> 8;
    index = (index & INDEX_MASK);

    /*      1.15 with exp 1  */
    out = pRecipTable[index];

    /* calculation of reciprocal value */
    /* running approximation for two iterations */
    for (i = 0; i < 2; i++)
    {
      tempVal = (q15_t) (((q31_t) in * out) >> 15);
      tempVal = 0x7FFF - tempVal;
      /*      1.15 with exp 1 */
      out = (q15_t) (((q31_t) out * tempVal) >> 14);
    }

    /* write output */
    *dst = out;

    /* return num of signbits of out = 1/in value */
    return (signBits + 1);

  }


  /*
   * @brief C custom defined intrinisic function for only M0 processors
   */
#if defined(ARM_MATH_CM0_FAMILY)

  static __INLINE q31_t __SSAT(
  q31_t x,
  uint32_t y)
  {
    int32_t posMax, negMin;
    uint32_t i;

    posMax = 1;
    for (i = 0; i < (y - 1); i++)
    {
      posMax = posMax * 2;
    }

    if(x > 0)
    {
      posMax = (posMax - 1);

      if(x > posMax)
      {
        x = posMax;
      }
    }
    else
    {
      negMin = -posMax;

      if(x < negMin)
      {
        x = negMin;
      }
    }
    return (x);


  }

#endif /* end of ARM_MATH_CM0_FAMILY */



  /*
   * @brief C custom defined intrinsic function for M3 and M0 processors
   */
#if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY)

  /*
   * @brief C custom defined QADD8 for M3 and M0 processors
   */
  static __INLINE q31_t __QADD8(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q7_t r, s, t, u;

    r = (q7_t) x;
    s = (q7_t) y;

    r = __SSAT((q31_t) (r + s), 8);
    s = __SSAT(((q31_t) (((x << 16) >> 24) + ((y << 16) >> 24))), 8);
    t = __SSAT(((q31_t) (((x << 8) >> 24) + ((y << 8) >> 24))), 8);
    u = __SSAT(((q31_t) ((x >> 24) + (y >> 24))), 8);

    sum =
      (((q31_t) u << 24) & 0xFF000000) | (((q31_t) t << 16) & 0x00FF0000) |
      (((q31_t) s << 8) & 0x0000FF00) | (r & 0x000000FF);

    return sum;

  }

  /*
   * @brief C custom defined QSUB8 for M3 and M0 processors
   */
  static __INLINE q31_t __QSUB8(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s, t, u;

    r = (q7_t) x;
    s = (q7_t) y;

    r = __SSAT((r - s), 8);
    s = __SSAT(((q31_t) (((x << 16) >> 24) - ((y << 16) >> 24))), 8) << 8;
    t = __SSAT(((q31_t) (((x << 8) >> 24) - ((y << 8) >> 24))), 8) << 16;
    u = __SSAT(((q31_t) ((x >> 24) - (y >> 24))), 8) << 24;

    sum =
      (u & 0xFF000000) | (t & 0x00FF0000) | (s & 0x0000FF00) | (r &
                                                                0x000000FF);

    return sum;
  }

  /*
   * @brief C custom defined QADD16 for M3 and M0 processors
   */

  /*
   * @brief C custom defined QADD16 for M3 and M0 processors
   */
  static __INLINE q31_t __QADD16(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = __SSAT(r + s, 16);
    s = __SSAT(((q31_t) ((x >> 16) + (y >> 16))), 16) << 16;

    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return sum;

  }

  /*
   * @brief C custom defined SHADD16 for M3 and M0 processors
   */
  static __INLINE q31_t __SHADD16(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = ((r >> 1) + (s >> 1));
    s = ((q31_t) ((x >> 17) + (y >> 17))) << 16;

    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return sum;

  }

  /*
   * @brief C custom defined QSUB16 for M3 and M0 processors
   */
  static __INLINE q31_t __QSUB16(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = __SSAT(r - s, 16);
    s = __SSAT(((q31_t) ((x >> 16) - (y >> 16))), 16) << 16;

    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return sum;
  }

  /*
   * @brief C custom defined SHSUB16 for M3 and M0 processors
   */
  static __INLINE q31_t __SHSUB16(
  q31_t x,
  q31_t y)
  {

    q31_t diff;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = ((r >> 1) - (s >> 1));
    s = (((x >> 17) - (y >> 17)) << 16);

    diff = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return diff;
  }

  /*
   * @brief C custom defined QASX for M3 and M0 processors
   */
  static __INLINE q31_t __QASX(
  q31_t x,
  q31_t y)
  {

    q31_t sum = 0;

    sum =
      ((sum +
        clip_q31_to_q15((q31_t) ((q15_t) (x >> 16) + (q15_t) y))) << 16) +
      clip_q31_to_q15((q31_t) ((q15_t) x - (q15_t) (y >> 16)));

    return sum;
  }

  /*
   * @brief C custom defined SHASX for M3 and M0 processors
   */
  static __INLINE q31_t __SHASX(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = ((r >> 1) - (y >> 17));
    s = (((x >> 17) + (s >> 1)) << 16);

    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return sum;
  }


  /*
   * @brief C custom defined QSAX for M3 and M0 processors
   */
  static __INLINE q31_t __QSAX(
  q31_t x,
  q31_t y)
  {

    q31_t sum = 0;

    sum =
      ((sum +
        clip_q31_to_q15((q31_t) ((q15_t) (x >> 16) - (q15_t) y))) << 16) +
      clip_q31_to_q15((q31_t) ((q15_t) x + (q15_t) (y >> 16)));

    return sum;
  }

  /*
   * @brief C custom defined SHSAX for M3 and M0 processors
   */
  static __INLINE q31_t __SHSAX(
  q31_t x,
  q31_t y)
  {

    q31_t sum;
    q31_t r, s;

    r = (q15_t) x;
    s = (q15_t) y;

    r = ((r >> 1) + (y >> 17));
    s = (((x >> 17) - (s >> 1)) << 16);

    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);

    return sum;
  }

  /*
   * @brief C custom defined SMUSDX for M3 and M0 processors
   */
  static __INLINE q31_t __SMUSDX(
  q31_t x,
  q31_t y)
  {

    return ((q31_t) (((q15_t) x * (q15_t) (y >> 16)) -
                     ((q15_t) (x >> 16) * (q15_t) y)));
  }

  /*
   * @brief C custom defined SMUADX for M3 and M0 processors
   */
  static __INLINE q31_t __SMUADX(
  q31_t x,
  q31_t y)
  {

    return ((q31_t) (((q15_t) x * (q15_t) (y >> 16)) +
                     ((q15_t) (x >> 16) * (q15_t) y)));
  }

  /*
   * @brief C custom defined QADD for M3 and M0 processors
   */
  static __INLINE q31_t __QADD(
  q31_t x,
  q31_t y)
  {
    return clip_q63_to_q31((q63_t) x + y);
  }

  /*
   * @brief C custom defined QSUB for M3 and M0 processors
   */
  static __INLINE q31_t __QSUB(
  q31_t x,
  q31_t y)
  {
    return clip_q63_to_q31((q63_t) x - y);
  }

  /*
   * @brief C custom defined SMLAD for M3 and M0 processors
   */
  static __INLINE q31_t __SMLAD(
  q31_t x,
  q31_t y,
  q31_t sum)
  {

    return (sum + ((q15_t) (x >> 16) * (q15_t) (y >> 16)) +
            ((q15_t) x * (q15_t) y));
  }

  /*
   * @brief C custom defined SMLADX for M3 and M0 processors
   */
  static __INLINE q31_t __SMLADX(
  q31_t x,
  q31_t y,
  q31_t sum)
  {

    return (sum + ((q15_t) (x >> 16) * (q15_t) (y)) +
            ((q15_t) x * (q15_t) (y >> 16)));
  }

  /*
   * @brief C custom defined SMLSDX for M3 and M0 processors
   */
  static __INLINE q31_t __SMLSDX(
  q31_t x,
  q31_t y,
  q31_t sum)
  {

    return (sum - ((q15_t) (x >> 16) * (q15_t) (y)) +
            ((q15_t) x * (q15_t) (y >> 16)));
  }

  /*
   * @brief C custom defined SMLALD for M3 and M0 processors
   */
  static __INLINE q63_t __SMLALD(
  q31_t x,
  q31_t y,
  q63_t sum)
  {

    return (sum + ((q15_t) (x >> 16) * (q15_t) (y >> 16)) +
            ((q15_t) x * (q15_t) y));
  }

  /*
   * @brief C custom defined SMLALDX for M3 and M0 processors
   */
  static __INLINE q63_t __SMLALDX(
  q31_t x,
  q31_t y,
  q63_t sum)
  {

    return (sum + ((q15_t) (x >> 16) * (q15_t) y)) +
      ((q15_t) x * (q15_t) (y >> 16));
  }

  /*
   * @brief C custom defined SMUAD for M3 and M0 processors
   */
  static __INLINE q31_t __SMUAD(
  q31_t x,
  q31_t y)
  {

    return (((x >> 16) * (y >> 16)) +
            (((x << 16) >> 16) * ((y << 16) >> 16)));
  }

  /*
   * @brief C custom defined SMUSD for M3 and M0 processors
   */
  static __INLINE q31_t __SMUSD(
  q31_t x,
  q31_t y)
  {

    return (-((x >> 16) * (y >> 16)) +
            (((x << 16) >> 16) * ((y << 16) >> 16)));
  }


  /*
   * @brief C custom defined SXTB16 for M3 and M0 processors
   */
  static __INLINE q31_t __SXTB16(
  q31_t x)
  {

    return ((((x << 24) >> 24) & 0x0000FFFF) |
            (((x << 8) >> 8) & 0xFFFF0000));
  }


#endif /* defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */


  /**
   * @brief Instance structure for the Q7 FIR filter.
   */
  typedef struct
  {
    uint16_t numTaps;        /**< number of filter coefficients in the filter. */
    q7_t *pState;            /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q7_t *pCoeffs;           /**< points to the coefficient array. The array is of length numTaps.*/
  } arm_fir_instance_q7;

  /**
   * @brief Instance structure for the Q15 FIR filter.
   */
  typedef struct
  {
    uint16_t numTaps;         /**< number of filter coefficients in the filter. */
    q15_t *pState;            /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q15_t *pCoeffs;           /**< points to the coefficient array. The array is of length numTaps.*/
  } arm_fir_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR filter.
   */
  typedef struct
  {
    uint16_t numTaps;         /**< number of filter coefficients in the filter. */
    q31_t *pState;            /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q31_t *pCoeffs;           /**< points to the coefficient array. The array is of length numTaps. */
  } arm_fir_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR filter.
   */
  typedef struct
  {
    uint16_t numTaps;     /**< number of filter coefficients in the filter. */
    float32_t *pState;    /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    float32_t *pCoeffs;   /**< points to the coefficient array. The array is of length numTaps. */
  } arm_fir_instance_f32;


  /**
   * @brief Processing function for the Q7 FIR filter.
   * @param[in] *S points to an instance of the Q7 FIR filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_q7(
  const arm_fir_instance_q7 * S,
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q7 FIR filter.
   * @param[in,out] *S points to an instance of the Q7 FIR structure.
   * @param[in] numTaps  Number of filter coefficients in the filter.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of samples that are processed.
   * @return none
   */
  void arm_fir_init_q7(
  arm_fir_instance_q7 * S,
  uint16_t numTaps,
  q7_t * pCoeffs,
  q7_t * pState,
  uint32_t blockSize);


  /**
   * @brief Processing function for the Q15 FIR filter.
   * @param[in] *S points to an instance of the Q15 FIR structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_q15(
  const arm_fir_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the fast Q15 FIR filter for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q15 FIR filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_fast_q15(
  const arm_fir_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q15 FIR filter.
   * @param[in,out] *S points to an instance of the Q15 FIR filter structure.
   * @param[in] numTaps  Number of filter coefficients in the filter. Must be even and greater than or equal to 4.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of samples that are processed at a time.
   * @return The function returns ARM_MATH_SUCCESS if initialization was successful or ARM_MATH_ARGUMENT_ERROR if
   * <code>numTaps</code> is not a supported value.
   */

  arm_status arm_fir_init_q15(
  arm_fir_instance_q15 * S,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR filter.
   * @param[in] *S points to an instance of the Q31 FIR filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_q31(
  const arm_fir_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the fast Q31 FIR filter for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q31 FIR structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_fast_q31(
  const arm_fir_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q31 FIR filter.
   * @param[in,out] *S points to an instance of the Q31 FIR structure.
   * @param[in] 	numTaps  Number of filter coefficients in the filter.
   * @param[in] 	*pCoeffs points to the filter coefficients.
   * @param[in] 	*pState points to the state buffer.
   * @param[in] 	blockSize number of samples that are processed at a time.
   * @return 		none.
   */
  void arm_fir_init_q31(
  arm_fir_instance_q31 * S,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the floating-point FIR filter.
   * @param[in] *S points to an instance of the floating-point FIR structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_f32(
  const arm_fir_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the floating-point FIR filter.
   * @param[in,out] *S points to an instance of the floating-point FIR filter structure.
   * @param[in] 	numTaps  Number of filter coefficients in the filter.
   * @param[in] 	*pCoeffs points to the filter coefficients.
   * @param[in] 	*pState points to the state buffer.
   * @param[in] 	blockSize number of samples that are processed at a time.
   * @return    	none.
   */
  void arm_fir_init_f32(
  arm_fir_instance_f32 * S,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  uint32_t blockSize);


  /**
   * @brief Instance structure for the Q15 Biquad cascade filter.
   */
  typedef struct
  {
    int8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    q15_t *pState;            /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
    q15_t *pCoeffs;           /**< Points to the array of coefficients.  The array is of length 5*numStages. */
    int8_t postShift;         /**< Additional shift, in bits, applied to each output sample. */

  } arm_biquad_casd_df1_inst_q15;


  /**
   * @brief Instance structure for the Q31 Biquad cascade filter.
   */
  typedef struct
  {
    uint32_t numStages;      /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    q31_t *pState;           /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
    q31_t *pCoeffs;          /**< Points to the array of coefficients.  The array is of length 5*numStages. */
    uint8_t postShift;       /**< Additional shift, in bits, applied to each output sample. */

  } arm_biquad_casd_df1_inst_q31;

  /**
   * @brief Instance structure for the floating-point Biquad cascade filter.
   */
  typedef struct
  {
    uint32_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    float32_t *pState;          /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
    float32_t *pCoeffs;         /**< Points to the array of coefficients.  The array is of length 5*numStages. */


  } arm_biquad_casd_df1_inst_f32;



  /**
   * @brief Processing function for the Q15 Biquad cascade filter.
   * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.
   * @param[in]  *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in]  blockSize number of samples to process.
   * @return     none.
   */

  void arm_biquad_cascade_df1_q15(
  const arm_biquad_casd_df1_inst_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q15 Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the Q15 Biquad cascade structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @param[in]     postShift    Shift to be applied to the output. Varies according to the coefficients format
   * @return        none
   */

  void arm_biquad_cascade_df1_init_q15(
  arm_biquad_casd_df1_inst_q15 * S,
  uint8_t numStages,
  q15_t * pCoeffs,
  q15_t * pState,
  int8_t postShift);


  /**
   * @brief Fast but less precise processing function for the Q15 Biquad cascade filter for Cortex-M3 and Cortex-M4.
   * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.
   * @param[in]  *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in]  blockSize number of samples to process.
   * @return     none.
   */

  void arm_biquad_cascade_df1_fast_q15(
  const arm_biquad_casd_df1_inst_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);


  /**
   * @brief Processing function for the Q31 Biquad cascade filter
   * @param[in]  *S         points to an instance of the Q31 Biquad cascade structure.
   * @param[in]  *pSrc      points to the block of input data.
   * @param[out] *pDst      points to the block of output data.
   * @param[in]  blockSize  number of samples to process.
   * @return     none.
   */

  void arm_biquad_cascade_df1_q31(
  const arm_biquad_casd_df1_inst_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Fast but less precise processing function for the Q31 Biquad cascade filter for Cortex-M3 and Cortex-M4.
   * @param[in]  *S         points to an instance of the Q31 Biquad cascade structure.
   * @param[in]  *pSrc      points to the block of input data.
   * @param[out] *pDst      points to the block of output data.
   * @param[in]  blockSize  number of samples to process.
   * @return     none.
   */

  void arm_biquad_cascade_df1_fast_q31(
  const arm_biquad_casd_df1_inst_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q31 Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the Q31 Biquad cascade structure.
   * @param[in]     numStages      number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @param[in]     postShift    Shift to be applied to the output. Varies according to the coefficients format
   * @return        none
   */

  void arm_biquad_cascade_df1_init_q31(
  arm_biquad_casd_df1_inst_q31 * S,
  uint8_t numStages,
  q31_t * pCoeffs,
  q31_t * pState,
  int8_t postShift);

  /**
   * @brief Processing function for the floating-point Biquad cascade filter.
   * @param[in]  *S         points to an instance of the floating-point Biquad cascade structure.
   * @param[in]  *pSrc      points to the block of input data.
   * @param[out] *pDst      points to the block of output data.
   * @param[in]  blockSize  number of samples to process.
   * @return     none.
   */

  void arm_biquad_cascade_df1_f32(
  const arm_biquad_casd_df1_inst_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the floating-point Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the floating-point Biquad cascade structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @return        none
   */

  void arm_biquad_cascade_df1_init_f32(
  arm_biquad_casd_df1_inst_f32 * S,
  uint8_t numStages,
  float32_t * pCoeffs,
  float32_t * pState);


  /**
   * @brief Instance structure for the floating-point matrix structure.
   */

  typedef struct
  {
    uint16_t numRows;     /**< number of rows of the matrix.     */
    uint16_t numCols;     /**< number of columns of the matrix.  */
    float32_t *pData;     /**< points to the data of the matrix. */
  } arm_matrix_instance_f32;


  /**
   * @brief Instance structure for the floating-point matrix structure.
   */

  typedef struct
  {
    uint16_t numRows;     /**< number of rows of the matrix.     */
    uint16_t numCols;     /**< number of columns of the matrix.  */
    float64_t *pData;     /**< points to the data of the matrix. */
  } arm_matrix_instance_f64;

  /**
   * @brief Instance structure for the Q15 matrix structure.
   */

  typedef struct
  {
    uint16_t numRows;     /**< number of rows of the matrix.     */
    uint16_t numCols;     /**< number of columns of the matrix.  */
    q15_t *pData;         /**< points to the data of the matrix. */

  } arm_matrix_instance_q15;

  /**
   * @brief Instance structure for the Q31 matrix structure.
   */

  typedef struct
  {
    uint16_t numRows;     /**< number of rows of the matrix.     */
    uint16_t numCols;     /**< number of columns of the matrix.  */
    q31_t *pData;         /**< points to the data of the matrix. */

  } arm_matrix_instance_q31;



  /**
   * @brief Floating-point matrix addition.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_add_f32(
  const arm_matrix_instance_f32 * pSrcA,
  const arm_matrix_instance_f32 * pSrcB,
  arm_matrix_instance_f32 * pDst);

  /**
   * @brief Q15 matrix addition.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_add_q15(
  const arm_matrix_instance_q15 * pSrcA,
  const arm_matrix_instance_q15 * pSrcB,
  arm_matrix_instance_q15 * pDst);

  /**
   * @brief Q31 matrix addition.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_add_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst);

  /**
   * @brief Floating-point, complex, matrix multiplication.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_cmplx_mult_f32(
  const arm_matrix_instance_f32 * pSrcA,
  const arm_matrix_instance_f32 * pSrcB,
  arm_matrix_instance_f32 * pDst);

  /**
   * @brief Q15, complex,  matrix multiplication.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_cmplx_mult_q15(
  const arm_matrix_instance_q15 * pSrcA,
  const arm_matrix_instance_q15 * pSrcB,
  arm_matrix_instance_q15 * pDst,
  q15_t * pScratch);

  /**
   * @brief Q31, complex, matrix multiplication.
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_cmplx_mult_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst);


  /**
   * @brief Floating-point matrix transpose.
   * @param[in]  *pSrc points to the input matrix
   * @param[out] *pDst points to the output matrix
   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
   * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_trans_f32(
  const arm_matrix_instance_f32 * pSrc,
  arm_matrix_instance_f32 * pDst);


  /**
   * @brief Q15 matrix transpose.
   * @param[in]  *pSrc points to the input matrix
   * @param[out] *pDst points to the output matrix
   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
   * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_trans_q15(
  const arm_matrix_instance_q15 * pSrc,
  arm_matrix_instance_q15 * pDst);

  /**
   * @brief Q31 matrix transpose.
   * @param[in]  *pSrc points to the input matrix
   * @param[out] *pDst points to the output matrix
   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
   * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_trans_q31(
  const arm_matrix_instance_q31 * pSrc,
  arm_matrix_instance_q31 * pDst);


  /**
   * @brief Floating-point matrix multiplication
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_mult_f32(
  const arm_matrix_instance_f32 * pSrcA,
  const arm_matrix_instance_f32 * pSrcB,
  arm_matrix_instance_f32 * pDst);

  /**
   * @brief Q15 matrix multiplication
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @param[in]		 *pState points to the array for storing intermediate results
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_mult_q15(
  const arm_matrix_instance_q15 * pSrcA,
  const arm_matrix_instance_q15 * pSrcB,
  arm_matrix_instance_q15 * pDst,
  q15_t * pState);

  /**
   * @brief Q15 matrix multiplication (fast variant) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA  points to the first input matrix structure
   * @param[in]       *pSrcB  points to the second input matrix structure
   * @param[out]      *pDst   points to output matrix structure
   * @param[in]		  *pState points to the array for storing intermediate results
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_mult_fast_q15(
  const arm_matrix_instance_q15 * pSrcA,
  const arm_matrix_instance_q15 * pSrcB,
  arm_matrix_instance_q15 * pDst,
  q15_t * pState);

  /**
   * @brief Q31 matrix multiplication
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_mult_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst);

  /**
   * @brief Q31 matrix multiplication (fast variant) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_mult_fast_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst);


  /**
   * @brief Floating-point matrix subtraction
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_sub_f32(
  const arm_matrix_instance_f32 * pSrcA,
  const arm_matrix_instance_f32 * pSrcB,
  arm_matrix_instance_f32 * pDst);

  /**
   * @brief Q15 matrix subtraction
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_sub_q15(
  const arm_matrix_instance_q15 * pSrcA,
  const arm_matrix_instance_q15 * pSrcB,
  arm_matrix_instance_q15 * pDst);

  /**
   * @brief Q31 matrix subtraction
   * @param[in]       *pSrcA points to the first input matrix structure
   * @param[in]       *pSrcB points to the second input matrix structure
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_sub_q31(
  const arm_matrix_instance_q31 * pSrcA,
  const arm_matrix_instance_q31 * pSrcB,
  arm_matrix_instance_q31 * pDst);

  /**
   * @brief Floating-point matrix scaling.
   * @param[in]  *pSrc points to the input matrix
   * @param[in]  scale scale factor
   * @param[out] *pDst points to the output matrix
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_scale_f32(
  const arm_matrix_instance_f32 * pSrc,
  float32_t scale,
  arm_matrix_instance_f32 * pDst);

  /**
   * @brief Q15 matrix scaling.
   * @param[in]       *pSrc points to input matrix
   * @param[in]       scaleFract fractional portion of the scale factor
   * @param[in]       shift number of bits to shift the result by
   * @param[out]      *pDst points to output matrix
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_scale_q15(
  const arm_matrix_instance_q15 * pSrc,
  q15_t scaleFract,
  int32_t shift,
  arm_matrix_instance_q15 * pDst);

  /**
   * @brief Q31 matrix scaling.
   * @param[in]       *pSrc points to input matrix
   * @param[in]       scaleFract fractional portion of the scale factor
   * @param[in]       shift number of bits to shift the result by
   * @param[out]      *pDst points to output matrix structure
   * @return     The function returns either
   * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
   */

  arm_status arm_mat_scale_q31(
  const arm_matrix_instance_q31 * pSrc,
  q31_t scaleFract,
  int32_t shift,
  arm_matrix_instance_q31 * pDst);


  /**
   * @brief  Q31 matrix initialization.
   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
   * @param[in]     nRows          number of rows in the matrix.
   * @param[in]     nColumns       number of columns in the matrix.
   * @param[in]     *pData	       points to the matrix data array.
   * @return        none
   */

  void arm_mat_init_q31(
  arm_matrix_instance_q31 * S,
  uint16_t nRows,
  uint16_t nColumns,
  q31_t * pData);

  /**
   * @brief  Q15 matrix initialization.
   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
   * @param[in]     nRows          number of rows in the matrix.
   * @param[in]     nColumns       number of columns in the matrix.
   * @param[in]     *pData	       points to the matrix data array.
   * @return        none
   */

  void arm_mat_init_q15(
  arm_matrix_instance_q15 * S,
  uint16_t nRows,
  uint16_t nColumns,
  q15_t * pData);

  /**
   * @brief  Floating-point matrix initialization.
   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
   * @param[in]     nRows          number of rows in the matrix.
   * @param[in]     nColumns       number of columns in the matrix.
   * @param[in]     *pData	       points to the matrix data array.
   * @return        none
   */

  void arm_mat_init_f32(
  arm_matrix_instance_f32 * S,
  uint16_t nRows,
  uint16_t nColumns,
  float32_t * pData);



  /**
   * @brief Instance structure for the Q15 PID Control.
   */
  typedef struct
  {
    q15_t A0;    /**< The derived gain, A0 = Kp + Ki + Kd . */
#ifdef ARM_MATH_CM0_FAMILY
    q15_t A1;
    q15_t A2;
#else
    q31_t A1;           /**< The derived gain A1 = -Kp - 2Kd | Kd.*/
#endif
    q15_t state[3];       /**< The state array of length 3. */
    q15_t Kp;           /**< The proportional gain. */
    q15_t Ki;           /**< The integral gain. */
    q15_t Kd;           /**< The derivative gain. */
  } arm_pid_instance_q15;

  /**
   * @brief Instance structure for the Q31 PID Control.
   */
  typedef struct
  {
    q31_t A0;            /**< The derived gain, A0 = Kp + Ki + Kd . */
    q31_t A1;            /**< The derived gain, A1 = -Kp - 2Kd. */
    q31_t A2;            /**< The derived gain, A2 = Kd . */
    q31_t state[3];      /**< The state array of length 3. */
    q31_t Kp;            /**< The proportional gain. */
    q31_t Ki;            /**< The integral gain. */
    q31_t Kd;            /**< The derivative gain. */

  } arm_pid_instance_q31;

  /**
   * @brief Instance structure for the floating-point PID Control.
   */
  typedef struct
  {
    float32_t A0;          /**< The derived gain, A0 = Kp + Ki + Kd . */
    float32_t A1;          /**< The derived gain, A1 = -Kp - 2Kd. */
    float32_t A2;          /**< The derived gain, A2 = Kd . */
    float32_t state[3];    /**< The state array of length 3. */
    float32_t Kp;               /**< The proportional gain. */
    float32_t Ki;               /**< The integral gain. */
    float32_t Kd;               /**< The derivative gain. */
  } arm_pid_instance_f32;



  /**
   * @brief  Initialization function for the floating-point PID Control.
   * @param[in,out] *S      points to an instance of the PID structure.
   * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
   * @return none.
   */
  void arm_pid_init_f32(
  arm_pid_instance_f32 * S,
  int32_t resetStateFlag);

  /**
   * @brief  Reset function for the floating-point PID Control.
   * @param[in,out] *S is an instance of the floating-point PID Control structure
   * @return none
   */
  void arm_pid_reset_f32(
  arm_pid_instance_f32 * S);


  /**
   * @brief  Initialization function for the Q31 PID Control.
   * @param[in,out] *S points to an instance of the Q15 PID structure.
   * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
   * @return none.
   */
  void arm_pid_init_q31(
  arm_pid_instance_q31 * S,
  int32_t resetStateFlag);


  /**
   * @brief  Reset function for the Q31 PID Control.
   * @param[in,out] *S points to an instance of the Q31 PID Control structure
   * @return none
   */

  void arm_pid_reset_q31(
  arm_pid_instance_q31 * S);

  /**
   * @brief  Initialization function for the Q15 PID Control.
   * @param[in,out] *S points to an instance of the Q15 PID structure.
   * @param[in] resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
   * @return none.
   */
  void arm_pid_init_q15(
  arm_pid_instance_q15 * S,
  int32_t resetStateFlag);

  /**
   * @brief  Reset function for the Q15 PID Control.
   * @param[in,out] *S points to an instance of the q15 PID Control structure
   * @return none
   */
  void arm_pid_reset_q15(
  arm_pid_instance_q15 * S);


  /**
   * @brief Instance structure for the floating-point Linear Interpolate function.
   */
  typedef struct
  {
    uint32_t nValues;           /**< nValues */
    float32_t x1;               /**< x1 */
    float32_t xSpacing;         /**< xSpacing */
    float32_t *pYData;          /**< pointer to the table of Y values */
  } arm_linear_interp_instance_f32;

  /**
   * @brief Instance structure for the floating-point bilinear interpolation function.
   */

  typedef struct
  {
    uint16_t numRows;   /**< number of rows in the data table. */
    uint16_t numCols;   /**< number of columns in the data table. */
    float32_t *pData;   /**< points to the data table. */
  } arm_bilinear_interp_instance_f32;

   /**
   * @brief Instance structure for the Q31 bilinear interpolation function.
   */

  typedef struct
  {
    uint16_t numRows;   /**< number of rows in the data table. */
    uint16_t numCols;   /**< number of columns in the data table. */
    q31_t *pData;       /**< points to the data table. */
  } arm_bilinear_interp_instance_q31;

   /**
   * @brief Instance structure for the Q15 bilinear interpolation function.
   */

  typedef struct
  {
    uint16_t numRows;   /**< number of rows in the data table. */
    uint16_t numCols;   /**< number of columns in the data table. */
    q15_t *pData;       /**< points to the data table. */
  } arm_bilinear_interp_instance_q15;

   /**
   * @brief Instance structure for the Q15 bilinear interpolation function.
   */

  typedef struct
  {
    uint16_t numRows;   /**< number of rows in the data table. */
    uint16_t numCols;   /**< number of columns in the data table. */
    q7_t *pData;                /**< points to the data table. */
  } arm_bilinear_interp_instance_q7;


  /**
   * @brief Q7 vector multiplication.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst  points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_mult_q7(
  q7_t * pSrcA,
  q7_t * pSrcB,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q15 vector multiplication.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst  points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_mult_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q31 vector multiplication.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_mult_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Floating-point vector multiplication.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_mult_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  float32_t * pDst,
  uint32_t blockSize);






  /**
   * @brief Instance structure for the Q15 CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                 /**< length of the FFT. */
    uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    q15_t *pTwiddle;                     /**< points to the Sin twiddle factor table. */
    uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
  } arm_cfft_radix2_instance_q15;

/* Deprecated */
  arm_status arm_cfft_radix2_init_q15(
  arm_cfft_radix2_instance_q15 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

/* Deprecated */
  void arm_cfft_radix2_q15(
  const arm_cfft_radix2_instance_q15 * S,
  q15_t * pSrc);



  /**
   * @brief Instance structure for the Q15 CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                 /**< length of the FFT. */
    uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    q15_t *pTwiddle;                 /**< points to the twiddle factor table. */
    uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
  } arm_cfft_radix4_instance_q15;

/* Deprecated */
  arm_status arm_cfft_radix4_init_q15(
  arm_cfft_radix4_instance_q15 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

/* Deprecated */
  void arm_cfft_radix4_q15(
  const arm_cfft_radix4_instance_q15 * S,
  q15_t * pSrc);

  /**
   * @brief Instance structure for the Radix-2 Q31 CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                 /**< length of the FFT. */
    uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    q31_t *pTwiddle;                     /**< points to the Twiddle factor table. */
    uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
  } arm_cfft_radix2_instance_q31;

/* Deprecated */
  arm_status arm_cfft_radix2_init_q31(
  arm_cfft_radix2_instance_q31 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

/* Deprecated */
  void arm_cfft_radix2_q31(
  const arm_cfft_radix2_instance_q31 * S,
  q31_t * pSrc);

  /**
   * @brief Instance structure for the Q31 CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                 /**< length of the FFT. */
    uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    q31_t *pTwiddle;                 /**< points to the twiddle factor table. */
    uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
  } arm_cfft_radix4_instance_q31;

/* Deprecated */
  void arm_cfft_radix4_q31(
  const arm_cfft_radix4_instance_q31 * S,
  q31_t * pSrc);

/* Deprecated */
  arm_status arm_cfft_radix4_init_q31(
  arm_cfft_radix4_instance_q31 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

  /**
   * @brief Instance structure for the floating-point CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                   /**< length of the FFT. */
    uint8_t ifftFlag;                  /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;            /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    float32_t *pTwiddle;               /**< points to the Twiddle factor table. */
    uint16_t *pBitRevTable;            /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;         /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;             /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
    float32_t onebyfftLen;                 /**< value of 1/fftLen. */
  } arm_cfft_radix2_instance_f32;

/* Deprecated */
  arm_status arm_cfft_radix2_init_f32(
  arm_cfft_radix2_instance_f32 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

/* Deprecated */
  void arm_cfft_radix2_f32(
  const arm_cfft_radix2_instance_f32 * S,
  float32_t * pSrc);

  /**
   * @brief Instance structure for the floating-point CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                   /**< length of the FFT. */
    uint8_t ifftFlag;                  /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
    uint8_t bitReverseFlag;            /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
    float32_t *pTwiddle;               /**< points to the Twiddle factor table. */
    uint16_t *pBitRevTable;            /**< points to the bit reversal table. */
    uint16_t twidCoefModifier;         /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    uint16_t bitRevFactor;             /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
    float32_t onebyfftLen;                 /**< value of 1/fftLen. */
  } arm_cfft_radix4_instance_f32;

/* Deprecated */
  arm_status arm_cfft_radix4_init_f32(
  arm_cfft_radix4_instance_f32 * S,
  uint16_t fftLen,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

/* Deprecated */
  void arm_cfft_radix4_f32(
  const arm_cfft_radix4_instance_f32 * S,
  float32_t * pSrc);

  /**
   * @brief Instance structure for the fixed-point CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                   /**< length of the FFT. */
    const q15_t *pTwiddle;             /**< points to the Twiddle factor table. */
    const uint16_t *pBitRevTable;      /**< points to the bit reversal table. */
    uint16_t bitRevLength;             /**< bit reversal table length. */
  } arm_cfft_instance_q15;

void arm_cfft_q15( 
    const arm_cfft_instance_q15 * S, 
    q15_t * p1,
    uint8_t ifftFlag,
    uint8_t bitReverseFlag);  

  /**
   * @brief Instance structure for the fixed-point CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                   /**< length of the FFT. */
    const q31_t *pTwiddle;             /**< points to the Twiddle factor table. */
    const uint16_t *pBitRevTable;      /**< points to the bit reversal table. */
    uint16_t bitRevLength;             /**< bit reversal table length. */
  } arm_cfft_instance_q31;

void arm_cfft_q31( 
    const arm_cfft_instance_q31 * S, 
    q31_t * p1,
    uint8_t ifftFlag,
    uint8_t bitReverseFlag);  
  
  /**
   * @brief Instance structure for the floating-point CFFT/CIFFT function.
   */

  typedef struct
  {
    uint16_t fftLen;                   /**< length of the FFT. */
    const float32_t *pTwiddle;         /**< points to the Twiddle factor table. */
    const uint16_t *pBitRevTable;      /**< points to the bit reversal table. */
    uint16_t bitRevLength;             /**< bit reversal table length. */
  } arm_cfft_instance_f32;

  void arm_cfft_f32(
  const arm_cfft_instance_f32 * S,
  float32_t * p1,
  uint8_t ifftFlag,
  uint8_t bitReverseFlag);

  /**
   * @brief Instance structure for the Q15 RFFT/RIFFT function.
   */

  typedef struct
  {
    uint32_t fftLenReal;                      /**< length of the real FFT. */
    uint8_t ifftFlagR;                        /**< flag that selects forward (ifftFlagR=0) or inverse (ifftFlagR=1) transform. */
    uint8_t bitReverseFlagR;                  /**< flag that enables (bitReverseFlagR=1) or disables (bitReverseFlagR=0) bit reversal of output. */
    uint32_t twidCoefRModifier;               /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    q15_t *pTwiddleAReal;                     /**< points to the real twiddle factor table. */
    q15_t *pTwiddleBReal;                     /**< points to the imag twiddle factor table. */
    const arm_cfft_instance_q15 *pCfft;       /**< points to the complex FFT instance. */
  } arm_rfft_instance_q15;

  arm_status arm_rfft_init_q15(
  arm_rfft_instance_q15 * S,
  uint32_t fftLenReal,
  uint32_t ifftFlagR,
  uint32_t bitReverseFlag);

  void arm_rfft_q15(
  const arm_rfft_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst);

  /**
   * @brief Instance structure for the Q31 RFFT/RIFFT function.
   */

  typedef struct
  {
    uint32_t fftLenReal;                        /**< length of the real FFT. */
    uint8_t ifftFlagR;                          /**< flag that selects forward (ifftFlagR=0) or inverse (ifftFlagR=1) transform. */
    uint8_t bitReverseFlagR;                    /**< flag that enables (bitReverseFlagR=1) or disables (bitReverseFlagR=0) bit reversal of output. */
    uint32_t twidCoefRModifier;                 /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    q31_t *pTwiddleAReal;                       /**< points to the real twiddle factor table. */
    q31_t *pTwiddleBReal;                       /**< points to the imag twiddle factor table. */
    const arm_cfft_instance_q31 *pCfft;         /**< points to the complex FFT instance. */
  } arm_rfft_instance_q31;

  arm_status arm_rfft_init_q31(
  arm_rfft_instance_q31 * S,
  uint32_t fftLenReal,
  uint32_t ifftFlagR,
  uint32_t bitReverseFlag);

  void arm_rfft_q31(
  const arm_rfft_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst);

  /**
   * @brief Instance structure for the floating-point RFFT/RIFFT function.
   */

  typedef struct
  {
    uint32_t fftLenReal;                        /**< length of the real FFT. */
    uint16_t fftLenBy2;                         /**< length of the complex FFT. */
    uint8_t ifftFlagR;                          /**< flag that selects forward (ifftFlagR=0) or inverse (ifftFlagR=1) transform. */
    uint8_t bitReverseFlagR;                    /**< flag that enables (bitReverseFlagR=1) or disables (bitReverseFlagR=0) bit reversal of output. */
    uint32_t twidCoefRModifier;                     /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
    float32_t *pTwiddleAReal;                   /**< points to the real twiddle factor table. */
    float32_t *pTwiddleBReal;                   /**< points to the imag twiddle factor table. */
    arm_cfft_radix4_instance_f32 *pCfft;        /**< points to the complex FFT instance. */
  } arm_rfft_instance_f32;

  arm_status arm_rfft_init_f32(
  arm_rfft_instance_f32 * S,
  arm_cfft_radix4_instance_f32 * S_CFFT,
  uint32_t fftLenReal,
  uint32_t ifftFlagR,
  uint32_t bitReverseFlag);

  void arm_rfft_f32(
  const arm_rfft_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst);

  /**
   * @brief Instance structure for the floating-point RFFT/RIFFT function.
   */

typedef struct
  {
    arm_cfft_instance_f32 Sint;      /**< Internal CFFT structure. */
    uint16_t fftLenRFFT;                        /**< length of the real sequence */
	float32_t * pTwiddleRFFT;					/**< Twiddle factors real stage  */
  } arm_rfft_fast_instance_f32 ;

arm_status arm_rfft_fast_init_f32 (
	arm_rfft_fast_instance_f32 * S,
	uint16_t fftLen);

void arm_rfft_fast_f32(
  arm_rfft_fast_instance_f32 * S,
  float32_t * p, float32_t * pOut,
  uint8_t ifftFlag);

  /**
   * @brief Instance structure for the floating-point DCT4/IDCT4 function.
   */

  typedef struct
  {
    uint16_t N;                         /**< length of the DCT4. */
    uint16_t Nby2;                      /**< half of the length of the DCT4. */
    float32_t normalize;                /**< normalizing factor. */
    float32_t *pTwiddle;                /**< points to the twiddle factor table. */
    float32_t *pCosFactor;              /**< points to the cosFactor table. */
    arm_rfft_instance_f32 *pRfft;        /**< points to the real FFT instance. */
    arm_cfft_radix4_instance_f32 *pCfft; /**< points to the complex FFT instance. */
  } arm_dct4_instance_f32;

  /**
   * @brief  Initialization function for the floating-point DCT4/IDCT4.
   * @param[in,out] *S         points to an instance of floating-point DCT4/IDCT4 structure.
   * @param[in]     *S_RFFT    points to an instance of floating-point RFFT/RIFFT structure.
   * @param[in]     *S_CFFT    points to an instance of floating-point CFFT/CIFFT structure.
   * @param[in]     N          length of the DCT4.
   * @param[in]     Nby2       half of the length of the DCT4.
   * @param[in]     normalize  normalizing factor.
   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>fftLenReal</code> is not a supported transform length.
   */

  arm_status arm_dct4_init_f32(
  arm_dct4_instance_f32 * S,
  arm_rfft_instance_f32 * S_RFFT,
  arm_cfft_radix4_instance_f32 * S_CFFT,
  uint16_t N,
  uint16_t Nby2,
  float32_t normalize);

  /**
   * @brief Processing function for the floating-point DCT4/IDCT4.
   * @param[in]       *S             points to an instance of the floating-point DCT4/IDCT4 structure.
   * @param[in]       *pState        points to state buffer.
   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
   * @return none.
   */

  void arm_dct4_f32(
  const arm_dct4_instance_f32 * S,
  float32_t * pState,
  float32_t * pInlineBuffer);

  /**
   * @brief Instance structure for the Q31 DCT4/IDCT4 function.
   */

  typedef struct
  {
    uint16_t N;                         /**< length of the DCT4. */
    uint16_t Nby2;                      /**< half of the length of the DCT4. */
    q31_t normalize;                    /**< normalizing factor. */
    q31_t *pTwiddle;                    /**< points to the twiddle factor table. */
    q31_t *pCosFactor;                  /**< points to the cosFactor table. */
    arm_rfft_instance_q31 *pRfft;        /**< points to the real FFT instance. */
    arm_cfft_radix4_instance_q31 *pCfft; /**< points to the complex FFT instance. */
  } arm_dct4_instance_q31;

  /**
   * @brief  Initialization function for the Q31 DCT4/IDCT4.
   * @param[in,out] *S         points to an instance of Q31 DCT4/IDCT4 structure.
   * @param[in]     *S_RFFT    points to an instance of Q31 RFFT/RIFFT structure
   * @param[in]     *S_CFFT    points to an instance of Q31 CFFT/CIFFT structure
   * @param[in]     N          length of the DCT4.
   * @param[in]     Nby2       half of the length of the DCT4.
   * @param[in]     normalize  normalizing factor.
   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
   */

  arm_status arm_dct4_init_q31(
  arm_dct4_instance_q31 * S,
  arm_rfft_instance_q31 * S_RFFT,
  arm_cfft_radix4_instance_q31 * S_CFFT,
  uint16_t N,
  uint16_t Nby2,
  q31_t normalize);

  /**
   * @brief Processing function for the Q31 DCT4/IDCT4.
   * @param[in]       *S             points to an instance of the Q31 DCT4 structure.
   * @param[in]       *pState        points to state buffer.
   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
   * @return none.
   */

  void arm_dct4_q31(
  const arm_dct4_instance_q31 * S,
  q31_t * pState,
  q31_t * pInlineBuffer);

  /**
   * @brief Instance structure for the Q15 DCT4/IDCT4 function.
   */

  typedef struct
  {
    uint16_t N;                         /**< length of the DCT4. */
    uint16_t Nby2;                      /**< half of the length of the DCT4. */
    q15_t normalize;                    /**< normalizing factor. */
    q15_t *pTwiddle;                    /**< points to the twiddle factor table. */
    q15_t *pCosFactor;                  /**< points to the cosFactor table. */
    arm_rfft_instance_q15 *pRfft;        /**< points to the real FFT instance. */
    arm_cfft_radix4_instance_q15 *pCfft; /**< points to the complex FFT instance. */
  } arm_dct4_instance_q15;

  /**
   * @brief  Initialization function for the Q15 DCT4/IDCT4.
   * @param[in,out] *S         points to an instance of Q15 DCT4/IDCT4 structure.
   * @param[in]     *S_RFFT    points to an instance of Q15 RFFT/RIFFT structure.
   * @param[in]     *S_CFFT    points to an instance of Q15 CFFT/CIFFT structure.
   * @param[in]     N          length of the DCT4.
   * @param[in]     Nby2       half of the length of the DCT4.
   * @param[in]     normalize  normalizing factor.
   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
   */

  arm_status arm_dct4_init_q15(
  arm_dct4_instance_q15 * S,
  arm_rfft_instance_q15 * S_RFFT,
  arm_cfft_radix4_instance_q15 * S_CFFT,
  uint16_t N,
  uint16_t Nby2,
  q15_t normalize);

  /**
   * @brief Processing function for the Q15 DCT4/IDCT4.
   * @param[in]       *S             points to an instance of the Q15 DCT4 structure.
   * @param[in]       *pState        points to state buffer.
   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
   * @return none.
   */

  void arm_dct4_q15(
  const arm_dct4_instance_q15 * S,
  q15_t * pState,
  q15_t * pInlineBuffer);

  /**
   * @brief Floating-point vector addition.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_add_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q7 vector addition.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_add_q7(
  q7_t * pSrcA,
  q7_t * pSrcB,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q15 vector addition.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_add_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q31 vector addition.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_add_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Floating-point vector subtraction.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_sub_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q7 vector subtraction.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_sub_q7(
  q7_t * pSrcA,
  q7_t * pSrcB,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q15 vector subtraction.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_sub_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q31 vector subtraction.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_sub_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Multiplies a floating-point vector by a scalar.
   * @param[in]       *pSrc points to the input vector
   * @param[in]       scale scale factor to be applied
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in the vector
   * @return none.
   */

  void arm_scale_f32(
  float32_t * pSrc,
  float32_t scale,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Multiplies a Q7 vector by a scalar.
   * @param[in]       *pSrc points to the input vector
   * @param[in]       scaleFract fractional portion of the scale value
   * @param[in]       shift number of bits to shift the result by
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in the vector
   * @return none.
   */

  void arm_scale_q7(
  q7_t * pSrc,
  q7_t scaleFract,
  int8_t shift,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Multiplies a Q15 vector by a scalar.
   * @param[in]       *pSrc points to the input vector
   * @param[in]       scaleFract fractional portion of the scale value
   * @param[in]       shift number of bits to shift the result by
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in the vector
   * @return none.
   */

  void arm_scale_q15(
  q15_t * pSrc,
  q15_t scaleFract,
  int8_t shift,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Multiplies a Q31 vector by a scalar.
   * @param[in]       *pSrc points to the input vector
   * @param[in]       scaleFract fractional portion of the scale value
   * @param[in]       shift number of bits to shift the result by
   * @param[out]      *pDst points to the output vector
   * @param[in]       blockSize number of samples in the vector
   * @return none.
   */

  void arm_scale_q31(
  q31_t * pSrc,
  q31_t scaleFract,
  int8_t shift,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q7 vector absolute value.
   * @param[in]       *pSrc points to the input buffer
   * @param[out]      *pDst points to the output buffer
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_abs_q7(
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Floating-point vector absolute value.
   * @param[in]       *pSrc points to the input buffer
   * @param[out]      *pDst points to the output buffer
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_abs_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q15 vector absolute value.
   * @param[in]       *pSrc points to the input buffer
   * @param[out]      *pDst points to the output buffer
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_abs_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Q31 vector absolute value.
   * @param[in]       *pSrc points to the input buffer
   * @param[out]      *pDst points to the output buffer
   * @param[in]       blockSize number of samples in each vector
   * @return none.
   */

  void arm_abs_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Dot product of floating-point vectors.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[in]       blockSize number of samples in each vector
   * @param[out]      *result output result returned here
   * @return none.
   */

  void arm_dot_prod_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  uint32_t blockSize,
  float32_t * result);

  /**
   * @brief Dot product of Q7 vectors.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[in]       blockSize number of samples in each vector
   * @param[out]      *result output result returned here
   * @return none.
   */

  void arm_dot_prod_q7(
  q7_t * pSrcA,
  q7_t * pSrcB,
  uint32_t blockSize,
  q31_t * result);

  /**
   * @brief Dot product of Q15 vectors.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[in]       blockSize number of samples in each vector
   * @param[out]      *result output result returned here
   * @return none.
   */

  void arm_dot_prod_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  uint32_t blockSize,
  q63_t * result);

  /**
   * @brief Dot product of Q31 vectors.
   * @param[in]       *pSrcA points to the first input vector
   * @param[in]       *pSrcB points to the second input vector
   * @param[in]       blockSize number of samples in each vector
   * @param[out]      *result output result returned here
   * @return none.
   */

  void arm_dot_prod_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  uint32_t blockSize,
  q63_t * result);

  /**
   * @brief  Shifts the elements of a Q7 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q7(
  q7_t * pSrc,
  int8_t shiftBits,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Shifts the elements of a Q15 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q15(
  q15_t * pSrc,
  int8_t shiftBits,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Shifts the elements of a Q31 vector a specified number of bits.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_shift_q31(
  q31_t * pSrc,
  int8_t shiftBits,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a floating-point vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_f32(
  float32_t * pSrc,
  float32_t offset,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q7 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q7(
  q7_t * pSrc,
  q7_t offset,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q15 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q15(
  q15_t * pSrc,
  q15_t offset,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Adds a constant offset to a Q31 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[in]  offset is the offset to be added
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_offset_q31(
  q31_t * pSrc,
  q31_t offset,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a floating-point vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q7 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q7(
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q15 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Negates the elements of a Q31 vector.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  blockSize number of samples in the vector
   * @return none.
   */

  void arm_negate_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);
  /**
   * @brief  Copies the elements of a floating-point vector.
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q7 vector.
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q7(
  q7_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q15 vector.
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Copies the elements of a Q31 vector.
   * @param[in]  *pSrc input pointer
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_copy_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);
  /**
   * @brief  Fills a constant value into a floating-point vector.
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_f32(
  float32_t value,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q7 vector.
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q7(
  q7_t value,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q15 vector.
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q15(
  q15_t value,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Fills a constant value into a Q31 vector.
   * @param[in]  value input value to be filled
   * @param[out]  *pDst output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_fill_q31(
  q31_t value,
  q31_t * pDst,
  uint32_t blockSize);

/**
 * @brief Convolution of floating-point sequences.
 * @param[in] *pSrcA points to the first input sequence.
 * @param[in] srcALen length of the first input sequence.
 * @param[in] *pSrcB points to the second input sequence.
 * @param[in] srcBLen length of the second input sequence.
 * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.
 * @return none.
 */

  void arm_conv_f32(
  float32_t * pSrcA,
  uint32_t srcALen,
  float32_t * pSrcB,
  uint32_t srcBLen,
  float32_t * pDst);


  /**
   * @brief Convolution of Q15 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
   * @return none.
   */


  void arm_conv_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**
 * @brief Convolution of Q15 sequences.
 * @param[in] *pSrcA points to the first input sequence.
 * @param[in] srcALen length of the first input sequence.
 * @param[in] *pSrcB points to the second input sequence.
 * @param[in] srcBLen length of the second input sequence.
 * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.
 * @return none.
 */

  void arm_conv_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst);

  /**
   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_fast_q15(
			  q15_t * pSrcA,
			 uint32_t srcALen,
			  q15_t * pSrcB,
			 uint32_t srcBLen,
			 q15_t * pDst);

  /**
   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
   * @return none.
   */

  void arm_conv_fast_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);



  /**
   * @brief Convolution of Q31 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);

  /**
   * @brief Convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_fast_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);


    /**
   * @brief Convolution of Q7 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
   * @return none.
   */

  void arm_conv_opt_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);



  /**
   * @brief Convolution of Q7 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
   * @return none.
   */

  void arm_conv_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst);


  /**
   * @brief Partial convolution of floating-point sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_f32(
  float32_t * pSrcA,
  uint32_t srcALen,
  float32_t * pSrcB,
  uint32_t srcBLen,
  float32_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);

    /**
   * @brief Partial convolution of Q15 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**
   * @brief Partial convolution of Q15 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);

  /**
   * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_fast_q15(
				        q15_t * pSrcA,
				       uint32_t srcALen,
				        q15_t * pSrcB,
				       uint32_t srcBLen,
				       q15_t * pDst,
				       uint32_t firstIndex,
				       uint32_t numPoints);


  /**
   * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_fast_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


  /**
   * @brief Partial convolution of Q31 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);


  /**
   * @brief Partial convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_fast_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);


  /**
   * @brief Partial convolution of Q7 sequences
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_opt_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints,
  q15_t * pScratch1,
  q15_t * pScratch2);


/**
   * @brief Partial convolution of Q7 sequences.
   * @param[in]       *pSrcA points to the first input sequence.
   * @param[in]       srcALen length of the first input sequence.
   * @param[in]       *pSrcB points to the second input sequence.
   * @param[in]       srcBLen length of the second input sequence.
   * @param[out]      *pDst points to the block of output data
   * @param[in]       firstIndex is the first output sample to start with.
   * @param[in]       numPoints is the number of output points to be computed.
   * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
   */

  arm_status arm_conv_partial_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  uint32_t firstIndex,
  uint32_t numPoints);



  /**
   * @brief Instance structure for the Q15 FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                      /**< decimation factor. */
    uint16_t numTaps;               /**< number of coefficients in the filter. */
    q15_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
    q15_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
  } arm_fir_decimate_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                  /**< decimation factor. */
    uint16_t numTaps;           /**< number of coefficients in the filter. */
    q31_t *pCoeffs;              /**< points to the coefficient array. The array is of length numTaps.*/
    q31_t *pState;               /**< points to the state variable array. The array is of length numTaps+blockSize-1. */

  } arm_fir_decimate_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR decimator.
   */

  typedef struct
  {
    uint8_t M;                          /**< decimation factor. */
    uint16_t numTaps;                   /**< number of coefficients in the filter. */
    float32_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
    float32_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */

  } arm_fir_decimate_instance_f32;



  /**
   * @brief Processing function for the floating-point FIR decimator.
   * @param[in] *S points to an instance of the floating-point FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_f32(
  const arm_fir_decimate_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the floating-point FIR decimator.
   * @param[in,out] *S points to an instance of the floating-point FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_f32(
  arm_fir_decimate_instance_f32 * S,
  uint16_t numTaps,
  uint8_t M,
  float32_t * pCoeffs,
  float32_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q15 FIR decimator.
   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_q15(
  const arm_fir_decimate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q15 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_fast_q15(
  const arm_fir_decimate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);



  /**
   * @brief  Initialization function for the Q15 FIR decimator.
   * @param[in,out] *S points to an instance of the Q15 FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_q15(
  arm_fir_decimate_instance_q15 * S,
  uint16_t numTaps,
  uint8_t M,
  q15_t * pCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR decimator.
   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_q31(
  const arm_fir_decimate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data
   * @param[in] blockSize number of input samples to process per call.
   * @return none
   */

  void arm_fir_decimate_fast_q31(
  arm_fir_decimate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q31 FIR decimator.
   * @param[in,out] *S points to an instance of the Q31 FIR decimator structure.
   * @param[in] numTaps  number of coefficients in the filter.
   * @param[in] M  decimation factor.
   * @param[in] *pCoeffs points to the filter coefficients.
   * @param[in] *pState points to the state buffer.
   * @param[in] blockSize number of input samples to process per call.
   * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * <code>blockSize</code> is not a multiple of <code>M</code>.
   */

  arm_status arm_fir_decimate_init_q31(
  arm_fir_decimate_instance_q31 * S,
  uint16_t numTaps,
  uint8_t M,
  q31_t * pCoeffs,
  q31_t * pState,
  uint32_t blockSize);



  /**
   * @brief Instance structure for the Q15 FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                      /**< upsample factor. */
    uint16_t phaseLength;           /**< length of each polyphase filter component. */
    q15_t *pCoeffs;                 /**< points to the coefficient array. The array is of length L*phaseLength. */
    q15_t *pState;                  /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
  } arm_fir_interpolate_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                      /**< upsample factor. */
    uint16_t phaseLength;           /**< length of each polyphase filter component. */
    q31_t *pCoeffs;                  /**< points to the coefficient array. The array is of length L*phaseLength. */
    q31_t *pState;                   /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
  } arm_fir_interpolate_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR interpolator.
   */

  typedef struct
  {
    uint8_t L;                     /**< upsample factor. */
    uint16_t phaseLength;          /**< length of each polyphase filter component. */
    float32_t *pCoeffs;             /**< points to the coefficient array. The array is of length L*phaseLength. */
    float32_t *pState;              /**< points to the state variable array. The array is of length phaseLength+numTaps-1. */
  } arm_fir_interpolate_instance_f32;


  /**
   * @brief Processing function for the Q15 FIR interpolator.
   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_q15(
  const arm_fir_interpolate_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q15 FIR interpolator.
   * @param[in,out] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_q15(
  arm_fir_interpolate_instance_q15 * S,
  uint8_t L,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 FIR interpolator.
   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_q31(
  const arm_fir_interpolate_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q31 FIR interpolator.
   * @param[in,out] *S        points to an instance of the Q31 FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_q31(
  arm_fir_interpolate_instance_q31 * S,
  uint8_t L,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  uint32_t blockSize);


  /**
   * @brief Processing function for the floating-point FIR interpolator.
   * @param[in] *S        points to an instance of the floating-point FIR interpolator structure.
   * @param[in] *pSrc     points to the block of input data.
   * @param[out] *pDst    points to the block of output data.
   * @param[in] blockSize number of input samples to process per call.
   * @return none.
   */

  void arm_fir_interpolate_f32(
  const arm_fir_interpolate_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the floating-point FIR interpolator.
   * @param[in,out] *S        points to an instance of the floating-point FIR interpolator structure.
   * @param[in]     L         upsample factor.
   * @param[in]     numTaps   number of filter coefficients in the filter.
   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
   * @param[in]     *pState   points to the state buffer.
   * @param[in]     blockSize number of input samples to process per call.
   * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
   * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
   */

  arm_status arm_fir_interpolate_init_f32(
  arm_fir_interpolate_instance_f32 * S,
  uint8_t L,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  uint32_t blockSize);

  /**
   * @brief Instance structure for the high precision Q31 Biquad cascade filter.
   */

  typedef struct
  {
    uint8_t numStages;       /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    q63_t *pState;           /**< points to the array of state coefficients.  The array is of length 4*numStages. */
    q31_t *pCoeffs;          /**< points to the array of coefficients.  The array is of length 5*numStages. */
    uint8_t postShift;       /**< additional shift, in bits, applied to each output sample. */

  } arm_biquad_cas_df1_32x64_ins_q31;


  /**
   * @param[in]  *S        points to an instance of the high precision Q31 Biquad cascade filter structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_biquad_cas_df1_32x64_q31(
  const arm_biquad_cas_df1_32x64_ins_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);


  /**
   * @param[in,out] *S           points to an instance of the high precision Q31 Biquad cascade filter structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @param[in]     postShift    shift to be applied to the output. Varies according to the coefficients format
   * @return        none
   */

  void arm_biquad_cas_df1_32x64_init_q31(
  arm_biquad_cas_df1_32x64_ins_q31 * S,
  uint8_t numStages,
  q31_t * pCoeffs,
  q63_t * pState,
  uint8_t postShift);



  /**
   * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
   */

  typedef struct
  {
    uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    float32_t *pState;         /**< points to the array of state coefficients.  The array is of length 2*numStages. */
    float32_t *pCoeffs;        /**< points to the array of coefficients.  The array is of length 5*numStages. */
  } arm_biquad_cascade_df2T_instance_f32;



  /**
   * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
   */

  typedef struct
  {
    uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    float32_t *pState;         /**< points to the array of state coefficients.  The array is of length 4*numStages. */
    float32_t *pCoeffs;        /**< points to the array of coefficients.  The array is of length 5*numStages. */
  } arm_biquad_cascade_stereo_df2T_instance_f32;



  /**
   * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
   */

  typedef struct
  {
    uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
    float64_t *pState;         /**< points to the array of state coefficients.  The array is of length 2*numStages. */
    float64_t *pCoeffs;        /**< points to the array of coefficients.  The array is of length 5*numStages. */
  } arm_biquad_cascade_df2T_instance_f64;


  /**
   * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter.
   * @param[in]  *S        points to an instance of the filter data structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_biquad_cascade_df2T_f32(
  const arm_biquad_cascade_df2T_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);


  /**
   * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter. 2 channels
   * @param[in]  *S        points to an instance of the filter data structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_biquad_cascade_stereo_df2T_f32(
  const arm_biquad_cascade_stereo_df2T_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter.
   * @param[in]  *S        points to an instance of the filter data structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_biquad_cascade_df2T_f64(
  const arm_biquad_cascade_df2T_instance_f64 * S,
  float64_t * pSrc,
  float64_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the filter data structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @return        none
   */

  void arm_biquad_cascade_df2T_init_f32(
  arm_biquad_cascade_df2T_instance_f32 * S,
  uint8_t numStages,
  float32_t * pCoeffs,
  float32_t * pState);


  /**
   * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the filter data structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @return        none
   */

  void arm_biquad_cascade_stereo_df2T_init_f32(
  arm_biquad_cascade_stereo_df2T_instance_f32 * S,
  uint8_t numStages,
  float32_t * pCoeffs,
  float32_t * pState);


  /**
   * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
   * @param[in,out] *S           points to an instance of the filter data structure.
   * @param[in]     numStages    number of 2nd order stages in the filter.
   * @param[in]     *pCoeffs     points to the filter coefficients.
   * @param[in]     *pState      points to the state buffer.
   * @return        none
   */

  void arm_biquad_cascade_df2T_init_f64(
  arm_biquad_cascade_df2T_instance_f64 * S,
  uint8_t numStages,
  float64_t * pCoeffs,
  float64_t * pState);



  /**
   * @brief Instance structure for the Q15 FIR lattice filter.
   */

  typedef struct
  {
    uint16_t numStages;                          /**< number of filter stages. */
    q15_t *pState;                               /**< points to the state variable array. The array is of length numStages. */
    q15_t *pCoeffs;                              /**< points to the coefficient array. The array is of length numStages. */
  } arm_fir_lattice_instance_q15;

  /**
   * @brief Instance structure for the Q31 FIR lattice filter.
   */

  typedef struct
  {
    uint16_t numStages;                          /**< number of filter stages. */
    q31_t *pState;                               /**< points to the state variable array. The array is of length numStages. */
    q31_t *pCoeffs;                              /**< points to the coefficient array. The array is of length numStages. */
  } arm_fir_lattice_instance_q31;

  /**
   * @brief Instance structure for the floating-point FIR lattice filter.
   */

  typedef struct
  {
    uint16_t numStages;                  /**< number of filter stages. */
    float32_t *pState;                   /**< points to the state variable array. The array is of length numStages. */
    float32_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numStages. */
  } arm_fir_lattice_instance_f32;

  /**
   * @brief Initialization function for the Q15 FIR lattice filter.
   * @param[in] *S points to an instance of the Q15 FIR lattice structure.
   * @param[in] numStages  number of filter stages.
   * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
   * @param[in] *pState points to the state buffer.  The array is of length numStages.
   * @return none.
   */

  void arm_fir_lattice_init_q15(
  arm_fir_lattice_instance_q15 * S,
  uint16_t numStages,
  q15_t * pCoeffs,
  q15_t * pState);


  /**
   * @brief Processing function for the Q15 FIR lattice filter.
   * @param[in] *S points to an instance of the Q15 FIR lattice structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */
  void arm_fir_lattice_q15(
  const arm_fir_lattice_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Initialization function for the Q31 FIR lattice filter.
   * @param[in] *S points to an instance of the Q31 FIR lattice structure.
   * @param[in] numStages  number of filter stages.
   * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
   * @param[in] *pState points to the state buffer.   The array is of length numStages.
   * @return none.
   */

  void arm_fir_lattice_init_q31(
  arm_fir_lattice_instance_q31 * S,
  uint16_t numStages,
  q31_t * pCoeffs,
  q31_t * pState);


  /**
   * @brief Processing function for the Q31 FIR lattice filter.
   * @param[in]  *S        points to an instance of the Q31 FIR lattice structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_fir_lattice_q31(
  const arm_fir_lattice_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

/**
 * @brief Initialization function for the floating-point FIR lattice filter.
 * @param[in] *S points to an instance of the floating-point FIR lattice structure.
 * @param[in] numStages  number of filter stages.
 * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
 * @param[in] *pState points to the state buffer.  The array is of length numStages.
 * @return none.
 */

  void arm_fir_lattice_init_f32(
  arm_fir_lattice_instance_f32 * S,
  uint16_t numStages,
  float32_t * pCoeffs,
  float32_t * pState);

  /**
   * @brief Processing function for the floating-point FIR lattice filter.
   * @param[in]  *S        points to an instance of the floating-point FIR lattice structure.
   * @param[in]  *pSrc     points to the block of input data.
   * @param[out] *pDst     points to the block of output data
   * @param[in]  blockSize number of samples to process.
   * @return none.
   */

  void arm_fir_lattice_f32(
  const arm_fir_lattice_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Instance structure for the Q15 IIR lattice filter.
   */
  typedef struct
  {
    uint16_t numStages;                         /**< number of stages in the filter. */
    q15_t *pState;                              /**< points to the state variable array. The array is of length numStages+blockSize. */
    q15_t *pkCoeffs;                            /**< points to the reflection coefficient array. The array is of length numStages. */
    q15_t *pvCoeffs;                            /**< points to the ladder coefficient array. The array is of length numStages+1. */
  } arm_iir_lattice_instance_q15;

  /**
   * @brief Instance structure for the Q31 IIR lattice filter.
   */
  typedef struct
  {
    uint16_t numStages;                         /**< number of stages in the filter. */
    q31_t *pState;                              /**< points to the state variable array. The array is of length numStages+blockSize. */
    q31_t *pkCoeffs;                            /**< points to the reflection coefficient array. The array is of length numStages. */
    q31_t *pvCoeffs;                            /**< points to the ladder coefficient array. The array is of length numStages+1. */
  } arm_iir_lattice_instance_q31;

  /**
   * @brief Instance structure for the floating-point IIR lattice filter.
   */
  typedef struct
  {
    uint16_t numStages;                         /**< number of stages in the filter. */
    float32_t *pState;                          /**< points to the state variable array. The array is of length numStages+blockSize. */
    float32_t *pkCoeffs;                        /**< points to the reflection coefficient array. The array is of length numStages. */
    float32_t *pvCoeffs;                        /**< points to the ladder coefficient array. The array is of length numStages+1. */
  } arm_iir_lattice_instance_f32;

  /**
   * @brief Processing function for the floating-point IIR lattice filter.
   * @param[in] *S points to an instance of the floating-point IIR lattice structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_iir_lattice_f32(
  const arm_iir_lattice_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Initialization function for the floating-point IIR lattice filter.
   * @param[in] *S points to an instance of the floating-point IIR lattice structure.
   * @param[in] numStages number of stages in the filter.
   * @param[in] *pkCoeffs points to the reflection coefficient buffer.  The array is of length numStages.
   * @param[in] *pvCoeffs points to the ladder coefficient buffer.  The array is of length numStages+1.
   * @param[in] *pState points to the state buffer.  The array is of length numStages+blockSize-1.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_iir_lattice_init_f32(
  arm_iir_lattice_instance_f32 * S,
  uint16_t numStages,
  float32_t * pkCoeffs,
  float32_t * pvCoeffs,
  float32_t * pState,
  uint32_t blockSize);


  /**
   * @brief Processing function for the Q31 IIR lattice filter.
   * @param[in] *S points to an instance of the Q31 IIR lattice structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_iir_lattice_q31(
  const arm_iir_lattice_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);


  /**
   * @brief Initialization function for the Q31 IIR lattice filter.
   * @param[in] *S points to an instance of the Q31 IIR lattice structure.
   * @param[in] numStages number of stages in the filter.
   * @param[in] *pkCoeffs points to the reflection coefficient buffer.  The array is of length numStages.
   * @param[in] *pvCoeffs points to the ladder coefficient buffer.  The array is of length numStages+1.
   * @param[in] *pState points to the state buffer.  The array is of length numStages+blockSize.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_iir_lattice_init_q31(
  arm_iir_lattice_instance_q31 * S,
  uint16_t numStages,
  q31_t * pkCoeffs,
  q31_t * pvCoeffs,
  q31_t * pState,
  uint32_t blockSize);


  /**
   * @brief Processing function for the Q15 IIR lattice filter.
   * @param[in] *S points to an instance of the Q15 IIR lattice structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[out] *pDst points to the block of output data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_iir_lattice_q15(
  const arm_iir_lattice_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);


/**
 * @brief Initialization function for the Q15 IIR lattice filter.
 * @param[in] *S points to an instance of the fixed-point Q15 IIR lattice structure.
 * @param[in] numStages  number of stages in the filter.
 * @param[in] *pkCoeffs points to reflection coefficient buffer.  The array is of length numStages.
 * @param[in] *pvCoeffs points to ladder coefficient buffer.  The array is of length numStages+1.
 * @param[in] *pState points to state buffer.  The array is of length numStages+blockSize.
 * @param[in] blockSize number of samples to process per call.
 * @return none.
 */

  void arm_iir_lattice_init_q15(
  arm_iir_lattice_instance_q15 * S,
  uint16_t numStages,
  q15_t * pkCoeffs,
  q15_t * pvCoeffs,
  q15_t * pState,
  uint32_t blockSize);

  /**
   * @brief Instance structure for the floating-point LMS filter.
   */

  typedef struct
  {
    uint16_t numTaps;    /**< number of coefficients in the filter. */
    float32_t *pState;   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    float32_t *pCoeffs;  /**< points to the coefficient array. The array is of length numTaps. */
    float32_t mu;        /**< step size that controls filter coefficient updates. */
  } arm_lms_instance_f32;

  /**
   * @brief Processing function for floating-point LMS filter.
   * @param[in]  *S points to an instance of the floating-point LMS filter structure.
   * @param[in]  *pSrc points to the block of input data.
   * @param[in]  *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in]  blockSize number of samples to process.
   * @return     none.
   */

  void arm_lms_f32(
  const arm_lms_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pRef,
  float32_t * pOut,
  float32_t * pErr,
  uint32_t blockSize);

  /**
   * @brief Initialization function for floating-point LMS filter.
   * @param[in] *S points to an instance of the floating-point LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to the coefficient buffer.
   * @param[in] *pState points to state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_init_f32(
  arm_lms_instance_f32 * S,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  float32_t mu,
  uint32_t blockSize);

  /**
   * @brief Instance structure for the Q15 LMS filter.
   */

  typedef struct
  {
    uint16_t numTaps;    /**< number of coefficients in the filter. */
    q15_t *pState;       /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q15_t *pCoeffs;      /**< points to the coefficient array. The array is of length numTaps. */
    q15_t mu;            /**< step size that controls filter coefficient updates. */
    uint32_t postShift;  /**< bit shift applied to coefficients. */
  } arm_lms_instance_q15;


  /**
   * @brief Initialization function for the Q15 LMS filter.
   * @param[in] *S points to an instance of the Q15 LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to the coefficient buffer.
   * @param[in] *pState points to the state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @param[in] postShift bit shift applied to coefficients.
   * @return    none.
   */

  void arm_lms_init_q15(
  arm_lms_instance_q15 * S,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  q15_t mu,
  uint32_t blockSize,
  uint32_t postShift);

  /**
   * @brief Processing function for Q15 LMS filter.
   * @param[in] *S points to an instance of the Q15 LMS filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[in] *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_q15(
  const arm_lms_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pRef,
  q15_t * pOut,
  q15_t * pErr,
  uint32_t blockSize);


  /**
   * @brief Instance structure for the Q31 LMS filter.
   */

  typedef struct
  {
    uint16_t numTaps;    /**< number of coefficients in the filter. */
    q31_t *pState;       /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q31_t *pCoeffs;      /**< points to the coefficient array. The array is of length numTaps. */
    q31_t mu;            /**< step size that controls filter coefficient updates. */
    uint32_t postShift;  /**< bit shift applied to coefficients. */

  } arm_lms_instance_q31;

  /**
   * @brief Processing function for Q31 LMS filter.
   * @param[in]  *S points to an instance of the Q15 LMS filter structure.
   * @param[in]  *pSrc points to the block of input data.
   * @param[in]  *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in]  blockSize number of samples to process.
   * @return     none.
   */

  void arm_lms_q31(
  const arm_lms_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pRef,
  q31_t * pOut,
  q31_t * pErr,
  uint32_t blockSize);

  /**
   * @brief Initialization function for Q31 LMS filter.
   * @param[in] *S points to an instance of the Q31 LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to coefficient buffer.
   * @param[in] *pState points to state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @param[in] postShift bit shift applied to coefficients.
   * @return none.
   */

  void arm_lms_init_q31(
  arm_lms_instance_q31 * S,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  q31_t mu,
  uint32_t blockSize,
  uint32_t postShift);

  /**
   * @brief Instance structure for the floating-point normalized LMS filter.
   */

  typedef struct
  {
    uint16_t numTaps;     /**< number of coefficients in the filter. */
    float32_t *pState;    /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    float32_t *pCoeffs;   /**< points to the coefficient array. The array is of length numTaps. */
    float32_t mu;        /**< step size that control filter coefficient updates. */
    float32_t energy;    /**< saves previous frame energy. */
    float32_t x0;        /**< saves previous input sample. */
  } arm_lms_norm_instance_f32;

  /**
   * @brief Processing function for floating-point normalized LMS filter.
   * @param[in] *S points to an instance of the floating-point normalized LMS filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[in] *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_norm_f32(
  arm_lms_norm_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pRef,
  float32_t * pOut,
  float32_t * pErr,
  uint32_t blockSize);

  /**
   * @brief Initialization function for floating-point normalized LMS filter.
   * @param[in] *S points to an instance of the floating-point LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to coefficient buffer.
   * @param[in] *pState points to state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_norm_init_f32(
  arm_lms_norm_instance_f32 * S,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  float32_t mu,
  uint32_t blockSize);


  /**
   * @brief Instance structure for the Q31 normalized LMS filter.
   */
  typedef struct
  {
    uint16_t numTaps;     /**< number of coefficients in the filter. */
    q31_t *pState;        /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q31_t *pCoeffs;       /**< points to the coefficient array. The array is of length numTaps. */
    q31_t mu;             /**< step size that controls filter coefficient updates. */
    uint8_t postShift;    /**< bit shift applied to coefficients. */
    q31_t *recipTable;    /**< points to the reciprocal initial value table. */
    q31_t energy;         /**< saves previous frame energy. */
    q31_t x0;             /**< saves previous input sample. */
  } arm_lms_norm_instance_q31;

  /**
   * @brief Processing function for Q31 normalized LMS filter.
   * @param[in] *S points to an instance of the Q31 normalized LMS filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[in] *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_norm_q31(
  arm_lms_norm_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pRef,
  q31_t * pOut,
  q31_t * pErr,
  uint32_t blockSize);

  /**
   * @brief Initialization function for Q31 normalized LMS filter.
   * @param[in] *S points to an instance of the Q31 normalized LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to coefficient buffer.
   * @param[in] *pState points to state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @param[in] postShift bit shift applied to coefficients.
   * @return none.
   */

  void arm_lms_norm_init_q31(
  arm_lms_norm_instance_q31 * S,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  q31_t mu,
  uint32_t blockSize,
  uint8_t postShift);

  /**
   * @brief Instance structure for the Q15 normalized LMS filter.
   */

  typedef struct
  {
    uint16_t numTaps;    /**< Number of coefficients in the filter. */
    q15_t *pState;        /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
    q15_t *pCoeffs;       /**< points to the coefficient array. The array is of length numTaps. */
    q15_t mu;            /**< step size that controls filter coefficient updates. */
    uint8_t postShift;   /**< bit shift applied to coefficients. */
    q15_t *recipTable;   /**< Points to the reciprocal initial value table. */
    q15_t energy;        /**< saves previous frame energy. */
    q15_t x0;            /**< saves previous input sample. */
  } arm_lms_norm_instance_q15;

  /**
   * @brief Processing function for Q15 normalized LMS filter.
   * @param[in] *S points to an instance of the Q15 normalized LMS filter structure.
   * @param[in] *pSrc points to the block of input data.
   * @param[in] *pRef points to the block of reference data.
   * @param[out] *pOut points to the block of output data.
   * @param[out] *pErr points to the block of error data.
   * @param[in] blockSize number of samples to process.
   * @return none.
   */

  void arm_lms_norm_q15(
  arm_lms_norm_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pRef,
  q15_t * pOut,
  q15_t * pErr,
  uint32_t blockSize);


  /**
   * @brief Initialization function for Q15 normalized LMS filter.
   * @param[in] *S points to an instance of the Q15 normalized LMS filter structure.
   * @param[in] numTaps  number of filter coefficients.
   * @param[in] *pCoeffs points to coefficient buffer.
   * @param[in] *pState points to state buffer.
   * @param[in] mu step size that controls filter coefficient updates.
   * @param[in] blockSize number of samples to process.
   * @param[in] postShift bit shift applied to coefficients.
   * @return none.
   */

  void arm_lms_norm_init_q15(
  arm_lms_norm_instance_q15 * S,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  q15_t mu,
  uint32_t blockSize,
  uint8_t postShift);

  /**
   * @brief Correlation of floating-point sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_f32(
  float32_t * pSrcA,
  uint32_t srcALen,
  float32_t * pSrcB,
  uint32_t srcBLen,
  float32_t * pDst);


   /**
   * @brief Correlation of Q15 sequences
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @param[in]  *pScratch points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @return none.
   */
  void arm_correlate_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch);


  /**
   * @brief Correlation of Q15 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst);

  /**
   * @brief Correlation of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_fast_q15(
			       q15_t * pSrcA,
			      uint32_t srcALen,
			       q15_t * pSrcB,
			      uint32_t srcBLen,
			      q15_t * pDst);



  /**
   * @brief Correlation of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @param[in]  *pScratch points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @return none.
   */

  void arm_correlate_fast_opt_q15(
  q15_t * pSrcA,
  uint32_t srcALen,
  q15_t * pSrcB,
  uint32_t srcBLen,
  q15_t * pDst,
  q15_t * pScratch);

  /**
   * @brief Correlation of Q31 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);

  /**
   * @brief Correlation of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_fast_q31(
  q31_t * pSrcA,
  uint32_t srcALen,
  q31_t * pSrcB,
  uint32_t srcBLen,
  q31_t * pDst);



 /**
   * @brief Correlation of Q7 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
   * @return none.
   */

  void arm_correlate_opt_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst,
  q15_t * pScratch1,
  q15_t * pScratch2);


  /**
   * @brief Correlation of Q7 sequences.
   * @param[in] *pSrcA points to the first input sequence.
   * @param[in] srcALen length of the first input sequence.
   * @param[in] *pSrcB points to the second input sequence.
   * @param[in] srcBLen length of the second input sequence.
   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
   * @return none.
   */

  void arm_correlate_q7(
  q7_t * pSrcA,
  uint32_t srcALen,
  q7_t * pSrcB,
  uint32_t srcBLen,
  q7_t * pDst);


  /**
   * @brief Instance structure for the floating-point sparse FIR filter.
   */
  typedef struct
  {
    uint16_t numTaps;             /**< number of coefficients in the filter. */
    uint16_t stateIndex;          /**< state buffer index.  Points to the oldest sample in the state buffer. */
    float32_t *pState;            /**< points to the state buffer array. The array is of length maxDelay+blockSize-1. */
    float32_t *pCoeffs;           /**< points to the coefficient array. The array is of length numTaps.*/
    uint16_t maxDelay;            /**< maximum offset specified by the pTapDelay array. */
    int32_t *pTapDelay;           /**< points to the array of delay values.  The array is of length numTaps. */
  } arm_fir_sparse_instance_f32;

  /**
   * @brief Instance structure for the Q31 sparse FIR filter.
   */

  typedef struct
  {
    uint16_t numTaps;             /**< number of coefficients in the filter. */
    uint16_t stateIndex;          /**< state buffer index.  Points to the oldest sample in the state buffer. */
    q31_t *pState;                /**< points to the state buffer array. The array is of length maxDelay+blockSize-1. */
    q31_t *pCoeffs;               /**< points to the coefficient array. The array is of length numTaps.*/
    uint16_t maxDelay;            /**< maximum offset specified by the pTapDelay array. */
    int32_t *pTapDelay;           /**< points to the array of delay values.  The array is of length numTaps. */
  } arm_fir_sparse_instance_q31;

  /**
   * @brief Instance structure for the Q15 sparse FIR filter.
   */

  typedef struct
  {
    uint16_t numTaps;             /**< number of coefficients in the filter. */
    uint16_t stateIndex;          /**< state buffer index.  Points to the oldest sample in the state buffer. */
    q15_t *pState;                /**< points to the state buffer array. The array is of length maxDelay+blockSize-1. */
    q15_t *pCoeffs;               /**< points to the coefficient array. The array is of length numTaps.*/
    uint16_t maxDelay;            /**< maximum offset specified by the pTapDelay array. */
    int32_t *pTapDelay;           /**< points to the array of delay values.  The array is of length numTaps. */
  } arm_fir_sparse_instance_q15;

  /**
   * @brief Instance structure for the Q7 sparse FIR filter.
   */

  typedef struct
  {
    uint16_t numTaps;             /**< number of coefficients in the filter. */
    uint16_t stateIndex;          /**< state buffer index.  Points to the oldest sample in the state buffer. */
    q7_t *pState;                 /**< points to the state buffer array. The array is of length maxDelay+blockSize-1. */
    q7_t *pCoeffs;                /**< points to the coefficient array. The array is of length numTaps.*/
    uint16_t maxDelay;            /**< maximum offset specified by the pTapDelay array. */
    int32_t *pTapDelay;           /**< points to the array of delay values.  The array is of length numTaps. */
  } arm_fir_sparse_instance_q7;

  /**
   * @brief Processing function for the floating-point sparse FIR filter.
   * @param[in]  *S          points to an instance of the floating-point sparse FIR structure.
   * @param[in]  *pSrc       points to the block of input data.
   * @param[out] *pDst       points to the block of output data
   * @param[in]  *pScratchIn points to a temporary buffer of size blockSize.
   * @param[in]  blockSize   number of input samples to process per call.
   * @return none.
   */

  void arm_fir_sparse_f32(
  arm_fir_sparse_instance_f32 * S,
  float32_t * pSrc,
  float32_t * pDst,
  float32_t * pScratchIn,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the floating-point sparse FIR filter.
   * @param[in,out] *S         points to an instance of the floating-point sparse FIR structure.
   * @param[in]     numTaps    number of nonzero coefficients in the filter.
   * @param[in]     *pCoeffs   points to the array of filter coefficients.
   * @param[in]     *pState    points to the state buffer.
   * @param[in]     *pTapDelay points to the array of offset times.
   * @param[in]     maxDelay   maximum offset time supported.
   * @param[in]     blockSize  number of samples that will be processed per block.
   * @return none
   */

  void arm_fir_sparse_init_f32(
  arm_fir_sparse_instance_f32 * S,
  uint16_t numTaps,
  float32_t * pCoeffs,
  float32_t * pState,
  int32_t * pTapDelay,
  uint16_t maxDelay,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q31 sparse FIR filter.
   * @param[in]  *S          points to an instance of the Q31 sparse FIR structure.
   * @param[in]  *pSrc       points to the block of input data.
   * @param[out] *pDst       points to the block of output data
   * @param[in]  *pScratchIn points to a temporary buffer of size blockSize.
   * @param[in]  blockSize   number of input samples to process per call.
   * @return none.
   */

  void arm_fir_sparse_q31(
  arm_fir_sparse_instance_q31 * S,
  q31_t * pSrc,
  q31_t * pDst,
  q31_t * pScratchIn,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q31 sparse FIR filter.
   * @param[in,out] *S         points to an instance of the Q31 sparse FIR structure.
   * @param[in]     numTaps    number of nonzero coefficients in the filter.
   * @param[in]     *pCoeffs   points to the array of filter coefficients.
   * @param[in]     *pState    points to the state buffer.
   * @param[in]     *pTapDelay points to the array of offset times.
   * @param[in]     maxDelay   maximum offset time supported.
   * @param[in]     blockSize  number of samples that will be processed per block.
   * @return none
   */

  void arm_fir_sparse_init_q31(
  arm_fir_sparse_instance_q31 * S,
  uint16_t numTaps,
  q31_t * pCoeffs,
  q31_t * pState,
  int32_t * pTapDelay,
  uint16_t maxDelay,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q15 sparse FIR filter.
   * @param[in]  *S           points to an instance of the Q15 sparse FIR structure.
   * @param[in]  *pSrc        points to the block of input data.
   * @param[out] *pDst        points to the block of output data
   * @param[in]  *pScratchIn  points to a temporary buffer of size blockSize.
   * @param[in]  *pScratchOut points to a temporary buffer of size blockSize.
   * @param[in]  blockSize    number of input samples to process per call.
   * @return none.
   */

  void arm_fir_sparse_q15(
  arm_fir_sparse_instance_q15 * S,
  q15_t * pSrc,
  q15_t * pDst,
  q15_t * pScratchIn,
  q31_t * pScratchOut,
  uint32_t blockSize);


  /**
   * @brief  Initialization function for the Q15 sparse FIR filter.
   * @param[in,out] *S         points to an instance of the Q15 sparse FIR structure.
   * @param[in]     numTaps    number of nonzero coefficients in the filter.
   * @param[in]     *pCoeffs   points to the array of filter coefficients.
   * @param[in]     *pState    points to the state buffer.
   * @param[in]     *pTapDelay points to the array of offset times.
   * @param[in]     maxDelay   maximum offset time supported.
   * @param[in]     blockSize  number of samples that will be processed per block.
   * @return none
   */

  void arm_fir_sparse_init_q15(
  arm_fir_sparse_instance_q15 * S,
  uint16_t numTaps,
  q15_t * pCoeffs,
  q15_t * pState,
  int32_t * pTapDelay,
  uint16_t maxDelay,
  uint32_t blockSize);

  /**
   * @brief Processing function for the Q7 sparse FIR filter.
   * @param[in]  *S           points to an instance of the Q7 sparse FIR structure.
   * @param[in]  *pSrc        points to the block of input data.
   * @param[out] *pDst        points to the block of output data
   * @param[in]  *pScratchIn  points to a temporary buffer of size blockSize.
   * @param[in]  *pScratchOut points to a temporary buffer of size blockSize.
   * @param[in]  blockSize    number of input samples to process per call.
   * @return none.
   */

  void arm_fir_sparse_q7(
  arm_fir_sparse_instance_q7 * S,
  q7_t * pSrc,
  q7_t * pDst,
  q7_t * pScratchIn,
  q31_t * pScratchOut,
  uint32_t blockSize);

  /**
   * @brief  Initialization function for the Q7 sparse FIR filter.
   * @param[in,out] *S         points to an instance of the Q7 sparse FIR structure.
   * @param[in]     numTaps    number of nonzero coefficients in the filter.
   * @param[in]     *pCoeffs   points to the array of filter coefficients.
   * @param[in]     *pState    points to the state buffer.
   * @param[in]     *pTapDelay points to the array of offset times.
   * @param[in]     maxDelay   maximum offset time supported.
   * @param[in]     blockSize  number of samples that will be processed per block.
   * @return none
   */

  void arm_fir_sparse_init_q7(
  arm_fir_sparse_instance_q7 * S,
  uint16_t numTaps,
  q7_t * pCoeffs,
  q7_t * pState,
  int32_t * pTapDelay,
  uint16_t maxDelay,
  uint32_t blockSize);


  /*
   * @brief  Floating-point sin_cos function.
   * @param[in]  theta    input value in degrees
   * @param[out] *pSinVal points to the processed sine output.
   * @param[out] *pCosVal points to the processed cos output.
   * @return none.
   */

  void arm_sin_cos_f32(
  float32_t theta,
  float32_t * pSinVal,
  float32_t * pCcosVal);

  /*
   * @brief  Q31 sin_cos function.
   * @param[in]  theta    scaled input value in degrees
   * @param[out] *pSinVal points to the processed sine output.
   * @param[out] *pCosVal points to the processed cosine output.
   * @return none.
   */

  void arm_sin_cos_q31(
  q31_t theta,
  q31_t * pSinVal,
  q31_t * pCosVal);


  /**
   * @brief  Floating-point complex conjugate.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_conj_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q31 complex conjugate.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_conj_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q15 complex conjugate.
   * @param[in]  *pSrc points to the input vector
   * @param[out]  *pDst points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_conj_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t numSamples);



  /**
   * @brief  Floating-point complex magnitude squared
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_squared_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q31 complex magnitude squared
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_squared_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q15 complex magnitude squared
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_squared_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t numSamples);


 /**
   * @ingroup groupController
   */

  /**
   * @defgroup PID PID Motor Control
   *
   * A Proportional Integral Derivative (PID) controller is a generic feedback control
   * loop mechanism widely used in industrial control systems.
   * A PID controller is the most commonly used type of feedback controller.
   *
   * This set of functions implements (PID) controllers
   * for Q15, Q31, and floating-point data types.  The functions operate on a single sample
   * of data and each call to the function returns a single processed value.
   * <code>S</code> points to an instance of the PID control data structure.  <code>in</code>
   * is the input sample value. The functions return the output value.
   *
   * \par Algorithm:
   * <pre>
   *    y[n] = y[n-1] + A0 * x[n] + A1 * x[n-1] + A2 * x[n-2]
   *    A0 = Kp + Ki + Kd
   *    A1 = (-Kp ) - (2 * Kd )
   *    A2 = Kd  </pre>
   *
   * \par
   * where \c Kp is proportional constant, \c Ki is Integral constant and \c Kd is Derivative constant
   *
   * \par
   * \image html PID.gif "Proportional Integral Derivative Controller"
   *
   * \par
   * The PID controller calculates an "error" value as the difference between
   * the measured output and the reference input.
   * The controller attempts to minimize the error by adjusting the process control inputs.
   * The proportional value determines the reaction to the current error,
   * the integral value determines the reaction based on the sum of recent errors,
   * and the derivative value determines the reaction based on the rate at which the error has been changing.
   *
   * \par Instance Structure
   * The Gains A0, A1, A2 and state variables for a PID controller are stored together in an instance data structure.
   * A separate instance structure must be defined for each PID Controller.
   * There are separate instance structure declarations for each of the 3 supported data types.
   *
   * \par Reset Functions
   * There is also an associated reset function for each data type which clears the state array.
   *
   * \par Initialization Functions
   * There is also an associated initialization function for each data type.
   * The initialization function performs the following operations:
   * - Initializes the Gains A0, A1, A2 from Kp,Ki, Kd gains.
   * - Zeros out the values in the state buffer.
   *
   * \par
   * Instance structure cannot be placed into a const data section and it is recommended to use the initialization function.
   *
   * \par Fixed-Point Behavior
   * Care must be taken when using the fixed-point versions of the PID Controller functions.
   * In particular, the overflow and saturation behavior of the accumulator used in each function must be considered.
   * Refer to the function specific documentation below for usage guidelines.
   */

  /**
   * @addtogroup PID
   * @{
   */

  /**
   * @brief  Process function for the floating-point PID Control.
   * @param[in,out] *S is an instance of the floating-point PID Control structure
   * @param[in] in input sample to process
   * @return out processed output sample.
   */


  static __INLINE float32_t arm_pid_f32(
  arm_pid_instance_f32 * S,
  float32_t in)
  {
    float32_t out;

    /* y[n] = y[n-1] + A0 * x[n] + A1 * x[n-1] + A2 * x[n-2]  */
    out = (S->A0 * in) +
      (S->A1 * S->state[0]) + (S->A2 * S->state[1]) + (S->state[2]);

    /* Update state */
    S->state[1] = S->state[0];
    S->state[0] = in;
    S->state[2] = out;

    /* return to application */
    return (out);

  }

  /**
   * @brief  Process function for the Q31 PID Control.
   * @param[in,out] *S points to an instance of the Q31 PID Control structure
   * @param[in] in input sample to process
   * @return out processed output sample.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using an internal 64-bit accumulator.
   * The accumulator has a 2.62 format and maintains full precision of the intermediate multiplication results but provides only a single guard bit.
   * Thus, if the accumulator result overflows it wraps around rather than clip.
   * In order to avoid overflows completely the input signal must be scaled down by 2 bits as there are four additions.
   * After all multiply-accumulates are performed, the 2.62 accumulator is truncated to 1.32 format and then saturated to 1.31 format.
   */

  static __INLINE q31_t arm_pid_q31(
  arm_pid_instance_q31 * S,
  q31_t in)
  {
    q63_t acc;
    q31_t out;

    /* acc = A0 * x[n]  */
    acc = (q63_t) S->A0 * in;

    /* acc += A1 * x[n-1] */
    acc += (q63_t) S->A1 * S->state[0];

    /* acc += A2 * x[n-2]  */
    acc += (q63_t) S->A2 * S->state[1];

    /* convert output to 1.31 format to add y[n-1] */
    out = (q31_t) (acc >> 31u);

    /* out += y[n-1] */
    out += S->state[2];

    /* Update state */
    S->state[1] = S->state[0];
    S->state[0] = in;
    S->state[2] = out;

    /* return to application */
    return (out);

  }

  /**
   * @brief  Process function for the Q15 PID Control.
   * @param[in,out] *S points to an instance of the Q15 PID Control structure
   * @param[in] in input sample to process
   * @return out processed output sample.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using a 64-bit internal accumulator.
   * Both Gains and state variables are represented in 1.15 format and multiplications yield a 2.30 result.
   * The 2.30 intermediate results are accumulated in a 64-bit accumulator in 34.30 format.
   * There is no risk of internal overflow with this approach and the full precision of intermediate multiplications is preserved.
   * After all additions have been performed, the accumulator is truncated to 34.15 format by discarding low 15 bits.
   * Lastly, the accumulator is saturated to yield a result in 1.15 format.
   */

  static __INLINE q15_t arm_pid_q15(
  arm_pid_instance_q15 * S,
  q15_t in)
  {
    q63_t acc;
    q15_t out;

#ifndef ARM_MATH_CM0_FAMILY
    __SIMD32_TYPE *vstate;

    /* Implementation of PID controller */

    /* acc = A0 * x[n]  */
    acc = (q31_t) __SMUAD(S->A0, in);

    /* acc += A1 * x[n-1] + A2 * x[n-2]  */
    vstate = __SIMD32_CONST(S->state);
    acc = __SMLALD(S->A1, (q31_t) *vstate, acc);

#else
    /* acc = A0 * x[n]  */
    acc = ((q31_t) S->A0) * in;

    /* acc += A1 * x[n-1] + A2 * x[n-2]  */
    acc += (q31_t) S->A1 * S->state[0];
    acc += (q31_t) S->A2 * S->state[1];

#endif

    /* acc += y[n-1] */
    acc += (q31_t) S->state[2] << 15;

    /* saturate the output */
    out = (q15_t) (__SSAT((acc >> 15), 16));

    /* Update state */
    S->state[1] = S->state[0];
    S->state[0] = in;
    S->state[2] = out;

    /* return to application */
    return (out);

  }

  /**
   * @} end of PID group
   */


  /**
   * @brief Floating-point matrix inverse.
   * @param[in]  *src points to the instance of the input floating-point matrix structure.
   * @param[out] *dst points to the instance of the output floating-point matrix structure.
   * @return The function returns ARM_MATH_SIZE_MISMATCH, if the dimensions do not match.
   * If the input matrix is singular (does not have an inverse), then the algorithm terminates and returns error status ARM_MATH_SINGULAR.
   */

  arm_status arm_mat_inverse_f32(
  const arm_matrix_instance_f32 * src,
  arm_matrix_instance_f32 * dst);


  /**
   * @brief Floating-point matrix inverse.
   * @param[in]  *src points to the instance of the input floating-point matrix structure.
   * @param[out] *dst points to the instance of the output floating-point matrix structure.
   * @return The function returns ARM_MATH_SIZE_MISMATCH, if the dimensions do not match.
   * If the input matrix is singular (does not have an inverse), then the algorithm terminates and returns error status ARM_MATH_SINGULAR.
   */

  arm_status arm_mat_inverse_f64(
  const arm_matrix_instance_f64 * src,
  arm_matrix_instance_f64 * dst);



  /**
   * @ingroup groupController
   */


  /**
   * @defgroup clarke Vector Clarke Transform
   * Forward Clarke transform converts the instantaneous stator phases into a two-coordinate time invariant vector.
   * Generally the Clarke transform uses three-phase currents <code>Ia, Ib and Ic</code> to calculate currents
   * in the two-phase orthogonal stator axis <code>Ialpha</code> and <code>Ibeta</code>.
   * When <code>Ialpha</code> is superposed with <code>Ia</code> as shown in the figure below
   * \image html clarke.gif Stator current space vector and its components in (a,b).
   * and <code>Ia + Ib + Ic = 0</code>, in this condition <code>Ialpha</code> and <code>Ibeta</code>
   * can be calculated using only <code>Ia</code> and <code>Ib</code>.
   *
   * The function operates on a single sample of data and each call to the function returns the processed output.
   * The library provides separate functions for Q31 and floating-point data types.
   * \par Algorithm
   * \image html clarkeFormula.gif
   * where <code>Ia</code> and <code>Ib</code> are the instantaneous stator phases and
   * <code>pIalpha</code> and <code>pIbeta</code> are the two coordinates of time invariant vector.
   * \par Fixed-Point Behavior
   * Care must be taken when using the Q31 version of the Clarke transform.
   * In particular, the overflow and saturation behavior of the accumulator used must be considered.
   * Refer to the function specific documentation below for usage guidelines.
   */

  /**
   * @addtogroup clarke
   * @{
   */

  /**
   *
   * @brief  Floating-point Clarke transform
   * @param[in]       Ia       input three-phase coordinate <code>a</code>
   * @param[in]       Ib       input three-phase coordinate <code>b</code>
   * @param[out]      *pIalpha points to output two-phase orthogonal vector axis alpha
   * @param[out]      *pIbeta  points to output two-phase orthogonal vector axis beta
   * @return none.
   */

  static __INLINE void arm_clarke_f32(
  float32_t Ia,
  float32_t Ib,
  float32_t * pIalpha,
  float32_t * pIbeta)
  {
    /* Calculate pIalpha using the equation, pIalpha = Ia */
    *pIalpha = Ia;

    /* Calculate pIbeta using the equation, pIbeta = (1/sqrt(3)) * Ia + (2/sqrt(3)) * Ib */
    *pIbeta =
      ((float32_t) 0.57735026919 * Ia + (float32_t) 1.15470053838 * Ib);

  }

  /**
   * @brief  Clarke transform for Q31 version
   * @param[in]       Ia       input three-phase coordinate <code>a</code>
   * @param[in]       Ib       input three-phase coordinate <code>b</code>
   * @param[out]      *pIalpha points to output two-phase orthogonal vector axis alpha
   * @param[out]      *pIbeta  points to output two-phase orthogonal vector axis beta
   * @return none.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using an internal 32-bit accumulator.
   * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
   * There is saturation on the addition, hence there is no risk of overflow.
   */

  static __INLINE void arm_clarke_q31(
  q31_t Ia,
  q31_t Ib,
  q31_t * pIalpha,
  q31_t * pIbeta)
  {
    q31_t product1, product2;                    /* Temporary variables used to store intermediate results */

    /* Calculating pIalpha from Ia by equation pIalpha = Ia */
    *pIalpha = Ia;

    /* Intermediate product is calculated by (1/(sqrt(3)) * Ia) */
    product1 = (q31_t) (((q63_t) Ia * 0x24F34E8B) >> 30);

    /* Intermediate product is calculated by (2/sqrt(3) * Ib) */
    product2 = (q31_t) (((q63_t) Ib * 0x49E69D16) >> 30);

    /* pIbeta is calculated by adding the intermediate products */
    *pIbeta = __QADD(product1, product2);
  }

  /**
   * @} end of clarke group
   */

  /**
   * @brief  Converts the elements of the Q7 vector to Q31 vector.
   * @param[in]  *pSrc     input pointer
   * @param[out]  *pDst    output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_q7_to_q31(
  q7_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);




  /**
   * @ingroup groupController
   */

  /**
   * @defgroup inv_clarke Vector Inverse Clarke Transform
   * Inverse Clarke transform converts the two-coordinate time invariant vector into instantaneous stator phases.
   *
   * The function operates on a single sample of data and each call to the function returns the processed output.
   * The library provides separate functions for Q31 and floating-point data types.
   * \par Algorithm
   * \image html clarkeInvFormula.gif
   * where <code>pIa</code> and <code>pIb</code> are the instantaneous stator phases and
   * <code>Ialpha</code> and <code>Ibeta</code> are the two coordinates of time invariant vector.
   * \par Fixed-Point Behavior
   * Care must be taken when using the Q31 version of the Clarke transform.
   * In particular, the overflow and saturation behavior of the accumulator used must be considered.
   * Refer to the function specific documentation below for usage guidelines.
   */

  /**
   * @addtogroup inv_clarke
   * @{
   */

   /**
   * @brief  Floating-point Inverse Clarke transform
   * @param[in]       Ialpha  input two-phase orthogonal vector axis alpha
   * @param[in]       Ibeta   input two-phase orthogonal vector axis beta
   * @param[out]      *pIa    points to output three-phase coordinate <code>a</code>
   * @param[out]      *pIb    points to output three-phase coordinate <code>b</code>
   * @return none.
   */


  static __INLINE void arm_inv_clarke_f32(
  float32_t Ialpha,
  float32_t Ibeta,
  float32_t * pIa,
  float32_t * pIb)
  {
    /* Calculating pIa from Ialpha by equation pIa = Ialpha */
    *pIa = Ialpha;

    /* Calculating pIb from Ialpha and Ibeta by equation pIb = -(1/2) * Ialpha + (sqrt(3)/2) * Ibeta */
    *pIb = -0.5 * Ialpha + (float32_t) 0.8660254039 *Ibeta;

  }

  /**
   * @brief  Inverse Clarke transform for Q31 version
   * @param[in]       Ialpha  input two-phase orthogonal vector axis alpha
   * @param[in]       Ibeta   input two-phase orthogonal vector axis beta
   * @param[out]      *pIa    points to output three-phase coordinate <code>a</code>
   * @param[out]      *pIb    points to output three-phase coordinate <code>b</code>
   * @return none.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using an internal 32-bit accumulator.
   * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
   * There is saturation on the subtraction, hence there is no risk of overflow.
   */

  static __INLINE void arm_inv_clarke_q31(
  q31_t Ialpha,
  q31_t Ibeta,
  q31_t * pIa,
  q31_t * pIb)
  {
    q31_t product1, product2;                    /* Temporary variables used to store intermediate results */

    /* Calculating pIa from Ialpha by equation pIa = Ialpha */
    *pIa = Ialpha;

    /* Intermediate product is calculated by (1/(2*sqrt(3)) * Ia) */
    product1 = (q31_t) (((q63_t) (Ialpha) * (0x40000000)) >> 31);

    /* Intermediate product is calculated by (1/sqrt(3) * pIb) */
    product2 = (q31_t) (((q63_t) (Ibeta) * (0x6ED9EBA1)) >> 31);

    /* pIb is calculated by subtracting the products */
    *pIb = __QSUB(product2, product1);

  }

  /**
   * @} end of inv_clarke group
   */

  /**
   * @brief  Converts the elements of the Q7 vector to Q15 vector.
   * @param[in]  *pSrc     input pointer
   * @param[out] *pDst     output pointer
   * @param[in]  blockSize number of samples to process
   * @return none.
   */
  void arm_q7_to_q15(
  q7_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);



  /**
   * @ingroup groupController
   */

  /**
   * @defgroup park Vector Park Transform
   *
   * Forward Park transform converts the input two-coordinate vector to flux and torque components.
   * The Park transform can be used to realize the transformation of the <code>Ialpha</code> and the <code>Ibeta</code> currents
   * from the stationary to the moving reference frame and control the spatial relationship between
   * the stator vector current and rotor flux vector.
   * If we consider the d axis aligned with the rotor flux, the diagram below shows the
   * current vector and the relationship from the two reference frames:
   * \image html park.gif "Stator current space vector and its component in (a,b) and in the d,q rotating reference frame"
   *
   * The function operates on a single sample of data and each call to the function returns the processed output.
   * The library provides separate functions for Q31 and floating-point data types.
   * \par Algorithm
   * \image html parkFormula.gif
   * where <code>Ialpha</code> and <code>Ibeta</code> are the stator vector components,
   * <code>pId</code> and <code>pIq</code> are rotor vector components and <code>cosVal</code> and <code>sinVal</code> are the
   * cosine and sine values of theta (rotor flux position).
   * \par Fixed-Point Behavior
   * Care must be taken when using the Q31 version of the Park transform.
   * In particular, the overflow and saturation behavior of the accumulator used must be considered.
   * Refer to the function specific documentation below for usage guidelines.
   */

  /**
   * @addtogroup park
   * @{
   */

  /**
   * @brief Floating-point Park transform
   * @param[in]       Ialpha input two-phase vector coordinate alpha
   * @param[in]       Ibeta  input two-phase vector coordinate beta
   * @param[out]      *pId   points to output	rotor reference frame d
   * @param[out]      *pIq   points to output	rotor reference frame q
   * @param[in]       sinVal sine value of rotation angle theta
   * @param[in]       cosVal cosine value of rotation angle theta
   * @return none.
   *
   * The function implements the forward Park transform.
   *
   */

  static __INLINE void arm_park_f32(
  float32_t Ialpha,
  float32_t Ibeta,
  float32_t * pId,
  float32_t * pIq,
  float32_t sinVal,
  float32_t cosVal)
  {
    /* Calculate pId using the equation, pId = Ialpha * cosVal + Ibeta * sinVal */
    *pId = Ialpha * cosVal + Ibeta * sinVal;

    /* Calculate pIq using the equation, pIq = - Ialpha * sinVal + Ibeta * cosVal */
    *pIq = -Ialpha * sinVal + Ibeta * cosVal;

  }

  /**
   * @brief  Park transform for Q31 version
   * @param[in]       Ialpha input two-phase vector coordinate alpha
   * @param[in]       Ibeta  input two-phase vector coordinate beta
   * @param[out]      *pId   points to output rotor reference frame d
   * @param[out]      *pIq   points to output rotor reference frame q
   * @param[in]       sinVal sine value of rotation angle theta
   * @param[in]       cosVal cosine value of rotation angle theta
   * @return none.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using an internal 32-bit accumulator.
   * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
   * There is saturation on the addition and subtraction, hence there is no risk of overflow.
   */


  static __INLINE void arm_park_q31(
  q31_t Ialpha,
  q31_t Ibeta,
  q31_t * pId,
  q31_t * pIq,
  q31_t sinVal,
  q31_t cosVal)
  {
    q31_t product1, product2;                    /* Temporary variables used to store intermediate results */
    q31_t product3, product4;                    /* Temporary variables used to store intermediate results */

    /* Intermediate product is calculated by (Ialpha * cosVal) */
    product1 = (q31_t) (((q63_t) (Ialpha) * (cosVal)) >> 31);

    /* Intermediate product is calculated by (Ibeta * sinVal) */
    product2 = (q31_t) (((q63_t) (Ibeta) * (sinVal)) >> 31);


    /* Intermediate product is calculated by (Ialpha * sinVal) */
    product3 = (q31_t) (((q63_t) (Ialpha) * (sinVal)) >> 31);

    /* Intermediate product is calculated by (Ibeta * cosVal) */
    product4 = (q31_t) (((q63_t) (Ibeta) * (cosVal)) >> 31);

    /* Calculate pId by adding the two intermediate products 1 and 2 */
    *pId = __QADD(product1, product2);

    /* Calculate pIq by subtracting the two intermediate products 3 from 4 */
    *pIq = __QSUB(product4, product3);
  }

  /**
   * @} end of park group
   */

  /**
   * @brief  Converts the elements of the Q7 vector to floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q7_to_float(
  q7_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);


  /**
   * @ingroup groupController
   */

  /**
   * @defgroup inv_park Vector Inverse Park transform
   * Inverse Park transform converts the input flux and torque components to two-coordinate vector.
   *
   * The function operates on a single sample of data and each call to the function returns the processed output.
   * The library provides separate functions for Q31 and floating-point data types.
   * \par Algorithm
   * \image html parkInvFormula.gif
   * where <code>pIalpha</code> and <code>pIbeta</code> are the stator vector components,
   * <code>Id</code> and <code>Iq</code> are rotor vector components and <code>cosVal</code> and <code>sinVal</code> are the
   * cosine and sine values of theta (rotor flux position).
   * \par Fixed-Point Behavior
   * Care must be taken when using the Q31 version of the Park transform.
   * In particular, the overflow and saturation behavior of the accumulator used must be considered.
   * Refer to the function specific documentation below for usage guidelines.
   */

  /**
   * @addtogroup inv_park
   * @{
   */

   /**
   * @brief  Floating-point Inverse Park transform
   * @param[in]       Id        input coordinate of rotor reference frame d
   * @param[in]       Iq        input coordinate of rotor reference frame q
   * @param[out]      *pIalpha  points to output two-phase orthogonal vector axis alpha
   * @param[out]      *pIbeta   points to output two-phase orthogonal vector axis beta
   * @param[in]       sinVal    sine value of rotation angle theta
   * @param[in]       cosVal    cosine value of rotation angle theta
   * @return none.
   */

  static __INLINE void arm_inv_park_f32(
  float32_t Id,
  float32_t Iq,
  float32_t * pIalpha,
  float32_t * pIbeta,
  float32_t sinVal,
  float32_t cosVal)
  {
    /* Calculate pIalpha using the equation, pIalpha = Id * cosVal - Iq * sinVal */
    *pIalpha = Id * cosVal - Iq * sinVal;

    /* Calculate pIbeta using the equation, pIbeta = Id * sinVal + Iq * cosVal */
    *pIbeta = Id * sinVal + Iq * cosVal;

  }


  /**
   * @brief  Inverse Park transform for	Q31 version
   * @param[in]       Id        input coordinate of rotor reference frame d
   * @param[in]       Iq        input coordinate of rotor reference frame q
   * @param[out]      *pIalpha  points to output two-phase orthogonal vector axis alpha
   * @param[out]      *pIbeta   points to output two-phase orthogonal vector axis beta
   * @param[in]       sinVal    sine value of rotation angle theta
   * @param[in]       cosVal    cosine value of rotation angle theta
   * @return none.
   *
   * <b>Scaling and Overflow Behavior:</b>
   * \par
   * The function is implemented using an internal 32-bit accumulator.
   * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
   * There is saturation on the addition, hence there is no risk of overflow.
   */


  static __INLINE void arm_inv_park_q31(
  q31_t Id,
  q31_t Iq,
  q31_t * pIalpha,
  q31_t * pIbeta,
  q31_t sinVal,
  q31_t cosVal)
  {
    q31_t product1, product2;                    /* Temporary variables used to store intermediate results */
    q31_t product3, product4;                    /* Temporary variables used to store intermediate results */

    /* Intermediate product is calculated by (Id * cosVal) */
    product1 = (q31_t) (((q63_t) (Id) * (cosVal)) >> 31);

    /* Intermediate product is calculated by (Iq * sinVal) */
    product2 = (q31_t) (((q63_t) (Iq) * (sinVal)) >> 31);


    /* Intermediate product is calculated by (Id * sinVal) */
    product3 = (q31_t) (((q63_t) (Id) * (sinVal)) >> 31);

    /* Intermediate product is calculated by (Iq * cosVal) */
    product4 = (q31_t) (((q63_t) (Iq) * (cosVal)) >> 31);

    /* Calculate pIalpha by using the two intermediate products 1 and 2 */
    *pIalpha = __QSUB(product1, product2);

    /* Calculate pIbeta by using the two intermediate products 3 and 4 */
    *pIbeta = __QADD(product4, product3);

  }

  /**
   * @} end of Inverse park group
   */


  /**
   * @brief  Converts the elements of the Q31 vector to floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q31_to_float(
  q31_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);

  /**
   * @ingroup groupInterpolation
   */

  /**
   * @defgroup LinearInterpolate Linear Interpolation
   *
   * Linear interpolation is a method of curve fitting using linear polynomials.
   * Linear interpolation works by effectively drawing a straight line between two neighboring samples and returning the appropriate point along that line
   *
   * \par
   * \image html LinearInterp.gif "Linear interpolation"
   *
   * \par
   * A  Linear Interpolate function calculates an output value(y), for the input(x)
   * using linear interpolation of the input values x0, x1( nearest input values) and the output values y0 and y1(nearest output values)
   *
   * \par Algorithm:
   * <pre>
   *       y = y0 + (x - x0) * ((y1 - y0)/(x1-x0))
   *       where x0, x1 are nearest values of input x
   *             y0, y1 are nearest values to output y
   * </pre>
   *
   * \par
   * This set of functions implements Linear interpolation process
   * for Q7, Q15, Q31, and floating-point data types.  The functions operate on a single
   * sample of data and each call to the function returns a single processed value.
   * <code>S</code> points to an instance of the Linear Interpolate function data structure.
   * <code>x</code> is the input sample value. The functions returns the output value.
   *
   * \par
   * if x is outside of the table boundary, Linear interpolation returns first value of the table
   * if x is below input range and returns last value of table if x is above range.
   */

  /**
   * @addtogroup LinearInterpolate
   * @{
   */

  /**
   * @brief  Process function for the floating-point Linear Interpolation Function.
   * @param[in,out] *S is an instance of the floating-point Linear Interpolation structure
   * @param[in] x input sample to process
   * @return y processed output sample.
   *
   */

  static __INLINE float32_t arm_linear_interp_f32(
  arm_linear_interp_instance_f32 * S,
  float32_t x)
  {

    float32_t y;
    float32_t x0, x1;                            /* Nearest input values */
    float32_t y0, y1;                            /* Nearest output values */
    float32_t xSpacing = S->xSpacing;            /* spacing between input values */
    int32_t i;                                   /* Index variable */
    float32_t *pYData = S->pYData;               /* pointer to output table */

    /* Calculation of index */
    i = (int32_t) ((x - S->x1) / xSpacing);

    if(i < 0)
    {
      /* Iniatilize output for below specified range as least output value of table */
      y = pYData[0];
    }
    else if((uint32_t)i >= S->nValues)
    {
      /* Iniatilize output for above specified range as last output value of table */
      y = pYData[S->nValues - 1];
    }
    else
    {
      /* Calculation of nearest input values */
      x0 = S->x1 + i * xSpacing;
      x1 = S->x1 + (i + 1) * xSpacing;

      /* Read of nearest output values */
      y0 = pYData[i];
      y1 = pYData[i + 1];

      /* Calculation of output */
      y = y0 + (x - x0) * ((y1 - y0) / (x1 - x0));

    }

    /* returns output value */
    return (y);
  }

   /**
   *
   * @brief  Process function for the Q31 Linear Interpolation Function.
   * @param[in] *pYData  pointer to Q31 Linear Interpolation table
   * @param[in] x input sample to process
   * @param[in] nValues number of table values
   * @return y processed output sample.
   *
   * \par
   * Input sample <code>x</code> is in 12.20 format which contains 12 bits for table index and 20 bits for fractional part.
   * This function can support maximum of table size 2^12.
   *
   */


  static __INLINE q31_t arm_linear_interp_q31(
  q31_t * pYData,
  q31_t x,
  uint32_t nValues)
  {
    q31_t y;                                     /* output */
    q31_t y0, y1;                                /* Nearest output values */
    q31_t fract;                                 /* fractional part */
    int32_t index;                               /* Index to read nearest output values */

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    index = ((x & 0xFFF00000) >> 20);

    if(index >= (int32_t)(nValues - 1))
    {
      return (pYData[nValues - 1]);
    }
    else if(index < 0)
    {
      return (pYData[0]);
    }
    else
    {

      /* 20 bits for the fractional part */
      /* shift left by 11 to keep fract in 1.31 format */
      fract = (x & 0x000FFFFF) << 11;

      /* Read two nearest output values from the index in 1.31(q31) format */
      y0 = pYData[index];
      y1 = pYData[index + 1u];

      /* Calculation of y0 * (1-fract) and y is in 2.30 format */
      y = ((q31_t) ((q63_t) y0 * (0x7FFFFFFF - fract) >> 32));

      /* Calculation of y0 * (1-fract) + y1 *fract and y is in 2.30 format */
      y += ((q31_t) (((q63_t) y1 * fract) >> 32));

      /* Convert y to 1.31 format */
      return (y << 1u);

    }

  }

  /**
   *
   * @brief  Process function for the Q15 Linear Interpolation Function.
   * @param[in] *pYData  pointer to Q15 Linear Interpolation table
   * @param[in] x input sample to process
   * @param[in] nValues number of table values
   * @return y processed output sample.
   *
   * \par
   * Input sample <code>x</code> is in 12.20 format which contains 12 bits for table index and 20 bits for fractional part.
   * This function can support maximum of table size 2^12.
   *
   */


  static __INLINE q15_t arm_linear_interp_q15(
  q15_t * pYData,
  q31_t x,
  uint32_t nValues)
  {
    q63_t y;                                     /* output */
    q15_t y0, y1;                                /* Nearest output values */
    q31_t fract;                                 /* fractional part */
    int32_t index;                               /* Index to read nearest output values */

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    index = ((x & 0xFFF00000) >> 20u);

    if(index >= (int32_t)(nValues - 1))
    {
      return (pYData[nValues - 1]);
    }
    else if(index < 0)
    {
      return (pYData[0]);
    }
    else
    {
      /* 20 bits for the fractional part */
      /* fract is in 12.20 format */
      fract = (x & 0x000FFFFF);

      /* Read two nearest output values from the index */
      y0 = pYData[index];
      y1 = pYData[index + 1u];

      /* Calculation of y0 * (1-fract) and y is in 13.35 format */
      y = ((q63_t) y0 * (0xFFFFF - fract));

      /* Calculation of (y0 * (1-fract) + y1 * fract) and y is in 13.35 format */
      y += ((q63_t) y1 * (fract));

      /* convert y to 1.15 format */
      return (y >> 20);
    }


  }

  /**
   *
   * @brief  Process function for the Q7 Linear Interpolation Function.
   * @param[in] *pYData  pointer to Q7 Linear Interpolation table
   * @param[in] x input sample to process
   * @param[in] nValues number of table values
   * @return y processed output sample.
   *
   * \par
   * Input sample <code>x</code> is in 12.20 format which contains 12 bits for table index and 20 bits for fractional part.
   * This function can support maximum of table size 2^12.
   */


  static __INLINE q7_t arm_linear_interp_q7(
  q7_t * pYData,
  q31_t x,
  uint32_t nValues)
  {
    q31_t y;                                     /* output */
    q7_t y0, y1;                                 /* Nearest output values */
    q31_t fract;                                 /* fractional part */
    uint32_t index;                              /* Index to read nearest output values */

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    if (x < 0)
    {
      return (pYData[0]);
    }
    index = (x >> 20) & 0xfff;


    if(index >= (nValues - 1))
    {
      return (pYData[nValues - 1]);
    }
    else
    {

      /* 20 bits for the fractional part */
      /* fract is in 12.20 format */
      fract = (x & 0x000FFFFF);

      /* Read two nearest output values from the index and are in 1.7(q7) format */
      y0 = pYData[index];
      y1 = pYData[index + 1u];

      /* Calculation of y0 * (1-fract ) and y is in 13.27(q27) format */
      y = ((y0 * (0xFFFFF - fract)));

      /* Calculation of y1 * fract + y0 * (1-fract) and y is in 13.27(q27) format */
      y += (y1 * fract);

      /* convert y to 1.7(q7) format */
      return (y >> 20u);

    }

  }
  /**
   * @} end of LinearInterpolate group
   */

  /**
   * @brief  Fast approximation to the trigonometric sine function for floating-point data.
   * @param[in] x input value in radians.
   * @return  sin(x).
   */

  float32_t arm_sin_f32(
  float32_t x);

  /**
   * @brief  Fast approximation to the trigonometric sine function for Q31 data.
   * @param[in] x Scaled input value in radians.
   * @return  sin(x).
   */

  q31_t arm_sin_q31(
  q31_t x);

  /**
   * @brief  Fast approximation to the trigonometric sine function for Q15 data.
   * @param[in] x Scaled input value in radians.
   * @return  sin(x).
   */

  q15_t arm_sin_q15(
  q15_t x);

  /**
   * @brief  Fast approximation to the trigonometric cosine function for floating-point data.
   * @param[in] x input value in radians.
   * @return  cos(x).
   */

  float32_t arm_cos_f32(
  float32_t x);

  /**
   * @brief Fast approximation to the trigonometric cosine function for Q31 data.
   * @param[in] x Scaled input value in radians.
   * @return  cos(x).
   */

  q31_t arm_cos_q31(
  q31_t x);

  /**
   * @brief  Fast approximation to the trigonometric cosine function for Q15 data.
   * @param[in] x Scaled input value in radians.
   * @return  cos(x).
   */

  q15_t arm_cos_q15(
  q15_t x);


  /**
   * @ingroup groupFastMath
   */


  /**
   * @defgroup SQRT Square Root
   *
   * Computes the square root of a number.
   * There are separate functions for Q15, Q31, and floating-point data types.
   * The square root function is computed using the Newton-Raphson algorithm.
   * This is an iterative algorithm of the form:
   * <pre>
   *      x1 = x0 - f(x0)/f'(x0)
   * </pre>
   * where <code>x1</code> is the current estimate,
   * <code>x0</code> is the previous estimate, and
   * <code>f'(x0)</code> is the derivative of <code>f()</code> evaluated at <code>x0</code>.
   * For the square root function, the algorithm reduces to:
   * <pre>
   *     x0 = in/2                         [initial guess]
   *     x1 = 1/2 * ( x0 + in / x0)        [each iteration]
   * </pre>
   */


  /**
   * @addtogroup SQRT
   * @{
   */

  /**
   * @brief  Floating-point square root function.
   * @param[in]  in     input value.
   * @param[out] *pOut  square root of input value.
   * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
   * <code>in</code> is negative value and returns zero output for negative values.
   */

  static __INLINE arm_status arm_sqrt_f32(
  float32_t in,
  float32_t * pOut)
  {
    if(in >= 0.0f)
    {

//      #if __FPU_USED
#if (__FPU_USED == 1) && defined ( __CC_ARM   )
      *pOut = __sqrtf(in);
#else
      *pOut = sqrtf(in);
#endif

      return (ARM_MATH_SUCCESS);
    }
    else
    {
      *pOut = 0.0f;
      return (ARM_MATH_ARGUMENT_ERROR);
    }

  }


  /**
   * @brief Q31 square root function.
   * @param[in]   in    input value.  The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.
   * @param[out]  *pOut square root of input value.
   * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
   * <code>in</code> is negative value and returns zero output for negative values.
   */
  arm_status arm_sqrt_q31(
  q31_t in,
  q31_t * pOut);

  /**
   * @brief  Q15 square root function.
   * @param[in]   in     input value.  The range of the input value is [0 +1) or 0x0000 to 0x7FFF.
   * @param[out]  *pOut  square root of input value.
   * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
   * <code>in</code> is negative value and returns zero output for negative values.
   */
  arm_status arm_sqrt_q15(
  q15_t in,
  q15_t * pOut);

  /**
   * @} end of SQRT group
   */






  /**
   * @brief floating-point Circular write function.
   */

  static __INLINE void arm_circularWrite_f32(
  int32_t * circBuffer,
  int32_t L,
  uint16_t * writeOffset,
  int32_t bufferInc,
  const int32_t * src,
  int32_t srcInc,
  uint32_t blockSize)
  {
    uint32_t i = 0u;
    int32_t wOffset;

    /* Copy the value of Index pointer that points
     * to the current location where the input samples to be copied */
    wOffset = *writeOffset;

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the input sample to the circular buffer */
      circBuffer[wOffset] = *src;

      /* Update the input pointer */
      src += srcInc;

      /* Circularly update wOffset.  Watch out for positive and negative value */
      wOffset += bufferInc;
      if(wOffset >= L)
        wOffset -= L;

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *writeOffset = wOffset;
  }



  /**
   * @brief floating-point Circular Read function.
   */
  static __INLINE void arm_circularRead_f32(
  int32_t * circBuffer,
  int32_t L,
  int32_t * readOffset,
  int32_t bufferInc,
  int32_t * dst,
  int32_t * dst_base,
  int32_t dst_length,
  int32_t dstInc,
  uint32_t blockSize)
  {
    uint32_t i = 0u;
    int32_t rOffset, dst_end;

    /* Copy the value of Index pointer that points
     * to the current location from where the input samples to be read */
    rOffset = *readOffset;
    dst_end = (int32_t) (dst_base + dst_length);

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the sample from the circular buffer to the destination buffer */
      *dst = circBuffer[rOffset];

      /* Update the input pointer */
      dst += dstInc;

      if(dst == (int32_t *) dst_end)
      {
        dst = dst_base;
      }

      /* Circularly update rOffset.  Watch out for positive and negative value  */
      rOffset += bufferInc;

      if(rOffset >= L)
      {
        rOffset -= L;
      }

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *readOffset = rOffset;
  }

  /**
   * @brief Q15 Circular write function.
   */

  static __INLINE void arm_circularWrite_q15(
  q15_t * circBuffer,
  int32_t L,
  uint16_t * writeOffset,
  int32_t bufferInc,
  const q15_t * src,
  int32_t srcInc,
  uint32_t blockSize)
  {
    uint32_t i = 0u;
    int32_t wOffset;

    /* Copy the value of Index pointer that points
     * to the current location where the input samples to be copied */
    wOffset = *writeOffset;

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the input sample to the circular buffer */
      circBuffer[wOffset] = *src;

      /* Update the input pointer */
      src += srcInc;

      /* Circularly update wOffset.  Watch out for positive and negative value */
      wOffset += bufferInc;
      if(wOffset >= L)
        wOffset -= L;

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *writeOffset = wOffset;
  }



  /**
   * @brief Q15 Circular Read function.
   */
  static __INLINE void arm_circularRead_q15(
  q15_t * circBuffer,
  int32_t L,
  int32_t * readOffset,
  int32_t bufferInc,
  q15_t * dst,
  q15_t * dst_base,
  int32_t dst_length,
  int32_t dstInc,
  uint32_t blockSize)
  {
    uint32_t i = 0;
    int32_t rOffset, dst_end;

    /* Copy the value of Index pointer that points
     * to the current location from where the input samples to be read */
    rOffset = *readOffset;

    dst_end = (int32_t) (dst_base + dst_length);

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the sample from the circular buffer to the destination buffer */
      *dst = circBuffer[rOffset];

      /* Update the input pointer */
      dst += dstInc;

      if(dst == (q15_t *) dst_end)
      {
        dst = dst_base;
      }

      /* Circularly update wOffset.  Watch out for positive and negative value */
      rOffset += bufferInc;

      if(rOffset >= L)
      {
        rOffset -= L;
      }

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *readOffset = rOffset;
  }


  /**
   * @brief Q7 Circular write function.
   */

  static __INLINE void arm_circularWrite_q7(
  q7_t * circBuffer,
  int32_t L,
  uint16_t * writeOffset,
  int32_t bufferInc,
  const q7_t * src,
  int32_t srcInc,
  uint32_t blockSize)
  {
    uint32_t i = 0u;
    int32_t wOffset;

    /* Copy the value of Index pointer that points
     * to the current location where the input samples to be copied */
    wOffset = *writeOffset;

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the input sample to the circular buffer */
      circBuffer[wOffset] = *src;

      /* Update the input pointer */
      src += srcInc;

      /* Circularly update wOffset.  Watch out for positive and negative value */
      wOffset += bufferInc;
      if(wOffset >= L)
        wOffset -= L;

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *writeOffset = wOffset;
  }



  /**
   * @brief Q7 Circular Read function.
   */
  static __INLINE void arm_circularRead_q7(
  q7_t * circBuffer,
  int32_t L,
  int32_t * readOffset,
  int32_t bufferInc,
  q7_t * dst,
  q7_t * dst_base,
  int32_t dst_length,
  int32_t dstInc,
  uint32_t blockSize)
  {
    uint32_t i = 0;
    int32_t rOffset, dst_end;

    /* Copy the value of Index pointer that points
     * to the current location from where the input samples to be read */
    rOffset = *readOffset;

    dst_end = (int32_t) (dst_base + dst_length);

    /* Loop over the blockSize */
    i = blockSize;

    while(i > 0u)
    {
      /* copy the sample from the circular buffer to the destination buffer */
      *dst = circBuffer[rOffset];

      /* Update the input pointer */
      dst += dstInc;

      if(dst == (q7_t *) dst_end)
      {
        dst = dst_base;
      }

      /* Circularly update rOffset.  Watch out for positive and negative value */
      rOffset += bufferInc;

      if(rOffset >= L)
      {
        rOffset -= L;
      }

      /* Decrement the loop counter */
      i--;
    }

    /* Update the index pointer */
    *readOffset = rOffset;
  }


  /**
   * @brief  Sum of the squares of the elements of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_power_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q63_t * pResult);

  /**
   * @brief  Sum of the squares of the elements of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_power_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult);

  /**
   * @brief  Sum of the squares of the elements of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_power_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q63_t * pResult);

  /**
   * @brief  Sum of the squares of the elements of a Q7 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_power_q7(
  q7_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult);

  /**
   * @brief  Mean value of a Q7 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_mean_q7(
  q7_t * pSrc,
  uint32_t blockSize,
  q7_t * pResult);

  /**
   * @brief  Mean value of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */
  void arm_mean_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult);

  /**
   * @brief  Mean value of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */
  void arm_mean_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult);

  /**
   * @brief  Mean value of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */
  void arm_mean_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult);

  /**
   * @brief  Variance of the elements of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_var_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult);

  /**
   * @brief  Variance of the elements of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_var_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult);

  /**
   * @brief  Variance of the elements of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_var_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult);

  /**
   * @brief  Root Mean Square of the elements of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_rms_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult);

  /**
   * @brief  Root Mean Square of the elements of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_rms_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult);

  /**
   * @brief  Root Mean Square of the elements of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_rms_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult);

  /**
   * @brief  Standard deviation of the elements of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_std_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult);

  /**
   * @brief  Standard deviation of the elements of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_std_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult);

  /**
   * @brief  Standard deviation of the elements of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output value.
   * @return none.
   */

  void arm_std_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult);

  /**
   * @brief  Floating-point complex magnitude
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_f32(
  float32_t * pSrc,
  float32_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q31 complex magnitude
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_q31(
  q31_t * pSrc,
  q31_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q15 complex magnitude
   * @param[in]  *pSrc points to the complex input vector
   * @param[out]  *pDst points to the real output vector
   * @param[in]  numSamples number of complex samples in the input vector
   * @return none.
   */

  void arm_cmplx_mag_q15(
  q15_t * pSrc,
  q15_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q15 complex dot product
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[in]  numSamples number of complex samples in each vector
   * @param[out]  *realResult real part of the result returned here
   * @param[out]  *imagResult imaginary part of the result returned here
   * @return none.
   */

  void arm_cmplx_dot_prod_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  uint32_t numSamples,
  q31_t * realResult,
  q31_t * imagResult);

  /**
   * @brief  Q31 complex dot product
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[in]  numSamples number of complex samples in each vector
   * @param[out]  *realResult real part of the result returned here
   * @param[out]  *imagResult imaginary part of the result returned here
   * @return none.
   */

  void arm_cmplx_dot_prod_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  uint32_t numSamples,
  q63_t * realResult,
  q63_t * imagResult);

  /**
   * @brief  Floating-point complex dot product
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[in]  numSamples number of complex samples in each vector
   * @param[out]  *realResult real part of the result returned here
   * @param[out]  *imagResult imaginary part of the result returned here
   * @return none.
   */

  void arm_cmplx_dot_prod_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  uint32_t numSamples,
  float32_t * realResult,
  float32_t * imagResult);

  /**
   * @brief  Q15 complex-by-real multiplication
   * @param[in]  *pSrcCmplx points to the complex input vector
   * @param[in]  *pSrcReal points to the real input vector
   * @param[out]  *pCmplxDst points to the complex output vector
   * @param[in]  numSamples number of samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_real_q15(
  q15_t * pSrcCmplx,
  q15_t * pSrcReal,
  q15_t * pCmplxDst,
  uint32_t numSamples);

  /**
   * @brief  Q31 complex-by-real multiplication
   * @param[in]  *pSrcCmplx points to the complex input vector
   * @param[in]  *pSrcReal points to the real input vector
   * @param[out]  *pCmplxDst points to the complex output vector
   * @param[in]  numSamples number of samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_real_q31(
  q31_t * pSrcCmplx,
  q31_t * pSrcReal,
  q31_t * pCmplxDst,
  uint32_t numSamples);

  /**
   * @brief  Floating-point complex-by-real multiplication
   * @param[in]  *pSrcCmplx points to the complex input vector
   * @param[in]  *pSrcReal points to the real input vector
   * @param[out]  *pCmplxDst points to the complex output vector
   * @param[in]  numSamples number of samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_real_f32(
  float32_t * pSrcCmplx,
  float32_t * pSrcReal,
  float32_t * pCmplxDst,
  uint32_t numSamples);

  /**
   * @brief  Minimum value of a Q7 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *result is output pointer
   * @param[in]  index is the array index of the minimum value in the input buffer.
   * @return none.
   */

  void arm_min_q7(
  q7_t * pSrc,
  uint32_t blockSize,
  q7_t * result,
  uint32_t * index);

  /**
   * @brief  Minimum value of a Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output pointer
   * @param[in]  *pIndex is the array index of the minimum value in the input buffer.
   * @return none.
   */

  void arm_min_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult,
  uint32_t * pIndex);

  /**
   * @brief  Minimum value of a Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output pointer
   * @param[out]  *pIndex is the array index of the minimum value in the input buffer.
   * @return none.
   */
  void arm_min_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult,
  uint32_t * pIndex);

  /**
   * @brief  Minimum value of a floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[in]  blockSize is the number of samples to process
   * @param[out]  *pResult is output pointer
   * @param[out]  *pIndex is the array index of the minimum value in the input buffer.
   * @return none.
   */

  void arm_min_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult,
  uint32_t * pIndex);

/**
 * @brief Maximum value of a Q7 vector.
 * @param[in]       *pSrc points to the input buffer
 * @param[in]       blockSize length of the input vector
 * @param[out]      *pResult maximum value returned here
 * @param[out]      *pIndex index of maximum value returned here
 * @return none.
 */

  void arm_max_q7(
  q7_t * pSrc,
  uint32_t blockSize,
  q7_t * pResult,
  uint32_t * pIndex);

/**
 * @brief Maximum value of a Q15 vector.
 * @param[in]       *pSrc points to the input buffer
 * @param[in]       blockSize length of the input vector
 * @param[out]      *pResult maximum value returned here
 * @param[out]      *pIndex index of maximum value returned here
 * @return none.
 */

  void arm_max_q15(
  q15_t * pSrc,
  uint32_t blockSize,
  q15_t * pResult,
  uint32_t * pIndex);

/**
 * @brief Maximum value of a Q31 vector.
 * @param[in]       *pSrc points to the input buffer
 * @param[in]       blockSize length of the input vector
 * @param[out]      *pResult maximum value returned here
 * @param[out]      *pIndex index of maximum value returned here
 * @return none.
 */

  void arm_max_q31(
  q31_t * pSrc,
  uint32_t blockSize,
  q31_t * pResult,
  uint32_t * pIndex);

/**
 * @brief Maximum value of a floating-point vector.
 * @param[in]       *pSrc points to the input buffer
 * @param[in]       blockSize length of the input vector
 * @param[out]      *pResult maximum value returned here
 * @param[out]      *pIndex index of maximum value returned here
 * @return none.
 */

  void arm_max_f32(
  float32_t * pSrc,
  uint32_t blockSize,
  float32_t * pResult,
  uint32_t * pIndex);

  /**
   * @brief  Q15 complex-by-complex multiplication
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[out]  *pDst  points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_cmplx_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  q15_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Q31 complex-by-complex multiplication
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[out]  *pDst  points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_cmplx_q31(
  q31_t * pSrcA,
  q31_t * pSrcB,
  q31_t * pDst,
  uint32_t numSamples);

  /**
   * @brief  Floating-point complex-by-complex multiplication
   * @param[in]  *pSrcA points to the first input vector
   * @param[in]  *pSrcB points to the second input vector
   * @param[out]  *pDst  points to the output vector
   * @param[in]  numSamples number of complex samples in each vector
   * @return none.
   */

  void arm_cmplx_mult_cmplx_f32(
  float32_t * pSrcA,
  float32_t * pSrcB,
  float32_t * pDst,
  uint32_t numSamples);

  /**
   * @brief Converts the elements of the floating-point vector to Q31 vector.
   * @param[in]       *pSrc points to the floating-point input vector
   * @param[out]      *pDst points to the Q31 output vector
   * @param[in]       blockSize length of the input vector
   * @return none.
   */
  void arm_float_to_q31(
  float32_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Converts the elements of the floating-point vector to Q15 vector.
   * @param[in]       *pSrc points to the floating-point input vector
   * @param[out]      *pDst points to the Q15 output vector
   * @param[in]       blockSize length of the input vector
   * @return          none
   */
  void arm_float_to_q15(
  float32_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief Converts the elements of the floating-point vector to Q7 vector.
   * @param[in]       *pSrc points to the floating-point input vector
   * @param[out]      *pDst points to the Q7 output vector
   * @param[in]       blockSize length of the input vector
   * @return          none
   */
  void arm_float_to_q7(
  float32_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Converts the elements of the Q31 vector to Q15 vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q31_to_q15(
  q31_t * pSrc,
  q15_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Converts the elements of the Q31 vector to Q7 vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q31_to_q7(
  q31_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);

  /**
   * @brief  Converts the elements of the Q15 vector to floating-point vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q15_to_float(
  q15_t * pSrc,
  float32_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Converts the elements of the Q15 vector to Q31 vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q15_to_q31(
  q15_t * pSrc,
  q31_t * pDst,
  uint32_t blockSize);


  /**
   * @brief  Converts the elements of the Q15 vector to Q7 vector.
   * @param[in]  *pSrc is input pointer
   * @param[out]  *pDst is output pointer
   * @param[in]  blockSize is the number of samples to process
   * @return none.
   */
  void arm_q15_to_q7(
  q15_t * pSrc,
  q7_t * pDst,
  uint32_t blockSize);


  /**
   * @ingroup groupInterpolation
   */

  /**
   * @defgroup BilinearInterpolate Bilinear Interpolation
   *
   * Bilinear interpolation is an extension of linear interpolation applied to a two dimensional grid.
   * The underlying function <code>f(x, y)</code> is sampled on a regular grid and the interpolation process
   * determines values between the grid points.
   * Bilinear interpolation is equivalent to two step linear interpolation, first in the x-dimension and then in the y-dimension.
   * Bilinear interpolation is often used in image processing to rescale images.
   * The CMSIS DSP library provides bilinear interpolation functions for Q7, Q15, Q31, and floating-point data types.
   *
   * <b>Algorithm</b>
   * \par
   * The instance structure used by the bilinear interpolation functions describes a two dimensional data table.
   * For floating-point, the instance structure is defined as:
   * <pre>
   *   typedef struct
   *   {
   *     uint16_t numRows;
   *     uint16_t numCols;
   *     float32_t *pData;
   * } arm_bilinear_interp_instance_f32;
   * </pre>
   *
   * \par
   * where <code>numRows</code> specifies the number of rows in the table;
   * <code>numCols</code> specifies the number of columns in the table;
   * and <code>pData</code> points to an array of size <code>numRows*numCols</code> values.
   * The data table <code>pTable</code> is organized in row order and the supplied data values fall on integer indexes.
   * That is, table element (x,y) is located at <code>pTable[x + y*numCols]</code> where x and y are integers.
   *
   * \par
   * Let <code>(x, y)</code> specify the desired interpolation point.  Then define:
   * <pre>
   *     XF = floor(x)
   *     YF = floor(y)
   * </pre>
   * \par
   * The interpolated output point is computed as:
   * <pre>
   *  f(x, y) = f(XF, YF) * (1-(x-XF)) * (1-(y-YF))
   *           + f(XF+1, YF) * (x-XF)*(1-(y-YF))
   *           + f(XF, YF+1) * (1-(x-XF))*(y-YF)
   *           + f(XF+1, YF+1) * (x-XF)*(y-YF)
   * </pre>
   * Note that the coordinates (x, y) contain integer and fractional components.
   * The integer components specify which portion of the table to use while the
   * fractional components control the interpolation processor.
   *
   * \par
   * if (x,y) are outside of the table boundary, Bilinear interpolation returns zero output.
   */

  /**
   * @addtogroup BilinearInterpolate
   * @{
   */

  /**
  *
  * @brief  Floating-point bilinear interpolation.
  * @param[in,out] *S points to an instance of the interpolation structure.
  * @param[in] X interpolation coordinate.
  * @param[in] Y interpolation coordinate.
  * @return out interpolated value.
  */


  static __INLINE float32_t arm_bilinear_interp_f32(
  const arm_bilinear_interp_instance_f32 * S,
  float32_t X,
  float32_t Y)
  {
    float32_t out;
    float32_t f00, f01, f10, f11;
    float32_t *pData = S->pData;
    int32_t xIndex, yIndex, index;
    float32_t xdiff, ydiff;
    float32_t b1, b2, b3, b4;

    xIndex = (int32_t) X;
    yIndex = (int32_t) Y;

    /* Care taken for table outside boundary */
    /* Returns zero output when values are outside table boundary */
    if(xIndex < 0 || xIndex > (S->numRows - 1) || yIndex < 0
       || yIndex > (S->numCols - 1))
    {
      return (0);
    }

    /* Calculation of index for two nearest points in X-direction */
    index = (xIndex - 1) + (yIndex - 1) * S->numCols;


    /* Read two nearest points in X-direction */
    f00 = pData[index];
    f01 = pData[index + 1];

    /* Calculation of index for two nearest points in Y-direction */
    index = (xIndex - 1) + (yIndex) * S->numCols;


    /* Read two nearest points in Y-direction */
    f10 = pData[index];
    f11 = pData[index + 1];

    /* Calculation of intermediate values */
    b1 = f00;
    b2 = f01 - f00;
    b3 = f10 - f00;
    b4 = f00 - f01 - f10 + f11;

    /* Calculation of fractional part in X */
    xdiff = X - xIndex;

    /* Calculation of fractional part in Y */
    ydiff = Y - yIndex;

    /* Calculation of bi-linear interpolated output */
    out = b1 + b2 * xdiff + b3 * ydiff + b4 * xdiff * ydiff;

    /* return to application */
    return (out);

  }

  /**
  *
  * @brief  Q31 bilinear interpolation.
  * @param[in,out] *S points to an instance of the interpolation structure.
  * @param[in] X interpolation coordinate in 12.20 format.
  * @param[in] Y interpolation coordinate in 12.20 format.
  * @return out interpolated value.
  */

  static __INLINE q31_t arm_bilinear_interp_q31(
  arm_bilinear_interp_instance_q31 * S,
  q31_t X,
  q31_t Y)
  {
    q31_t out;                                   /* Temporary output */
    q31_t acc = 0;                               /* output */
    q31_t xfract, yfract;                        /* X, Y fractional parts */
    q31_t x1, x2, y1, y2;                        /* Nearest output values */
    int32_t rI, cI;                              /* Row and column indices */
    q31_t *pYData = S->pData;                    /* pointer to output table values */
    uint32_t nCols = S->numCols;                 /* num of rows */


    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    rI = ((X & 0xFFF00000) >> 20u);

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    cI = ((Y & 0xFFF00000) >> 20u);

    /* Care taken for table outside boundary */
    /* Returns zero output when values are outside table boundary */
    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
    {
      return (0);
    }

    /* 20 bits for the fractional part */
    /* shift left xfract by 11 to keep 1.31 format */
    xfract = (X & 0x000FFFFF) << 11u;

    /* Read two nearest output values from the index */
    x1 = pYData[(rI) + nCols * (cI)];
    x2 = pYData[(rI) + nCols * (cI) + 1u];

    /* 20 bits for the fractional part */
    /* shift left yfract by 11 to keep 1.31 format */
    yfract = (Y & 0x000FFFFF) << 11u;

    /* Read two nearest output values from the index */
    y1 = pYData[(rI) + nCols * (cI + 1)];
    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];

    /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 3.29(q29) format */
    out = ((q31_t) (((q63_t) x1 * (0x7FFFFFFF - xfract)) >> 32));
    acc = ((q31_t) (((q63_t) out * (0x7FFFFFFF - yfract)) >> 32));

    /* x2 * (xfract) * (1-yfract)  in 3.29(q29) and adding to acc */
    out = ((q31_t) ((q63_t) x2 * (0x7FFFFFFF - yfract) >> 32));
    acc += ((q31_t) ((q63_t) out * (xfract) >> 32));

    /* y1 * (1 - xfract) * (yfract)  in 3.29(q29) and adding to acc */
    out = ((q31_t) ((q63_t) y1 * (0x7FFFFFFF - xfract) >> 32));
    acc += ((q31_t) ((q63_t) out * (yfract) >> 32));

    /* y2 * (xfract) * (yfract)  in 3.29(q29) and adding to acc */
    out = ((q31_t) ((q63_t) y2 * (xfract) >> 32));
    acc += ((q31_t) ((q63_t) out * (yfract) >> 32));

    /* Convert acc to 1.31(q31) format */
    return (acc << 2u);

  }

  /**
  * @brief  Q15 bilinear interpolation.
  * @param[in,out] *S points to an instance of the interpolation structure.
  * @param[in] X interpolation coordinate in 12.20 format.
  * @param[in] Y interpolation coordinate in 12.20 format.
  * @return out interpolated value.
  */

  static __INLINE q15_t arm_bilinear_interp_q15(
  arm_bilinear_interp_instance_q15 * S,
  q31_t X,
  q31_t Y)
  {
    q63_t acc = 0;                               /* output */
    q31_t out;                                   /* Temporary output */
    q15_t x1, x2, y1, y2;                        /* Nearest output values */
    q31_t xfract, yfract;                        /* X, Y fractional parts */
    int32_t rI, cI;                              /* Row and column indices */
    q15_t *pYData = S->pData;                    /* pointer to output table values */
    uint32_t nCols = S->numCols;                 /* num of rows */

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    rI = ((X & 0xFFF00000) >> 20);

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    cI = ((Y & 0xFFF00000) >> 20);

    /* Care taken for table outside boundary */
    /* Returns zero output when values are outside table boundary */
    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
    {
      return (0);
    }

    /* 20 bits for the fractional part */
    /* xfract should be in 12.20 format */
    xfract = (X & 0x000FFFFF);

    /* Read two nearest output values from the index */
    x1 = pYData[(rI) + nCols * (cI)];
    x2 = pYData[(rI) + nCols * (cI) + 1u];


    /* 20 bits for the fractional part */
    /* yfract should be in 12.20 format */
    yfract = (Y & 0x000FFFFF);

    /* Read two nearest output values from the index */
    y1 = pYData[(rI) + nCols * (cI + 1)];
    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];

    /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 13.51 format */

    /* x1 is in 1.15(q15), xfract in 12.20 format and out is in 13.35 format */
    /* convert 13.35 to 13.31 by right shifting  and out is in 1.31 */
    out = (q31_t) (((q63_t) x1 * (0xFFFFF - xfract)) >> 4u);
    acc = ((q63_t) out * (0xFFFFF - yfract));

    /* x2 * (xfract) * (1-yfract)  in 1.51 and adding to acc */
    out = (q31_t) (((q63_t) x2 * (0xFFFFF - yfract)) >> 4u);
    acc += ((q63_t) out * (xfract));

    /* y1 * (1 - xfract) * (yfract)  in 1.51 and adding to acc */
    out = (q31_t) (((q63_t) y1 * (0xFFFFF - xfract)) >> 4u);
    acc += ((q63_t) out * (yfract));

    /* y2 * (xfract) * (yfract)  in 1.51 and adding to acc */
    out = (q31_t) (((q63_t) y2 * (xfract)) >> 4u);
    acc += ((q63_t) out * (yfract));

    /* acc is in 13.51 format and down shift acc by 36 times */
    /* Convert out to 1.15 format */
    return (acc >> 36);

  }

  /**
  * @brief  Q7 bilinear interpolation.
  * @param[in,out] *S points to an instance of the interpolation structure.
  * @param[in] X interpolation coordinate in 12.20 format.
  * @param[in] Y interpolation coordinate in 12.20 format.
  * @return out interpolated value.
  */

  static __INLINE q7_t arm_bilinear_interp_q7(
  arm_bilinear_interp_instance_q7 * S,
  q31_t X,
  q31_t Y)
  {
    q63_t acc = 0;                               /* output */
    q31_t out;                                   /* Temporary output */
    q31_t xfract, yfract;                        /* X, Y fractional parts */
    q7_t x1, x2, y1, y2;                         /* Nearest output values */
    int32_t rI, cI;                              /* Row and column indices */
    q7_t *pYData = S->pData;                     /* pointer to output table values */
    uint32_t nCols = S->numCols;                 /* num of rows */

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    rI = ((X & 0xFFF00000) >> 20);

    /* Input is in 12.20 format */
    /* 12 bits for the table index */
    /* Index value calculation */
    cI = ((Y & 0xFFF00000) >> 20);

    /* Care taken for table outside boundary */
    /* Returns zero output when values are outside table boundary */
    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
    {
      return (0);
    }

    /* 20 bits for the fractional part */
    /* xfract should be in 12.20 format */
    xfract = (X & 0x000FFFFF);

    /* Read two nearest output values from the index */
    x1 = pYData[(rI) + nCols * (cI)];
    x2 = pYData[(rI) + nCols * (cI) + 1u];


    /* 20 bits for the fractional part */
    /* yfract should be in 12.20 format */
    yfract = (Y & 0x000FFFFF);

    /* Read two nearest output values from the index */
    y1 = pYData[(rI) + nCols * (cI + 1)];
    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];

    /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 16.47 format */
    out = ((x1 * (0xFFFFF - xfract)));
    acc = (((q63_t) out * (0xFFFFF - yfract)));

    /* x2 * (xfract) * (1-yfract)  in 2.22 and adding to acc */
    out = ((x2 * (0xFFFFF - yfract)));
    acc += (((q63_t) out * (xfract)));

    /* y1 * (1 - xfract) * (yfract)  in 2.22 and adding to acc */
    out = ((y1 * (0xFFFFF - xfract)));
    acc += (((q63_t) out * (yfract)));

    /* y2 * (xfract) * (yfract)  in 2.22 and adding to acc */
    out = ((y2 * (yfract)));
    acc += (((q63_t) out * (xfract)));

    /* acc in 16.47 format and down shift by 40 to convert to 1.7 format */
    return (acc >> 40);

  }

  /**
   * @} end of BilinearInterpolate group
   */
   

//SMMLAR
#define multAcc_32x32_keep32_R(a, x, y) \
    a = (q31_t) (((((q63_t) a) << 32) + ((q63_t) x * y) + 0x80000000LL ) >> 32)

//SMMLSR
#define multSub_32x32_keep32_R(a, x, y) \
    a = (q31_t) (((((q63_t) a) << 32) - ((q63_t) x * y) + 0x80000000LL ) >> 32)

//SMMULR
#define mult_32x32_keep32_R(a, x, y) \
    a = (q31_t) (((q63_t) x * y + 0x80000000LL ) >> 32)

//SMMLA
#define multAcc_32x32_keep32(a, x, y) \
    a += (q31_t) (((q63_t) x * y) >> 32)

//SMMLS
#define multSub_32x32_keep32(a, x, y) \
    a -= (q31_t) (((q63_t) x * y) >> 32)

//SMMUL
#define mult_32x32_keep32(a, x, y) \
    a = (q31_t) (((q63_t) x * y ) >> 32)


#if defined ( __CC_ARM ) //Keil

//Enter low optimization region - place directly above function definition
    #ifdef ARM_MATH_CM4
      #define LOW_OPTIMIZATION_ENTER \
         _Pragma ("push")         \
         _Pragma ("O1")
    #else
      #define LOW_OPTIMIZATION_ENTER 
    #endif

//Exit low optimization region - place directly after end of function definition
    #ifdef ARM_MATH_CM4
      #define LOW_OPTIMIZATION_EXIT \
         _Pragma ("pop")
    #else
      #define LOW_OPTIMIZATION_EXIT  
    #endif

//Enter low optimization region - place directly above function definition
  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER

//Exit low optimization region - place directly after end of function definition
  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT

#elif defined(__ICCARM__) //IAR

//Enter low optimization region - place directly above function definition
    #ifdef ARM_MATH_CM4
      #define LOW_OPTIMIZATION_ENTER \
         _Pragma ("optimize=low")
    #else
      #define LOW_OPTIMIZATION_ENTER   
    #endif

//Exit low optimization region - place directly after end of function definition
  #define LOW_OPTIMIZATION_EXIT

//Enter low optimization region - place directly above function definition
    #ifdef ARM_MATH_CM4
      #define IAR_ONLY_LOW_OPTIMIZATION_ENTER \
         _Pragma ("optimize=low")
    #else
      #define IAR_ONLY_LOW_OPTIMIZATION_ENTER   
    #endif

//Exit low optimization region - place directly after end of function definition
  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT

#elif defined(__GNUC__)

  #define LOW_OPTIMIZATION_ENTER __attribute__(( optimize("-O1") ))

  #define LOW_OPTIMIZATION_EXIT

  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER

  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT

#elif defined(__CSMC__)		// Cosmic

#define LOW_OPTIMIZATION_ENTER
#define LOW_OPTIMIZATION_EXIT
#define IAR_ONLY_LOW_OPTIMIZATION_ENTER
#define IAR_ONLY_LOW_OPTIMIZATION_EXIT

#elif defined(__TASKING__)		// TASKING

#define LOW_OPTIMIZATION_ENTER
#define LOW_OPTIMIZATION_EXIT
#define IAR_ONLY_LOW_OPTIMIZATION_ENTER
#define IAR_ONLY_LOW_OPTIMIZATION_EXIT

#endif


#ifdef	__cplusplus
}
#endif


#endif /* _ARM_MATH_H */

/**
 *
 * End of file.
 */