aboutsummaryrefslogtreecommitdiff
path: root/ecdsa_fpga_microcode.cpp
blob: 29920c60e285cc0d710ce7cfd923fff095085fc2 (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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
//------------------------------------------------------------------------------
//
// ecdsa_fpga_microcode.cpp
// --------------------------------
// Microcode Architecture for ECDSA
//
// Authors: Pavel Shatov
//
// Copyright (c) 2018, 2021 NORDUnet A/S
//
// 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 the NORDUnet 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 HOLDER 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.
//
//------------------------------------------------------------------------------


//------------------------------------------------------------------------------
// Required for Microcode Routines
//------------------------------------------------------------------------------
#define USE_MICROCODE


//------------------------------------------------------------------------------
// Headers
//------------------------------------------------------------------------------
#include "ecdsa_fpga_model.h"


//------------------------------------------------------------------------------
// Global Buffers
//------------------------------------------------------------------------------
FPGA_BUFFER BUF_LO[ECDSA_UOP_OPERAND_COUNT];
FPGA_BUFFER BUF_HI[ECDSA_UOP_OPERAND_COUNT];


//------------------------------------------------------------------------------
// Global Flags
//------------------------------------------------------------------------------
bool uop_flagz_r0z;
bool uop_flagz_r1z;


//------------------------------------------------------------------------------
void uop_move(UOP_BANK src, int s_op, UOP_BANK dst, int d_op)
//------------------------------------------------------------------------------
{
	FPGA_BUFFER *s_ptr = NULL;
	FPGA_BUFFER *d_ptr = NULL;

	if (src == BANK_LO) s_ptr = &BUF_LO[s_op];
	if (src == BANK_HI) s_ptr = &BUF_HI[s_op];
	if (dst == BANK_LO) d_ptr = &BUF_LO[d_op];
	if (dst == BANK_HI) d_ptr = &BUF_HI[d_op];

	fpga_multiword_copy(s_ptr, d_ptr);
}


//------------------------------------------------------------------------------
void uop_cmpz(UOP_BANK src, int s_op)
//------------------------------------------------------------------------------
{
    bool flagz;

    FPGA_BUFFER *s_ptr = NULL;

	if (src == BANK_LO)	s_ptr = &BUF_LO[s_op];
	if (src == BANK_HI) s_ptr = &BUF_HI[s_op];

    flagz = fpga_multiword_is_zero(s_ptr);

    switch (s_op)
    {
        case CYCLE_R0Z:
            uop_flagz_r0z = flagz;
            break;
        case CYCLE_R1Z:
            uop_flagz_r1z = flagz;
            break;
    }
}


//------------------------------------------------------------------------------
void uop_calc(UOP_MATH math,
              UOP_BANK src, int s_op1, int s_op2,
              UOP_BANK dst, int d_op)
//------------------------------------------------------------------------------
{
	FPGA_BUFFER *s_ptr1 = NULL;
	FPGA_BUFFER *s_ptr2 = NULL;
	FPGA_BUFFER *d_ptr = NULL;
	FPGA_BUFFER *n_ptr = NULL;

	if (src == BANK_LO)
	{	s_ptr1 = &BUF_LO[s_op1];
		s_ptr2 = &BUF_LO[s_op2];
	}
	if (src == BANK_HI)
	{	s_ptr1 = &BUF_HI[s_op1];
		s_ptr2 = &BUF_HI[s_op2];
	}
	if (dst == BANK_LO)
	{	d_ptr = &BUF_LO[d_op];
	}
	if (dst == BANK_HI)
	{	d_ptr = &BUF_HI[d_op];
	}

	if (math == ADD) fpga_modular_add(s_ptr1, s_ptr2, d_ptr);
	if (math == SUB) fpga_modular_sub(s_ptr1, s_ptr2, d_ptr);
	if (math == MUL) fpga_modular_mul(s_ptr1, s_ptr2, d_ptr);

#ifdef DUMP_UOP_OUTPUTS
    if (math == ADD) dump_uop_output("ADD", d_ptr);
    if (math == SUB) dump_uop_output("SUB", d_ptr);
    if (math == MUL) dump_uop_output("MUL", d_ptr);
#endif

}


//------------------------------------------------------------------------------
void uop_load(const FPGA_BUFFER *mem, UOP_BANK dst, int d_op)
//------------------------------------------------------------------------------
{
	FPGA_BUFFER *d_ptr = NULL;
	if (dst == BANK_LO) d_ptr = &BUF_LO[d_op];
	if (dst == BANK_HI) d_ptr = &BUF_HI[d_op];

	fpga_multiword_copy(mem, d_ptr);
}


//------------------------------------------------------------------------------
void uop_stor(UOP_BANK src, int s_op, FPGA_BUFFER *mem)
//------------------------------------------------------------------------------
{
	FPGA_BUFFER *s_ptr = NULL;
	if (src == BANK_LO)
	{	s_ptr = &BUF_LO[s_op];
	}
	if (src == BANK_HI)
	{	s_ptr = &BUF_HI[s_op];
	}

	fpga_multiword_copy(s_ptr, mem);
}


//------------------------------------------------------------------------------
void fpga_modular_inv23_p256_microcode()
//------------------------------------------------------------------------------
//
// This computes A2 = RZ^-2 and A3 = RZ^-3.
//
// RZ is read from the lower bank, A2 and A3 are written to the upper bank.
//
//------------------------------------------------------------------------------
{
	uop_loop;

    //
    // operand placement map:
    //
    // X1  - LO,HI (RZ)
    // X2  - LO,HI
    // X3  - LO,HI
    // X6  - LO
    // X12 - HI
    // X15 - LO,HI
    // X30 - HI
    // X32 - LO,HI

    /* BEGIN_MICROCODE: INVERT_P256 */

    // first obtain intermediate helper quantities (X#)

	// mirror X1 to HI bank (don't waste time copying to X1, just use RZ)
	uop_move(BANK_LO, CYCLE_R0Z, BANK_HI, CYCLE_R0Z);

	// compute X2 and mirror to the other bank
	uop_calc(MUL, BANK_LO, CYCLE_R0Z, CYCLE_R0Z, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, CYCLE_R0Z, INVERT_R1, BANK_LO, INVERT_X2);
	uop_move(BANK_LO, INVERT_X2, BANK_HI, INVERT_X2);

	// compute X3 and mirror to the other bank
	uop_calc(MUL, BANK_LO, INVERT_X2, INVERT_X2, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, CYCLE_R0Z, BANK_LO, INVERT_X3);
	uop_move(BANK_LO, INVERT_X3, BANK_HI, INVERT_X3);

	// compute X6 (stored in the lower bank)
	uop_calc(MUL, BANK_LO, INVERT_X3, INVERT_X3, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_X3, BANK_LO, INVERT_X6);

	// compute X12 (stored in the upper bank)
	uop_calc(MUL, BANK_LO, INVERT_X6, INVERT_X6, BANK_HI, INVERT_R1);
	uop_cycle(5);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_X6, BANK_HI, INVERT_X12);
	
	// compute X15 and mirror to the other bank
	uop_calc(MUL, BANK_HI, INVERT_X12, INVERT_X12, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
	uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_X3, BANK_HI, INVERT_X15);
	uop_move(BANK_HI, INVERT_X15, BANK_LO, INVERT_X15);

	// compute X30 (stored in the upper bank)
	uop_calc(MUL, BANK_HI, INVERT_X15, INVERT_X15, BANK_LO, INVERT_R1);
	uop_cycle(14);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_X15, BANK_HI, INVERT_X30);

	// compute X32 and mirror to the other bank
	uop_calc(MUL, BANK_HI, INVERT_X30, INVERT_X30, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
	uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X2, BANK_LO, INVERT_X32);
	uop_move(BANK_LO, INVERT_X32, BANK_HI, INVERT_X32);

	// now compute the final results

	uop_calc(MUL, BANK_LO, INVERT_X32, INVERT_X32, BANK_HI, INVERT_R1);

	uop_cycle(31);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();

	uop_calc(MUL, BANK_LO, INVERT_R2, CYCLE_R0Z, BANK_HI, INVERT_R1);

	uop_cycle(128);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();

	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_X32, BANK_LO, INVERT_R2);

	uop_cycle(32);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
	uop_repeat();

	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_X32, BANK_HI, INVERT_R1);

	uop_cycle(30);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();

	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_X30, BANK_LO, INVERT_R2);
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);

    // move A2 into the upper bank
	uop_move(BANK_LO, INVERT_R2, BANK_HI, INVERT_A2);

    // A3 ends up in the upper bank by itself
	uop_calc(MUL, BANK_HI, INVERT_A2, INVERT_A2, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, CYCLE_R0Z, BANK_HI, INVERT_A3);

    /* END_MICROCODE */
}


//------------------------------------------------------------------------------
void fpga_modular_inv23_p384_microcode()
//------------------------------------------------------------------------------
//
// This computes A2 = RZ^-2 and A3 = RZ^-3.
//
// RZ is read from the lower bank, A2 and A3 are written to the upper bank.
//
//------------------------------------------------------------------------------
{
	uop_loop;

    //
    // operand placement map:
    //
    // X1  - LO,HI (RZ)
    // X2  - LO,HI
    // X3  - LO,HI
    // X6  - LO
    // X12 - HI
    // X15 - LO,HI
    // X30 - HI
    // X32 - LO,HI

    /* BEGIN_MICROCODE: INVERT_P384 */

    // first obtain intermediate helper quantities (X#)

	// mirror X1 to HI bank (don't waste time copying to X1, just use RZ)
	uop_move(BANK_LO, CYCLE_R0Z, BANK_HI, CYCLE_R0Z);

	// compute X2 and mirror to the other bank
	uop_calc(MUL, BANK_LO, CYCLE_R0Z, CYCLE_R0Z, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, CYCLE_R0Z, INVERT_R1, BANK_LO, INVERT_X2);
	uop_move(BANK_LO, INVERT_X2, BANK_HI, INVERT_X2);

	// compute X3 and mirror to the other bank
	uop_calc(MUL, BANK_LO, INVERT_X2, INVERT_X2, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, CYCLE_R0Z, BANK_LO, INVERT_X3);
	uop_move(BANK_LO, INVERT_X3, BANK_HI, INVERT_X3);

	// compute X6 (stored in the lower bank)
	uop_calc(MUL, BANK_LO, INVERT_X3, INVERT_X3, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_calc(MUL, BANK_HI, INVERT_R1, INVERT_X3, BANK_LO, INVERT_X6);

	// compute X12 (stored in the upper bank)
	uop_calc(MUL, BANK_LO, INVERT_X6, INVERT_X6, BANK_HI, INVERT_R1);
	uop_cycle(5);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_X6, BANK_HI, INVERT_X12);
	
	// compute X15 and mirror to the other bank
	uop_calc(MUL, BANK_HI, INVERT_X12, INVERT_X12, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
	uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_X3, BANK_HI, INVERT_X15);
	uop_move(BANK_HI, INVERT_X15, BANK_LO, INVERT_X15);

	// compute X30 (stored in the upper bank)
	uop_calc(MUL, BANK_HI, INVERT_X15, INVERT_X15, BANK_LO, INVERT_R1);
	uop_cycle(14);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_X15, BANK_HI, INVERT_X30);

    // compute X60 (stored in the lower bank)
	uop_calc(MUL, BANK_HI, INVERT_X30, INVERT_X30, BANK_LO, INVERT_R1);
	uop_cycle(29);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X30, BANK_LO, INVERT_X60);

    // compute X120 (stored in the upper bank)
	uop_calc(MUL, BANK_LO, INVERT_X60, INVERT_X60, BANK_HI, INVERT_R1);
	uop_cycle(59);
		uop_calc_if_even(MUL, BANK_HI, INVERT_R1, INVERT_R1, BANK_LO, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_LO, INVERT_R2, INVERT_R2, BANK_HI, INVERT_R1);
	uop_repeat();
	uop_calc(MUL, BANK_LO, INVERT_R2, INVERT_X60, BANK_HI, INVERT_X120);

	// now compute the final results

	uop_calc(MUL, BANK_HI, INVERT_X120, INVERT_X120, BANK_LO, INVERT_R1);

	uop_cycle(119);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();

    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X120, BANK_LO, INVERT_R1);

	uop_cycle(15);
		uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
		uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();

    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X15, BANK_LO, INVERT_R1);

    uop_cycle(31);
	    uop_calc_if_even(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
        uop_calc_if_odd (MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
	uop_repeat();

    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X30, BANK_LO, INVERT_R1);
    uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
    uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_X2, BANK_HI, INVERT_R2);

    uop_cycle(94);
	    uop_calc_if_even(MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);
        uop_calc_if_odd (MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
	uop_repeat();

    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_X30, BANK_LO, INVERT_R1);
    uop_calc(MUL, BANK_LO, INVERT_R1, INVERT_R1, BANK_HI, INVERT_R2);
    uop_calc(MUL, BANK_HI, INVERT_R2, INVERT_R2, BANK_LO, INVERT_R1);

    // move A2 into the upper bank
	uop_move(BANK_LO, INVERT_R1, BANK_HI, INVERT_A2);

    // A3 ends up in the upper bank by itself
	uop_calc(MUL, BANK_HI, INVERT_A2, INVERT_A2, BANK_LO, INVERT_R1);
	uop_calc(MUL, BANK_LO, INVERT_R1, CYCLE_R0Z, BANK_HI, INVERT_A3);

    /* END_MICROCODE */
}


//------------------------------------------------------------------------------
// End-of-File
//------------------------------------------------------------------------------