5 * ternlogi <https://bugs.libre-soc.org/show_bug.cgi?id=745>
6 * grev <https://bugs.libre-soc.org/show_bug.cgi?id=755>
7 * remove Rc=1 from ternlog due to conflicts in encoding as well
8 as saving space <https://bugs.libre-soc.org/show_bug.cgi?id=753#c5>
9 * GF2^M <https://bugs.libre-soc.org/show_bug.cgi?id=782>
15 this extension amalgamates bitmanipulation primitives from many sources, including RISC-V bitmanip, Packed SIMD, AVX-512 and OpenPOWER VSX. Vectorisation and SIMD are removed: these are straight scalar (element) operations making them suitable for embedded applications.
16 Vectorisation Context is provided by [[openpower/sv]].
18 When combined with SV, scalar variants of bitmanip operations found in VSX are added so that VSX may be retired as "legacy" in the far future (10 to 20 years). Also, VSX is hundreds of opcodes, requires 128 bit pathways, and is wholly unsuited to low power or embedded scenarios.
20 ternlogv is experimental and is the only operation that may be considered a "Packed SIMD". It is added as a variant of the already well-justified ternlog operation (done in AVX512 as an immediate only) "because it looks fun". As it is based on the LUT4 concept it will allow accelerated emulation of FPGAs. Other vendors of ISAs are buying FPGA companies to achieve similar objectives.
22 general-purpose Galois Field 2^M operations are added so as to avoid huge custom opcode proliferation across many areas of Computer Science. however for convenience and also to avoid setup costs, some of the more common operations (clmul, crc32) are also added. The expectation is that these operations would all be covered by the same pipeline.
24 note that there are brownfield spaces below that could incorporate some of the set-before-first and other scalar operations listed in [[sv/vector_ops]], and
25 the [[sv/av_opcodes]] as well as [[sv/setvl]]
29 * <https://en.wikiversity.org/wiki/Reed%E2%80%93Solomon_codes_for_coders>
30 * <https://maths-people.anu.edu.au/~brent/pd/rpb232tr.pdf>
34 minor opcode allocation
37 | ------ |--| --------- |
45 | 111 |0 | ternlogcr |
49 | dest | src1 | subop | op |
50 | ---- | ---- | ----- | -------- |
51 | RT | RA | .. | bmatflip |
55 | dest | src1 | src2 | subop | op |
56 | ---- | ---- | ---- | ----- | -------- |
57 | RT | RA | RB | or | bmatflip |
58 | RT | RA | RB | xor | bmatflip |
59 | RT | RA | RB | | grev |
60 | RT | RA | RB | | clmul* |
61 | RT | RA | RB | | gorc |
62 | RT | RA | RB | shuf | shuffle |
63 | RT | RA | RB | unshuf| shuffle |
64 | RT | RA | RB | width | xperm |
65 | RT | RA | RB | type | minmax |
66 | RT | RA | RB | | av abs avgadd |
67 | RT | RA | RB | type | vmask ops |
77 TODO: convert all instructions to use RT and not RS
79 | 0.5|6.10|11.15|16.20 |21..25 | 26....30 |31| name |
80 | -- | -- | --- | --- | ----- | -------- |--| ------ |
81 | NN | RT | RA | RB | im0-4 | im5-7 00 |0 | ternlogi |
82 | NN | RT | RA | RB | im0-4 | im5-7 00 |1 | grevlog |
83 | NN | RT | RA | s0-4 | im0-4 | im5-7 01 |s5| grevlogi |
84 | NN | RS | RA | RB | RC | 00 011 |Rc| gfmadd |
85 | NN | RS | RA | RB | RC | 10 011 |Rc| gfmaddsub |
86 | NN | RT | RA | RB | sh0-4 | sh5 1 011 |Rc| bmrevi |
88 | 0.5|6.10|11.15| 16.23 |24.27 | 28.30 |31| name |
89 | -- | -- | --- | ----- | ---- | ----- |--| ------ |
90 | NN | RT | RA | imm | mask | 111 |1 | ternlogv |
92 | 0.5|6.8 | 9.11|12.14|15|16.23|24.27 | 28.30|31| name |
93 | -- | -- | --- | --- |- |-----|----- | -----|--| -------|
94 | NN | BA | BB | BC |0 |imm | mask | 111 |0 | ternlogcr |
96 ops (note that av avg and abs as well as vec scalar mask
99 TODO: convert from RA, RB, and RC to correct field names of RT, RA, and RB, and
100 double check that instructions didn't need 3 inputs.
102 | 0.5|6.10|11.15|16.20| 21 | 22.23 | 24....30 |31| name |
103 | -- | -- | --- | --- | -- | ----- | -------- |--| ---- |
104 | NN | RA | RB | | 0 | | 0000 110 |Rc| rsvd |
105 | NN | RA | RB | RC | 1 | itype | 0000 110 |Rc| xperm |
106 | NN | RA | RB | RC | 0 | itype | 0100 110 |Rc| minmax |
107 | NN | RA | RB | RC | 1 | 00 | 0100 110 |Rc| av avgadd |
108 | NN | RA | RB | RC | 1 | 01 | 0100 110 |Rc| av abs |
109 | NN | RA | RB | | 1 | 10 | 0100 110 |Rc| rsvd |
110 | NN | RA | RB | | 1 | 11 | 0100 110 |Rc| rsvd |
111 | NN | RA | RB | sh | SH | itype | 1000 110 |Rc| bmopsi |
112 | NN | RA | RB | | | | 1100 110 |Rc| rsvd |
113 | NN | RT | RA | RB | 1 | 00 | 0001 110 |Rc| gfdiv |
114 | NN | RT | RA | RB | 1 | 01 | 0001 110 |Rc| gfmod |
115 | NN | RT | RA | RB | 1 | 10 | 0001 110 |Rc| gfmul |
116 | NN | RA | RB | | 1 | 11 | 0001 110 |Rc| rsvd |
117 | NN | RA | RB | RC | 0 | 00 | 0001 110 |Rc| vec sbfm |
118 | NN | RA | RB | RC | 0 | 01 | 0001 110 |Rc| vec sofm |
119 | NN | RA | RB | RC | 0 | 10 | 0001 110 |Rc| vec sifm |
120 | NN | RA | RB | RC | 0 | 11 | 0001 110 |Rc| vec cprop |
121 | NN | RA | RB | | 0 | | 0101 110 |Rc| rsvd |
122 | NN | RA | RB | RC | 0 | 00 | 0010 110 |Rc| gorc |
123 | NN | RA | RB | sh | SH | 00 | 1010 110 |Rc| gorci |
124 | NN | RA | RB | RC | 0 | 00 | 0110 110 |Rc| gorcw |
125 | NN | RA | RB | sh | 0 | 00 | 1110 110 |Rc| gorcwi |
126 | NN | RA | RB | RC | 1 | 00 | 1110 110 |Rc| bmator |
127 | NN | RA | RB | RC | 0 | 01 | 0010 110 |Rc| grev |
128 | NN | RA | RB | RC | 1 | 01 | 0010 110 |Rc| clmul |
129 | NN | RA | RB | sh | SH | 01 | 1010 110 |Rc| grevi |
130 | NN | RA | RB | RC | 0 | 01 | 0110 110 |Rc| grevw |
131 | NN | RA | RB | sh | 0 | 01 | 1110 110 |Rc| grevwi |
132 | NN | RA | RB | RC | 1 | 01 | 1110 110 |Rc| bmatxor |
133 | NN | RA | RB | RC | 0 | 10 | 0010 110 |Rc| shfl |
134 | NN | RA | RB | sh | SH | 10 | 1010 110 |Rc| shfli |
135 | NN | RA | RB | RC | 0 | 10 | 0110 110 |Rc| shflw |
136 | NN | RA | RB | RC | | 10 | 1110 110 |Rc| rsvd |
137 | NN | RA | RB | RC | 0 | 11 | 1110 110 |Rc| clmulr |
138 | NN | RA | RB | RC | 1 | 11 | 1110 110 |Rc| clmulh |
139 | NN | | | | | | --11 110 |Rc| setvl |
141 # bit to byte permute
143 similar to matrix permute in RV bitmanip, which has XOR and OR variants
147 b = VSR[VRB+32].dword[i].byte[k].bit[j]
148 VSR[VRT+32].dword[i].byte[j].bit[k] = b
152 signed and unsigned min/max for integer. this is sort-of partly synthesiseable in [[sv/svp64]] with pred-result as long as the dest reg is one of the sources, but not both signed and unsigned. when the dest is also one of the srces and the mv fails due to the CR bittest failing this will only overwrite the dest where the src is greater (or less).
154 signed/unsigned min/max gives more flexibility.
157 uint_xlen_t min(uint_xlen_t rs1, uint_xlen_t rs2)
158 { return (int_xlen_t)rs1 < (int_xlen_t)rs2 ? rs1 : rs2;
160 uint_xlen_t max(uint_xlen_t rs1, uint_xlen_t rs2)
161 { return (int_xlen_t)rs1 > (int_xlen_t)rs2 ? rs1 : rs2;
163 uint_xlen_t minu(uint_xlen_t rs1, uint_xlen_t rs2)
164 { return rs1 < rs2 ? rs1 : rs2;
166 uint_xlen_t maxu(uint_xlen_t rs1, uint_xlen_t rs2)
167 { return rs1 > rs2 ? rs1 : rs2;
174 Similar to FPGA LUTs: for every bit perform a lookup into a table using an 8bit immediate, or in another register.
176 Like the x86 AVX512F [vpternlogd/vpternlogq](https://www.felixcloutier.com/x86/vpternlogd:vpternlogq) instructions.
180 | 0.5|6.10|11.15|16.20| 21..25| 26..30 |31|
181 | -- | -- | --- | --- | ----- | -------- |--|
182 | NN | RT | RA | RB | im0-4 | im5-7 00 |0 |
185 idx = c << 2 | b << 1 | a
186 return imm[idx] # idx by LSB0 order
189 RT[i] = lut3(imm, RB[i], RA[i], RT[i])
191 bits 21..22 may be used to specify a mode, such as treating the whole integer zero/nonzero and putting 1/0 in the result, rather than bitwise test.
195 a 4 operand variant which becomes more along the lines of an FPGA:
197 | 0.5|6.10|11.15|16.20|21.25| 26...30 |31|
198 | -- | -- | --- | --- | --- | -------- |--|
199 | NN | RT | RA | RB | RC | mode 100 |1 |
202 idx = RT[i] << 2 | RA[i] << 1 | RB[i]
203 RT[i] = (RC & (1<<idx)) != 0
205 mode (2 bit) may be used to do inversion of ordering, similar to carryless mul,
210 also, another possible variant involving swizzle and vec4:
212 | 0.5|6.10|11.15| 16.23 |24.27 | 28.30 |31|
213 | -- | -- | --- | ----- | ---- | ----- |--|
214 | NN | RT | RA | imm | mask | 101 |1 |
217 idx = RA.x[i] << 2 | RA.y[i] << 1 | RA.z[i]
218 res = (imm & (1<<idx)) != 0
220 if mask[j]: RT[i+j*8] = res
224 another mode selection would be CRs not Ints.
226 | 0.5|6.8 | 9.11|12.14|15|16.23|24.27 | 28.30|31|
227 | -- | -- | --- | --- |- |-----|----- | -----|--|
228 | NN | BA | BB | BC |0 |imm | mask | 101 |0 |
231 if not mask[i] continue
232 idx = crregs[BA][i] << 2 |
235 crregs[BA][i] = (imm & (1<<idx)) != 0
239 based on RV bitmanip, covered by ternlog bitops
242 uint_xlen_t cmix(uint_xlen_t RA, uint_xlen_t RB, uint_xlen_t RC) {
243 return (RA & RB) | (RC & ~RB);
250 based on RV bitmanip singlebit set, instruction format similar to shift
251 [[isa/fixedshift]]. bmext is actually covered already (shift-with-mask rldicl but only immediate version).
252 however bitmask-invert is not, and set/clr are not covered, although they can use the same Shift ALU.
254 bmext (RB) version is not the same as rldicl because bmext is a right shift by RC, where rldicl is a left rotate. for the immediate version this does not matter, so a bmexti is not required.
255 bmrev however there is no direct equivalent and consequently a bmrevi is required.
257 bmset (register for mask amount) is particularly useful for creating
258 predicate masks where the length is a dynamic runtime quantity.
259 bmset(RA=0, RB=0, RC=mask) will produce a run of ones of length "mask" in a single instruction without needing to initialise or depend on any other registers.
261 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31| name |
262 | -- | -- | --- | --- | --- | ------- |--| ----- |
263 | NN | RT | RA | RB | RC | mode 010 |Rc| bm* |
267 uint_xlen_t bmset(RA, RB, sh)
269 int shamt = RB & (XLEN - 1);
271 return RA | (mask << shamt);
274 uint_xlen_t bmclr(RA, RB, sh)
276 int shamt = RB & (XLEN - 1);
278 return RA & ~(mask << shamt);
281 uint_xlen_t bminv(RA, RB, sh)
283 int shamt = RB & (XLEN - 1);
285 return RA ^ (mask << shamt);
288 uint_xlen_t bmext(RA, RB, sh)
290 int shamt = RB & (XLEN - 1);
292 return mask & (RA >> shamt);
296 bitmask extract with reverse. can be done by bitinverting all of RA and getting bits of RA from the opposite end.
300 rev[0:msb] = ra[msb:0];
303 uint_xlen_t bmextrev(RA, RB, sh)
305 int shamt = (RB & (XLEN - 1));
306 shamt = (XLEN-1)-shamt; # shift other end
307 bra = bitreverse(RA) # swap LSB-MSB
309 return mask & (bra >> shamt);
313 | 0.5|6.10|11.15|16.20|21.26| 27..30 |31| name |
314 | -- | -- | --- | --- | --- | ------- |--| ------ |
315 | NN | RT | RA | RB | sh | 1 011 |Rc| bmrevi |
320 generalised reverse combined with a LUT2 and allowing
321 zero when RA=0 provides a wide range of instructions
322 and a means to set regular 64 bit patterns in one
328 return imm[idx] # idx by LSB0 order
330 dorow(imm, step_i, chunksize):
332 step_o[j] = lut2(imm, step_i[j], step_i[j ^ chunk_size])
335 uint64_t grevlut64(uint64_t RA, uint64_t RB, uint8 lut2)
339 int imm = lut2 & 0b1111;
342 if (shamt & step) x = dorow(imm, x, step)
350 based on RV bitmanip, this is also known as a butterfly network. however
351 where a butterfly network allows setting of every crossbar setting in
352 every row and every column, generalised-reverse (grev) only allows
353 a per-row decision: every entry in the same row must either switch or
356 <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/8/8c/Butterfly_Network.jpg/474px-Butterfly_Network.jpg" />
359 uint64_t grev64(uint64_t RA, uint64_t RB)
363 if (shamt & 1) x = ((x & 0x5555555555555555LL) << 1) |
364 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
365 if (shamt & 2) x = ((x & 0x3333333333333333LL) << 2) |
366 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
367 if (shamt & 4) x = ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
368 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
369 if (shamt & 8) x = ((x & 0x00FF00FF00FF00FFLL) << 8) |
370 ((x & 0xFF00FF00FF00FF00LL) >> 8);
371 if (shamt & 16) x = ((x & 0x0000FFFF0000FFFFLL) << 16) |
372 ((x & 0xFFFF0000FFFF0000LL) >> 16);
373 if (shamt & 32) x = ((x & 0x00000000FFFFFFFFLL) << 32) |
374 ((x & 0xFFFFFFFF00000000LL) >> 32);
380 # shuffle / unshuffle
385 uint32_t shfl32(uint32_t RA, uint32_t RB)
389 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
390 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
391 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
392 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
395 uint32_t unshfl32(uint32_t RA, uint32_t RB)
399 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
400 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
401 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
402 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
406 uint64_t shuffle64_stage(uint64_t src, uint64_t maskL, uint64_t maskR, int N)
408 uint64_t x = src & ~(maskL | maskR);
409 x |= ((src << N) & maskL) | ((src >> N) & maskR);
412 uint64_t shfl64(uint64_t RA, uint64_t RB)
416 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
417 0x00000000ffff0000LL, 16);
418 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
419 0x0000ff000000ff00LL, 8);
420 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
421 0x00f000f000f000f0LL, 4);
422 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
423 0x0c0c0c0c0c0c0c0cLL, 2);
424 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
425 0x2222222222222222LL, 1);
428 uint64_t unshfl64(uint64_t RA, uint64_t RB)
432 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
433 0x2222222222222222LL, 1);
434 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
435 0x0c0c0c0c0c0c0c0cLL, 2);
436 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
437 0x00f000f000f000f0LL, 4);
438 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
439 0x0000ff000000ff00LL, 8);
440 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
441 0x00000000ffff0000LL, 16);
451 uint_xlen_t xperm(uint_xlen_t RA, uint_xlen_t RB, int sz_log2)
454 uint_xlen_t sz = 1LL << sz_log2;
455 uint_xlen_t mask = (1LL << sz) - 1;
456 for (int i = 0; i < XLEN; i += sz) {
457 uint_xlen_t pos = ((RB >> i) & mask) << sz_log2;
459 r |= ((RA >> pos) & mask) << i;
463 uint_xlen_t xperm_n (uint_xlen_t RA, uint_xlen_t RB)
464 { return xperm(RA, RB, 2); }
465 uint_xlen_t xperm_b (uint_xlen_t RA, uint_xlen_t RB)
466 { return xperm(RA, RB, 3); }
467 uint_xlen_t xperm_h (uint_xlen_t RA, uint_xlen_t RB)
468 { return xperm(RA, RB, 4); }
469 uint_xlen_t xperm_w (uint_xlen_t RA, uint_xlen_t RB)
470 { return xperm(RA, RB, 5); }
478 uint32_t gorc32(uint32_t RA, uint32_t RB)
482 if (shamt & 1) x |= ((x & 0x55555555) << 1) | ((x & 0xAAAAAAAA) >> 1);
483 if (shamt & 2) x |= ((x & 0x33333333) << 2) | ((x & 0xCCCCCCCC) >> 2);
484 if (shamt & 4) x |= ((x & 0x0F0F0F0F) << 4) | ((x & 0xF0F0F0F0) >> 4);
485 if (shamt & 8) x |= ((x & 0x00FF00FF) << 8) | ((x & 0xFF00FF00) >> 8);
486 if (shamt & 16) x |= ((x & 0x0000FFFF) << 16) | ((x & 0xFFFF0000) >> 16);
489 uint64_t gorc64(uint64_t RA, uint64_t RB)
493 if (shamt & 1) x |= ((x & 0x5555555555555555LL) << 1) |
494 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
495 if (shamt & 2) x |= ((x & 0x3333333333333333LL) << 2) |
496 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
497 if (shamt & 4) x |= ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
498 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
499 if (shamt & 8) x |= ((x & 0x00FF00FF00FF00FFLL) << 8) |
500 ((x & 0xFF00FF00FF00FF00LL) >> 8);
501 if (shamt & 16) x |= ((x & 0x0000FFFF0000FFFFLL) << 16) |
502 ((x & 0xFFFF0000FFFF0000LL) >> 16);
503 if (shamt & 32) x |= ((x & 0x00000000FFFFFFFFLL) << 32) |
504 ((x & 0xFFFFFFFF00000000LL) >> 32);
514 * <https://courses.csail.mit.edu/6.857/2016/files/ffield.py>
515 * <https://engineering.purdue.edu/kak/compsec/NewLectures/Lecture7.pdf>
516 * <https://foss.heptapod.net/math/libgf2/-/blob/branch/default/src/libgf2/gf2.py>
518 ## SPRs to set modulo and degree
520 to save registers and make operations orthogonal with standard
521 arithmetic the modulo is to be set in an SPR
523 ## Twin Butterfly (Tukey-Cooley) Mul-add-sub
525 used in combination with SV FFT REMAP to perform
528 gffmadd RT,RA,RC,RB (Rc=0)
529 gffmadd. RT,RA,RC,RB (Rc=1)
533 RT <- GFMULADD(RA, RC, RB)
534 RS <- GFMULADD(RA, RC, RB)
539 with the modulo and degree being in an SPR, multiply can be identical
540 equivalent to standard integer add
544 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31|
545 | -- | -- | --- | --- | --- | ------ |--|
546 | NN | RT | RA | RB |11000| 01110 |Rc|
551 from functools import reduce
561 # constants used in the multGF2 function
562 mask1 = mask2 = polyred = None
565 """Define parameters of binary finite field GF(2^m)/g(x)
566 - irPoly: coefficients of irreducible polynomial g(x)
568 # degree: extension degree of binary field
569 degree = gf_degree(irPoly)
572 """Convert an integer into a polynomial"""
573 return [(sInt >> i) & 1
574 for i in reversed(range(sInt.bit_length()))]
576 global mask1, mask2, polyred
577 mask1 = mask2 = 1 << degree
579 polyred = reduce(lambda x, y: (x << 1) + y, i2P(irPoly)[1:])
582 """Multiply two polynomials in GF(2^m)/g(x)"""
585 # standard long-multiplication: check LSB and add
589 # standard modulo: check MSB and add polynomial
595 if __name__ == "__main__":
597 # Define binary field GF(2^3)/x^3 + x + 1
598 setGF2(0b1011) # degree 3
600 # Evaluate the product (x^2 + x + 1)(x^2 + 1)
601 print("{:02x}".format(multGF2(0b111, 0b101)))
603 # Define binary field GF(2^8)/x^8 + x^4 + x^3 + x + 1
604 # (used in the Advanced Encryption Standard-AES)
605 setGF2(0b100011011) # degree 8
607 # Evaluate the product (x^7)(x^7 + x + 1)
608 print("{:02x}".format(multGF2(0b10000000, 0b10000011)))
621 def FullDivision(self, f, v):
623 Takes two arguments, f, v
624 fDegree and vDegree are the degrees of the field elements
625 f and v represented as a polynomials.
626 This method returns the field elements a and b such that
628 f(x) = a(x) * v(x) + b(x).
630 That is, a is the divisor and b is the remainder, or in
631 other words a is like floor(f/v) and b is like f modulo v.
634 fDegree, vDegree = gf_degree(f), gf_degree(v)
638 while (i >= vDegree):
639 if (mask & rem): # check MSB
640 res ^= (1 << (i - vDegree))
641 rem ^= ( v << (i - vDegree)))
647 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31| name |
648 | -- | -- | --- | --- | --- | ------- |--| ----- |
649 | NN | RS | RA | deg | RC | 0 1 011 |Rc| gfaddi |
650 | NN | RS | RA | RB | RC | 1 1 111 |Rc| gfadd |
652 GFMOD is a pseudo-op where RA=0
657 see https://en.wikipedia.org/wiki/CLMUL_instruction_set
659 these are GF2 operations with the modulo set to 2^degree.
660 they are worth adding as their own non-overwrite operations
661 (in the same pipeline).
664 uint_xlen_t clmul(uint_xlen_t RA, uint_xlen_t RB)
667 for (int i = 0; i < XLEN; i++)
672 uint_xlen_t clmulh(uint_xlen_t RA, uint_xlen_t RB)
675 for (int i = 1; i < XLEN; i++)
680 uint_xlen_t clmulr(uint_xlen_t RA, uint_xlen_t RB)
683 for (int i = 0; i < XLEN; i++)
685 x ^= RA >> (XLEN-i-1);
693 uint64_t bmatflip(uint64_t RA)
701 uint64_t bmatxor(uint64_t RA, uint64_t RB)
704 uint64_t RBt = bmatflip(RB);
705 uint8_t u[8]; // rows of RA
706 uint8_t v[8]; // cols of RB
707 for (int i = 0; i < 8; i++) {
712 for (int i = 0; i < 64; i++) {
713 if (pcnt(u[i / 8] & v[i % 8]) & 1)
718 uint64_t bmator(uint64_t RA, uint64_t RB)
721 uint64_t RBt = bmatflip(RB);
722 uint8_t u[8]; // rows of RA
723 uint8_t v[8]; // cols of RB
724 for (int i = 0; i < 8; i++) {
729 for (int i = 0; i < 64; i++) {
730 if ((u[i / 8] & v[i % 8]) != 0)
738 # Already in POWER ISA
740 ## count leading/trailing zeros with mask
746 do i = 0 to 63 if((RB)i=1) then do
747 if((RS)i=1) then break end end count ← count + 1
753 vpdepd VRT,VRA,VRB, identical to RV bitmamip bdep, found already in v3.1 p106
756 if VSR[VRB+32].dword[i].bit[63-m]=1 then do
757 result = VSR[VRA+32].dword[i].bit[63-k]
758 VSR[VRT+32].dword[i].bit[63-m] = result
764 uint_xlen_t bdep(uint_xlen_t RA, uint_xlen_t RB)
767 for (int i = 0, j = 0; i < XLEN; i++)
770 r |= uint_xlen_t(1) << i;
780 other way round: identical to RV bext, found in v3.1 p196
783 uint_xlen_t bext(uint_xlen_t RA, uint_xlen_t RB)
786 for (int i = 0, j = 0; i < XLEN; i++)
789 r |= uint_xlen_t(1) << j;
798 found in v3.1 p106 so not to be added here
808 if((RB)63-i==1) then do
809 result63-ptr1 = (RS)63-i