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>
14 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.
15 Vectorisation Context is provided by [[openpower/sv]].
17 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.
19 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.
21 general-purpose Galois Field 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.
23 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
24 the [[sv/av_opcodes]] as well as [[sv/setvl]]
28 * <https://en.wikiversity.org/wiki/Reed%E2%80%93Solomon_codes_for_coders>
29 * <https://maths-people.anu.edu.au/~brent/pd/rpb232tr.pdf>
33 minor opcode allocation
36 | ------ |--| --------- |
43 | 101 |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 |
76 TODO: convert all instructions to use RT and not RS
78 | 0.5|6.10|11.15|16.20 |21..25 | 26....30 |31| name |
79 | -- | -- | --- | --- | ----- | -------- |--| ------ |
80 | NN | RT | RA | RB | RC | mode 000 |1 | ternlog |
81 | NN | RT | RA | RB | im0-4 | im5-7 00 |0 | ternlogi |
82 | NN | RT | RA | RB | / im0-3 | 00 100 |1 | grevlog |
83 | NN | RT | RA | s0-5 | s6 im0-3| 01 100 |1 | grevlogi |
84 | NN | RT | RA | | | 1- 100 |1 | rsvd |
85 | NN | RS | RA | RB | RC | 00 011 |Rc| gfmul |
86 | NN | RS | RA | RB | RC | 01 011 |Rc| gfadd |
87 | NN | RT | RA | RB | deg | 10 011 |Rc| gfinv |
88 | NN | RS | RA | RB | deg | 11 011 |Rc| gfmuli |
89 | NN | RS | RA | RB | deg | 11 111 |Rc| gfaddi |
91 | 0.5|6.10|11.15| 16.23 |24.27 | 28.30 |31| name |
92 | -- | -- | --- | ----- | ---- | ----- |--| ------ |
93 | NN | RT | RA | imm | mask | 101 |1 | ternlogv |
95 | 0.5|6.8 | 9.11|12.14|15|16.23|24.27 | 28.30|31| name |
96 | -- | -- | --- | --- |- |-----|----- | -----|--| -------|
97 | NN | BA | BB | BC |0 |imm | mask | 101 |0 | ternlogcr |
99 ops (note that av avg and abs as well as vec scalar mask
102 TODO: convert from RA, RB, and RC to correct field names of RT, RA, and RB, and
103 double check that instructions didn't need 3 inputs.
105 | 0.5|6.10|11.15|16.20| 21 | 22.23 | 24....30 |31| name |
106 | -- | -- | --- | --- | -- | ----- | -------- |--| ---- |
107 | NN | RA | RB | | 0 | | 0000 110 |Rc| rsvd |
108 | NN | RA | RB | RC | 1 | itype | 0000 110 |Rc| xperm |
109 | NN | RA | RB | RC | 0 | itype | 0100 110 |Rc| minmax |
110 | NN | RA | RB | RC | 1 | 00 | 0100 110 |Rc| av avgadd |
111 | NN | RA | RB | RC | 1 | 01 | 0100 110 |Rc| av abs |
112 | NN | RA | RB | | 1 | 10 | 0100 110 |Rc| rsvd |
113 | NN | RA | RB | | 1 | 11 | 0100 110 |Rc| rsvd |
114 | NN | RA | RB | sh | SH | itype | 1000 110 |Rc| bmopsi |
115 | NN | RA | RB | | | | 1100 110 |Rc| rsvd |
116 | NN | RA | RB | | 1 | | 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* |
264 | NN | RT | RA | RB | RC | 0 1 111 |Rc| bmrev |
268 uint_xlen_t bmset(RA, RB, sh)
270 int shamt = RB & (XLEN - 1);
272 return RA | (mask << shamt);
275 uint_xlen_t bmclr(RA, RB, sh)
277 int shamt = RB & (XLEN - 1);
279 return RA & ~(mask << shamt);
282 uint_xlen_t bminv(RA, RB, sh)
284 int shamt = RB & (XLEN - 1);
286 return RA ^ (mask << shamt);
289 uint_xlen_t bmext(RA, RB, sh)
291 int shamt = RB & (XLEN - 1);
293 return mask & (RA >> shamt);
297 bitmask extract with reverse. can be done by bitinverting all of RA and getting bits of RA from the opposite end.
301 rev[0:msb] = ra[msb:0];
304 uint_xlen_t bmextrev(RA, RB, sh)
306 int shamt = (RB & (XLEN - 1));
307 shamt = (XLEN-1)-shamt; # shift other end
308 bra = bitreverse(RA) # swap LSB-MSB
310 return mask & (bra >> shamt);
314 | 0.5|6.10|11.15|16.20|21.26| 27..30 |31| name |
315 | -- | -- | --- | --- | --- | ------- |--| ------ |
316 | NN | RT | RA | RB | sh | 0 111 |Rc| bmrevi |
322 based on RV bitmanip, this is also known as a butterfly network. however
323 where a butterfly network allows setting of every crossbar setting in
324 every row and every column, generalised-reverse (grev) only allows
325 a per-row decision: every entry in the same row must either switch or
328 <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/8/8c/Butterfly_Network.jpg/474px-Butterfly_Network.jpg" />
331 uint64_t grev64(uint64_t RA, uint64_t RB)
335 if (shamt & 1) x = ((x & 0x5555555555555555LL) << 1) |
336 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
337 if (shamt & 2) x = ((x & 0x3333333333333333LL) << 2) |
338 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
339 if (shamt & 4) x = ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
340 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
341 if (shamt & 8) x = ((x & 0x00FF00FF00FF00FFLL) << 8) |
342 ((x & 0xFF00FF00FF00FF00LL) >> 8);
343 if (shamt & 16) x = ((x & 0x0000FFFF0000FFFFLL) << 16) |
344 ((x & 0xFFFF0000FFFF0000LL) >> 16);
345 if (shamt & 32) x = ((x & 0x00000000FFFFFFFFLL) << 32) |
346 ((x & 0xFFFFFFFF00000000LL) >> 32);
352 # shuffle / unshuffle
357 uint32_t shfl32(uint32_t RA, uint32_t RB)
361 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
362 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
363 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
364 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
367 uint32_t unshfl32(uint32_t RA, uint32_t RB)
371 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
372 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
373 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
374 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
378 uint64_t shuffle64_stage(uint64_t src, uint64_t maskL, uint64_t maskR, int N)
380 uint64_t x = src & ~(maskL | maskR);
381 x |= ((src << N) & maskL) | ((src >> N) & maskR);
384 uint64_t shfl64(uint64_t RA, uint64_t RB)
388 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
389 0x00000000ffff0000LL, 16);
390 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
391 0x0000ff000000ff00LL, 8);
392 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
393 0x00f000f000f000f0LL, 4);
394 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
395 0x0c0c0c0c0c0c0c0cLL, 2);
396 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
397 0x2222222222222222LL, 1);
400 uint64_t unshfl64(uint64_t RA, uint64_t RB)
404 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
405 0x2222222222222222LL, 1);
406 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
407 0x0c0c0c0c0c0c0c0cLL, 2);
408 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
409 0x00f000f000f000f0LL, 4);
410 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
411 0x0000ff000000ff00LL, 8);
412 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
413 0x00000000ffff0000LL, 16);
423 uint_xlen_t xperm(uint_xlen_t RA, uint_xlen_t RB, int sz_log2)
426 uint_xlen_t sz = 1LL << sz_log2;
427 uint_xlen_t mask = (1LL << sz) - 1;
428 for (int i = 0; i < XLEN; i += sz) {
429 uint_xlen_t pos = ((RB >> i) & mask) << sz_log2;
431 r |= ((RA >> pos) & mask) << i;
435 uint_xlen_t xperm_n (uint_xlen_t RA, uint_xlen_t RB)
436 { return xperm(RA, RB, 2); }
437 uint_xlen_t xperm_b (uint_xlen_t RA, uint_xlen_t RB)
438 { return xperm(RA, RB, 3); }
439 uint_xlen_t xperm_h (uint_xlen_t RA, uint_xlen_t RB)
440 { return xperm(RA, RB, 4); }
441 uint_xlen_t xperm_w (uint_xlen_t RA, uint_xlen_t RB)
442 { return xperm(RA, RB, 5); }
450 uint32_t gorc32(uint32_t RA, uint32_t RB)
454 if (shamt & 1) x |= ((x & 0x55555555) << 1) | ((x & 0xAAAAAAAA) >> 1);
455 if (shamt & 2) x |= ((x & 0x33333333) << 2) | ((x & 0xCCCCCCCC) >> 2);
456 if (shamt & 4) x |= ((x & 0x0F0F0F0F) << 4) | ((x & 0xF0F0F0F0) >> 4);
457 if (shamt & 8) x |= ((x & 0x00FF00FF) << 8) | ((x & 0xFF00FF00) >> 8);
458 if (shamt & 16) x |= ((x & 0x0000FFFF) << 16) | ((x & 0xFFFF0000) >> 16);
461 uint64_t gorc64(uint64_t RA, uint64_t RB)
465 if (shamt & 1) x |= ((x & 0x5555555555555555LL) << 1) |
466 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
467 if (shamt & 2) x |= ((x & 0x3333333333333333LL) << 2) |
468 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
469 if (shamt & 4) x |= ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
470 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
471 if (shamt & 8) x |= ((x & 0x00FF00FF00FF00FFLL) << 8) |
472 ((x & 0xFF00FF00FF00FF00LL) >> 8);
473 if (shamt & 16) x |= ((x & 0x0000FFFF0000FFFFLL) << 16) |
474 ((x & 0xFFFF0000FFFF0000LL) >> 16);
475 if (shamt & 32) x |= ((x & 0x00000000FFFFFFFFLL) << 32) |
476 ((x & 0xFFFFFFFF00000000LL) >> 32);
484 see <https://courses.csail.mit.edu/6.857/2016/files/ffield.py>
488 this requires 3 parameters and a "degree"
490 RT = GFMUL(RA, RB, gfdegree, modulo=RC)
492 realistically with the degree also needing to be an immediate it should be brought down to an overwrite version:
494 RS = GFMUL(RS, RA, gfdegree, modulo=RC)
495 RS = GFMUL(RS, RA, gfdegree=RB, modulo=RC)
497 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31|
498 | -- | -- | --- | --- | --- | ------- |--|
499 | NN | RS | RA | deg | RC | 00 011 |Rc|
500 | NN | RS | RA | RB | RC | 11 011 |Rc|
502 where the SimpleV variant may override RS-as-src differently from RS-as-dest
507 from functools import reduce
509 # constants used in the multGF2 function
510 mask1 = mask2 = polyred = None
512 def setGF2(degree, irPoly):
513 """Define parameters of binary finite field GF(2^m)/g(x)
514 - degree: extension degree of binary field
515 - irPoly: coefficients of irreducible polynomial g(x)
518 """Convert an integer into a polynomial"""
519 return [(sInt >> i) & 1
520 for i in reversed(range(sInt.bit_length()))]
522 global mask1, mask2, polyred
523 mask1 = mask2 = 1 << degree
525 polyred = reduce(lambda x, y: (x << 1) + y, i2P(irPoly)[1:])
528 """Multiply two polynomials in GF(2^m)/g(x)"""
539 if __name__ == "__main__":
541 # Define binary field GF(2^3)/x^3 + x + 1
544 # Evaluate the product (x^2 + x + 1)(x^2 + 1)
545 print("{:02x}".format(multGF2(0b111, 0b101)))
547 # Define binary field GF(2^8)/x^8 + x^4 + x^3 + x + 1
548 # (used in the Advanced Encryption Standard-AES)
549 setGF2(8, 0b100011011)
551 # Evaluate the product (x^7)(x^7 + x + 1)
552 print("{:02x}".format(multGF2(0b10000000, 0b10000011)))
556 RS = GFADDI(RS, RA|0, gfdegree, modulo=RC)
557 RS = GFADD(RS, RA|0, gfdegree=RB, modulo=RC)
559 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31| name |
560 | -- | -- | --- | --- | --- | ------- |--| ----- |
561 | NN | RS | RA | deg | RC | 0 1 011 |Rc| gfaddi |
562 | NN | RS | RA | RB | RC | 1 1 111 |Rc| gfadd |
564 GFMOD is a pseudo-op where RA=0
577 def gf_invert(a, mod=0x1B) :
592 a %= 256 # Emulating 8-bit overflow
593 g1 %= 256 # Emulating 8-bit overflow
595 j = gf_degree(a) - gf_degree(v)
603 see https://en.wikipedia.org/wiki/CLMUL_instruction_set
605 these are GF2 operations with the modulo set to 2^degree.
606 they are worth adding as their own non-overwrite operations
607 (in the same pipeline).
610 uint_xlen_t clmul(uint_xlen_t RA, uint_xlen_t RB)
613 for (int i = 0; i < XLEN; i++)
618 uint_xlen_t clmulh(uint_xlen_t RA, uint_xlen_t RB)
621 for (int i = 1; i < XLEN; i++)
626 uint_xlen_t clmulr(uint_xlen_t RA, uint_xlen_t RB)
629 for (int i = 0; i < XLEN; i++)
631 x ^= RA >> (XLEN-i-1);
639 uint64_t bmatflip(uint64_t RA)
647 uint64_t bmatxor(uint64_t RA, uint64_t RB)
650 uint64_t RBt = bmatflip(RB);
651 uint8_t u[8]; // rows of RA
652 uint8_t v[8]; // cols of RB
653 for (int i = 0; i < 8; i++) {
658 for (int i = 0; i < 64; i++) {
659 if (pcnt(u[i / 8] & v[i % 8]) & 1)
664 uint64_t bmator(uint64_t RA, uint64_t RB)
667 uint64_t RBt = bmatflip(RB);
668 uint8_t u[8]; // rows of RA
669 uint8_t v[8]; // cols of RB
670 for (int i = 0; i < 8; i++) {
675 for (int i = 0; i < 64; i++) {
676 if ((u[i / 8] & v[i % 8]) != 0)
684 # Already in POWER ISA
686 ## count leading/trailing zeros with mask
692 do i = 0 to 63 if((RB)i=1) then do
693 if((RS)i=1) then break end end count ← count + 1
699 vpdepd VRT,VRA,VRB, identical to RV bitmamip bdep, found already in v3.1 p106
702 if VSR[VRB+32].dword[i].bit[63-m]=1 then do
703 result = VSR[VRA+32].dword[i].bit[63-k]
704 VSR[VRT+32].dword[i].bit[63-m] = result
710 uint_xlen_t bdep(uint_xlen_t RA, uint_xlen_t RB)
713 for (int i = 0, j = 0; i < XLEN; i++)
716 r |= uint_xlen_t(1) << i;
726 other way round: identical to RV bext, found in v3.1 p196
729 uint_xlen_t bext(uint_xlen_t RA, uint_xlen_t RB)
732 for (int i = 0, j = 0; i < XLEN; i++)
735 r |= uint_xlen_t(1) << j;
744 found in v3.1 p106 so not to be added here
754 if((RB)63-i==1) then do
755 result63-ptr1 = (RS)63-i