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 | RS | RA | RB | RC | 00 011 |Rc| gfmul |
83 | NN | RS | RA | RB | RC | 01 011 |Rc| gfadd |
84 | NN | RT | RA | RB | deg | 10 011 |Rc| gfinv |
85 | NN | RS | RA | RB | deg | 11 011 |Rc| gfmuli |
86 | NN | RS | RA | RB | deg | 11 111 |Rc| gfaddi |
88 | 0.5|6.10|11.15| 16.23 |24.27 | 28.30 |31| name |
89 | -- | -- | --- | ----- | ---- | ----- |--| ------ |
90 | NN | RT | RA | imm | mask | 101 |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 | 101 |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 | RA | RB | | 1 | | 0001 110 |Rc| rsvd |
114 | NN | RA | RB | RC | 0 | 00 | 0001 110 |Rc| vec sbfm |
115 | NN | RA | RB | RC | 0 | 01 | 0001 110 |Rc| vec sofm |
116 | NN | RA | RB | RC | 0 | 10 | 0001 110 |Rc| vec sifm |
117 | NN | RA | RB | RC | 0 | 11 | 0001 110 |Rc| vec cprop |
118 | NN | RA | RB | | 0 | | 0101 110 |Rc| rsvd |
119 | NN | RA | RB | RC | 0 | 00 | 0010 110 |Rc| gorc |
120 | NN | RA | RB | sh | SH | 00 | 1010 110 |Rc| gorci |
121 | NN | RA | RB | RC | 0 | 00 | 0110 110 |Rc| gorcw |
122 | NN | RA | RB | sh | 0 | 00 | 1110 110 |Rc| gorcwi |
123 | NN | RA | RB | RC | 1 | 00 | 1110 110 |Rc| bmator |
124 | NN | RA | RB | RC | 0 | 01 | 0010 110 |Rc| grev |
125 | NN | RA | RB | RC | 1 | 01 | 0010 110 |Rc| clmul |
126 | NN | RA | RB | sh | SH | 01 | 1010 110 |Rc| grevi |
127 | NN | RA | RB | RC | 0 | 01 | 0110 110 |Rc| grevw |
128 | NN | RA | RB | sh | 0 | 01 | 1110 110 |Rc| grevwi |
129 | NN | RA | RB | RC | 1 | 01 | 1110 110 |Rc| bmatxor |
130 | NN | RA | RB | RC | 0 | 10 | 0010 110 |Rc| shfl |
131 | NN | RA | RB | sh | SH | 10 | 1010 110 |Rc| shfli |
132 | NN | RA | RB | RC | 0 | 10 | 0110 110 |Rc| shflw |
133 | NN | RA | RB | RC | | 10 | 1110 110 |Rc| rsvd |
134 | NN | RA | RB | RC | 0 | 11 | 1110 110 |Rc| clmulr |
135 | NN | RA | RB | RC | 1 | 11 | 1110 110 |Rc| clmulh |
136 | NN | | | | | | --11 110 |Rc| setvl |
138 # bit to byte permute
140 similar to matrix permute in RV bitmanip, which has XOR and OR variants
144 b = VSR[VRB+32].dword[i].byte[k].bit[j]
145 VSR[VRT+32].dword[i].byte[j].bit[k] = b
149 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).
151 signed/unsigned min/max gives more flexibility.
154 uint_xlen_t min(uint_xlen_t rs1, uint_xlen_t rs2)
155 { return (int_xlen_t)rs1 < (int_xlen_t)rs2 ? rs1 : rs2;
157 uint_xlen_t max(uint_xlen_t rs1, uint_xlen_t rs2)
158 { return (int_xlen_t)rs1 > (int_xlen_t)rs2 ? rs1 : rs2;
160 uint_xlen_t minu(uint_xlen_t rs1, uint_xlen_t rs2)
161 { return rs1 < rs2 ? rs1 : rs2;
163 uint_xlen_t maxu(uint_xlen_t rs1, uint_xlen_t rs2)
164 { return rs1 > rs2 ? rs1 : rs2;
171 Similar to FPGA LUTs: for every bit perform a lookup into a table using an 8bit immediate, or in another register.
173 Like the x86 AVX512F [vpternlogd/vpternlogq](https://www.felixcloutier.com/x86/vpternlogd:vpternlogq) instructions.
177 | 0.5|6.10|11.15|16.20| 21..25| 26..30 |31|
178 | -- | -- | --- | --- | ----- | -------- |--|
179 | NN | RT | RA | RB | im0-4 | im5-7 00 |0 |
182 idx = RT[i] << 2 | RA[i] << 1 | RB[i]
183 RT[i] = (imm & (1<<idx)) != 0
185 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.
189 a 4 operand variant which becomes more along the lines of an FPGA:
191 | 0.5|6.10|11.15|16.20|21.25| 26...30 |31|
192 | -- | -- | --- | --- | --- | -------- |--|
193 | NN | RT | RA | RB | RC | mode 100 |1 |
196 idx = RT[i] << 2 | RA[i] << 1 | RB[i]
197 RT[i] = (RC & (1<<idx)) != 0
199 mode (2 bit) may be used to do inversion of ordering, similar to carryless mul,
204 also, another possible variant involving swizzle and vec4:
206 | 0.5|6.10|11.15| 16.23 |24.27 | 28.30 |31|
207 | -- | -- | --- | ----- | ---- | ----- |--|
208 | NN | RT | RA | imm | mask | 101 |1 |
211 idx = RA.x[i] << 2 | RA.y[i] << 1 | RA.z[i]
212 res = (imm & (1<<idx)) != 0
214 if mask[j]: RT[i+j*8] = res
218 another mode selection would be CRs not Ints.
220 | 0.5|6.8 | 9.11|12.14|15|16.23|24.27 | 28.30|31|
221 | -- | -- | --- | --- |- |-----|----- | -----|--|
222 | NN | BA | BB | BC |0 |imm | mask | 101 |0 |
225 if not mask[i] continue
226 idx = crregs[BA][i] << 2 |
229 crregs[BA][i] = (imm & (1<<idx)) != 0
233 based on RV bitmanip, covered by ternlog bitops
236 uint_xlen_t cmix(uint_xlen_t RA, uint_xlen_t RB, uint_xlen_t RC) {
237 return (RA & RB) | (RC & ~RB);
244 based on RV bitmanip singlebit set, instruction format similar to shift
245 [[isa/fixedshift]]. bmext is actually covered already (shift-with-mask rldicl but only immediate version).
246 however bitmask-invert is not, and set/clr are not covered, although they can use the same Shift ALU.
248 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.
249 bmrev however there is no direct equivalent and consequently a bmrevi is required.
251 bmset (register for mask amount) is particularly useful for creating
252 predicate masks where the length is a dynamic runtime quantity.
253 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.
255 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31| name |
256 | -- | -- | --- | --- | --- | ------- |--| ----- |
257 | NN | RT | RA | RB | RC | mode 010 |Rc| bm* |
258 | NN | RT | RA | RB | RC | 0 1 111 |Rc| bmrev |
262 uint_xlen_t bmset(RA, RB, sh)
264 int shamt = RB & (XLEN - 1);
266 return RA | (mask << shamt);
269 uint_xlen_t bmclr(RA, RB, sh)
271 int shamt = RB & (XLEN - 1);
273 return RA & ~(mask << shamt);
276 uint_xlen_t bminv(RA, RB, sh)
278 int shamt = RB & (XLEN - 1);
280 return RA ^ (mask << shamt);
283 uint_xlen_t bmext(RA, RB, sh)
285 int shamt = RB & (XLEN - 1);
287 return mask & (RA >> shamt);
291 bitmask extract with reverse. can be done by bitinverting all of RA and getting bits of RA from the opposite end.
295 rev[0:msb] = ra[msb:0];
298 uint_xlen_t bmextrev(RA, RB, sh)
300 int shamt = (RB & (XLEN - 1));
301 shamt = (XLEN-1)-shamt; # shift other end
302 bra = bitreverse(RA) # swap LSB-MSB
304 return mask & (bra >> shamt);
308 | 0.5|6.10|11.15|16.20|21.26| 27..30 |31| name |
309 | -- | -- | --- | --- | --- | ------- |--| ------ |
310 | NN | RT | RA | RB | sh | 0 111 |Rc| bmrevi |
316 based on RV bitmanip, this is also known as a butterfly network. however
317 where a butterfly network allows setting of every crossbar setting in
318 every row and every column, generalised-reverse (grev) only allows
319 a per-row decision: every entry in the same row must either switch or
322 <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/8/8c/Butterfly_Network.jpg/474px-Butterfly_Network.jpg" />
325 uint64_t grev64(uint64_t RA, uint64_t RB)
329 if (shamt & 1) x = ((x & 0x5555555555555555LL) << 1) |
330 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
331 if (shamt & 2) x = ((x & 0x3333333333333333LL) << 2) |
332 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
333 if (shamt & 4) x = ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
334 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
335 if (shamt & 8) x = ((x & 0x00FF00FF00FF00FFLL) << 8) |
336 ((x & 0xFF00FF00FF00FF00LL) >> 8);
337 if (shamt & 16) x = ((x & 0x0000FFFF0000FFFFLL) << 16) |
338 ((x & 0xFFFF0000FFFF0000LL) >> 16);
339 if (shamt & 32) x = ((x & 0x00000000FFFFFFFFLL) << 32) |
340 ((x & 0xFFFFFFFF00000000LL) >> 32);
346 # shuffle / unshuffle
351 uint32_t shfl32(uint32_t RA, uint32_t RB)
355 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
356 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
357 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
358 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
361 uint32_t unshfl32(uint32_t RA, uint32_t RB)
365 if (shamt & 1) x = shuffle32_stage(x, 0x44444444, 0x22222222, 1);
366 if (shamt & 2) x = shuffle32_stage(x, 0x30303030, 0x0c0c0c0c, 2);
367 if (shamt & 4) x = shuffle32_stage(x, 0x0f000f00, 0x00f000f0, 4);
368 if (shamt & 8) x = shuffle32_stage(x, 0x00ff0000, 0x0000ff00, 8);
372 uint64_t shuffle64_stage(uint64_t src, uint64_t maskL, uint64_t maskR, int N)
374 uint64_t x = src & ~(maskL | maskR);
375 x |= ((src << N) & maskL) | ((src >> N) & maskR);
378 uint64_t shfl64(uint64_t RA, uint64_t RB)
382 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
383 0x00000000ffff0000LL, 16);
384 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
385 0x0000ff000000ff00LL, 8);
386 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
387 0x00f000f000f000f0LL, 4);
388 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
389 0x0c0c0c0c0c0c0c0cLL, 2);
390 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
391 0x2222222222222222LL, 1);
394 uint64_t unshfl64(uint64_t RA, uint64_t RB)
398 if (shamt & 1) x = shuffle64_stage(x, 0x4444444444444444LL,
399 0x2222222222222222LL, 1);
400 if (shamt & 2) x = shuffle64_stage(x, 0x3030303030303030LL,
401 0x0c0c0c0c0c0c0c0cLL, 2);
402 if (shamt & 4) x = shuffle64_stage(x, 0x0f000f000f000f00LL,
403 0x00f000f000f000f0LL, 4);
404 if (shamt & 8) x = shuffle64_stage(x, 0x00ff000000ff0000LL,
405 0x0000ff000000ff00LL, 8);
406 if (shamt & 16) x = shuffle64_stage(x, 0x0000ffff00000000LL,
407 0x00000000ffff0000LL, 16);
417 uint_xlen_t xperm(uint_xlen_t RA, uint_xlen_t RB, int sz_log2)
420 uint_xlen_t sz = 1LL << sz_log2;
421 uint_xlen_t mask = (1LL << sz) - 1;
422 for (int i = 0; i < XLEN; i += sz) {
423 uint_xlen_t pos = ((RB >> i) & mask) << sz_log2;
425 r |= ((RA >> pos) & mask) << i;
429 uint_xlen_t xperm_n (uint_xlen_t RA, uint_xlen_t RB)
430 { return xperm(RA, RB, 2); }
431 uint_xlen_t xperm_b (uint_xlen_t RA, uint_xlen_t RB)
432 { return xperm(RA, RB, 3); }
433 uint_xlen_t xperm_h (uint_xlen_t RA, uint_xlen_t RB)
434 { return xperm(RA, RB, 4); }
435 uint_xlen_t xperm_w (uint_xlen_t RA, uint_xlen_t RB)
436 { return xperm(RA, RB, 5); }
444 uint32_t gorc32(uint32_t RA, uint32_t RB)
448 if (shamt & 1) x |= ((x & 0x55555555) << 1) | ((x & 0xAAAAAAAA) >> 1);
449 if (shamt & 2) x |= ((x & 0x33333333) << 2) | ((x & 0xCCCCCCCC) >> 2);
450 if (shamt & 4) x |= ((x & 0x0F0F0F0F) << 4) | ((x & 0xF0F0F0F0) >> 4);
451 if (shamt & 8) x |= ((x & 0x00FF00FF) << 8) | ((x & 0xFF00FF00) >> 8);
452 if (shamt & 16) x |= ((x & 0x0000FFFF) << 16) | ((x & 0xFFFF0000) >> 16);
455 uint64_t gorc64(uint64_t RA, uint64_t RB)
459 if (shamt & 1) x |= ((x & 0x5555555555555555LL) << 1) |
460 ((x & 0xAAAAAAAAAAAAAAAALL) >> 1);
461 if (shamt & 2) x |= ((x & 0x3333333333333333LL) << 2) |
462 ((x & 0xCCCCCCCCCCCCCCCCLL) >> 2);
463 if (shamt & 4) x |= ((x & 0x0F0F0F0F0F0F0F0FLL) << 4) |
464 ((x & 0xF0F0F0F0F0F0F0F0LL) >> 4);
465 if (shamt & 8) x |= ((x & 0x00FF00FF00FF00FFLL) << 8) |
466 ((x & 0xFF00FF00FF00FF00LL) >> 8);
467 if (shamt & 16) x |= ((x & 0x0000FFFF0000FFFFLL) << 16) |
468 ((x & 0xFFFF0000FFFF0000LL) >> 16);
469 if (shamt & 32) x |= ((x & 0x00000000FFFFFFFFLL) << 32) |
470 ((x & 0xFFFFFFFF00000000LL) >> 32);
478 see <https://courses.csail.mit.edu/6.857/2016/files/ffield.py>
482 this requires 3 parameters and a "degree"
484 RT = GFMUL(RA, RB, gfdegree, modulo=RC)
486 realistically with the degree also needing to be an immediate it should be brought down to an overwrite version:
488 RS = GFMUL(RS, RA, gfdegree, modulo=RC)
489 RS = GFMUL(RS, RA, gfdegree=RB, modulo=RC)
491 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31|
492 | -- | -- | --- | --- | --- | ------- |--|
493 | NN | RS | RA | deg | RC | 00 011 |Rc|
494 | NN | RS | RA | RB | RC | 11 011 |Rc|
496 where the SimpleV variant may override RS-as-src differently from RS-as-dest
501 from functools import reduce
503 # constants used in the multGF2 function
504 mask1 = mask2 = polyred = None
506 def setGF2(degree, irPoly):
507 """Define parameters of binary finite field GF(2^m)/g(x)
508 - degree: extension degree of binary field
509 - irPoly: coefficients of irreducible polynomial g(x)
512 """Convert an integer into a polynomial"""
513 return [(sInt >> i) & 1
514 for i in reversed(range(sInt.bit_length()))]
516 global mask1, mask2, polyred
517 mask1 = mask2 = 1 << degree
519 polyred = reduce(lambda x, y: (x << 1) + y, i2P(irPoly)[1:])
522 """Multiply two polynomials in GF(2^m)/g(x)"""
533 if __name__ == "__main__":
535 # Define binary field GF(2^3)/x^3 + x + 1
538 # Evaluate the product (x^2 + x + 1)(x^2 + 1)
539 print("{:02x}".format(multGF2(0b111, 0b101)))
541 # Define binary field GF(2^8)/x^8 + x^4 + x^3 + x + 1
542 # (used in the Advanced Encryption Standard-AES)
543 setGF2(8, 0b100011011)
545 # Evaluate the product (x^7)(x^7 + x + 1)
546 print("{:02x}".format(multGF2(0b10000000, 0b10000011)))
550 RS = GFADDI(RS, RA|0, gfdegree, modulo=RC)
551 RS = GFADD(RS, RA|0, gfdegree=RB, modulo=RC)
553 | 0.5|6.10|11.15|16.20|21.25| 26..30 |31| name |
554 | -- | -- | --- | --- | --- | ------- |--| ----- |
555 | NN | RS | RA | deg | RC | 0 1 011 |Rc| gfaddi |
556 | NN | RS | RA | RB | RC | 1 1 111 |Rc| gfadd |
558 GFMOD is a pseudo-op where RA=0
571 def gf_invert(a, mod=0x1B) :
586 a %= 256 # Emulating 8-bit overflow
587 g1 %= 256 # Emulating 8-bit overflow
589 j = gf_degree(a) - gf_degree(v)
597 see https://en.wikipedia.org/wiki/CLMUL_instruction_set
599 these are GF2 operations with the modulo set to 2^degree.
600 they are worth adding as their own non-overwrite operations
601 (in the same pipeline).
604 uint_xlen_t clmul(uint_xlen_t RA, uint_xlen_t RB)
607 for (int i = 0; i < XLEN; i++)
612 uint_xlen_t clmulh(uint_xlen_t RA, uint_xlen_t RB)
615 for (int i = 1; i < XLEN; i++)
620 uint_xlen_t clmulr(uint_xlen_t RA, uint_xlen_t RB)
623 for (int i = 0; i < XLEN; i++)
625 x ^= RA >> (XLEN-i-1);
633 uint64_t bmatflip(uint64_t RA)
641 uint64_t bmatxor(uint64_t RA, uint64_t RB)
644 uint64_t RBt = bmatflip(RB);
645 uint8_t u[8]; // rows of RA
646 uint8_t v[8]; // cols of RB
647 for (int i = 0; i < 8; i++) {
652 for (int i = 0; i < 64; i++) {
653 if (pcnt(u[i / 8] & v[i % 8]) & 1)
658 uint64_t bmator(uint64_t RA, uint64_t RB)
661 uint64_t RBt = bmatflip(RB);
662 uint8_t u[8]; // rows of RA
663 uint8_t v[8]; // cols of RB
664 for (int i = 0; i < 8; i++) {
669 for (int i = 0; i < 64; i++) {
670 if ((u[i / 8] & v[i % 8]) != 0)
678 # Already in POWER ISA
680 ## count leading/trailing zeros with mask
686 do i = 0 to 63 if((RB)i=1) then do
687 if((RS)i=1) then break end end count ← count + 1
693 vpdepd VRT,VRA,VRB, identical to RV bitmamip bdep, found already in v3.1 p106
696 if VSR[VRB+32].dword[i].bit[63-m]=1 then do
697 result = VSR[VRA+32].dword[i].bit[63-k]
698 VSR[VRT+32].dword[i].bit[63-m] = result
704 uint_xlen_t bdep(uint_xlen_t RA, uint_xlen_t RB)
707 for (int i = 0, j = 0; i < XLEN; i++)
710 r |= uint_xlen_t(1) << i;
720 other way round: identical to RV bext, found in v3.1 p196
723 uint_xlen_t bext(uint_xlen_t RA, uint_xlen_t RB)
726 for (int i = 0, j = 0; i < XLEN; i++)
729 r |= uint_xlen_t(1) << j;
738 found in v3.1 p106 so not to be added here
748 if((RB)63-i==1) then do
749 result63-ptr1 = (RS)63-i