> I am looking into using the PDEP/PEXT machine instructions as part of Nim > proc:s and it seems to me that the asm keyword requires that you somehow know > which registers contains which variable.
No you can use GCC/Clang extended ASM. <https://github.com/mratsim/finite-fields/blob/97e40060cefeb4e2ef5fc5a1c355977caae79674/add_carry.nim#L73-L113> func add256_asm(a: var BigInt[256], b: BigInt[256]) {.noinline.}= var tmp: uint64 when defined(gcc): asm """ movq 0+%[b], %[tmp] addq %[tmp], 0+%[a] movq 8+%[b], %[tmp] adcq %[tmp], 8+%[a] movq 16+%[b], %[tmp] adcq %[tmp], 16+%[a] movq 24+%[b], %[tmp] adcq %[tmp], 24+%[a] : [tmp] "+r" (`tmp`), [a] "=&m" (`a->limbs[0]`) : [b] "m"(`b->limbs[0]`) : "cc" """ elif defined(clang): # https://lists.llvm.org/pipermail/llvm-dev/2017-August/116202.html # Remove the 0 from 8+0 when the proc is inline .... asm """ movq 0+0%[b], %[tmp] addq %[tmp], 0+0%[a] movq 8+0%[b], %[tmp] adcq %[tmp], 8+0%[a] movq 16+0%[b], %[tmp] adcq %[tmp], 16+0%[a] movq 24+0%[b], %[tmp] adcq %[tmp], 24+0%[a] : [tmp] "+r" (`tmp`), [a] "=&m" (`a->limbs[0]`) : [b] "m"(`b->limbs[0]`) : "cc" """ else: {.error: "Unsupported compiler".} Run
