Source: jellyfish
Version: 2.2.6-1
User: [email protected]
Usertags: arm64
Jellyfish seems to be easy to port. Just provide alternatives to the
inline assembler in rectangular_binary_matrix.hpp:
#ifdef __x86_64__
#define AND_XOR(off) \
asm("movdqa (%[s],%[i]), %[load]\n\t" \
"pand " #off "(%[p]),%[load]\n\t" \
"pxor %[load],%[acc]\n\t" \
: [acc]"=&x"(acc) \
: "[acc]"(acc), [i]"r"(i), [p]"r"(p), [s]"r"(smear), [load]"x"(load))
#else
#define AND_XOR(off) do { \
xmm_t a = { smear[i / 8], smear[i / 8 + 1] }; \
xmm_t b = { p[(off) / 8], p[(off) / 8 + 1] }; \
acc ^= a & b; \
} while (0)
#endif
#ifdef __x86_64__
uint64_t res1, res2;
asm("movd %[acc], %[res1]\n\t"
"psrldq $8, %[acc]\n\t"
"movd %[acc], %[res2]\n\t"
: [res1]"=r"(res1), [res2]"=r"(res2)
: [acc]"x"(acc));
return res1 ^ res2;
#else
return acc[0] ^ acc[1];
#endif
Then replace AND_XOR("0x30") with AND_XOR(0x30), AND_XOR("") with
AND_XOR(0), and so on.
You might find the non-assembler version performs just as well on amd64, too,
in which case you could simplify the code.
Tested on arm64. Likely to work on some other architectures.
