a582564b24
The second and (last) optimized XOR syndrome calculation. This version supports right and left side optimization. All CPUs with architecture older than Haswell will benefit from it. It should be noted that SSE2 movntdq kills performance for memory areas that are read and written simultaneously in chunks smaller than cache line size. So use movdqa instead for P/Q writes in sse21 and sse22 XOR functions. Signed-off-by: Markus Stockhausen <stockhausen@collogia.de> Signed-off-by: NeilBrown <neilb@suse.de> |
||
|---|---|---|
| .. | ||
| test | ||
| .gitignore | ||
| Makefile | ||
| algos.c | ||
| altivec.uc | ||
| avx2.c | ||
| int.uc | ||
| mktables.c | ||
| mmx.c | ||
| neon.c | ||
| neon.uc | ||
| recov.c | ||
| recov_avx2.c | ||
| recov_ssse3.c | ||
| sse1.c | ||
| sse2.c | ||
| tilegx.uc | ||
| unroll.awk | ||
| x86.h | ||