diff options
| -rw-r--r-- | src/crypto/blake2s-x86_64.S | 140 |
1 files changed, 70 insertions, 70 deletions
diff --git a/src/crypto/blake2s-x86_64.S b/src/crypto/blake2s-x86_64.S index 3827d2e..4a8ab75 100644 --- a/src/crypto/blake2s-x86_64.S +++ b/src/crypto/blake2s-x86_64.S @@ -606,79 +606,79 @@ ENDPROC(blake2s_compress_avx) #ifdef CONFIG_AS_AVX512 ENTRY(blake2s_compress_avx512) vmovdqu (%rdi),%xmm0 - vmovdqu 0x10(%rdi),%xmm1 - vmovdqu 0x20(%rdi),%xmm4 - vmovq %rcx,%xmm5 - vmovdqa IV(%rip),%xmm14 - vmovdqa IV+16(%rip),%xmm15 - jmp .Lblake2s_compress_avx512_mainloop + vmovdqu 0x10(%rdi),%xmm1 + vmovdqu 0x20(%rdi),%xmm4 + vmovq %rcx,%xmm5 + vmovdqa IV(%rip),%xmm14 + vmovdqa IV+16(%rip),%xmm15 + jmp .Lblake2s_compress_avx512_mainloop .align 32 .Lblake2s_compress_avx512_mainloop: - vmovdqa %xmm0,%xmm10 - vmovdqa %xmm1,%xmm11 - vpaddq %xmm5,%xmm4,%xmm4 - vmovdqa %xmm14,%xmm2 - vpxor %xmm15,%xmm4,%xmm3 - vmovdqu (%rsi),%ymm6 - vmovdqu 0x20(%rsi),%ymm7 - addq $0x40,%rsi - leaq SIGMA(%rip),%rax - movb $0xa,%cl + vmovdqa %xmm0,%xmm10 + vmovdqa %xmm1,%xmm11 + vpaddq %xmm5,%xmm4,%xmm4 + vmovdqa %xmm14,%xmm2 + vpxor %xmm15,%xmm4,%xmm3 + vmovdqu (%rsi),%ymm6 + vmovdqu 0x20(%rsi),%ymm7 + addq $0x40,%rsi + leaq SIGMA(%rip),%rax + movb $0xa,%cl .Lblake2s_compress_avx512_roundloop: - addq $0x40,%rax - vmovdqa -0x40(%rax),%ymm8 - vmovdqa -0x20(%rax),%ymm9 - vpermi2d %ymm7,%ymm6,%ymm8 - vpermi2d %ymm7,%ymm6,%ymm9 - vmovdqa %ymm8,%ymm6 - vmovdqa %ymm9,%ymm7 - vpaddd %xmm8,%xmm0,%xmm0 - vpaddd %xmm1,%xmm0,%xmm0 - vpxor %xmm0,%xmm3,%xmm3 - vprord $0x10,%xmm3,%xmm3 - vpaddd %xmm3,%xmm2,%xmm2 - vpxor %xmm2,%xmm1,%xmm1 - vprord $0xc,%xmm1,%xmm1 - vextracti128 $0x1,%ymm8,%xmm8 - vpaddd %xmm8,%xmm0,%xmm0 - vpaddd %xmm1,%xmm0,%xmm0 - vpxor %xmm0,%xmm3,%xmm3 - vprord $0x8,%xmm3,%xmm3 - vpaddd %xmm3,%xmm2,%xmm2 - vpxor %xmm2,%xmm1,%xmm1 - vprord $0x7,%xmm1,%xmm1 - vpshufd $0x39,%xmm1,%xmm1 - vpshufd $0x4e,%xmm2,%xmm2 - vpshufd $0x93,%xmm3,%xmm3 - vpaddd %xmm9,%xmm0,%xmm0 - vpaddd %xmm1,%xmm0,%xmm0 - vpxor %xmm0,%xmm3,%xmm3 - vprord $0x10,%xmm3,%xmm3 - vpaddd %xmm3,%xmm2,%xmm2 - vpxor %xmm2,%xmm1,%xmm1 - vprord $0xc,%xmm1,%xmm1 - vextracti128 $0x1,%ymm9,%xmm9 - vpaddd %xmm9,%xmm0,%xmm0 - vpaddd %xmm1,%xmm0,%xmm0 - vpxor %xmm0,%xmm3,%xmm3 - vprord $0x8,%xmm3,%xmm3 - vpaddd %xmm3,%xmm2,%xmm2 - vpxor %xmm2,%xmm1,%xmm1 - vprord $0x7,%xmm1,%xmm1 - vpshufd $0x93,%xmm1,%xmm1 - vpshufd $0x4e,%xmm2,%xmm2 - vpshufd $0x39,%xmm3,%xmm3 - decb %cl - jne .Lblake2s_compress_avx512_roundloop - vpxor %xmm10,%xmm0,%xmm0 - vpxor %xmm11,%xmm1,%xmm1 - vpxor %xmm2,%xmm0,%xmm0 - vpxor %xmm3,%xmm1,%xmm1 - decq %rdx - jne .Lblake2s_compress_avx512_mainloop - vmovdqu %xmm0,(%rdi) - vmovdqu %xmm1,0x10(%rdi) - vmovdqu %xmm4,0x20(%rdi) + addq $0x40,%rax + vmovdqa -0x40(%rax),%ymm8 + vmovdqa -0x20(%rax),%ymm9 + vpermi2d %ymm7,%ymm6,%ymm8 + vpermi2d %ymm7,%ymm6,%ymm9 + vmovdqa %ymm8,%ymm6 + vmovdqa %ymm9,%ymm7 + vpaddd %xmm8,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x10,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0xc,%xmm1,%xmm1 + vextracti128 $0x1,%ymm8,%xmm8 + vpaddd %xmm8,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x8,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0x7,%xmm1,%xmm1 + vpshufd $0x39,%xmm1,%xmm1 + vpshufd $0x4e,%xmm2,%xmm2 + vpshufd $0x93,%xmm3,%xmm3 + vpaddd %xmm9,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x10,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0xc,%xmm1,%xmm1 + vextracti128 $0x1,%ymm9,%xmm9 + vpaddd %xmm9,%xmm0,%xmm0 + vpaddd %xmm1,%xmm0,%xmm0 + vpxor %xmm0,%xmm3,%xmm3 + vprord $0x8,%xmm3,%xmm3 + vpaddd %xmm3,%xmm2,%xmm2 + vpxor %xmm2,%xmm1,%xmm1 + vprord $0x7,%xmm1,%xmm1 + vpshufd $0x93,%xmm1,%xmm1 + vpshufd $0x4e,%xmm2,%xmm2 + vpshufd $0x39,%xmm3,%xmm3 + decb %cl + jne .Lblake2s_compress_avx512_roundloop + vpxor %xmm10,%xmm0,%xmm0 + vpxor %xmm11,%xmm1,%xmm1 + vpxor %xmm2,%xmm0,%xmm0 + vpxor %xmm3,%xmm1,%xmm1 + decq %rdx + jne .Lblake2s_compress_avx512_mainloop + vmovdqu %xmm0,(%rdi) + vmovdqu %xmm1,0x10(%rdi) + vmovdqu %xmm4,0x20(%rdi) vzeroupper retq ENDPROC(blake2s_compress_avx512) |