[Bug tree-optimization/98856] [11 Regression] botan AES-128/XTS is slower by ~17% since r11-6649-g285fa338b06b804e72997c4d876ecf08a9c083af

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98856

--- Comment #19 from Richard Biener <rguenth at gcc dot gnu.org> ---
So to recover performance we need both, avoiding the latency on the vector plus
avoiding the spilling.  This variant is fast:

.L56:
        .cfi_restore_state
        vmovdqu (%rsi), %xmm4
        movq    8(%rsi), %rdx
        shrq    $63, %rdx
        imulq   $135, %rdx, %rdi
        movq    (%rsi), %rdx
        vmovq   %rdi, %xmm0
        vpsllq  $1, %xmm4, %xmm1
        shrq    $63, %rdx
        vmovq   %rdx, %xmm5
        vpunpcklqdq %xmm5, %xmm0, %xmm0
        vpxor   %xmm1, %xmm0, %xmm0
        vmovdqu %xmm0, (%rax)
        jmp     .L53

compared to the original:

.L56:
        .cfi_restore_state
        vmovdqu (%rsi), %xmm4
        vmovdqa %xmm4, 16(%rsp)
        movq    24(%rsp), %rdx
        vmovdqa 16(%rsp), %xmm5
        shrq    $63, %rdx
        imulq   $135, %rdx, %rdi
        movq    16(%rsp), %rdx
        vmovq   %rdi, %xmm0
        vpsllq  $1, %xmm5, %xmm1
        shrq    $63, %rdx
        vpinsrq $1, %rdx, %xmm0, %xmm0
        vpxor   %xmm1, %xmm0, %xmm0
        vmovdqu %xmm0, (%rax)
        jmp     .L53