[Bug target/103850] missed optimization in AVX code

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103850

--- Comment #5 from Richard Biener <rguenth at gcc dot gnu.org> ---
Note the issue can be reproduced without -ffast-math as well where the
functions are nearly identical so I fear you are running into some
micro-architectural hazard.  Maybe


.L3:
        vmovapd %ymm2, %ymm0
        vmovapd %ymm3, %ymm1
.L2:
        vbroadcastsd    (%rsi), %ymm2
        vbroadcastsd    8(%rsi), %ymm4
        addq    $32, %rdx
        addq    $16, %rsi
        vmovapd %ymm2, %ymm3
        vfmadd132pd     -32(%rsp), %ymm4, %ymm2
        vfmadd132pd     %ymm15, %ymm4, %ymm3
        vbroadcastsd    -24(%rdx), %ymm4
        vfmadd132pd     %ymm1, %ymm14, %ymm3
        vmovapd %ymm1, %ymm14
        vfmadd231pd     %ymm1, %ymm4, %ymm11
        vfmadd231pd     %ymm0, %ymm4, %ymm7
        vbroadcastsd    -8(%rdx), %ymm4
        vfmadd132pd     %ymm0, %ymm13, %ymm2
        vbroadcastsd    -32(%rdx), %ymm13
        vfmadd231pd     %ymm1, %ymm4, %ymm9
        vfmadd231pd     %ymm0, %ymm4, %ymm5
        vfmadd231pd     %ymm1, %ymm13, %ymm12
        vfmadd231pd     %ymm0, %ymm13, %ymm8
        vbroadcastsd    -16(%rdx), %ymm13
        vfmadd231pd     %ymm1, %ymm13, %ymm10
        vfmadd231pd     %ymm0, %ymm13, %ymm6
        vmovapd %ymm0, %ymm13
        cmpq    %rdx, %rax
        jne     .L3

is easier to handle since there's only one data dependence on the
addq $32, %rdx of the followup loads but for (slow)

.L8:
        vmovapd %ymm2, %ymm0
        vmovapd %ymm3, %ymm1
.L7:
        vbroadcastsd    8(%rdx), %ymm2
        vbroadcastsd    (%rdx), %ymm3
        addq    $16, %rsi
        addq    $32, %rdx
        vbroadcastsd    -8(%rsi), %ymm4
        vfmadd231pd     %ymm1, %ymm2, %ymm11
        vfmadd231pd     %ymm0, %ymm2, %ymm7
        vbroadcastsd    -8(%rdx), %ymm2
        vfmadd231pd     %ymm1, %ymm3, %ymm12
        vfmadd231pd     %ymm0, %ymm3, %ymm8
        vbroadcastsd    -16(%rdx), %ymm3
        vfmadd231pd     %ymm1, %ymm2, %ymm9
        vfmadd231pd     %ymm0, %ymm2, %ymm5
        vbroadcastsd    -16(%rsi), %ymm2
        vfmadd231pd     %ymm1, %ymm3, %ymm10
        vfmadd231pd     %ymm0, %ymm3, %ymm6
        vmovapd %ymm2, %ymm3
        vfmadd132pd     -32(%rsp), %ymm4, %ymm2
        vfmadd132pd     %ymm15, %ymm4, %ymm3
        vfmadd132pd     %ymm1, %ymm14, %ymm3
        vmovapd %ymm1, %ymm14
        vfmadd132pd     %ymm0, %ymm13, %ymm2
        vmovapd %ymm0, %ymm13
        cmpq    %rsi, %rax
        jne     .L8

both increments impose dependences on the following loads.