https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108141
--- Comment #1 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
Just counting number of instructions it is shorter though:
--- pr64110.s.r13-4726 2022-12-16 03:57:42.000000000 -0500
+++ pr64110.s.r13-4727 2022-12-16 03:57:48.000000000 -0500
@@ -11,106 +11,105 @@ bar:
pushl %ebx
andl $-32, %esp
subl $64, %esp
- movzwl 8(%ebp), %edi
+ movzwl 8(%ebp), %eax
+ movw %ax, 30(%esp)
movl a, %eax
- vmovd %edi, %xmm1
+ vpbroadcastw 30(%esp), %xmm2
+ vpbroadcastw 30(%esp), %ymm0
leal -1(%eax), %edx
- vmovd %edi, %xmm0
movl %edx, a
- vpbroadcastw %xmm1, %xmm1
- vpbroadcastw %xmm0, %ymm0
+ vmovdqa %xmm2, (%esp)
testl %eax, %eax
- je .L24
- movw %di, 62(%esp)
- vmovdqa %xmm1, 32(%esp)
- vmovdqa %ymm0, (%esp)
- vzeroupper
+ je .L23
.p2align 4,,10
.p2align 3
.L2:
+ vmovdqa %ymm0, 32(%esp)
+ vzeroupper
call foo
+ vmovdqa 32(%esp), %ymm0
testl %eax, %eax
jle .L3
- leal -1(%eax), %edi
+ leal -1(%eax), %esi
movl b, %ebx
- movl %edi, 52(%esp)
- cmpl $14, %edi
+ movl %esi, 24(%esp)
+ cmpl $14, %esi
jbe .L10
movl %eax, %ecx
movl %ebx, %edx
shrl $4, %ecx
sall $5, %ecx
- leal (%ecx,%ebx), %esi
+ leal (%ecx,%ebx), %edi
andl $32, %ecx
- jne .L21
- movzwl 62(%esp), %edi
- vmovdqa (%esp), %ymm0
+ je .L5
+ leal 32(%ebx), %edx
+ vmovdqu %ymm0, (%ebx)
+ cmpl %edi, %edx
+ je .L22
.p2align 4,,10
.p2align 3
.L5:
vmovdqu %ymm0, (%edx)
addl $64, %edx
vmovdqu %ymm0, -32(%edx)
- cmpl %esi, %edx
+ cmpl %edi, %edx
jne .L5
- movw %di, 62(%esp)
.L22:
movl %eax, %edx
andl $-16, %edx
- movl %edx, %esi
+ movl %edx, %edi
leal (%ebx,%edx,2), %ecx
cmpl %edx, %eax
- je .L29
- vzeroupper
+ je .L6
.L4:
- movl %eax, %edi
- subl %esi, %edi
- movl %edi, 56(%esp)
- decl %edi
- cmpl $6, %edi
+ movl %eax, %esi
+ subl %edi, %esi
+ movl %esi, 32(%esp)
+ decl %esi
+ cmpl $6, %esi
jbe .L7
- movl 56(%esp), %edi
- vmovdqa 32(%esp), %xmm2
- vmovdqu %xmm2, (%ebx,%esi,2)
- movl %edi, %esi
- andl $-8, %esi
- addl %esi, %edx
- leal (%ecx,%esi,2), %ecx
- movl %edi, %esi
- andl $7, %esi
+ movl 32(%esp), %esi
+ vmovdqa (%esp), %xmm1
+ vmovdqu %xmm1, (%ebx,%edi,2)
+ movl %esi, %edi
+ andl $-8, %edi
+ addl %edi, %edx
+ leal (%ecx,%edi,2), %ecx
+ movl %esi, %edi
+ andl $7, %edi
je .L6
.L7:
- movzwl 62(%esp), %edi
- leal 1(%edx), %esi
- movw %di, (%ecx)
- cmpl %esi, %eax
- jle .L6
- leal 2(%edx), %esi
- movw %di, 2(%ecx)
- cmpl %esi, %eax
- jle .L6
- leal 3(%edx), %esi
- movw %di, 4(%ecx)
- cmpl %esi, %eax
- jle .L6
- leal 4(%edx), %esi
- movw %di, 6(%ecx)
- cmpl %esi, %eax
- jle .L6
- leal 5(%edx), %esi
- movw %di, 8(%ecx)
- cmpl %esi, %eax
+ movzwl 30(%esp), %esi
+ leal 1(%edx), %edi
+ movw %si, (%ecx)
+ cmpl %edi, %eax
+ jle .L6
+ leal 2(%edx), %edi
+ movw %si, 2(%ecx)
+ cmpl %edi, %eax
+ jle .L6
+ leal 3(%edx), %edi
+ movw %si, 4(%ecx)
+ cmpl %edi, %eax
+ jle .L6
+ leal 4(%edx), %edi
+ movw %si, 6(%ecx)
+ cmpl %edi, %eax
+ jle .L6
+ leal 5(%edx), %edi
+ movw %si, 8(%ecx)
+ cmpl %edi, %eax
jle .L6
addl $6, %edx
- movw %di, 10(%ecx)
+ movw %si, 10(%ecx)
cmpl %edx, %eax
jle .L6
- movw %di, 12(%ecx)
+ movw %si, 12(%ecx)
.L6:
leal (%ebx,%eax,2), %eax
- movzwl 62(%esp), %ecx
+ movzwl 30(%esp), %ecx
movl %eax, b
- movl 52(%esp), %eax
+ movl 24(%esp), %eax
movw %cx, (%ebx,%eax,2)
.L3:
movl a, %eax
@@ -118,39 +117,19 @@ bar:
movl %edx, a
testl %eax, %eax
jne .L2
+.L23:
+ vzeroupper
leal -12(%ebp), %esp
popl %ebx
popl %esi
popl %edi
popl %ebp
ret
- .p2align 4,,10
- .p2align 3
-.L21:
- vmovdqa (%esp), %ymm3
- leal 32(%ebx), %edx
- vmovdqu %ymm3, (%ebx)
- cmpl %esi, %edx
- je .L22
- movzwl 62(%esp), %edi
- vmovdqa %ymm3, %ymm0
- jmp .L5
.L10:
movl %ebx, %ecx
- xorl %esi, %esi
+ xorl %edi, %edi
xorl %edx, %edx
jmp .L4
-.L29:
- vzeroupper
- jmp .L6
-.L24:
- vzeroupper
- leal -12(%ebp), %esp
- popl %ebx
- popl %esi
- popl %edi
- popl %ebp
- ret
.size bar, .-bar
.globl b
.bss
