https://gcc.gnu.org/bugzilla/show_bug.cgi?id=116274
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |crazylht at gmail dot com
--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
struct a { int x,y,z,w; };
int test(struct a a) { return a.x+a.y+a.z+a.w; }
behaves similarly.
I do have a patch for the vectorizer costing that avoids vectorizing in
these cases. We will still vectorize
struct a { short a0,a1,a2,a3,a4,a5,a6,a7; };
short test(struct a a) { return a.a0+a.a1+a.a2+a.a3+a.a4+a.a5+a.a6+a.a7; }
generating
test:
.LFB0:
.cfi_startproc
movaps %xmm1, -24(%rsp)
movq -16(%rsp), %rdx
movq %rdi, %xmm1
movq %rsi, %xmm3
pinsrq $1, %rdx, %xmm1
punpcklqdq %xmm3, %xmm1
movaps %xmm1, -24(%rsp)
movdqa %xmm1, %xmm2
pinsrq $1, -16(%rsp), %xmm2
movdqa %xmm2, %xmm0
psrldq $8, %xmm0
paddw %xmm1, %xmm0
movdqa %xmm0, %xmm1
psrldq $4, %xmm1
paddw %xmm1, %xmm0
movdqa %xmm0, %xmm1
psrldq $2, %xmm1
paddw %xmm1, %xmm0
pextrw $0, %xmm0, %eax
ret
as opposed to
test:
.LFB0:
.cfi_startproc
movl %edi, %eax
movq %rdi, %rdx
sarl $16, %eax
salq $16, %rdx
addl %edi, %eax
sarq $48, %rdx
addl %edx, %eax
sarq $48, %rdi
movl %esi, %edx
addl %edi, %eax
sarl $16, %edx
addl %esi, %eax
addl %edx, %eax
movq %rsi, %rdx
sarq $48, %rsi
salq $16, %rdx
sarq $48, %rdx
addl %edx, %eax
addl %esi, %eax
ret
it still has the odd (dead)
movaps %xmm1, -24(%rsp)
movq -16(%rsp), %rdx
The
movaps %xmm1, -24(%rsp)
movdqa %xmm1, %xmm2
pinsrq $1, -16(%rsp), %xmm2
codegen is probably an RA/LRA artifact caused by bad instruction constraints
and the refuse to reload to a gpr. Not sure if a move high to gpr is a thing,
pextrq would work for sure. But an unpck looks like a better match anyway.
