https://gcc.gnu.org/bugzilla/show_bug.cgi?id=87505
Bug ID: 87505
Summary: Vectorizer generates a lot of code for a small loop
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: hiraditya at msn dot com
Target Milestone: ---
test.cpp
#include <cstdint>
int bar(int* v, std::size_t base) {
int sum = 0;
for (int i = base; i < base + 4; ++i) {
sum += v[i];
}
return sum;
}
$ gcc-8.2 -std=c++17 -O3 -DNDEBUG test.cpp
bar(int*, unsigned long):
movslq %esi, %rcx
leaq 4(%rsi), %r8
movl %esi, %edx
cmpq %r8, %rcx
jnb .L7
leaq 3(%rsi), %rax
movq %r8, %r9
subq %rcx, %rax
subq %rcx, %r9
cmpq $3, %rax
jbe .L8
movq %r9, %rdx
leaq (%rdi,%rcx,4), %rax
pxor %xmm0, %xmm0
shrq $2, %rdx
salq $4, %rdx
addq %rax, %rdx
.L5:
movdqu (%rax), %xmm2
addq $16, %rax
paddd %xmm2, %xmm0
cmpq %rdx, %rax
jne .L5
movdqa %xmm0, %xmm1
movq %r9, %r10
psrldq $8, %xmm1
andq $-4, %r10
paddd %xmm1, %xmm0
addq %r10, %rcx
leal (%rsi,%r10), %edx
movdqa %xmm0, %xmm1
psrldq $4, %xmm1
paddd %xmm1, %xmm0
movd %xmm0, %eax
cmpq %r10, %r9
je .L10
.L3:
addl (%rdi,%rcx,4), %eax
leal 1(%rdx), %ecx
movslq %ecx, %rcx
cmpq %r8, %rcx
jnb .L1
addl (%rdi,%rcx,4), %eax
leal 2(%rdx), %ecx
movslq %ecx, %rcx
cmpq %rcx, %r8
jbe .L1
addl $3, %edx
addl (%rdi,%rcx,4), %eax
movslq %edx, %rdx
cmpq %rdx, %r8
jbe .L1
addl (%rdi,%rdx,4), %eax
ret
.L7:
xorl %eax, %eax
.L1:
ret
.L10:
ret
.L8:
xorl %eax, %eax
jmp .L3
