https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115040
Bug ID: 115040
Summary: Missed optimization opportunity in std::find
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: ---
https://gcc.godbolt.org/z/s3hv15935
```
#include <algorithm>
#include <vector>
#include <cstdint>
bool find_epi8(const std::vector<int8_t>& v) {
return std::find(v.begin(), v.end(), 42) != v.end();
}
bool find_epi32(const std::vector<int32_t>& v) {
return std::find(v.begin(), v.end(), 42) != v.end();
}
```
$ gcc -O3 -ftree-vectorize -march=pantherlake
```
find_epi8(std::vector<signed char, std::allocator<signed char> > const&):
mov rcx, QWORD PTR [rdi+8]
mov rdx, QWORD PTR [rdi]
mov rsi, rcx
sub rsi, rdx
mov rax, rsi
sar rax, 2
test rax, rax
jle .L2
lea rax, [rdx+rax*4]
jmp .L8
.L3:
cmp BYTE PTR [rdx+1], 42
je .L23
cmp BYTE PTR [rdx+2], 42
je .L24
cmp BYTE PTR [rdx+3], 42
je .L25
add rdx, 4
cmp rdx, rax
je .L26
.L8:
cmp BYTE PTR [rdx], 42
jne .L3
.L21:
cmp rcx, rdx
setne al
ret
.L26:
mov rsi, rcx
sub rsi, rdx
.L2:
cmp rsi, 2
je .L9
cmp rsi, 3
je .L10
cmp rsi, 1
je .L11
xor eax, eax
ret
.L10:
cmp BYTE PTR [rdx], 42
je .L21
add rdx, 1
.L9:
cmp BYTE PTR [rdx], 42
je .L21
add rdx, 1
.L11:
cmp BYTE PTR [rdx], 42
sete al
cmp rcx, rdx
setne dl
and eax, edx
ret
.L23:
add rdx, 1
cmp rcx, rdx
setne al
ret
.L24:
add rdx, 2
cmp rcx, rdx
setne al
ret
.L25:
add rdx, 3
cmp rcx, rdx
setne al
ret
find_epi32(std::vector<int, std::allocator<int> > const&):
mov rcx, QWORD PTR [rdi+8]
mov rdx, QWORD PTR [rdi]
mov rax, rcx
sub rax, rdx
mov rsi, rax
sar rax, 4
sar rsi, 2
test rax, rax
jle .L28
sal rax, 4
add rax, rdx
jmp .L34
.L29:
cmp DWORD PTR [rdx+4], 42
je .L48
cmp DWORD PTR [rdx+8], 42
je .L49
cmp DWORD PTR [rdx+12], 42
je .L50
add rdx, 16
cmp rdx, rax
je .L51
.L34:
cmp DWORD PTR [rdx], 42
jne .L29
.L47:
cmp rcx, rdx
setne al
ret
.L51:
mov rsi, rcx
sub rsi, rdx
sar rsi, 2
.L28:
cmp rsi, 2
je .L35
cmp rsi, 3
je .L36
cmp rsi, 1
je .L37
xor eax, eax
ret
.L36:
cmp DWORD PTR [rdx], 42
je .L47
add rdx, 4
.L35:
cmp DWORD PTR [rdx], 42
je .L47
add rdx, 4
.L37:
cmp DWORD PTR [rdx], 42
sete al
cmp rcx, rdx
setne dl
and eax, edx
ret
.L48:
add rdx, 4
cmp rcx, rdx
setne al
ret
.L49:
add rdx, 8
cmp rcx, rdx
setne al
ret
.L50:
add rdx, 12
cmp rcx, rdx
setne al
ret
```
clang lowers both the calls to (w)memchr
--- Comment #1 from Sam James <sjames at gcc dot gnu.org> ---
*** Bug 115041 has been marked as a duplicate of this bug. ***
