https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115454
Bug ID: 115454
Summary: std::experimental::find_last_set is buggy on x86-64-v4
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: libstdc++
Assignee: unassigned at gcc dot gnu.org
Reporter: lee.imple at gmail dot com
Target Milestone: ---
We are using a simd with 4 uint64_t elements (with `deduce_t`) on x86-64-v4.
We are trying to find the last element with the value -1 (i.e. all 1s).
The code is as following (available at https://godbolt.org/z/3f1nszf8E ),
compiled with the options `-O3 -march=x86-64-v4 -std=c++20`.
```c++
#include <experimental/simd>
#include <cstdint>
using deduce_t_element = std::experimental::simd<
std::uint64_t,
std::experimental::simd_abi::deduce_t<std::uint64_t, 4>
>;
using fixed_size_element = std::experimental::simd<
std::uint64_t,
std::experimental::simd_abi::fixed_size<4>
>;
int f_deduce(deduce_t_element e) {
return find_last_set(e != -1);
}
int f_fixed_size(fixed_size_element e) {
return find_last_set(e != -1);
}
```
G++ trunk gives the following assembly (I add the comments).
```asm
f_deduce(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_VecBltnBtmsk<32> >):
vpcmpeqd %ymm1, %ymm1, %ymm1
movl $-1, %eax
vpcmpq $4, %ymm1, %ymm0, %k0
kmovb %k0, %edx
orb $-16, %dl # %dl |= 0xf0
je .L1
movzbl %dl, %edx
movl $31, %eax
lzcntl %edx, %edx # leading zeros is 24
# because the next byte is always 0b1111
subl %edx, %eax # so we get the result is 31 - 24 = 7
.L1:
ret
f_fixed_size(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_Fixed<4> >):
vpcmpeqd %ymm0, %ymm0, %ymm0
movl $63, %edx
vpcmpq $4, (%rdi), %ymm0, %k0
kmovb %k0, %eax
andl $15, %eax
lzcntq %rax, %rax
subl %eax, %edx
movl %edx, %eax
vzeroupper
ret
```
In fact, the first function always gives the result 7 whatever argument it
gets, which is more obvious from clang++'s result.
```asm
f_deduce(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_VecBltnBtmsk<32>>): #
@f_deduce(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_VecBltnBtmsk<32>>)
movl $7, %eax
retq
f_fixed_size(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_Fixed<4>>): #
@f_fixed_size(std::experimental::parallelism_v2::simd<unsigned long,
std::experimental::parallelism_v2::simd_abi::_Fixed<4>>)
vpcmpeqd %ymm0, %ymm0, %ymm0
vpcmpeqq (%rdi), %ymm0, %k0
kmovd %k0, %eax
xorb $15, %al
movzbl %al, %eax
lzcntq %rax, %rcx
movl $63, %eax
subl %ecx, %eax
vzeroupper
retq
```
I don't know why, but compiled result of `fixed_size_simd` seems to be
different.
