https://gcc.gnu.org/bugzilla/show_bug.cgi?id=109985
Bug ID: 109985
Summary: __builtin_prefetch ignored by GCC 12/13
Product: gcc
Version: 13.1.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: pdimov at gmail dot com
Target Milestone: ---
We are investigating a Boost.Unordered performance regression with GCC 12,
on the following benchmark:
https://github.com/boostorg/boost_unordered_benchmarks/blob/4c717baac1bff8d3e51cb8485b72bbb63d533265/scattered_lookup.cpp
and it looks like the reason is that GCC 12 (and 13) ignore a call to
`__builtin_prefetch`.
While GCC 11 generates this:
```
.L108:
mov r8, r12
movdqa xmm0, xmm1
sal r8, 4
lea r14, [r10+r8]
pcmpeqb xmm0, XMMWORD PTR [r14]
pmovmskb edx, xmm0
and edx, 32767
je .L104
sub r8, r12
sal r8, 4
add r8, QWORD PTR [rbx+32]
prefetcht0 [r8]
.L106:
xor r15d, r15d
rep bsf r15d, edx
movsx r15, r15d
sal r15, 4
add r15, r8
cmp rsi, QWORD PTR [r15]
jne .L144
add r9, QWORD PTR [r15+8]
mov rax, rdi
cmp r11, rdi
jne .L145
```
(https://godbolt.org/z/d663fdM16 - prefetcht0 [r8] right before L106)
GCC 12 generates this in the same function:
```
.L108:
mov r8, r10
movdqa xmm0, xmm1
sal r8, 4
lea r9, [rbp+0+r8]
pcmpeqb xmm0, XMMWORD PTR [r9]
pmovmskb edx, xmm0
and edx, 32767
je .L104
mov rdi, QWORD PTR [rsp+16]
sub r8, r10
mov QWORD PTR [rsp+24], rax
sal r8, 4
mov rdi, QWORD PTR [rdi+32]
mov QWORD PTR [rsp+8], rdi
mov rax, rdi
.L106:
xor edi, edi
rep bsf edi, edx
movsx rdi, edi
sal rdi, 4
add rdi, r8
add rdi, rax
cmp r11, QWORD PTR [rdi]
jne .L143
add rsi, 8
add rbx, QWORD PTR [rdi+8]
cmp r12, rsi
jne .L109
```
(https://godbolt.org/z/T7csq7TPz - no prefetcht0 instruction before L106)
Simplifying this code unfortunately leads to the prefetcht0 being generated.
