public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug c++/105968] New: GCC vectorizes but reports that it did not vectorize
@ 2022-06-14 8:55 steveire at gmail dot com
2022-06-14 9:02 ` [Bug c++/105968] " crazylht at gmail dot com
2022-06-14 10:22 ` rguenth at gcc dot gnu.org
0 siblings, 2 replies; 3+ messages in thread
From: steveire at gmail dot com @ 2022-06-14 8:55 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105968
Bug ID: 105968
Summary: GCC vectorizes but reports that it did not vectorize
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: c++
Assignee: unassigned at gcc dot gnu.org
Reporter: steveire at gmail dot com
Target Milestone: ---
I'm looking for a way to know if GCC autovectorizes some code.
Starting with this testcase which I picked up somewhere:
```
#define N 10000
#define NTIMES 100000
double a[N] __attribute__ ((aligned (16)));
double b[N] __attribute__ ((aligned (16)));
double c[N] __attribute__ ((aligned (16)));
double r[N] __attribute__ ((aligned (16)));
int muladd (void) {
int i, times;
for (times = 0; times < NTIMES; times++) {
#if 1
// count up
for (i = 0; i < N; ++i)
r[i] = (a[i] + b[i]) * c[i];
#else
// count down (old gcc won't auto-vectorize)
for (i = N-1; i >= 0; --i)
r[i] = (a[i] + b[i]) * c[i];
#endif
}
return 0;
}
```
the command
```
g++ -O2 -ftree-vectorize -fno-verbose-asm -mavx2 -fopt-info-vec-all -c test.cpp
```
reports
```
test.cpp:9:5: note: vectorized 1 loops in function.
```
However, with -O3, GCC reports that it did not vectorize:
```
g++ -O3 -ftree-vectorize -fno-verbose-asm -mavx2 -fopt-info-vec-all -c test.cpp
```
output:
```
test.cpp:9:5: note: vectorized 0 loops in function.
```
even though vector instructions are generated.
Demo https://godbolt.org/z/3o41r7jWc
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug c++/105968] GCC vectorizes but reports that it did not vectorize
2022-06-14 8:55 [Bug c++/105968] New: GCC vectorizes but reports that it did not vectorize steveire at gmail dot com
@ 2022-06-14 9:02 ` crazylht at gmail dot com
2022-06-14 10:22 ` rguenth at gcc dot gnu.org
1 sibling, 0 replies; 3+ messages in thread
From: crazylht at gmail dot com @ 2022-06-14 9:02 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105968
Hongtao.liu <crazylht at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |crazylht at gmail dot com
--- Comment #1 from Hongtao.liu <crazylht at gmail dot com> ---
> even though vector instructions are generated.
>
No it's scalar instructions, but the issue here is why vectorizer is ok for -O2
-O2 -ftree-vectorize -mavx2 but not for -O3 -ftree-vectorize -mavx2
muladd():
xor eax, eax
.L2:
vmovsd xmm0, QWORD PTR a[rax]
vaddsd xmm0, xmm0, QWORD PTR b[rax]
add rax, 8
vmulsd xmm0, xmm0, QWORD PTR c[rax-8]
vmovsd QWORD PTR r[rax-8], xmm0
cmp rax, 80000
jne .L2
xor eax, eax
ret
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug c++/105968] GCC vectorizes but reports that it did not vectorize
2022-06-14 8:55 [Bug c++/105968] New: GCC vectorizes but reports that it did not vectorize steveire at gmail dot com
2022-06-14 9:02 ` [Bug c++/105968] " crazylht at gmail dot com
@ 2022-06-14 10:22 ` rguenth at gcc dot gnu.org
1 sibling, 0 replies; 3+ messages in thread
From: rguenth at gcc dot gnu.org @ 2022-06-14 10:22 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105968
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |RESOLVED
Resolution|--- |WONTFIX
--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
> ./cc1 -quiet t.c -O3 -mavx2 -fopt-info
t.c:11:25: optimized: loops interchanged in loop nest
> ./cc1 -quiet t.c -O2 -mavx2 -fopt-info
t.c:14:19: optimized: loop vectorized using 32 byte vectors
so we interchange the loop to
for (i = 0; i < N; ++i)
for (times = 0; times < NTIMES; times++)
r[i] = (a[i] + b[i]) * c[i];
which is indeed good for memory locality (now, we should then eliminate
the inner loop completely but we have no such facility - only unrolling
and DSE/DCE would do this but nothing on the high-level loop form).
"Benchmark" issue. The outer loop should have a memory clobber.
Oh, and we should in theory be able to vectorize the outer loop if
N is a multiple of the vector element count. But:
t.c:11:25: note: === vect_analyze_data_ref_accesses ===
t.c:11:25: note: zero step in inner loop of nest
t.c:11:25: missed: not vectorized: complicated access pattern.
t.c:15:14: missed: not vectorized: complicated access pattern.
t.c:11:25: missed: bad data access.
so we don't handle this exact issue (maybe the offending check can
simply be elided - assuming dependence checking handles zero steps
correctly).
Putting
__asm__ volatile ("" : : : "memory");
at the end of the outer loop vectorizes with -O3 as well (but doesn't
interchange).
Not a bug I think unless you want to make it a bug about not vectorizing
the outer loop after interchange.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-06-14 10:22 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-06-14 8:55 [Bug c++/105968] New: GCC vectorizes but reports that it did not vectorize steveire at gmail dot com
2022-06-14 9:02 ` [Bug c++/105968] " crazylht at gmail dot com
2022-06-14 10:22 ` rguenth at gcc dot gnu.org
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).