public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug target/102856] New: [nvptx] Misaligned accesses with cheap vectorization enabled
@ 2021-10-20 12:21 jules at gcc dot gnu.org
  2021-11-08 10:16 ` [Bug target/102856] " tschwinge at gcc dot gnu.org
  0 siblings, 1 reply; 2+ messages in thread
From: jules at gcc dot gnu.org @ 2021-10-20 12:21 UTC (permalink / raw)
  To: gcc-bugs

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102856

            Bug ID: 102856
           Summary: [nvptx] Misaligned accesses with cheap vectorization
                    enabled
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: jules at gcc dot gnu.org
  Target Milestone: ---

Since revision 2b8453c401b699ed93c085d0413ab4b5030bcdb8 I am seeing several
OpenMP tests fail with misaligned access errors:

PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-11.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-12.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-16.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-3.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-5.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-6.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c++/../libgomp.c-c++-common/for-9.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-11.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-12.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-16.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-3.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-5.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-6.c
execution test
PASS -> FAIL: nvidia-1/libgomp.sum:libgomp.c/../libgomp.c-c++-common/for-9.c
execution test

These look like, e.g.:

$ ./for-11.exe 

libgomp: cuCtxSynchronize error: misaligned address

libgomp: cuMemFree_v2 error: misaligned address

libgomp: device finalization failed

I suspect the reason is that an operation that is now being vectorized (e.g.
"st.v2.u64 [%frame], %r28;") requires higher alignment than the original scalar
accesses it replaces.

I haven't spotted an obvious culprit for the problem in the nvptx backend. This
is OpenMP, so it could be the soft stack handling -- or it could be something
else.

^ permalink raw reply	[flat|nested] 2+ messages in thread

* [Bug target/102856] [nvptx] Misaligned accesses with cheap vectorization enabled
  2021-10-20 12:21 [Bug target/102856] New: [nvptx] Misaligned accesses with cheap vectorization enabled jules at gcc dot gnu.org
@ 2021-11-08 10:16 ` tschwinge at gcc dot gnu.org
  0 siblings, 0 replies; 2+ messages in thread
From: tschwinge at gcc dot gnu.org @ 2021-11-08 10:16 UTC (permalink / raw)
  To: gcc-bugs

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102856

Thomas Schwinge <tschwinge at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |RESOLVED
         Resolution|---                         |DUPLICATE
                 CC|                            |jakub at gcc dot gnu.org,
                   |                            |tschwinge at gcc dot gnu.org,
                   |                            |vries at gcc dot gnu.org
           Keywords|wrong-code                  |openmp

--- Comment #1 from Thomas Schwinge <tschwinge at gcc dot gnu.org> ---
Belatedly confirmed -- and the issue again disappeared with commit
r12-4529-gc7abdf46fb7ac9a0c37f120feff3fcc3a752584f "openmp: Fix up struct
gomp_work_share handling [PR102838]".  Thus suppositionally resolving as
duplicate (but I have not actually investigated/analyzed this issue here).

*** This bug has been marked as a duplicate of bug 102838 ***

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2021-11-08 10:16 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-20 12:21 [Bug target/102856] New: [nvptx] Misaligned accesses with cheap vectorization enabled jules at gcc dot gnu.org
2021-11-08 10:16 ` [Bug target/102856] " tschwinge 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).