Page MenuHomePhabricator

AMDGPU: Document why we use (non-volatile) BUFFER_WBINVL1 in graphics
Needs ReviewPublic

Authored by nhaehnle on Nov 9 2020, 8:41 AM.

Details

Summary

Graphics never used volatile vs. non-volatile in anything even
approaching a principled way, and trying to fix all the drivers years
later is fraught with unnecessary risk.

Let's just document why things are the way they are and be done with it.

Change-Id: If937c95834b712da8561e262bc41c5669e45c78c

Diff Detail

Unit TestsFailed

TimeTest
380 mslinux > HWAddressSanitizer-x86_64.TestCases::sizes.cpp
Script: -- : 'RUN: at line 3'; /mnt/disks/ssd0/agent/llvm-project/build/./bin/clang --driver-mode=g++ -m64 -gline-tables-only -fsanitize=hwaddress -fuse-ld=lld -mcmodel=large -mllvm -hwasan-globals -mllvm -hwasan-use-short-granules -mllvm -hwasan-instrument-landing-pads=0 -mllvm -hwasan-instrument-personality-functions /mnt/disks/ssd0/agent/llvm-project/compiler-rt/test/hwasan/TestCases/sizes.cpp -nostdlib++ -lstdc++ -o /mnt/disks/ssd0/agent/llvm-project/build/projects/compiler-rt/test/hwasan/X86_64/TestCases/Output/sizes.cpp.tmp

Event Timeline

nhaehnle created this revision.Nov 9 2020, 8:41 AM
Herald added a project: Restricted Project. · View Herald TranscriptNov 9 2020, 8:41 AM
nhaehnle requested review of this revision.Nov 9 2020, 8:41 AM
nhaehnle updated this revision to Diff 303898.Nov 9 2020, 9:10 AM

It seems the MTYPE numbering was changed on gfx9, reflect that in the comment.

t-tye added inline comments.Nov 9 2020, 11:24 AM
llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
904

BUFFER_WBINVL1

After our internal discussion of this fizzled out, I am no longer actually sure whether this analysis is correct.

Should this be abandoned?