diff options
| author | Jay Foad <jay.foad@amd.com> | 2025-07-23 13:24:03 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-23 13:24:03 +0100 |
| commit | 2147e29f641f22822e2b0e10c978b28b06db1aeb (patch) | |
| tree | a20c540c0363598dd8edd7fbe87e56f58adef0e4 /llvm/unittests/Support/DebugTest.cpp | |
| parent | 18edd82716a710e40cbed3bd81b8c9e64060c171 (diff) | |
| download | llvm-2147e29f641f22822e2b0e10c978b28b06db1aeb.zip llvm-2147e29f641f22822e2b0e10c978b28b06db1aeb.tar.gz llvm-2147e29f641f22822e2b0e10c978b28b06db1aeb.tar.bz2 | |
[AMDGPU] Tests for unnecessary S_WAIT_XCNT insertion (#145688)
Hardware does an implicit "S_WAIT_XCNT 0" between SMEM and VMEM
instructions, so there will never be outstanding address translations
for both SMEM and VMEM at the same time.
Diffstat (limited to 'llvm/unittests/Support/DebugTest.cpp')
0 files changed, 0 insertions, 0 deletions