aboutsummaryrefslogtreecommitdiff
path: root/lldb/packages/Python/lldbsuite/test/configuration.py
diff options
context:
space:
mode:
authorMatt Arsenault <Matthew.Arsenault@amd.com>2025-08-22 13:55:04 +0900
committerGitHub <noreply@github.com>2025-08-22 13:55:04 +0900
commit01f785cac4f5863f27012e347b9ae9287830c07e (patch)
treef97542dca781ab57cf037c16f6a9bf67d5027db1 /lldb/packages/Python/lldbsuite/test/configuration.py
parent6a7ade03d1fced72bbe25cb3cf9efde8c928e563 (diff)
downloadllvm-01f785cac4f5863f27012e347b9ae9287830c07e.zip
llvm-01f785cac4f5863f27012e347b9ae9287830c07e.tar.gz
llvm-01f785cac4f5863f27012e347b9ae9287830c07e.tar.bz2
AMDGPU: Expand remaining system atomic operations (#122137)
System scope atomics need to use cmpxchg loops if we know nothing about the allocation the address is from. aea5980e26e6a87dab9f8acb10eb3a59dd143cb1 started this, this expands the set to cover the remaining integer operations. Don't expand xchg and add, those theoretically should work over PCIe. This is a pre-commit which will introduce performance regressions. Subsequent changes will add handling of new atomicrmw metadata, which will avoid the expansion. Note this still isn't conservative enough; we do need to expand some device scope atomics if the memory is in fine-grained remote memory.
Diffstat (limited to 'lldb/packages/Python/lldbsuite/test/configuration.py')
0 files changed, 0 insertions, 0 deletions