aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/CodeGen/MachineOperand.cpp
diff options
context:
space:
mode:
authorChristian Sigg <csigg@google.com>2021-06-10 07:50:29 +0200
committerChristian Sigg <csigg@google.com>2021-06-10 08:43:45 +0200
commit0b21371e1201f23e0f1de2de56ef8eed9c43d6db (patch)
tree3c99fda2d2d54ac93a48070d4bf57b2243554955 /llvm/lib/CodeGen/MachineOperand.cpp
parenta115c5247f5a6c68f99d081c970e78eeebad5414 (diff)
downloadllvm-0b21371e1201f23e0f1de2de56ef8eed9c43d6db.zip
llvm-0b21371e1201f23e0f1de2de56ef8eed9c43d6db.tar.gz
llvm-0b21371e1201f23e0f1de2de56ef8eed9c43d6db.tar.bz2
[mlir] Support pre-existing tokens in 'gpu-async-region'
Allow gpu ops implementing the async interface to already be async when running the GpuAsyncRegionPass. That pass threads a 'current token' through a block with ops implementing the gpu async interface. After this change, existing async ops (returning a !gpu.async.token) set the current token. Existing synchronous `gpu.wait` ops reset the current token. Reviewed By: herhut Differential Revision: https://reviews.llvm.org/D103396
Diffstat (limited to 'llvm/lib/CodeGen/MachineOperand.cpp')
0 files changed, 0 insertions, 0 deletions