| Commit message (Collapse) | Author | Age |
... | |
| |
| |
| |
| | |
PiperOrigin-RevId: 205164273
|
|\ \
| | |
| | |
| | |
| | |
| | | |
ROCmSoftwarePlatform:upstream-staging-stream-executor
PiperOrigin-RevId: 205140328
|
| | |
| | |
| | |
| | |
| | |
| | | |
bias activation.
PiperOrigin-RevId: 205008958
|
| | |
| | |
| | |
| | |
| | |
| | | |
returned errors, but crashes instead.
PiperOrigin-RevId: 205000883
|
| | |
| | |
| | |
| | | |
PiperOrigin-RevId: 204975773
|
|\ \ \
| | | |
| | | |
| | | |
| | | |
| | | | |
ROCmSoftwarePlatform:upstream-staging-stream-executor-pooling-interface
PiperOrigin-RevId: 204805678
|
| | | |
| | | |
| | | |
| | | | |
PiperOrigin-RevId: 204327453
|
| | | |
| | | |
| | | |
| | | | |
PiperOrigin-RevId: 204326206
|
| |/ /
|/| |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | | |
1) StreamInterface::CudaStreamMemberHack()
Despite the fact that StreamExecutor and GPU common runtime are largely
orthogonal, this particular routine in StreamExecutor is used in GPU common
runtime and a couple of other operators. In this commit it's renamed as
StreamInterface::GpuStreamMemberHack() and their call sites are also changed.
2) StreamExecutorInterface::CudaContextHack()
This member is renamed to StramExecutorInterface::GpuContextHack().
Changes introduced in this commit includes:
- some StreamExecutor interfaces and CUDA implementation
- GPU common runtime related to interface changes in StreamExecutor
- operators affected by interface changes in StreamExecutor
|
| |/
|/| |
|
|/
|
|
|
|
| |
Due to the design of MIOpen, the DNN library on ROCm platform, an instance of
ScratchAllocator has to be passed into pooling routines. This commit address
such interface changes and the implementation in CUDA StreamExecutor.
|
|
|
|
| |
PiperOrigin-RevId: 203959955
|
|
|
|
|
|
|
|
|
|
|
| |
Instead of having one stream for compute, host-to-device and device-to-host transfers, switch to having separate streams, just like the GPU does.
Add a se::Event field to XlaTensor to allow accurate inter-stream dependencies to be created.
As part of this:
- Fix TransferManager::TransferLiteralFrom/ToDevice to correctly make generated substreams wait on their master stream.
- Fix Stream::BlockHostUntilDone() to not block on or return substreams. This behavior is completely broken and not only nondeterministically returns substreams to the pool but causes indefinite hangs with the HostStream.
PiperOrigin-RevId: 203726543
|
|
|
|
|
|
| |
TowerLocalVariables.
PiperOrigin-RevId: 203520287
|
|\ |
|
| |
| |
| |
| | |
PiperOrigin-RevId: 203037623
|
| |
| |
| |
| |
| |
| | |
to be zeroed.
PiperOrigin-RevId: 203001311
|
|\ \
| | |
| | | |
Fix MPI build issue with bazel
|
| | |
| | |
| | |
| | | |
PiperOrigin-RevId: 202392792
|
| | |
| | |
| | |
| | | |
PiperOrigin-RevId: 202347723
|
| | |
| | |
| | |
| | | |
PiperOrigin-RevId: 202292422
|
| | |
| | |
| | |
| | | |
PiperOrigin-RevId: 202260254
|
|/ /
| |
| |
| | |
Signed-off-by: Yong Tang <yong.tang.github@outlook.com>
|
| |
| |
| |
| | |
PiperOrigin-RevId: 202551122
|
| |
| |
| |
| | |
PiperOrigin-RevId: 202392792
|
| |
| |
| |
| | |
PiperOrigin-RevId: 202347723
|
| |
| |
| |
| | |
PiperOrigin-RevId: 202292422
|
|/
|
|
| |
PiperOrigin-RevId: 202260254
|
|
|
|
| |
PiperOrigin-RevId: 202179928
|
|
|
|
| |
PiperOrigin-RevId: 201239428
|
|
|
|
|
|
| |
again in the future. Users are interested to make it work and we don't want to be in the way.
PiperOrigin-RevId: 201214857
|
|
|
|
| |
PiperOrigin-RevId: 200783258
|
|
|
|
|
|
|
|
| |
Whilst the switch statement covers all possible enum values, the compiler still complains that it reaches the end of the function without returning a value.
I add an "unknown" string, mirroring the one in the function just above.
PiperOrigin-RevId: 200452885
|
|
|
|
| |
PiperOrigin-RevId: 200432478
|
|
|
|
| |
PiperOrigin-RevId: 200411493
|
|
|
|
| |
PiperOrigin-RevId: 200333639
|
|
|
|
|
|
| |
longer supported.
PiperOrigin-RevId: 200200356
|
|
|
|
|
|
| |
No functional changes.
PiperOrigin-RevId: 200199956
|
|
|
|
| |
PiperOrigin-RevId: 199780350
|
|
|
|
| |
PiperOrigin-RevId: 199321021
|
|
|
|
| |
PiperOrigin-RevId: 198836479
|
|
|
|
|
|
| |
This fixes an error when running resnet50_batch128_fp16 with --v=2.
PiperOrigin-RevId: 198798196
|
|
|
|
| |
PiperOrigin-RevId: 198513480
|
|
|
|
|
|
|
| |
Revert #18413. Too many internal test failures due to the name scope change caused by this change.
Revert #18192. Cannot use re2::StringPiece internally. Need alternative for set call. Will pull and clean this up in a separate change.
PiperOrigin-RevId: 197991247
|
|
|
|
| |
PiperOrigin-RevId: 197650067
|
|
|
|
| |
PiperOrigin-RevId: 197490523
|
|
|
|
|
|
| |
because that breaks XLA tests.
PiperOrigin-RevId: 197328103
|
|
|
|
| |
PiperOrigin-RevId: 197167501
|
|
|
|
| |
PiperOrigin-RevId: 197137612
|
|
|
|
|
|
| |
Enable CUDNN_FFT_TILING_FORWARD for cuDNN >= 7.
PiperOrigin-RevId: 197118212
|