STT-tensorflow/tensorflow/stream_executor/rocm
Deven Desai 856f899e4e [ROCm] Fix for the ROCm CSB breakage - 200604
This PR addresses 2 unit test failures introduced by the following commit
bd20260350

failing unit tests

```
//tensorflow/core/common_runtime/gpu:gpu_device_test
//tensorflow/core/common_runtime/gpu:gpu_device_unified_memory_test
```

It is different from PR #40164, which fixes the build error on the ROCm platform.

The commit above adds unit tests that check the assignment of priority values to GPU streams. Because ROCm support for assigning priority values to GPU streams is missing, those unit tests fail.

This PR/commit adds the missing ROCm support, and updates the unit test to work with AMD GPUs too. The valid priority value range seems to be different for AMD GPUs (0,2) as compared to NVidia GPUs (-1, 0), and hence the changes requrired in the testcases too.
2020-06-05 00:36:29 +00:00
..
BUILD
rocm_activation.h
rocm_blas.cc [ROCm] Adding complex datatype support for StridedBatchGemm API calls 2020-04-15 21:32:43 +00:00
rocm_blas.h Merge pull request #35666 from ROCmSoftwarePlatform:google_upstream_rocblas_complex 2020-04-01 10:59:11 -07:00
rocm_diagnostics.cc
rocm_diagnostics.h
rocm_dnn.cc PR #37679: Support two CUDNN CTC Loss algorithms 2020-04-10 14:15:07 -07:00
rocm_dnn.h PR #37679: Support two CUDNN CTC Loss algorithms 2020-04-10 14:15:07 -07:00
rocm_driver.cc [ROCm] Fix for the ROCm CSB breakage - 200604 2020-06-05 00:36:29 +00:00
rocm_driver_wrapper.h [ROCm] Fix for the ROCm CSB breakage - 200604 2020-06-05 00:36:29 +00:00
rocm_event.cc
rocm_fft.cc
rocm_fft.h
rocm_gpu_executor.cc Reviewer requests 2020-05-15 19:55:27 +00:00
rocm_kernel.cc
rocm_platform.cc
rocm_platform.h
rocm_platform_id.cc
rocm_platform_id.h
rocm_rng.cc