HomePhabricator

[OpenMP] Use primary context in CUDA plugin

Authored by ye-luo on Jul 7 2020, 7:13 AM.

Description

[OpenMP] Use primary context in CUDA plugin

Summary:
Retaining per device primary context is preferred to creating a context owned by the plugin.

From CUDA documentation

  1. Note that the use of multiple CUcontext s per device within a single process will substantially degrade performance and is strongly discouraged. Instead, it is highly recommended that the implicit one-to-one device-to-context mapping for the process provided by the CUDA Runtime API be used." from https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__DRIVER.html
  2. Right under cuCtxCreate. In most cases it is recommended to use cuDevicePrimaryCtxRetain. https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__CTX.html#group__CUDA__CTX_1g65dc0012348bc84810e2103a40d8e2cf
  3. The primary context is unique per device and shared with the CUDA runtime API. These functions allow integration with other libraries using CUDA. https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__PRIMARY__CTX.html#group__CUDA__PRIMARY__CTX

Two issues are addressed by this patch:

  1. Not using the primary context caused interoperability issue with libraries like cublas, cusolver. CUBLAS_STATUS_EXECUTION_FAILED and cudaErrorInvalidResourceHandle
  2. On OLCF summit, "Error returned from cuCtxCreate" and "CUDA error is: invalid device ordinal"

Regarding the flags of the primary context. If it is inactive, we set CU_CTX_SCHED_BLOCKING_SYNC. If it is already active, we respect the current flags.

Reviewers: grokos, ABataev, jdoerfert, protze.joachim, AndreyChurbanov, Hahnfeld

Reviewed By: jdoerfert

Subscribers: openmp-commits, yaxunl, guansong, sstefan1, tianshilei1992

Tags: #openmp

Differential Revision: https://reviews.llvm.org/D82718

Details

Committed
tianshilei1992Jul 7 2020, 7:14 AM
Reviewer
jdoerfert
Differential Revision
D82718: [OpenMP] Use primary context in CUDA plugin
Parents
rGc9fb7f81715a: [DEBUGINFO]Add dwarf versions to the test, NFC.
Branches
Unknown
Tags
Unknown