[all-commits] [llvm/llvm-project] c5348a: [OpenMP] Use primary context in CUDA plugin

[Ye Luo via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: c5348aecd7723e7aa7b18406d0c97724c0659f34
      https://github.com/llvm/llvm-project/commit/c5348aecd7723e7aa7b18406d0c97724c0659f34
  Author: Ye Luo <yeluo at anl.gov>
  Date:   2020-07-07 (Tue, 07 Jul 2020)

  Changed paths:
    M openmp/libomptarget/plugins/cuda/src/rtl.cpp

  Log Message:
  -----------
  [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