AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2.7.3-1

Browse Source 
Add support for A100 GPU and related platforms.
Add support for CUDA 11.
Add support for send/receive operations (beta).


[ROCm/rccl commit: 5949d96f36]
This commit is contained in:
Sylvain Jeaugey
2020-05-12 14:40:18 -07:00
parent c43022b9d8
commit 89072c82e5
54 changed files with 2051 additions and 1254 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rccl/src/include/checks.h
+7 -7
View File
@@ -1,5 +1,5 @@
/*************************************************************************
* Copyright (c) 2019, NVIDIA CORPORATION. All rights reserved.
* Copyright (c) 2019-2020, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
@@ -11,17 +11,17 @@
// Check CUDA calls
#define CUDACHECK(cmd) do { \
cudaError_t e = cmd; \
if( e != cudaSuccess ) { \
WARN("Cuda failure '%s'", cudaGetErrorString(e)); \
cudaError_t err = cmd; \
if( err != cudaSuccess ) { \
WARN("Cuda failure '%s'", cudaGetErrorString(err)); \
return ncclUnhandledCudaError; \
} \
} while(false)
#define CUDACHECKGOTO(cmd, res, label) do { \
cudaError_t e = cmd; \
if( e != cudaSuccess ) { \
WARN("Cuda failure '%s'", cudaGetErrorString(e)); \
cudaError_t err = cmd; \
if( err != cudaSuccess ) { \
WARN("Cuda failure '%s'", cudaGetErrorString(err)); \
res = ncclUnhandledCudaError; \
goto label; \
} \