squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Merge pull request #26 from NVIDIA/cutlass_1.1

Browse Source 
Clarification to README
This commit is contained in:
Andrew Kerr 2018-09-21 11:44:47 -07:00 committed by GitHub
commit d419094c28
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -56,7 +56,10 @@ when compiled with CUDA 10.0.
# Compatibility
CUTLASS requires CUDA 9 but performs best with [CUDA 10.0 Toolkit](ttps://developer.nvidia.com/cuda-toolkit) or later.
CUTLASS performs best when compiled with the [CUDA 10.0 Toolkit](ttps://developer.nvidia.com/cuda-toolkit).
It is compatible with CUDA 9.0, 9.1, and 9.2, but these versions of the CUDA Toolkit do not support new Turing WMMA features.
We have tested the following environments.
|**Operating System** | **Compiler** |
|-----------------|----------|
@ -64,7 +67,7 @@ CUTLASS requires CUDA 9 but performs best with [CUDA 10.0 Toolkit](ttps://develo
| | Microsoft Visual Studio 2017|
| Ubuntu 14.04 | GCC 4.8.2 |
| Ubuntu 16.04 | GCC 5.4.0 |
| Ubuntu 18.04 | GCC 7.3.0 |
CUTLASS runs successfully on the following NVIDIA GPUs, and it is expected to be efficient on
any Maxwell-, Pascal-, or Volta-architecture NVIDIA GPU.