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 # 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** | |**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| | | Microsoft Visual Studio 2017|
| Ubuntu 14.04 | GCC 4.8.2 | | Ubuntu 14.04 | GCC 4.8.2 |
| Ubuntu 16.04 | GCC 5.4.0 | | 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 CUTLASS runs successfully on the following NVIDIA GPUs, and it is expected to be efficient on
any Maxwell-, Pascal-, or Volta-architecture NVIDIA GPU. any Maxwell-, Pascal-, or Volta-architecture NVIDIA GPU.