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

Fix typo in shared memory layout description (#471)

Browse Source
This commit is contained in:
Masahiro Masuda 2022-04-25 07:32:13 +09:00 committed by GitHub
parent dd77fadc70
commit 70f3ba57f5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
media/docs/implicit_gemm_convolution.md
View File

@ -596,7 +596,7 @@ As described in the CUTLASS GTC 2019 presentation [slides](https://developer.dow
[recording](https://developer.nvidia.com/gtc/2019/video/S9593), an access to Shared Memory will be conflict-free if [recording](https://developer.nvidia.com/gtc/2019/video/S9593), an access to Shared Memory will be conflict-free if
the following conditions are satisfied across each warp: the following conditions are satisfied across each warp:
- {T0, T1, .., T7} do not access the same 128-bit bank - {T0, T1, .., T7} do not access the same 128-bit bank
- {T8, T9, .., T16} do not access the same 128-bit bank - {T8, T9, .., T15} do not access the same 128-bit bank
- {T16, T17, .., T23} do not access the same 128-bit bank - {T16, T17, .., T23} do not access the same 128-bit bank
- {T24, T25, .., T31} do not access the same 128-bit bank - {T24, T25, .., T31} do not access the same 128-bit bank