leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

v4.1 release update v2. (#2481)

Browse Source
This commit is contained in:
Junkai-Wu
2025-07-21 22:03:55 -04:00
committed by GitHub
parent 9baa06dd57
commit fd6cfe1ed0
179 changed files with 7878 additions and 1286 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/59_ampere_gather_scatter_conv/README.md
+1 -1
View File
@@ -188,7 +188,7 @@ Running this example on an RTX 3080Ti prints the following performance numbers (
```
$> ./examples/59_ampere_gather_scatter_conv/59_ampere_gather_scatter_conv --n=131072 --i=128 --no-check
Ampere convolution forward propogation kernel supporting both affine and gather/scatter tensors.
Ampere convolution forward propagation kernel supporting both affine and gather/scatter tensors.
Allocating tensors ... done.
Initializing data ... done.
examples/59_ampere_gather_scatter_conv/ampere_gather_scatter_conv.cu
+2 -2
View File
@@ -29,7 +29,7 @@
*
**************************************************************************************************/
/*! \file
\brief Example demonstrating CuTe and CUTLASS 3.x based Ampere convolution forward propogation kernel
\brief Example demonstrating CuTe and CUTLASS 3.x based Ampere convolution forward propagation kernel
capable of operating on both affine and gather/scatter tensors.
This example demonstartes a few super cool features of CUTLASS and CuTe. It shows off
@@ -284,7 +284,7 @@ int ampere_gather_scatter_conv_fprop(
int
main(int argc, char const** argv) {
cutlass::CommandLine cmd(argc, argv);
std::cout << "Ampere convolution forward propogation kernel supporting both affine and gather/scatter tensors.\n\n";
std::cout << "Ampere convolution forward propagation kernel supporting both affine and gather/scatter tensors.\n\n";
if (cmd.check_cmd_line_flag("help")) {
std::cout
<< "Options:\n"