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

CUTLASS 3.4.0 (#1286)

Browse Source 
* CUTLASS 3.4.0

* Update CHANGELOG.md

---------

Co-authored-by: Pradeep Ramani <prramani@nvidia.com>
This commit is contained in:
Pradeep Ramani
2023-12-29 12:21:31 -08:00
committed by GitHub
parent b7508e3379
commit 8236f30675
211 changed files with 11409 additions and 2763 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/46_depthwise_simt_conv2dfprop/depthwise_simt_conv2dfprop.cu
View File

@ -306,7 +306,7 @@ struct Options {
/// Prints the usage statement.
std::ostream &print_usage(std::ostream &out) const {
out << "41_depthwise_gemm_fprop example\n\n"
out << "46_depthwise_gemm_fprop example\n\n"
<< " This example uses Ampere's Tensor Core operators on F16 data types to compute\n"
<< " forward convolution on tensors of layout NHWC.\n\n"
<< "Options:\n\n"
@ -554,7 +554,7 @@ Result profile_convolution(Options const &options) {
if (options.save_workspace) {
std::stringstream ss;
ss << "45_depthwise_simt_conv2dfprop" << options.input_size.n() << "x" << options.input_size.h()
ss << "46_depthwise_simt_conv2dfprop" << options.input_size.n() << "x" << options.input_size.h()
<< "x" << options.input_size.w() << "x" << options.input_size.c() << "_"
<< options.filter_size.n() << "x" << options.filter_size.h() << "x"
<< options.filter_size.w() << "x" << options.filter_size.c() << ".dat";