leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

v4.2 release. (#2587)

Browse Source 
* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line.

* v4.2 release.
This commit is contained in:
Junkai-Wu
2025-08-22 18:11:24 -04:00
committed by GitHub
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/76_blackwell_conv/76_blackwell_conv_dgrad.cu
+12 -3
View File
@@ -504,10 +504,19 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
if (__CUDACC_VER_MAJOR__ < 13) {
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
}
else {
if ((props.major != 10 || props.major != 11) && props.minor != 0) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 110)." << std::endl;
return 0;
}
}
//
// Parse options
//
examples/76_blackwell_conv/76_blackwell_conv_fprop.cu
+12 -3
View File
@@ -504,10 +504,19 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
if (__CUDACC_VER_MAJOR__ < 13) {
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
}
else {
if ((props.major != 10 || props.major != 11) && props.minor != 0) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 110)." << std::endl;
return 0;
}
}
//
// Parse options
//
examples/76_blackwell_conv/76_blackwell_conv_wgrad.cu
+13 -4
View File
@@ -500,10 +500,19 @@ int main(int argc, char const **args) {
CUDA_CHECK(cudaGetDeviceProperties(&props, current_device_id));
cudaError_t error = cudaGetDeviceProperties(&props, 0);
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
if (__CUDACC_VER_MAJOR__ < 13) {
if (props.major != 10 && (props.minor != 0 || props.minor != 1)) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 101)." << std::endl;
return 0;
}
}
else {
if ((props.major != 10 || props.major != 11) && props.minor != 0) {
std::cerr << "This example requires a GPU of NVIDIA's Blackwell architecture (compute capability 100 or 110)." << std::endl;
return 0;
}
}
//
// Parse options
//