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

v3.9 (#2185)

Browse Source 
* v3.8 update x

* fix blackwell gg

* doc change

* doc change

* doc change

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
This commit is contained in:
Yujia Zhai
2025-03-20 22:52:23 -07:00
committed by GitHub
parent 8c4d1dc47d
commit 62750a2b75
334 changed files with 91517 additions and 2656 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
tools/profiler/src/performance_report.cpp
View File

@@ -160,7 +160,7 @@ void PerformanceReport::append_result(PerformanceResult result) {
}
}
void PerformanceReport::sort_results(PerformanceResultVector &results) {
void PerformanceReport::sort_flops_per_byte(PerformanceResultVector &results) {
struct FlopsPerByteCompare
{
@@ -176,6 +176,19 @@ void PerformanceReport::sort_results(PerformanceResultVector &results) {
std::stable_sort(results.begin(), results.end(), FlopsPerByteCompare());
}
void PerformanceReport::sort_flops_per_sec(PerformanceResultVector &results) {
struct FlopsPerSecondCompare
{
bool operator()(const PerformanceResult &a, const PerformanceResult &b)
{
return a.gflops_per_sec() > b.gflops_per_sec();
}
};
std::stable_sort(results.begin(), results.end(), FlopsPerSecondCompare());
}
void PerformanceReport::append_results(PerformanceResultVector const &results) {
if (options_.report.verbose) {
@@ -195,8 +208,12 @@ PerformanceReport::~PerformanceReport() {
//
if (options_.report.verbose && !concatenated_results_.empty()) {
if (options_.report.sort_results) {
sort_results(concatenated_results_);
if (options_.report.sort_flops_per_byte) {
sort_flops_per_byte(concatenated_results_);
}
if (options_.report.sort_flops_per_sec) {
sort_flops_per_sec(concatenated_results_);
}
std::cout << "\n\n";