leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 25 Packages Projects Releases Wiki Activity

CUTLASS 3.8 Release (#2059)

Browse Source 
* CUTLASS 3.8 Release

* update

* Update README.md

* Revert "Update README.md"

This reverts commit b353e36fe83e0815f99b44e46c0c95494c44726b.

* update

* update

---------

Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
mihir-awatramani
2025-01-25 02:44:06 -05:00
committed by GitHub
co-authored by Haicheng Wu Haicheng Wu
parent 9eb01fa0b0
commit 389e493055
290 changed files with 91222 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/profiler/src/operation_profiler.cu
+17
View File
@@ -91,6 +91,11 @@ OperationProfiler::OperationProfiler(
{ArgumentTypeID::kInteger, {"cluster_m", "cluster-shape::m"}, "Cluster shape in the M dimension"},
{ArgumentTypeID::kInteger, {"cluster_n", "cluster-shape::n"}, "Cluster shape in the N dimension"},
{ArgumentTypeID::kInteger, {"cluster_k", "cluster-shape::k"}, "Cluster shape in the K dimension"},
{ArgumentTypeID::kInteger, {"cluster_m_fallback", "cluster-shape-fallback::m"}, "Fallback Cluster shape in the M dimension"},
{ArgumentTypeID::kInteger, {"cluster_n_fallback", "cluster-shape-fallback::n"}, "Fallback Cluster shape in the N dimension"},
{ArgumentTypeID::kInteger, {"cluster_k_fallback", "cluster-shape-fallback::k"}, "Fallback Cluster shape in the K dimension"},
{ArgumentTypeID::kInteger, {"stages", "threadblock-stages"}, "Number of stages of threadblock-scoped matrix multiply"},
{ArgumentTypeID::kInteger, {"warps_m", "warp-count::m"}, "Number of warps within threadblock along the M dimension"},
{ArgumentTypeID::kInteger, {"warps_n", "warp-count::n"}, "Number of warps within threadblock along the N dimension"},
@@ -174,6 +179,11 @@ bool OperationProfiler::satisfies(
return false;
}
}
bool dynamic_cluster = int64_t(op_desc.tile_description.cluster_shape.m()) == 0 ||
int64_t(op_desc.tile_description.cluster_shape.n()) == 0 ||
int64_t(op_desc.tile_description.cluster_shape.k()) == 0;
int64_t int_value;
if (arg_as_int(int_value, "inst_m", problem_space, problem)) {
@@ -212,6 +222,7 @@ bool OperationProfiler::satisfies(
}
}
if (!dynamic_cluster) {
if (arg_as_int(int_value, "cluster_m", problem_space, problem)) {
if (int64_t(op_desc.tile_description.cluster_shape.m()) != int_value) {
return false;
@@ -230,6 +241,7 @@ bool OperationProfiler::satisfies(
}
}
}
if (arg_as_int(int_value, "stages", problem_space, problem)) {
if (int64_t(op_desc.tile_description.threadblock_stages) != int_value) {
return false;
@@ -296,6 +308,11 @@ std::ostream& operator<<(std::ostream& out, library::OperationKind provider) {
if (provider == library::OperationKind::kGemm) {
out << "kGemm";
}
else if (provider == library::OperationKind::kBlockScaledGemm) {
out << "kBlockScaledGemm";
}
else if (provider == library::OperationKind::kRankK) {
out << "kRankK";
}