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

update 3.8 v2 (#2112)

Browse Source 
* update 3.8 v2

* update 3.8

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
This commit is contained in:
Yujia Zhai
2025-02-19 19:03:14 -08:00
committed by GitHub
parent e9627ce55b
commit b84e9802d8
166 changed files with 3986 additions and 4037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/util/include/cutlass/util/reference/device/tensor_compare.h
View File

@@ -138,7 +138,6 @@ bool BlockCompareEqual(
if (result != cudaSuccess) {
throw std::runtime_error("Failed to query occupancy.");
}
// Limit block size. This has the effect of increasing the number of items processed by a
// single thread and reduces the impact of initialization overhead.
block_size = (block_size < 128 ? block_size : 128);
@@ -205,7 +204,6 @@ bool BlockCompareRelativelyEqual(
if (result != cudaSuccess) {
throw std::runtime_error("Failed to query occupancy.");
}
// Limit block size. This has the effect of increasing the number of items processed by a
// single thread and reduces the impact of initialization overhead.
block_size = (block_size < 128 ? block_size : 128);

2
tools/util/include/cutlass/util/reference/device/tensor_foreach.h
View File

@@ -61,7 +61,6 @@ struct TensorForEach {
if (result != cudaSuccess) {
throw std::runtime_error("Failed to query occupancy.");
}
// Limit block size. This has the effect of increasing the number of items processed by a
// single thread and reduces the impact of initialization overhead.
block_size = (block_size < 128 ? block_size : 128);
@@ -124,7 +123,6 @@ struct BlockForEach {
if (result != cudaSuccess) {
throw std::runtime_error("Failed to query occupancy.");
}
// Limit block size. This has the effect of increasing the number of items processed by a
// single thread and reduces the impact of initialization overhead.
block_size = (block_size < 128 ? block_size : 128);