leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 29 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
2025-03-21 01:52:23 -04:00
committed by GitHub
co-authored by yuzhai Haicheng Wu Haicheng Wu
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
examples/63_hopper_gemm_with_weight_prefetch/kernel/sm90_gemm_tma_warpspecialized_with_prefetch.hpp
+2 -2
View File
@@ -362,11 +362,11 @@ public:
using ClusterSyncWithPrefetchBarrier = typename cutlass::arch::NamedBarrier;
auto prefetcher_arrive_barrier = ClusterSyncWithPrefetchBarrier(
blockDim.x * blockDim.y * blockDim.z,
/*reserved_named_barriers_*/ 14);
/*id*/ 0);
// Prefetcher warp doesn't arrive on this barrier.
auto cluster_arrive_barrier = ClusterSyncWithPrefetchBarrier(
blockDim.x * blockDim.y * blockDim.z - NumThreadsPerWarp,
/*reserved_named_barriers_*/ 15);
/*id*/ 1);
if (warp_group_role == WarpGroupRole::Producer && producer_warp_role == ProducerWarpRole::PrefetchMK) {
__syncwarp();