youngkingdom/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 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 b353e36fe8.

* 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
2025-01-24 23:44:06 -08:00
committed by GitHub
parent 9eb01fa0b0
commit 389e493055
290 changed files with 91223 additions and 292 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/65_distributed_gemm/65_distributed_gemm.cu
View File

@ -133,7 +133,8 @@ using namespace cute;
using TP = _8;
static constexpr int TP_ = TP{};
#if (defined(CUTLASS_ARCH_MMA_SM90_SUPPORTED) && (__CUDACC_VER_MAJOR__ >= 12) && (__CUDACC_VER_MINOR__ >= 4))
#if defined(CUTLASS_ARCH_MMA_SM90_SUPPORTED) && \
(__CUDACC_VER_MAJOR__ > 12 || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ >= 4))
// Distributed GEMM tiling/sharding schedule
// Choices:
@ -344,7 +345,8 @@ struct Result {
};
#if (defined(CUTLASS_ARCH_MMA_SM90_SUPPORTED) && (__CUDACC_VER_MAJOR__ >= 12) && (__CUDACC_VER_MINOR__ >= 4))
#if defined(CUTLASS_ARCH_MMA_SM90_SUPPORTED) && \
(__CUDACC_VER_MAJOR__ > 12 || (__CUDACC_VER_MAJOR__ == 12 && __CUDACC_VER_MINOR__ >= 4))
/////////////////////////////////////////////////////////////////////////////////////////////////
/// GEMM setup and evaluation