You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by ma...@apache.org on 2023/03/02 19:59:25 UTC
[tvm] branch main updated: [bugfix] Fix the write buffer scope of `mma_store_impl` (#14174)
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new bd8e7d3bd3 [bugfix] Fix the write buffer scope of `mma_store_impl` (#14174)
bd8e7d3bd3 is described below
commit bd8e7d3bd3b03185a537513ea94157c10f42ab82
Author: Zihao Ye <ex...@outlook.com>
AuthorDate: Fri Mar 3 03:59:14 2023 +0800
[bugfix] Fix the write buffer scope of `mma_store_impl` (#14174)
fix
---
python/tvm/tir/tensor_intrin/cuda.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/python/tvm/tir/tensor_intrin/cuda.py b/python/tvm/tir/tensor_intrin/cuda.py
index 6483b99454..da194f885d 100644
--- a/python/tvm/tir/tensor_intrin/cuda.py
+++ b/python/tvm/tir/tensor_intrin/cuda.py
@@ -392,7 +392,7 @@ def get_mma_store_intrin(dtype, local_size, scope="global"):
a, [WARP_SIZE, local_size], dtype=dtype, scope="warp", offset_factor=1
)
C = T.match_buffer(
- c, [M_DIM, N_DIM], dtype=dtype, scope="global", offset_factor=1, strides=[s0, s1]
+ c, [M_DIM, N_DIM], dtype=dtype, scope=scope, offset_factor=1, strides=[s0, s1]
)
with T.block("root"):