Skip to content

GitLab

"examples/cpp/vscode:/vscode.git/clone" did not exist on "35d644628fd31b1df00e2bc5b601b89c5fd335c6"
Commit 38bada23 authored by Jie's avatar Jie
Browse files

patching grid reduction to be volta-safe

parent 438f6f9f
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
csrc/welford.cu
View file @ 38bada23
...@@ -508,6 +508,7 @@ welford_kernel_c_last( ...@@ -508,6 +508,7 @@ welford_kernel_c_last(
} }
__threadfence(); __threadfence();
__syncthreads(); // ensuring writes to staging_ is visible to all blocks
__shared__ bool is_last_block_done; __shared__ bool is_last_block_done;
// mark block done // mark block done
...@@ -724,6 +725,7 @@ __global__ void reduce_bn_c_last_kernel( ...@@ -724,6 +725,7 @@ __global__ void reduce_bn_c_last_kernel(
} }
__threadfence(); __threadfence();
__syncthreads(); // ensuring writes to staging_ is visible to all blocks
__shared__ bool is_last_block_done; __shared__ bool is_last_block_done;
// mark block done // mark block done
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment