Skip to content

Update to stable NVTX release #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Update to stable NVTX release #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2c2325b
Update Synccheck/divergent_threads.cu
aladram May 14, 2025
b2d2427
Update NvtxNaming/README.md
evanramos-nvidia May 14, 2025
6280b6c
Update NVTX submodule to release-v3 branch
evanramos-nvidia May 14, 2025
c3d264e
Update .gitignore
evanramos-nvidia May 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
*.a
*.o
*.d
*.so
*.so.*
*.swp
Expand Down
2 changes: 1 addition & 1 deletion .gitmodules
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
[submodule "NVTX"]
path = NVTX
url = https://github.com/NVIDIA/NVTX
branch = dev-mem-api
branch = release-v3
2 changes: 1 addition & 1 deletion NVTX
Open in desktop
Submodule NVTX updated 715 files
2 changes: 1 addition & 1 deletion NvtxNaming/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ $ compute-sanitizer --nvtx=yes --leak-check=full --destroy-on-device-error=kerne
=========
========= LEAK SUMMARY: 1 bytes leaked in 1 allocations
========= ERROR SUMMARY: 1 error
$ compute-sanitizer --nvtx=yes --tool=initcheck --track-unused-memory=yes --destroy-on-device-error=kernel --show-backtrace=no ./NvtxNaming
$ compute-sanitizer --nvtx=yes --tool=initcheck --track-unused-memory --destroy-on-device-error=kernel --show-backtrace=no ./NvtxNaming
========= COMPUTE-SANITIZER
========= Unused memory in allocation 0x7efc4d000000 called My allocation of size 1
========= Not written any memory.
Expand Down
15 changes: 13 additions & 2 deletions Synccheck/divergent_threads.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,12 @@ static constexpr int Size = (NumThreads * DataBlocks) - 16;

__shared__ int smem[NumThreads];

__device__ __noinline__
void outlineSync()
{
__syncthreads();
}

__global__
void myKernel(int *data_in, int *sum_out)
{
Expand All @@ -51,11 +57,16 @@ void myKernel(int *data_in, int *sum_out)
if (offset < Size)
{
smem[tx] += data_in[offset];
__syncthreads();
outlineSync();
}
else
{
// We still need to wait before we continue
outlineSync();
}
}

if (tx == 0)
if (tx == blockDim.x - 1)
{
*sum_out = 0;
for (int i = 0; i < NumThreads; ++i)
Expand Down