Skip to content

Fix LUD kernel syncthreads bug and clean up microbenchmark binaries #77

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

Merged
JRPan merged 1 commit into from
Jan 22, 2026
Merged

Fix LUD kernel syncthreads bug and clean up microbenchmark binaries #77

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions src/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ accelwattch_hw_power: rodinia-3.1_hw_power parboil_hw_power cuda_samples-11.0_hw
#Disable clean for now, It has a bug!
# clean_dragon-naive clean_pannotia clean_proxy-apps

clean: clean_mlperf_inference clean_rodinia_2.0-ft clean_dragon-cdp clean_ispass-2009 clean_lonestargpu-2.0 clean_custom_apps clean_parboil clean_cutlass clean_rodinia-3.1 clean_heterosync clean_UVMSmart_test clean_cuda_samples clean_huggingface
clean: clean_mlperf_inference clean_rodinia_2.0-ft clean_dragon-cdp clean_ispass-2009 clean_lonestargpu-2.0 clean_custom_apps clean_parboil clean_cutlass clean_rodinia-3.1 clean_heterosync clean_UVMSmart_test clean_cuda_samples clean_huggingface clean_GPU_Microbenchmark
clean_accelwattch: clean_rodinia-3.1 clean_parboil clean_cutlass clean_cuda_samples-11.0 clean_cuda_samples_hw_power clean_rodinia-3.1_hw_power clean_parboil_hw_power clean_accelwattch_ubench

clean_data:
Expand Down Expand Up @@ -108,7 +108,7 @@ dragon-cdp: dragon-naive
GPU_Microbenchmark:
mkdir -p $(BINDIR)/$(BINSUBDIR)/
$(SETENV) $(MAKE) $(MAKE_ARGS) -C cuda/GPU_Microbenchmark
cp -r cuda/GPU_Microbenchmark/bin/* $(BINDIR)/$(BINSUBDIR)/
mv cuda/GPU_Microbenchmark/bin/* $(BINDIR)/$(BINSUBDIR)/
clean_GPU_Microbenchmark:
find cuda/GPU_Microbenchmark/ubench -type f -executable -delete

Expand Down
4 changes: 2 additions & 2 deletions src/cuda/GPU_Microbenchmark/common/common.mk
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,11 @@ LIB :=

release:
$(CC) $(NVCC_FLAGS) $(CUOPTS) $(SRC) -o $(EXE) -I$(INCLUDE) -L$(LIB) -lcudart
cp $(EXE) $(BIN_DIR)
mv $(EXE) $(BIN_DIR)

tuner:
$(CC) $(NVCC_FLAGS) $(CUOPTS) -DTUNER $(SRC) -o $(EXE) -I$(INCLUDE) -L$(LIB) -lcudart
cp $(EXE) $(BIN_DIR)
mv $(EXE) $(BIN_DIR)

clean:
rm -f *.o; rm -f $(EXE)
Expand Down
8 changes: 4 additions & 4 deletions src/cuda/rodinia/2.0-ft/lud/lud_kernel.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,14 +22,14 @@ lud_diagonal(float *m, int matrix_dim, int offset)
for(j=0; j < i; j++)
shadow[threadIdx.x][i] -= shadow[threadIdx.x][j]*shadow[j][i];
shadow[threadIdx.x][i] /= shadow[i][i];
}
__syncthreads();

__syncthreads();

if (threadIdx.x>i){
for(j=0; j < i+1; j++)
shadow[i+1][threadIdx.x] -= shadow[i+1][j]*shadow[j][threadIdx.x];

__syncthreads();
}
__syncthreads();
}

/*
Expand Down