AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SWDEV-339113 - Update sampl codes with correct kernel coordinate (#2704)

Browse Source 
Change-Id: Ibfc0fd285441cd3d79b312d2b739729a039a6f84
This commit is contained in:
ROCm CI Service Account
2022-06-02 17:07:52 +05:30
committed by GitHub
parent 7b0ed9e8d3
commit 5da168300f
14 changed files with 47 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
samples/2_Cookbook/7_streams/stream.cpp
+4 -4
View File
@@ -37,8 +37,8 @@ __global__ void matrixTranspose_static_shared(float* out, float* in,
const int width) {
__shared__ float sharedMem[WIDTH * WIDTH];
int x = hipBlockDim_x * hipBlockIdx_x + hipThreadIdx_x;
int y = hipBlockDim_y * hipBlockIdx_y + hipThreadIdx_y;
int x = blockDim.x * blockIdx.x + threadIdx.x;
int y = blockDim.y * blockIdx.y + threadIdx.y;
sharedMem[y * width + x] = in[x * width + y];
@@ -51,8 +51,8 @@ __global__ void matrixTranspose_dynamic_shared(float* out, float* in,
const int width) {
extern __shared__ float sharedMem[];
int x = hipBlockDim_x * hipBlockIdx_x + hipThreadIdx_x;
int y = hipBlockDim_y * hipBlockIdx_y + hipThreadIdx_y;
int x = blockDim.x * blockIdx.x + threadIdx.x;
int y = blockDim.y * blockIdx.y + threadIdx.y;
sharedMem[y * width + x] = in[x * width + y];