NASP/cuda-samples
85
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-10-25 22:28:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Apply consistent code formatting across the repo. Add clang-format and pre-commit hooks.

Browse Source
This commit is contained in:
Rob Armstrong
2025-03-27 10:30:07 -07:00
parent 2cd58fbc9a
commit ceab6e8bcc
782 changed files with 107230 additions and 106548 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
Samples/0_Introduction/simpleCUDA2GL/README.md
View File

@@ -34,4 +34,3 @@ Download and install the [CUDA Toolkit 12.5](https://developer.nvidia.com/cuda-d
Make sure the dependencies mentioned in [Dependencies]() section above are installed.
## References (for more details)

807
Samples/0_Introduction/simpleCUDA2GL/main.cpp
View File

File diff suppressed because it is too large Load Diff

38
Samples/0_Introduction/simpleCUDA2GL/simpleCUDA2GL.cu
View File

@@ -35,28 +35,30 @@ __device__ float clamp(float x, float a, float b) { return max(a, min(b, x)); }
__device__ int clamp(int x, int a, int b) { return max(a, min(b, x)); }
// convert floating point rgb color to 8-bit integer
__device__ int rgbToInt(float r, float g, float b) {
r = clamp(r, 0.0f, 255.0f);
g = clamp(g, 0.0f, 255.0f);
b = clamp(b, 0.0f, 255.0f);
return (int(b) << 16) | (int(g) << 8) | int(r);
__device__ int rgbToInt(float r, float g, float b)
{
r = clamp(r, 0.0f, 255.0f);
g = clamp(g, 0.0f, 255.0f);
b = clamp(b, 0.0f, 255.0f);
return (int(b) << 16) | (int(g) << 8) | int(r);
}
__global__ void cudaProcess(unsigned int *g_odata, int imgw) {
extern __shared__ uchar4 sdata[];
__global__ void cudaProcess(unsigned int *g_odata, int imgw)
{
extern __shared__ uchar4 sdata[];
int tx = threadIdx.x;
int ty = threadIdx.y;
int bw = blockDim.x;
int bh = blockDim.y;
int x = blockIdx.x * bw + tx;
int y = blockIdx.y * bh + ty;
int tx = threadIdx.x;
int ty = threadIdx.y;
int bw = blockDim.x;
int bh = blockDim.y;
int x = blockIdx.x * bw + tx;
int y = blockIdx.y * bh + ty;
uchar4 c4 = make_uchar4((x & 0x20) ? 100 : 0, 0, (y & 0x20) ? 100 : 0, 0);
g_odata[y * imgw + x] = rgbToInt(c4.z, c4.y, c4.x);
uchar4 c4 = make_uchar4((x & 0x20) ? 100 : 0, 0, (y & 0x20) ? 100 : 0, 0);
g_odata[y * imgw + x] = rgbToInt(c4.z, c4.y, c4.x);
}
extern "C" void launch_cudaProcess(dim3 grid, dim3 block, int sbytes,
unsigned int *g_odata, int imgw) {
cudaProcess<<<grid, block, sbytes>>>(g_odata, imgw);
extern "C" void launch_cudaProcess(dim3 grid, dim3 block, int sbytes, unsigned int *g_odata, int imgw)
{
cudaProcess<<<grid, block, sbytes>>>(g_odata, imgw);
}