aaron/ispc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

fixed cuda kernel

Browse Source
This commit is contained in:
Evghenii
2013-11-13 12:54:52 +01:00
parent 74db8cbab3
commit ca1dbc3d3b
2 changed files with 21 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples_cuda/deferred/kernels.cu
View File

@@ -805,8 +805,8 @@ RenderStatic(InputHeader inputHeaderPtr[],
unsigned int8 framebuffer_g[],
unsigned int8 framebuffer_b[]) {
const InputHeader &inputHeader = *inputHeaderPtr;
const InputDataArrays &inputData = *inputDataPtr;
const InputHeader inputHeader = *inputHeaderPtr;
const InputDataArrays inputData = *inputDataPtr;
int num_groups_x = (inputHeader.framebufferWidth +
MIN_TILE_WIDTH - 1) / MIN_TILE_WIDTH;
@@ -816,7 +816,9 @@ RenderStatic(InputHeader inputHeaderPtr[],
// Launch a task to render each tile, each of which is MIN_TILE_WIDTH
// by MIN_TILE_HEIGHT pixels.
RenderTile<<<dim3(num_groups_x,num_groups_y), 128>>>(num_groups_x, num_groups_y,
inputHeaderPtr, inputDataPtr, visualizeLightCount,
framebuffer_r, framebuffer_g, framebuffer_b);
if (programIndex == 0)
RenderTile<<<num_groups, 128>>>(num_groups_x, num_groups_y,
inputHeaderPtr, inputDataPtr, visualizeLightCount,
framebuffer_r, framebuffer_g, framebuffer_b);
cudaDeviceSynchronize();
}