Lines Matching refs:cuStream
666 cudaStream_t cuStream; member
696 cuStream(_cuStream), in applyHaarClassifierAnchorParallelFunctor()
724 <<<gridConf, blockConf, 0, cuStream>>> in call()
742 … dim3 gridConf, dim3 blockConf, cudaStream_t cuStream, in applyHaarClassifierAnchorParallelDynTemplate() argument
753 applyHaarClassifierAnchorParallelFunctor functor(gridConf, blockConf, cuStream, in applyHaarClassifierAnchorParallelDynTemplate()
776 cudaStream_t cuStream; member
806 cuStream(_cuStream), in applyHaarClassifierClassifierParallelFunctor()
832 <<<gridConf, blockConf, 0, cuStream>>> in call()
848 … dim3 gridConf, dim3 blockConf, cudaStream_t cuStream, in applyHaarClassifierClassifierParallelDynTemplate() argument
858 applyHaarClassifierClassifierParallelFunctor functor(gridConf, blockConf, cuStream, in applyHaarClassifierClassifierParallelDynTemplate()
879 cudaStream_t cuStream; member
896 cuStream(_cuStream), in initializeMaskVectorFunctor()
912 <<<gridConf, blockConf, 0, cuStream>>> in call()
923 dim3 gridConf, dim3 blockConf, cudaStream_t cuStream, in initializeMaskVectorDynTemplate() argument
929 initializeMaskVectorFunctor functor(gridConf, blockConf, cuStream, in initializeMaskVectorDynTemplate()
973 cudaStream_t cuStream) in ncvApplyHaarClassifierCascade_device() argument
1162 … 0, cudaMemcpyHostToDevice, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1163 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1178 gridInit, blockInit, cuStream, in ncvApplyHaarClassifierCascade_device()
1187 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1189 … 0, cudaMemcpyDeviceToHost, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1190 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1212 … 0, cudaMemcpyHostToDevice, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1213 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1227 cuStream, in ncvApplyHaarClassifierCascade_device()
1243 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1245 … 0, cudaMemcpyDeviceToHost, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1246 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1277 … 0, cudaMemcpyHostToDevice, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1278 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1297 cuStream, in ncvApplyHaarClassifierCascade_device()
1313 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1315 … 0, cudaMemcpyDeviceToHost, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1316 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1340 … 0, cudaMemcpyHostToDevice, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1341 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1358 cuStream, in ncvApplyHaarClassifierCascade_device()
1374 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1376 … 0, cudaMemcpyDeviceToHost, cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1377 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1394 d_vecPixelMaskTmp.copySolid(d_vecPixelMask, cuStream); in ncvApplyHaarClassifierCascade_device()
1395 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1402 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvApplyHaarClassifierCascade_device()
1491 cudaStream_t cuStream) in ncvGrowDetectionsVector_device() argument
1527 growDetectionsKernel<<<grid, block, 0, cuStream>>>(pixelMask.ptr(), numDetsToCopy, in ncvGrowDetectionsVector_device()
1564 cudaStream_t cuStream) in ncvDetectObjectsMultiScale_device() argument
1759 gpuAllocator, cpuAllocator, devProp, cuStream); in ncvDetectObjectsMultiScale_device()
1774 cuStream); in ncvDetectObjectsMultiScale_device()
1786 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvDetectObjectsMultiScale_device()
1787 ncvStat = d_hypothesesIntermediate.copySolid(h_hypothesesIntermediate, cuStream, in ncvDetectObjectsMultiScale_device()
1790 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvDetectObjectsMultiScale_device()
1816 … ncvStat = h_hypothesesIntermediate.copySolid(d_dstRects, cuStream, sizeof(NcvRect32u)); in ncvDetectObjectsMultiScale_device()
1849 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvDetectObjectsMultiScale_device()
1850 ncvStat = d_hypothesesIntermediate.copySolid(h_hypothesesIntermediate, cuStream, in ncvDetectObjectsMultiScale_device()
1853 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvDetectObjectsMultiScale_device()
1872 ncvStat = h_hypothesesIntermediate.copySolid(d_dstRects, cuStream, in ncvDetectObjectsMultiScale_device()
1880 ncvAssertCUDAReturn(cudaStreamSynchronize(cuStream), NCV_CUDA_ERROR); in ncvDetectObjectsMultiScale_device()
1883 d_dstRects.ptr(), dstNumRects, 255, cuStream); in ncvDetectObjectsMultiScale_device()