Navigation :

GPU Kernel Information Aggregated by Name

Search:

kernel_name	kernel_count	kernel_duration (us)	model_duration_percentage	kernel_flops	kernel_dram_read_bytes	kernel_dram_write_bytes	kernel_achieved_occupancy (%)	kernel_arithmetic_intensity (flops/byte)	kernel_arithmetic_throughput (GFlops)	kernel_memory_bound

kernel_name	kernel_count	kernel_duration (us)	model_duration_percentage	kernel_flops	kernel_dram_read_bytes	kernel_dram_write_bytes	kernel_achieved_occupancy (%)	kernel_arithmetic_intensity (flops/byte)	kernel_arithmetic_throughput (GFlops)	kernel_memory_bound
cudnn::maxwell::gemm::computeOffsetsKernel(cudnn::maxwell::gemm::ComputeOffsetsParams)	123	629.49	0.86	0	0.00	0.00	10.80	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	7	647.17	0.88	229834752	0.00	0.00	12.42	0.00	355.14	true
maxwell_scudnn_128x32_relu_interior_nn	0	44.33	0.06	13647872	0.00	0.00	25.00	0.00	307.85	true
maxwell_scudnn_128x32_relu_small_nn	112	1939.37	2.65	323174400	0.00	0.00	12.02	0.00	166.64	true
maxwell_scudnn_128x64_relu_interior_nn	1	78.67	0.11	40140800	0.00	0.00	9.75	0.00	510.26	true
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148t_nt	1983	29286.61	39.98	1832910848	0.00	0.00	12.79	0.00	62.59	true
void cudnn::detail::activation_fw_4d_kernel<float, float, 128, 1, 4, cudnn::detail::relu_func<float, (cudnnNanPropagation_t)0, false> >(cudnnTensorStruct, float const, cudnnTensorStruct, float, float, float, int, float)	26	252.17	0.34	2521344	0.00	0.00	39.10	0.00	10.00	true
void cudnn::detail::bn_fw_inf_1C11_kernel_NCHW<float, float, true, 1>(float, float, cudnnTensorStruct, float const, cudnnTensorStruct, float, cudnnTensorStruct, float const, float const, float const, float const, float)	26	307.67	0.42	15666432	0.00	0.00	51.85	0.00	50.92	true
void cudnn::detail::explicit_convolve_sgemm<float, int, 128, 5, 5, 3, 3, 3, 0, true>(int, int, int, float const, int, float const, int, float, kernel_conv_params, int, int, float, float, int, float, float*)	383	4452.74	6.08	46174976	0.00	0.00	3.10	0.00	10.37	true
void cudnn::detail::implicit_convolve_sgemm<float, float, 1024, 5, 5, 3, 3, 3, 1, true, false, true>(int, int, int, float const, int, float, float, kernel_conv_params, int, float, float, int, float, float*, int, int)	1	226.17	0.31	50381824	0.00	0.00	6.20	0.00	222.76	true
void cudnn::detail::pooling_fw_4d_kernel<float, float, cudnn::detail::averpooling_func<float>, 1, false>(cudnnTensorStruct, float const, cudnnTensorStruct, float, cudnnPoolingStruct, float, float, int, cudnn::reduced_divisor, cudnn::reduced_divisor)	0	27.00	0.04	32287	0.00	0.00	10.90	0.00	1.20	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	1983	15478.77	21.13	29458432	0.00	0.00	6.20	0.00	1.90	true
void gemv2T_kernel_val<int, int, float, float, float, 128, 16, 2, 2, false, cublasGemvParams<cublasGemvTensor<float const>, cublasGemvTensor<float>, float> >(cublasGemvParams<cublasGemvTensor<float const>, cublasGemvTensor<float>, float>, float, float)	0	33.83	0.05	1135000	0.00	0.00	48.10	0.00	33.55	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	383	4068.74	5.55	0	0.00	0.00	9.20	0.00	0.00	true
void mshadow::cuda::MapPlanKernel<mshadow::sv::plusto, 8, mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 2, float>, float>, mshadow::expr::Plan<mshadow::expr::Broadcast1DExp<mshadow::Tensor<mshadow::gpu, 1, float>, float, 2, 1>, float> >(mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 2, float>, float>, int, mshadow::Shape<2>, mshadow::expr::Plan<mshadow::expr::Broadcast1DExp<mshadow::Tensor<mshadow::gpu, 1, float>, float, 2, 1>, float>)	0	5.50	0.01	1000	0.00	0.00	12.40	0.00	0.18	true

Showing 1 to 15 of 15 entries

Download as CSV