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)	66	323.00	0.93	0	0.00	0.00	6.46	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	61	10488.67	30.18	9517760512	0.00	0.00	13.27	0.00	907.43	true
maxwell_scudnn_128x128_relu_small_nn	0	317.33	0.91	264470528	0.00	0.00	12.50	0.00	833.42	true
maxwell_scudnn_128x64_relu_interior_nn	2	268.67	0.77	237158400	0.00	0.00	9.72	0.00	882.73	true
maxwell_scudnn_128x64_relu_medium_nn	0	179.00	0.52	239239168	0.00	0.00	21.10	0.00	1336.53	true
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	29	3231.34	9.30	4435656704	0.00	0.00	14.37	0.00	1372.70	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)	100	1206.33	3.47	14927360	0.00	0.00	51.40	0.00	12.37	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)	101	1489.67	4.29	94712832	0.00	0.00	69.52	0.00	63.58	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*)	3	1470.00	4.23	834791936	0.00	0.00	7.24	0.00	567.89	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)	2	535.33	1.54	314873856	0.00	0.00	18.27	0.00	588.18	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	24.67	0.07	144598	0.00	0.00	11.90	0.00	5.86	true
void cudnn::detail::pooling_fw_4d_kernel<float, float, cudnn::detail::maxpooling_func<float, (cudnnNanPropagation_t)0>, 0, false>(cudnnTensorStruct, float const, cudnnTensorStruct, float, cudnnPoolingStruct, float, float, int, cudnn::reduced_divisor, cudnn::reduced_divisor)	0	61.33	0.18	200704	0.00	0.00	69.00	0.00	3.27	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	29	2582.67	7.43	117596160	0.00	0.00	49.58	0.00	45.53	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	87.67	0.25	4495000	0.00	0.00	48.50	0.00	51.27	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	3	649.67	1.87	0	0.00	0.00	5.18	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	5.33	0.02	1000	0.00	0.00	12.40	0.00	0.19	true
void mshadow::cuda::MapPlanKernel<mshadow::sv::saveto, 8, mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 1, float>, float>, mshadow::expr::Plan<mshadow::expr::ScalarExp<float>, float> >(mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 1, float>, float>, int, mshadow::Shape<2>, mshadow::expr::Plan<mshadow::expr::ScalarExp<float>, float>)	0	5.00	0.01	0	0.00	0.00	11.00	0.00	0.00	true
void mxnet::op::mxnet_op::mxnet_generic_kernel<mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::plus, 1>, float, float, float>(int, float, float, float)	32	711.00	2.05	8931328	0.00	0.00	81.84	0.00	12.56	true

Showing 1 to 18 of 18 entries

Download as CSV