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)	71	237.00	0.91	0	78421.33	267776.00	6.23	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	66	9287.33	35.64	10407903232	64251317.34	30715178.67	13.03	109.60	1120.66	false
maxwell_scudnn_128x128_relu_small_nn	0	251.00	0.96	264470528	480.00	54816.00	12.50	4782.81	1053.67	false
maxwell_scudnn_128x64_relu_interior_nn	2	242.33	0.93	237158400	7162997.33	3209301.33	7.97	22.86	978.64	true
maxwell_scudnn_128x64_relu_medium_nn	0	131.00	0.50	239239168	53.33	320.00	18.70	640819.77	1826.25	false
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	29	2428.00	9.32	4435656704	105960309.33	33249066.67	13.79	31.86	1826.88	false
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	1055.33	4.05	94712832	24404128.00	56672330.66	62.75	1.17	89.75	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*)	1	729.00	2.80	566306304	5291680.00	1169642.67	6.18	87.65	776.83	false
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	17.00	0.07	144598	12352.00	53.33	11.90	11.66	8.51	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	52.67	0.20	200704	4046272.00	1637226.67	70.80	0.04	3.81	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	29	1668.67	6.40	117596160	72526250.67	106852042.67	58.11	0.66	70.47	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	70.33	0.27	4495000	9700544.00	944768.00	39.00	0.42	63.91	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	1	206.33	0.79	0	223488.00	2750272.00	7.35	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	3.00	0.01	1000	6112.00	0.00	12.40	0.16	0.33	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	3.00	0.01	0	1792.00	0.00	10.70	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	540.67	2.08	8931328	54391936.00	19170570.67	81.97	0.12	16.52	true
void op_generic_tensor_kernel<2, float, float, float, 256, (cudnnGenericOp_t)8, (cudnnNanPropagation_t)0, (cudnnDimOrder_t)0, 1>(cudnnTensorStruct, float, cudnnTensorStruct, float const, cudnnTensorStruct, float const*, float, float, float, float, dimArray, reducedDivisorArray, bool)	100	708.67	2.72	29854720	18920053.33	28634368.00	87.75	0.63	42.13	true

Showing 1 to 17 of 17 entries

Download as CSV