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)	37	125.67	0.90	0	44106.66	252618.67	6.61	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	32	4500.00	32.17	5833359360	30732170.67	29301952.00	13.60	97.17	1296.30	false
maxwell_scudnn_128x128_relu_small_nn	0	249.33	1.78	264470528	0.00	59104.00	12.50	4474.66	1060.71	false
maxwell_scudnn_128x64_relu_interior_nn	2	240.67	1.72	237158400	7496768.00	3312309.33	7.89	21.94	985.43	true
maxwell_scudnn_128x64_relu_medium_nn	0	131.00	0.94	239239168	0.00	320.00	19.00	747622.40	1826.25	false
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	12	1087.00	7.77	2054242304	24325717.33	11958656.00	15.43	56.62	1889.83	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)	50	684.66	4.89	62333952	23597024.00	39992160.00	69.92	0.98	91.04	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	736.00	5.26	566306304	5167274.67	1165856.00	6.18	89.42	769.44	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	0.12	144028	12320.00	426.67	11.90	11.30	8.47	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	52.00	0.37	200704	4048842.67	1636469.33	70.90	0.04	3.86	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	12	756.00	5.40	52977664	18534794.67	26920234.67	56.88	1.17	70.08	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	70.00	0.50	4495000	9702997.33	944469.33	39.00	0.42	64.21	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	1	206.00	1.47	0	223552.00	2573632.00	7.37	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	3.33	0.02	1000	6112.00	0.00	12.40	0.16	0.30	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	0.02	0	1440.00	0.00	10.60	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)	15	387.33	2.77	5519360	39583317.33	17625717.33	83.89	0.10	14.25	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)	49	468.33	3.35	19618816	18930346.67	25614144.00	90.30	0.44	41.89	true

Showing 1 to 17 of 17 entries

Download as CSV