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::gemm::computeOffsetsKernel(cudnn::gemm::ComputeOffsetsParams)	4	16.67	0.19	0	1792.00	29013.33	6.06	0.00	0.00	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)	50	318.67	3.68	62333952	2314730.67	27837536.00	26.31	2.07	195.61	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)	34	2124.00	24.52	5108182528	64023082.67	22062677.33	5.30	59.34	2404.98	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	8.67	0.10	144028	3754.67	0.00	11.80	38.36	16.62	false
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	9.33	0.11	200704	5333.33	1144288.00	53.90	0.17	21.50	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	12	152.00	1.75	52977664	33162325.33	47198773.33	39.06	0.66	348.54	true
void gemv2T_kernel_val<int, int, float, float, float, 128, 16, 4, 4, false, cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float> >(cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float>, float, float)	0	18.00	0.21	4431000	8196416.00	964053.33	9.80	0.48	246.17	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	4.00	0.05	1000	5760.00	0.00	12.20	0.17	0.25	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	0.03	0	224.00	0.00	11.90	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	95.33	1.10	5519360	17309685.33	7716874.67	57.20	0.22	57.90	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	231.00	2.67	19618816	161920.00	7398954.67	51.31	2.59	84.93	true
volta_scudnn_128x64_relu_interior_nn_v1	3	97.00	1.12	425984000	272000.00	10454976.00	8.07	39.71	4391.59	false
volta_scudnn_128x64_relu_small_nn_v1	0	143.67	1.66	264470528	600352.00	172096.00	6.20	342.38	1840.86	false
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	12	735.00	8.49	2055782400	33997973.33	14390058.67	12.50	42.49	2796.99	false

Showing 1 to 14 of 14 entries

Download as CSV