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)	105	321.67	0.87	0	107072.00	322453.33	5.89	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	100	13638.33	36.75	14850195456	92600192.00	38985173.33	12.97	112.86	1088.86	false
maxwell_scudnn_128x128_relu_small_nn	0	269.00	0.72	264470528	0.00	92416.00	12.50	2861.74	983.16	false
maxwell_scudnn_128x64_relu_interior_nn	2	242.67	0.65	237158400	6699093.33	2944490.67	7.97	24.59	977.30	true
maxwell_scudnn_128x64_relu_medium_nn	0	131.33	0.35	239239168	0.00	213.33	19.20	1121435.35	1821.62	false
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	46	3749.67	10.11	6819561472	169032469.34	52561226.67	13.87	30.78	1818.71	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)	152	1504.67	4.06	134710272	32030741.33	80927968.00	61.76	1.19	89.53	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	722.00	1.95	566306304	5121984.00	1166880.00	6.20	90.05	784.36	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	0.05	144688	12181.33	7669.33	12.00	7.29	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	52.00	0.14	200704	4045322.67	1635925.33	71.00	0.04	3.86	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	46	2379.33	6.41	170811392	115702848.00	171986634.67	58.08	0.59	71.79	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	69.67	0.19	4495000	9705429.33	938762.67	39.00	0.42	64.52	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	1	206.33	0.56	0	205098.67	2571018.67	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	6080.00	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	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)	49	768.00	2.07	13146112	76774848.00	25764842.67	81.43	0.13	17.12	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)	151	991.33	2.67	42499072	22695552.00	37403072.00	87.00	0.71	42.87	true

Showing 1 to 17 of 17 entries

Download as CSV