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)	96	433.00	0.88	0	0.00	0.00	6.15	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	91	13243.33	27.05	13489373184	0.00	0.00	13.20	0.00	1018.58	true
maxwell_scudnn_128x128_relu_small_nn	0	268.33	0.55	264470528	0.00	0.00	12.50	0.00	985.61	true
maxwell_scudnn_128x64_relu_interior_nn	2	236.00	0.48	237158400	0.00	0.00	9.72	0.00	1004.91	true
maxwell_scudnn_128x64_relu_medium_nn	0	149.67	0.31	239239168	0.00	0.00	21.10	0.00	1598.48	true
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	46	4192.34	8.56	6819561472	0.00	0.00	14.55	0.00	1626.67	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)	151	1464.66	2.99	21249536	0.00	0.00	48.58	0.00	14.51	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)	152	1831.33	3.74	134710272	0.00	0.00	69.00	0.00	73.56	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	1319.33	2.69	834791936	0.00	0.00	7.17	0.00	632.74	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)	6	1044.34	2.13	734705664	0.00	0.00	18.44	0.00	703.52	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	21.00	0.04	144688	0.00	0.00	12.00	0.00	6.89	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	54.00	0.11	200704	0.00	0.00	68.90	0.00	3.72	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	46	3381.66	6.91	170811392	0.00	0.00	49.87	0.00	50.51	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	78.67	0.16	4495000	0.00	0.00	48.60	0.00	57.14	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	3	544.00	1.11	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	4.00	0.01	1000	0.00	0.00	12.40	0.00	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	4.00	0.01	0	0.00	0.00	11.10	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	899.00	1.84	13146112	0.00	0.00	82.09	0.00	14.62	true

Showing 1 to 18 of 18 entries

Download as CSV