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)	41	84.00	0.36	0	0.00	0.00	0.00	0.00	0.00	true
maxwell_scudnn_128x128_relu_interior_nn	37	3022.33	12.88	5755994112	0.00	0.00	0.00	0.00	1904.49	true
maxwell_scudnn_128x64_relu_interior_nn	2	169.33	0.72	237158400	0.00	0.00	0.00	0.00	1400.54	true
maxwell_scudnn_128x64_relu_medium_nn	0	61.17	0.26	239239168	0.00	0.00	0.00	0.00	3911.25	true
maxwell_scudnn_winograd_128x128_ldg1_ldg4_tile148n_nt	29	2264.33	9.65	4435656704	0.00	0.00	0.00	0.00	1958.92	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)	101	602.67	2.57	94712832	0.00	0.00	0.00	0.00	157.16	true
void cudnn::detail::explicit_convolve_sgemm<float, int, 1024, 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	850.50	3.63	806530560	0.00	0.00	0.00	0.00	948.30	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*)	22	2132.67	9.09	2849086464	0.00	0.00	0.00	0.00	1335.93	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)	4	535.67	2.28	818391040	0.00	0.00	0.00	0.00	1527.80	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	11.33	0.05	144598	0.00	0.00	0.00	0.00	12.76	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	19.00	0.08	200704	0.00	0.00	0.00	0.00	10.56	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	29	485.67	2.07	117596160	0.00	0.00	0.00	0.00	242.13	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	27.67	0.12	4495000	0.00	0.00	0.00	0.00	162.47	true
void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const, float, int)	26	2801.67	11.94	0	0.00	0.00	0.00	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	0.00	0.00	0.00	0.00	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	2.83	0.01	0	0.00	0.00	0.00	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	205.00	0.87	8931328	0.00	0.00	0.00	0.00	43.57	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	466.00	1.99	29854720	0.00	0.00	0.00	0.00	64.07	true

Showing 1 to 18 of 18 entries

Download as CSV