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)	0	3.00	0.04	0	938.67	8778.67	7.30	0.00	0.00	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)	44	1894.33	27.81	1549930697	1302560.00	5053568.00	3.34	243.85	818.19	false
void cudnn::detail::pooling_fw_4d_kernel<float, float, cudnn::detail::averpooling_func<float>, 2, false>(cudnnTensorStruct, float const, cudnnTensorStruct, float, cudnnPoolingStruct, float, float, int, cudnn::reduced_divisor, cudnn::reduced_divisor)	7	69.00	1.01	20229646	9557.33	1304618.67	40.69	15.39	293.18	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)	4	31.00	0.46	492352	6634.67	1869589.33	37.97	0.26	15.88	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	26	124.67	1.83	37416960	25493.33	20886506.67	13.83	1.79	300.14	true
void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, long>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_max_op<float const, float const>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const, Eigen::TensorCwiseNullaryOp<Eigen::internal::scalar_constant_op<float const>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, long>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, long>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_max_op<float const, float const>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const, Eigen::TensorCwiseNullaryOp<Eigen::internal::scalar_constant_op<float const>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, long)	44	142.00	2.08	0	1962.67	2036458.67	48.84	0.00	0.00	true
void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 2, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const, Eigen::TensorBroadcastingOp<Eigen::array<long, 2ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, int>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 2, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const, Eigen::TensorBroadcastingOp<Eigen::array<long, 2ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, int)	67	275.00	4.04	2921184	95637.33	208437.34	45.19	9.61	10.62	true
void tensorflow::(anonymous namespace)::GenerateNormalizedProb<float, float>(float const, float const, float const, float, int, int, bool)	0	3.00	0.04	24024	2048.00	42.67	6.20	11.49	8.01	true
void tensorflow::BiasNCHWKernel<float>(int, float const, float const, float*, int, int)	1	11.33	0.17	803817	4640.00	1475178.67	47.14	0.54	70.93	true
void tensorflow::functor::PadInputCustomKernelNCHW<float, 4>(int, float const, tensorflow::functor::Dimension<4>, float, tensorflow::functor::Dimension<4>, tensorflow::functor::Dimension<(4)-(2)>)	4	22.00	0.32	0	105386.67	385386.67	47.40	0.00	0.00	true
void tensorflow::functor::RowReduceKernel<cub::TransformInputIterator<float, tensorflow::(anonymous namespace)::SubtractAndExpFunctor<float, float>, cub::CountingInputIterator<int, long>, long>, float, cub::Sum>(cub::TransformInputIterator<float, tensorflow::(anonymous namespace)::SubtractAndExpFunctor<float, float>, cub::CountingInputIterator<int, long>, long>, float, int, int, cub::Sum, std::iterator_traits<cub::TransformInputIterator<float, tensorflow::(anonymous namespace)::SubtractAndExpFunctor<float, float>, cub::CountingInputIterator<int, long>, long> >::value_type)	0	8.00	0.12	10431	1962.67	128.00	2.30	4.99	1.30	true
void tensorflow::functor::RowReduceKernel<float const, float, cub::Max>(float const, float, int, int, cub::Max, std::iterator_traits<float const*>::value_type)	0	4.00	0.06	0	1450.67	256.00	4.00	0.00	0.00	true
void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const, tensorflow::functor::Dimension<3>, float)	70	536.00	7.87	0	44735104.00	20160970.67	44.62	0.00	0.00	true
void tensorflow::functor::SwapDimension1And2InTensor3UsingTiles<unsigned int, 1024, 1024, 2, false>(unsigned int const, tensorflow::functor::Dimension<3>, unsigned int)	0	6.00	0.09	0	3157.33	468170.67	59.00	0.00	0.00	true
volta_scudnn_128x64_relu_interior_nn_v1	0	17.33	0.25	40140800	11008.00	2279082.67	7.80	17.53	2315.86	true
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	26	1037.33	15.23	1713725440	323680.00	9630528.00	12.98	172.16	1652.05	false

Showing 1 to 16 of 16 entries

Download as CSV