GPU Kernel Information Aggregated by Name
| 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 | 2.00 | 0.01 | 0 | 0.00 | 0.00 | 0.00 | 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) | 2 | 3193.33 | 9.79 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 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 | 60.00 | 0.18 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
| void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>) | 11 | 336.33 | 1.03 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 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) | 14 | 172.67 | 0.53 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
| void tensorflow::BiasNCHWKernel<float>(int, float const*, float const*, float*, int, int) | 15 | 214.33 | 0.66 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
| void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const*, tensorflow::functor::Dimension<3>, float*) | 15 | 24958.67 | 76.49 | 0 | 0.00 | 0.00 | 0.00 | 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 | 0.02 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
| volta_scudnn_128x32_relu_small_nn_v1 | 0 | 40.67 | 0.12 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
| volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1 | 11 | 2373.00 | 7.27 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | true |
Showing 1 to 10 of 10 entries