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) | 10 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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*) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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) | 154 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| 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) | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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) | 3 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>) | 36 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, int>, 16, Eigen::MakePointer> const, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const> const> const, Eigen::GpuDevice>, long>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, int>, 16, Eigen::MakePointer> const, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, long>, 16, Eigen::MakePointer> const> const> const, Eigen::GpuDevice>, long) | 39 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseUnaryOp<Eigen::internal::scalar_left<float, float, Eigen::internal::scalar_product_op<float, float> >, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, int>, 16, Eigen::MakePointer> const> const> const, Eigen::GpuDevice>, int>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 1, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseUnaryOp<Eigen::internal::scalar_left<float, float, Eigen::internal::scalar_product_op<float, float> >, Eigen::TensorMap<Eigen::Tensor<float const, 1, 1, int>, 16, Eigen::MakePointer> const> const> const, Eigen::GpuDevice>, int) | 38 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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) | 189 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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) | 203 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void fft1d_c2r_32<float2, float, float, false, true, false, false>(float*, float2 const*, int, int3, int3, int2, int, float, float, float*, float*) | 19 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void fft1d_c2r_32<float2, float, float, false, true, false, true>(float*, float2 const*, int, int3, int3, int2, int, float, float, float*, float*) | 19 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void fft1d_r2c_32<float, float, float2, false, false>(float2*, float const*, int, int3, int3, int2, int2) | 19 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void fft1d_r2c_32<float, float, float2, false, true>(float2*, float const*, int, int3, int3, int2, int2) | 19 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void fft1d_r2c_32<float, float, float2, true, false>(float2*, float const*, int, int3, int3, int2, int2) | 39 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void gemv2N_kernel<int, int, float, float, float, 128, 8, 4, 4, 1, cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float> >(cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float>) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const*, float*, int) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::(anonymous namespace)::GenerateNormalizedProb<float, float>(float const*, float const*, float const*, float*, int, int, bool) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::BiasNCHWKernel<float>(int, float const*, float const*, float*, int, int) | 39 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::BiasNHWCKernel<float>(int, float const*, float const*, float*, int) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::functor::BlockReduceKernel<int*, int*, 256, tensorflow::functor::Prod<int> >(int*, int*, int, tensorflow::functor::Prod<int>, std::iterator_traits<int*>::value_type) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | 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 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const*, tensorflow::functor::Dimension<3>, float*) | 243 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| void tensorflow::functor::SwapDimension1And2InTensor3UsingTiles<unsigned int, 1024, 1024, 2, false>(unsigned int const*, tensorflow::functor::Dimension<3>, unsigned int*) | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| volta_gcgemm_64x32_nt | 39 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| volta_scudnn_128x32_relu_interior_nn_v1 | 0 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| volta_scudnn_128x64_relu_interior_nn_v1 | 9 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
| volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1 | 36 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | NaN | 0.00 | NaN | true |
Showing 1 to 29 of 29 entries