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
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)	56	3040.33	30.87	4726873065	14298005.33	16504789.33	3.36	153.46	1554.72	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)	9	110.00	1.12	44446259	19520.00	4530485.33	48.73	9.77	404.06	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	32.00	0.32	708640	315541.33	3746368.00	47.02	0.17	22.14	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	11	84.67	0.86	24053760	9838464.00	21527082.67	31.53	0.77	284.10	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)	62	233.67	2.37	0	18229.33	10040320.00	51.43	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)	93	399.33	4.05	8967488	3189472.00	6778997.34	48.74	0.90	22.46	true
void fft1d_c2r_32<float2, float, float, false, true, false, false>(float, float2 const, int, int3, int3, int2, int, float, float, float, float)	12	74.00	0.75	12718720	181290.67	3948693.33	1.84	3.08	171.87	true
void fft1d_c2r_32<float2, float, float, false, true, false, true>(float, float2 const, int, int3, int3, int2, int, float, float, float, float)	12	77.00	0.78	12718720	141632.00	4146698.67	1.85	2.97	165.18	true
void fft1d_r2c_32<float, float, float2, false, false>(float2, float const, int, int3, int3, int2, int2)	12	172.00	1.75	12781824	1447328.00	5386645.33	1.79	1.87	74.31	true
void fft1d_r2c_32<float, float, float2, false, true>(float2, float const, int, int3, int3, int2, int2)	12	127.67	1.30	12781824	1294944.00	6291733.33	1.79	1.68	100.12	true
void fft1d_r2c_32<float, float, float2, true, false>(float2, float const, int, int3, int3, int2, int2)	25	321.67	3.27	262471680	35136.00	71980277.33	13.99	3.64	815.97	true
void tensorflow::(anonymous namespace)::GenerateNormalizedProb<float, float>(float const, float const, float const, float, int, int, bool)	0	3.67	0.04	24024	2304.00	640.00	6.20	8.16	6.55	true
void tensorflow::BiasNCHWKernel<float>(int, float const, float const, float*, int, int)	0	4.00	0.04	1001	6304.00	128.00	47.60	0.16	0.25	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	0.08	10431	6720.00	0.00	2.40	1.55	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	4.67	0.05	0	4288.00	85.33	4.00	0.00	0.00	true
void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const, tensorflow::functor::Dimension<3>, float)	94	822.66	8.35	0	95759765.33	47059104.00	44.45	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	8.00	0.08	0	6741.33	125173.33	85.40	0.00	0.00	true
volta_gcgemm_64x32_nt	25	656.00	6.66	4904529920	1155424.00	20468266.67	7.87	226.81	7476.42	false
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	11	492.33	5.00	2606757888	26101002.67	27544192.00	15.55	48.59	5294.70	false

Showing 1 to 19 of 19 entries

Download as CSV