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
compute_gemm_pointers(float2*, float2 const, int, float2 const, int, float2 const, int, int)	14	53.67	0.08	0	4416.00	193194.67	2.61	0.00	0.00	true
cudnn::gemm::computeOffsetsKernel(cudnn::gemm::ComputeOffsetsParams)	46	167.33	0.25	0	13525.33	476330.67	5.75	0.00	0.00	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)	7	3902.00	5.72	2589394688	193430272.00	188909493.33	64.38	6.77	663.61	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	2043.00	2.99	63021056	239026016.00	106397013.33	69.91	0.18	30.85	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	4	38.67	0.06	8433664	246261.33	6672458.67	17.36	1.22	218.11	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	4843.33	7.09	0	1246108736.00	1319398976.00	95.72	0.00	0.00	true
void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 3, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorBroadcastingOp<Eigen::array<long, 3ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 3, 1, int>, 16, Eigen::MakePointer> const> const, Eigen::TensorBroadcastingOp<Eigen::array<long, 3ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 3, 1, int>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, int>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, 3, 1, int>, 16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_sum_op<float, float>, Eigen::TensorBroadcastingOp<Eigen::array<long, 3ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 3, 1, int>, 16, Eigen::MakePointer> const> const, Eigen::TensorBroadcastingOp<Eigen::array<long, 3ul> const, Eigen::TensorMap<Eigen::Tensor<float const, 3, 1, int>, 16, Eigen::MakePointer> const> const> const> const, Eigen::GpuDevice>, int)	67	4005.00	5.87	373911552	1273097674.67	1322349066.66	48.11	0.14	93.36	true
void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorSlicingOp<Eigen::array<int, 2ul> const, Eigen::array<int, 2ul> const, Eigen::TensorMap<Eigen::Tensor<float, 2, 1, int>, 16, Eigen::MakePointer> >, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const> const, Eigen::GpuDevice>, int>(Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorSlicingOp<Eigen::array<int, 2ul> const, Eigen::array<int, 2ul> const, Eigen::TensorMap<Eigen::Tensor<float, 2, 1, int>, 16, Eigen::MakePointer> >, Eigen::TensorMap<Eigen::Tensor<float const, 2, 1, int>, 16, Eigen::MakePointer> const> const, Eigen::GpuDevice>, int)	37	1675.19	2.45	0	589831082.66	591060042.67	95.54	0.00	0.00	true
void fft2d_c2r_16x16<float, false>(float, float2, int, int, int, int, int, int, int, int, int, int, float, float, int, float, float)	14	1047.33	1.53	1539084288	380075658.66	235849674.67	67.62	2.50	1469.53	true
void fft2d_c2r_32x32<float, false, false, 0u, false, false>(float, float2 const, int, int, int, int, int, int, int, int, int, float, float, cudnn::reduced_divisor, bool, float, float, int2, int, int)	5	857.00	1.26	1585446912	319895754.67	249702197.33	46.52	2.78	1850.00	true
void fft2d_r2c_16x16<float>(float2, float const, int, int, int, int, int, int, int, int)	29	1505.00	2.20	3137085440	194317408.00	810140192.00	65.72	3.12	2084.44	true
void fft2d_r2c_32x32<float, false, 0u, false>(float2, float const, int, int, int, int, int, int, int, int, int, cudnn::reduced_divisor, bool, int2, int, int)	5	696.00	1.02	1294598144	181428650.67	249843488.00	46.82	3.00	1860.05	true
void fft2d_r2c_32x32<float, false, 1u, true>(float2, float const, int, int, int, int, int, int, int, int, int, cudnn::reduced_divisor, bool, int2, int, int)	5	332.67	0.49	970948608	931818.67	183372565.33	44.83	5.27	2918.67	true
void flip_filter<float, float>(float, float const, int, int, int, int)	14	732.67	1.07	0	8362.67	17555498.67	4.01	0.00	0.00	true
void tensorflow::(anonymous namespace)::GenerateNormalizedProb<float, float>(float const, float const, float const, float, int, int, bool)	0	5.67	0.01	3075072	2560.00	256.00	37.70	1092.00	542.63	false
void tensorflow::BiasNCHWKernel<float>(int, float const, float const, float*, int, int)	1	1313.33	1.92	102888576	116611178.67	232125269.33	48.28	0.30	78.34	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	929.33	1.36	0	209626784.00	220147968.00	47.54	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	9.00	0.01	1291776	6656.00	384.00	6.20	183.49	143.53	false
void tensorflow::functor::RowReduceKernel<float const, float, cub::Max>(float const, float, int, int, cub::Max, std::iterator_traits<float const*>::value_type)	0	5.00	0.01	0	3840.00	682.67	6.20	0.00	0.00	true
void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const, tensorflow::functor::Dimension<3>, float)	70	568.33	0.83	0	44758037.33	49647253.33	44.54	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	274.67	0.40	0	77077994.67	79643914.67	93.30	0.00	0.00	true
volta_cgemm_32x32_tn	14	5280.67	7.74	62349115392	525989674.67	263971882.67	23.30	78.93	11807.05	false
volta_gcgemm_32x32_nt	5	1718.00	2.52	18600099840	436284010.67	323943872.00	16.66	24.47	10826.60	false
volta_scudnn_128x32_relu_interior_nn_v1	9	2981.00	4.37	31346753536	1286276384.00	116603573.33	20.64	22.34	10515.51	false
volta_scudnn_128x64_relu_interior_nn_v1	32	12146.67	17.79	128702398464	2241297301.33	517195210.67	20.58	46.66	10595.70	false
volta_scudnn_128x64_relu_medium_nn_v1	2	3116.11	4.56	35144073216	11277237.33	46985429.33	24.70	603.20	11278.18	false
volta_scudnn_128x64_relu_small_nn_v1	0	454.33	0.67	4627431424	3303637.33	4775690.67	15.50	572.75	10185.11	false
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	4	6385.67	9.35	70886359040	101450272.00	187807146.67	18.56	245.06	11100.86	false

Showing 1 to 28 of 28 entries

Download as CSV