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)	1	7.00	0.04	0	2912.00	18208.00	6.16	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)	93	6109.34	35.33	12821614176	16659562.67	34506314.67	3.85	250.59	2098.69	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)	14	198.67	1.15	91524913	50346.67	13958101.33	52.67	6.53	460.69	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	40.00	0.23	752768	4500394.67	4658058.67	53.40	0.08	18.82	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	15	66.00	0.38	5879808	10858.67	2733941.33	6.20	2.14	89.09	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)	99	366.67	2.12	0	428192.00	11884746.67	50.92	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)	148	641.00	3.71	15089184	10681376.00	13724853.34	49.32	0.62	23.54	true
void fft1d_c2r_32<float2, float, float, false, true, false, false>(float, float2 const, int, int3, int3, int2, int, float, float, float, float)	16	101.89	0.59	22658858.666	145461.33	2997920.00	2.39	7.21	222.39	true
void fft1d_c2r_32<float2, float, float, false, true, false, true>(float, float2 const, int, int3, int3, int2, int, float, float, float, float)	21	118.34	0.68	28526272	85482.67	2544789.33	2.35	10.85	241.06	true
void fft1d_r2c_32<float, float, float2, false, false>(float2, float const, int, int3, int3, int2, int2)	16	248.00	1.43	21257472	3228661.33	10814069.33	2.12	1.51	85.72	true
void fft1d_r2c_32<float, float, float2, false, true>(float2, float const, int, int3, int3, int2, int2)	21	240.33	1.39	28662272	5501589.33	16685898.67	2.21	1.29	119.26	true
void fft1d_r2c_32<float, float, float2, true, false>(float2, float const, int, int3, int3, int2, int2)	36	656.67	3.80	604778496	1703658.67	196121450.67	18.84	3.06	920.98	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	20.67	0.12	3202871	6157376.00	2072586.67	6.20	0.39	154.98	true
void tensorflow::(anonymous namespace)::GenerateNormalizedProb<float, float>(float const, float const, float const, float, int, int, bool)	0	4.00	0.02	24024	2368.00	2432.00	6.20	5.00	6.01	true
void tensorflow::BiasNHWCKernel<float>(int, float const, float const, float*, int)	0	3.67	0.02	1001	5600.00	213.33	47.20	0.17	0.27	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	3.67	0.02	0	3072.00	213.33	12.10	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	8.33	0.05	10431	6656.00	42.67	2.40	1.56	1.25	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	5.00	0.03	0	4096.00	85.33	3.90	0.00	0.00	true
void tensorflow::functor::ShuffleInTensor3Simple<float, 2, 1, 0, false>(int, float const, tensorflow::functor::Dimension<3>, float)	148	1376.33	7.96	0	164499242.67	71475285.34	43.74	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	0.05	0	7050.67	74378.67	82.60	0.00	0.00	true
volta_gcgemm_32x32_nt	2	35.56	0.21	124945920	37205.33	2005898.67	4.50	61.15	3514.06	false
volta_gcgemm_64x32_nt	35	1208.67	6.99	11253836800	122315968.00	71728170.67	10.12	58.00	9310.94	false
volta_scudnn_128x64_relu_interior_nn_v1	0	183.00	1.06	849838080	3501642.67	2118293.33	6.20	151.22	4643.92	false
volta_scudnn_128x64_relu_small_nn_v1	0	58.67	0.34	308969472	24128.00	1498282.67	6.20	202.95	5266.50	false
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	15	396.00	2.29	2641551360	4328170.67	20158645.34	15.76	107.88	6670.60	false

Showing 1 to 25 of 25 entries

Download as CSV