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)	0	4.33	0.10	0	96.00	0.00	21.80	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	53.67	1.25	1530368	14496042.67	8016554.67	55.40	0.07	28.52	true
void cudnn::winograd::generateWinogradTilesKernel<0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)	11	237.67	5.53	94789632	59561578.67	90082645.33	49.93	0.63	398.83	true
void gemv2T_kernel_val<int, int, float, float, float, 128, 16, 4, 4, false, cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float> >(cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float>, float, float)	0	25.00	0.58	8893000	16519978.67	18709.33	28.20	0.54	355.72	true
void gemv2T_kernel_val<long, long, float, float, float, 128, 16, 2, 2, false, cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float> >(cublasGemvParams<cublasGemvTensorStridedBatched<float const>, cublasGemvTensorStridedBatched<float>, float>, float, float)	1	572.00	13.31	261611520	302736128.00	312544.00	39.84	0.86	457.36	true
void mshadow::cuda::MapPlanKernel<mshadow::sv::plusto, 8, mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 2, float>, float>, mshadow::expr::Plan<mshadow::expr::Broadcast1DExp<mshadow::Tensor<mshadow::gpu, 1, float>, float, 2, 1>, float> >(mshadow::expr::Plan<mshadow::Tensor<mshadow::gpu, 2, float>, float>, int, mshadow::Shape<2>, mshadow::expr::Plan<mshadow::expr::Broadcast1DExp<mshadow::Tensor<mshadow::gpu, 1, float>, float, 2, 1>, float>)	2	11.00	0.26	9192	40298.67	0.00	12.20	0.23	0.84	true
void mxnet::op::mxnet_op::mxnet_generic_kernel<mxnet::op::mxnet_op::op_with_req<mxnet::op::mshadow_op::identity, 1>, float, float>(int, float, float)	1	6.00	0.14	0	0.00	0.00	12.25	0.00	0.00	true
void op_generic_tensor_kernel<2, float, float, float, 256, (cudnnGenericOp_t)0, (cudnnNanPropagation_t)0, (cudnnDimOrder_t)0, 0>(cudnnTensorStruct, float, cudnnTensorStruct, float const, cudnnTensorStruct, float const*, float, float, float, float, dimArray, reducedDivisorArray, bool)	12	188.00	4.37	67737600	37582858.67	35104864.00	77.56	0.93	360.30	true
void op_generic_tensor_kernel<2, float, float, float, 256, (cudnnGenericOp_t)8, (cudnnNanPropagation_t)0, (cudnnDimOrder_t)0, 1>(cudnnTensorStruct, float, cudnnTensorStruct, float const, cudnnTensorStruct, float const*, float, float, float, float, dimArray, reducedDivisorArray, bool)	14	160.00	3.72	27111424	28271456.00	43258336.00	80.52	0.38	169.45	true
void splitKreduce_kernel<float, float, float>(cublasSplitKParams<float>, float const, float const, float, float const, float const*)	0	4.00	0.09	4000	160.00	0.00	6.20	25.00	1.00	false
volta_scudnn_128x64_relu_small_nn_v1	0	31.67	0.74	211943424	8181.33	10622112.00	20.50	19.94	6692.88	false
volta_scudnn_winograd_128x128_ldg1_ldg4_relu_tile148t_nt_v1	11	1843.00	42.88	16521035776	197021045.33	67185248.00	20.21	62.53	8964.21	false

Showing 1 to 12 of 12 entries

Download as CSV