API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Feb 27th, 2017
241
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 19.50 KB | None | 0 0
raw download clone embed print report
  1. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally
  2. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
  3. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally
  4. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
  5. I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally
  6. ==91215== NVPROF is profiling process 91215, command: python alexnet_benchmark.py
  7. I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties:
  8. name: TITAN X (Pascal)
  9. major: 6 minor: 1 memoryClockRate (GHz) 1.531
  10. pciBusID 0000:04:00.0
  11. Total memory: 11.90GiB
  12. Free memory: 11.74GiB
  13. W tensorflow/stream_executor/cuda/cuda_driver.cc:590] creating context when one is currently active; existing: 0x2f1e9b0
  14. I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 1 with properties:
  15. name: Tesla K40c
  16. major: 3 minor: 5 memoryClockRate (GHz) 0.745
  17. pciBusID 0000:84:00.0
  18. Total memory: 11.17GiB
  19. Free memory: 11.09GiB
  20. I tensorflow/core/common_runtime/gpu/gpu_device.cc:777] Peer access not supported between device ordinals 0 and 1
  21. I tensorflow/core/common_runtime/gpu/gpu_device.cc:777] Peer access not supported between device ordinals 1 and 0
  22. I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 1
  23. I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y N
  24. I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 1: N Y
  25. I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:04:00.0)
  26. I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:1) -> (device: 1, name: Tesla K40c, pci bus id: 0000:84:00.0)
  27. ==91215== Profiling application: python alexnet_benchmark.py
  28. ==91215== Profiling result:
  29. Time(%) Time Calls Avg Min Max Name
  30. 18.90% 1.60256s 1448 1.1067ms 813.35us 6.0754ms cudnn_maxwell_gcgemm_64x64_tn_batched
  31. 13.27% 1.12468s 5170 217.54us 27.170us 585.95us void tensorflow::functor::SwapDimension1And2InTensor3UsingTiles<float, int=32, int=8>(float const *, tensorflow::functor::Dimension<int=3>, tensorflow::functor::SwapDimension1And2InTensor3UsingTiles<float, int=32, int=8>*)
  32. 8.95% 758.56ms 2438 311.14us 196.27us 565.62us void fft2d_r2c_16x16<float, bool=1>(float2*, float const *, int, int, int, int, int, int, int, int)
  33. 5.50% 465.84ms 221 2.1079ms 2.0377ms 2.6011ms maxwell_scudnn_128x64_large_nn
  34. 5.01% 424.98ms 902 471.16us 240.65us 2.1123ms void fft2d_r2c_32x32<float, bool=1>(float2*, float const *, int, int, int, int, int, int, int, int, int)
  35. 4.31% 365.17ms 1332 274.16us 17.344us 1.5425ms void flip_filter<float, float>(float*, float const *, int, int, int, int)
  36. 4.12% 348.94ms 1100 317.22us 133.13us 671.80us void tensorflow::BiasNHWCKernel<float>(int, float const *, float const , tensorflow::BiasNHWCKernel<float>*, int)
  37. 4.06% 344.01ms 112 3.0715ms 2.8623ms 3.3058ms maxwell_scudnn_128x64_stridedB_splitK_medium_nn
  38. 4.01% 340.27ms 1219 279.14us 176.10us 473.81us void fft2d_c2r_16x16<float, bool=0, bool=1>(float*, float2*, int, int, int, int, int, int, int, int, int, int, float, float)
  39. 3.76% 318.48ms 1100 289.53us 126.09us 593.15us void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, int=1, int=1, long>, int=16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_max_op<float const , float const >, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, long>, int=16, Eigen::MakePointer> const , Eigen::TensorCwiseNullaryOp<Eigen::internal::scalar_constant_op<float const >, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, long>, int=16, Eigen::MakePointer> const > const > const > const , Eigen::GpuDevice>, long>(float, int=1)
  40. 2.92% 247.11ms 330 748.82us 725.34us 908.01us void tensorflow::functor::PadInputCustomKernelNHWC<float, int=4>(int, float const *, tensorflow::functor::Dimension<int=4>, tensorflow::functor::PadInputCustomKernelNHWC<float, int=4>*, float const *, float const *)
  41. 2.88% 244.24ms 451 541.55us 208.84us 1.3232ms void fft2d_c2r_32x32<float, bool=0, bool=1>(float*, float2 const *, int, int, int, int, int, int, int, int, int, float, float)
  42. 2.83% 240.06ms 550 436.47us 186.57us 907.11us void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, int=1, int=1, long>, int=16, Eigen::MakePointer>, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_product_op<float const , float const >, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, long>, int=16, Eigen::MakePointer> const , Eigen::TensorConversionOp<float, Eigen::TensorCwiseBinaryOp<Eigen::internal::scalar_cmp_op<float const , float const , Eigen::internal::ComparisonName>, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, long>, int=16, Eigen::MakePointer> const , Eigen::TensorCwiseNullaryOp<Eigen::internal::scalar_constant_op<float const >, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, long>, int=16, Eigen::MakePointer> const > const > const > const > const > const , Eigen::GpuDevice>, long>(float, int=1)
  43. 2.67% 226.48ms 330 686.30us 231.40us 1.1047ms void cudnn::detail::pooling_bw_kernel_max<float, float, cudnn::detail::maxpooling_func<float, cudnnNanPropagation_t=1>>(cudnnTensorStruct, float const *, cudnn::detail::pooling_bw_kernel_max<float, float, cudnn::detail::maxpooling_func<float, cudnnNanPropagation_t=1>>, float const , cudnn::detail::pooling_bw_kernel_max<float, float, cudnn::detail::maxpooling_func<float, cudnnNanPropagation_t=1>>, float const , cudnn::detail::pooling_bw_kernel_max<float, float, cudnn::detail::maxpooling_func<float, cudnnNanPropagation_t=1>>, cudnnTensorStruct*, cudnnPoolingStruct, float, cudnnPoolingStruct, int, cudnn::reduced_divisor, float)
  44. 2.65% 224.91ms 116 1.9389ms 1.7271ms 3.1765ms maxwell_scudnn_winograd_128x128_tile228n_nt
  45. 2.56% 217.34ms 660 329.30us 108.58us 614.65us void tensorflow::_GLOBAL__N__66_tmpxft_0000200b_00000000_9_maxpooling_op_gpu_cu_compute_52_cpp1_ii_af505f36::MaxPoolForwardNHWC<float>(int, float const *, int, int, int, int, int, int, int, int, int, int, int, tensorflow::_GLOBAL__N__66_tmpxft_0000200b_00000000_9_maxpooling_op_gpu_cu_compute_52_cpp1_ii_af505f36::MaxPoolForwardNHWC<float>*, __int64*)
  46. 2.46% 208.23ms 330 631.00us 612.86us 723.01us void tensorflow::functor::SwapDimension1And2InTensor3<float>(int, float const *, tensorflow::functor::Dimension<int=3>, tensorflow::functor::SwapDimension1And2InTensor3<float>*)
  47. 2.00% 169.85ms 222 765.08us 735.14us 920.33us cudnn_maxwell_cgemm_64x64_tn_batched
  48. 1.69% 143.55ms 1210 118.63us 864ns 363.12us [CUDA memcpy DtoH]
  49. 1.47% 124.57ms 550 226.49us 92.516us 506.90us void tensorflow::BiasGradNHWC_SharedAtomics<float>(int, float const *, tensorflow::BiasGradNHWC_SharedAtomics<float>*, int)
  50. 0.77% 65.374ms 2090 31.279us 3.0720us 89.924us void tensorflow::functor::SwapDimension0And2InTensor3<float>(int, float const *, tensorflow::functor::Dimension<int=3>, tensorflow::functor::SwapDimension0And2InTensor3<float>*)
  51. 0.76% 64.379ms 334 192.75us 63.939us 277.23us void setTensor4d_kernel<float, float, int=16, int=16>(cudnnTensor4dStruct, float*, float)
  52. 0.37% 30.965ms 4 7.7412ms 5.3534ms 9.8128ms void cudnn::detail::dgrad_engine<float, int=128, int=6, int=8, int=3, int=3, int=5, bool=1>(int, int, int, float const *, int, float const , int, cudnn::detail::dgrad_engine<float, int=128, int=6, int=8, int=3, int=3, int=5, bool=1>*, kernel_grad_params, int, int, float, int)
  53. 0.28% 23.488ms 3 7.8293ms 4.6348ms 12.187ms void cudnn::detail::implicit_convolve_sgemm<float, int=512, int=6, int=8, int=3, int=3, int=5, int=1, bool=1, bool=0>(int, int, int, float const *, int, cudnn::detail::implicit_convolve_sgemm<float, int=512, int=6, int=8, int=3, int=3, int=5, int=1, bool=1, bool=0>*, float const *, kernel_conv_params, int, float, float)
  54. 0.25% 21.196ms 3 7.0652ms 4.1175ms 10.374ms void cudnn::detail::wgrad_alg0_engine<float, int=128, int=6, int=8, int=3, int=3, int=5, bool=1, int=512>(int, int, int, float const *, int, cudnn::detail::wgrad_alg0_engine<float, int=128, int=6, int=8, int=3, int=3, int=5, bool=1, int=512>*, float const , kernel_grad_params, int, float, int, int)
  55. 0.22% 18.361ms 6 3.0601ms 2.5114ms 3.7605ms maxwell_scudnn_128x128_stridedB_splitK_small_nn
  56. 0.15% 12.868ms 2 6.4340ms 6.3960ms 6.4719ms maxwell_scudnn_128x64_stridedB_splitK_small_nn
  57. 0.13% 11.059ms 3 3.6863ms 3.0853ms 4.5920ms maxwell_scudnn_128x128_small_nn
  58. 0.13% 10.793ms 1 10.793ms 10.793ms 10.793ms void cudnn::detail::explicit_convolve_sgemm<float, int, int=512, int=6, int=8, int=3, int=3, int=5, int=0, bool=0>(int, int, int, float const *, int, float const , int, cudnn::detail::explicit_convolve_sgemm<float, int, int=512, int=6, int=8, int=3, int=3, int=5, int=0, bool=0>*, kernel_conv_params, int, int, float, float)
  59. 0.11% 9.4712ms 2 4.7356ms 3.2551ms 6.2161ms maxwell_scudnn_128x64_stridedB_small_nn
  60. 0.11% 9.1170ms 2 4.5585ms 3.5786ms 5.5384ms void cudnn::detail::explicit_convolve_sgemm<float, int, int=512, int=6, int=8, int=3, int=3, int=5, int=0, bool=1>(int, int, int, float const *, int, float const , int, cudnn::detail::explicit_convolve_sgemm<float, int, int=512, int=6, int=8, int=3, int=3, int=5, int=0, bool=1>*, kernel_conv_params, int, int, float, float)
  61. 0.09% 7.5156ms 5 1.5031ms 586.30us 2.9270ms void im2col4d_kernel<float, int>(im2col4d_params, cudnnConvolutionStruct, cudnnTensor4dStruct, float const *, float*, int)
  62. 0.08% 7.1280ms 1 7.1280ms 7.1280ms 7.1280ms maxwell_scudnn_128x64_small_nn
  63. 0.07% 6.0585ms 2 3.0292ms 2.4185ms 3.6400ms maxwell_scudnn_128x128_stridedB_small_nn
  64. 0.07% 5.7305ms 1 5.7305ms 5.7305ms 5.7305ms void cudnn::detail::implicit_convolve_sgemm<float, int=128, int=6, int=7, int=3, int=3, int=5, int=1, bool=1, bool=0>(int, int, int, float const *, int, cudnn::detail::implicit_convolve_sgemm<float, int=128, int=6, int=7, int=3, int=3, int=5, int=1, bool=1, bool=0>*, float const *, kernel_conv_params, int, float, float)
  65. 0.06% 5.2956ms 1 5.2956ms 5.2956ms 5.2956ms void cudnn::detail::wgrad_alg0_engine<float, int=128, int=6, int=7, int=3, int=3, int=5, bool=1, int=512>(int, int, int, float const *, int, cudnn::detail::wgrad_alg0_engine<float, int=128, int=6, int=7, int=3, int=3, int=5, bool=1, int=512>*, float const , kernel_grad_params, int, float, int, int)
  66. 0.06% 5.2647ms 1 5.2647ms 5.2647ms 5.2647ms void cudnn::detail::implicit_convolve_sgemm<float, int=128, int=5, int=5, int=3, int=3, int=3, int=1, bool=1, bool=0>(int, int, int, float const *, int, cudnn::detail::implicit_convolve_sgemm<float, int=128, int=5, int=5, int=3, int=3, int=3, int=1, bool=1, bool=0>*, float const *, kernel_conv_params, int, float, float)
  67. 0.06% 5.0949ms 1 5.0949ms 5.0949ms 5.0949ms void cudnn::detail::explicit_convolve_sgemm<float, int, int=128, int=6, int=7, int=3, int=3, int=5, int=0, bool=1>(int, int, int, float const *, int, float const , int, cudnn::detail::explicit_convolve_sgemm<float, int, int=128, int=6, int=7, int=3, int=3, int=5, int=0, bool=1>*, kernel_conv_params, int, int, float, float)
  68. 0.05% 4.5246ms 1 4.5246ms 4.5246ms 4.5246ms void cudnn::detail::explicit_convolve_sgemm<float, int, int=128, int=5, int=5, int=3, int=3, int=3, int=0, bool=0>(int, int, int, float const *, int, float const , int, cudnn::detail::explicit_convolve_sgemm<float, int, int=128, int=5, int=5, int=3, int=3, int=3, int=0, bool=0>*, kernel_conv_params, int, int, float, float)
  69. 0.05% 3.9295ms 1 3.9295ms 3.9295ms 3.9295ms void cudnn::detail::wgrad_alg0_engine<float, int=512, int=6, int=5, int=3, int=3, int=3, bool=1, int=512>(int, int, int, float const *, int, cudnn::detail::wgrad_alg0_engine<float, int=512, int=6, int=5, int=3, int=3, int=3, bool=1, int=512>*, float const , kernel_grad_params, int, float, int, int)
  70. 0.04% 3.2639ms 116 28.136us 2.2720us 438.90us void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, int=1, int=1, int>, int=16, Eigen::MakePointer>, Eigen::TensorCwiseUnaryOp<Eigen::internal::scalar_right<float, float, Eigen::internal::scalar_product_op<float, float>>, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, int>, int=16, Eigen::MakePointer> const > const > const , Eigen::GpuDevice>, int>(float, int=1)
  71. 0.03% 2.9212ms 116 25.183us 19.841us 34.657us void cudnn::winograd::generateWinogradTilesKernel<int=0, float, float>(cudnn::winograd::GenerateWinogradTilesParams<float, float>)
  72. 0.01% 506.58us 11 46.052us 1.6000us 434.00us [CUDA memcpy DtoD]
  73. 0.01% 498.81us 6 83.134us 2.1120us 438.07us void Eigen::internal::EigenMetaKernel<Eigen::TensorEvaluator<Eigen::TensorAssignOp<Eigen::TensorMap<Eigen::Tensor<float, int=1, int=1, int>, int=16, Eigen::MakePointer>, Eigen::TensorCwiseUnaryOp<Eigen::internal::scalar_right<float, float, Eigen::internal::scalar_sum_op<float, float>>, Eigen::TensorMap<Eigen::Tensor<float const , int=1, int=1, int>, int=16, Eigen::MakePointer> const > const > const , Eigen::GpuDevice>, int>(float, int=1)
  74. 0.01% 443.03us 229 1.9340us 1.8240us 3.2000us cudnn::maxwell::gemm::computeOffsetsKernel(cudnn::maxwell::gemm::ComputeOffsetsParams)
  75. 0.00% 395.98us 1 395.98us 395.98us 395.98us void tensorflow::functor::FillPhiloxRandomKernelLaunch<tensorflow::random::NormalDistribution<tensorflow::random::PhiloxRandom, float>>(tensorflow::random::PhiloxRandom, tensorflow::random::PhiloxRandomResultElementType*, __int64, tensorflow::functor::FillPhiloxRandomKernelLaunch<tensorflow::random::NormalDistribution<tensorflow::random::PhiloxRandom, float>>)
  76. 0.00% 394.99us 5 78.998us 14.848us 136.42us void tensorflow::functor::FillPhiloxRandomKernelLaunch<tensorflow::random::TruncatedNormalDistribution<tensorflow::random::SingleSampleAdapter<tensorflow::random::PhiloxRandom>, float>>(tensorflow::random::PhiloxRandom, tensorflow::random::PhiloxRandomResultElementType*, __int64, tensorflow::functor::FillPhiloxRandomKernelLaunch<tensorflow::random::TruncatedNormalDistribution<tensorflow::random::SingleSampleAdapter<tensorflow::random::PhiloxRandom>, float>>)
  77. 0.00% 391.96us 562 697ns 576ns 6.1440us [CUDA memset]
  78. 0.00% 250.98us 120 2.0910us 1.8880us 2.2720us cudnn::maxwell::gemm::computeWgradOffsetsKernel(cudnn::maxwell::gemm::ComputeOffsetsParams)
  79. 0.00% 225.48us 124 1.8180us 1.6960us 2.1120us cudnn::maxwell::gemm::computeBOffsetsKernel(cudnn::maxwell::gemm::ComputeBOffsetsParams)
  80. 0.00% 223.02us 120 1.8580us 1.3440us 11.008us void cudnn::maxwell::gemm::setOutputKernel<float>(int, float*, float)
  81. 0.00% 12.032us 8 1.5040us 1.2480us 2.3040us [CUDA memcpy HtoD]
  82.  
  83. ==91215== API calls:
  84. Time(%) Time Calls Avg Min Max Name
  85. 63.82% 7.19684s 221 32.565ms 339.51us 51.307ms cuCtxSynchronize
  86. 9.98% 1.12557s 2 562.79ms 556.85ms 568.72ms cuDevicePrimaryCtxRetain
  87. 9.04% 1.01963s 21882 46.596us 8.7490us 652.66ms cudaLaunch
  88. 6.53% 736.70ms 492101 1.4970us 705ns 827.32us cuEventQuery
  89. 5.41% 609.86ms 8 76.233ms 22.279us 609.14ms cudaStreamCreateWithFlags
  90. 3.14% 354.64ms 64 5.5412ms 1.4091ms 21.912ms cuEventSynchronize
  91. 0.63% 71.197ms 150919 471ns 280ns 766.28us cudaSetupArgument
  92. 0.24% 26.535ms 2 13.267ms 9.1017ms 17.433ms cuMemAlloc
  93. 0.20% 23.006ms 1210 19.012us 8.8600us 133.16us cuMemcpyDtoHAsync
  94. 0.18% 20.677ms 9742 2.1220us 1.0350us 25.143us cudaStreamWaitEvent
  95. 0.18% 19.789ms 7376 2.6820us 1.2110us 28.776us cudaEventRecord
  96. 0.16% 18.386ms 21882 840ns 334ns 767.97us cudaConfigureCall
  97. 0.11% 12.298ms 550 22.359us 13.816us 56.188us cuMemsetD32Async
  98. 0.09% 9.8094ms 3 3.2698ms 1.4747ms 4.2015ms cuMemHostAlloc
  99. 0.06% 6.7944ms 10107 672ns 274ns 762.78us cudaGetLastError
  100. 0.05% 5.1881ms 2562 2.0250us 870ns 14.234us cuEventRecord
  101. 0.04% 4.0525ms 660 6.1400us 2.8600us 811.73us cudaStreamQuery
  102. 0.02% 2.3163ms 1217 1.9030us 1.0010us 14.494us cuStreamWaitEvent
  103. 0.02% 2.2673ms 4 566.82us 514.32us 618.66us cuMemGetInfo
  104. 0.02% 1.8821ms 376 5.0050us 211ns 186.80us cuDeviceGetAttribute
  105. 0.02% 1.7974ms 338 5.3170us 1.9140us 19.423us cudaEventCreate
  106. 0.01% 1.1840ms 338 3.5020us 1.7090us 16.352us cudaEventDestroy
  107. 0.01% 1.0757ms 2 537.86us 505.23us 570.48us cuDeviceTotalMem
  108. 0.01% 1.0731ms 3 357.69us 14.289us 531.29us cudaMalloc
  109. 0.01% 803.24us 2 401.62us 384.83us 418.41us cudaGetDeviceProperties
  110. 0.01% 691.32us 4 172.83us 158.26us 192.44us cuDeviceTotalMem
  111. 0.00% 491.16us 2 245.58us 171.56us 319.60us cuDeviceGetProperties
  112. 0.00% 388.12us 8 48.515us 22.529us 168.51us cuStreamCreate
  113. 0.00% 282.75us 6 47.125us 36.269us 64.555us cuDeviceGetName
  114. 0.00% 210.05us 146 1.4380us 628ns 6.6940us cuEventCreate
  115. 0.00% 202.05us 10 20.204us 15.019us 34.114us cudaMemsetAsync
  116. 0.00% 193.47us 11 17.587us 14.836us 29.834us cudaMemcpyAsync
  117. 0.00% 147.38us 146 1.0090us 537ns 10.067us cuEventDestroy
  118. 0.00% 137.38us 24 5.7240us 2.8640us 14.948us cudaBindTexture
  119. 0.00% 136.40us 7 19.485us 15.689us 31.919us cuMemcpyHtoDAsync
  120. 0.00% 128.81us 2 64.402us 62.592us 66.213us cuMemsetD32
  121. 0.00% 114.25us 64 1.7850us 1.4630us 5.6450us cuEventElapsedTime
  122. 0.00% 78.697us 24 3.2790us 500ns 9.5080us cuCtxSetCurrent
  123. 0.00% 71.042us 8 8.8800us 4.2280us 24.102us cuStreamDestroy
  124. 0.00% 62.617us 8 7.8270us 1.8660us 32.014us cuStreamQuery
  125. 0.00% 46.035us 24 1.9180us 1.0550us 3.3500us cudaUnbindTexture
  126. 0.00% 35.458us 24 1.4770us 934ns 9.4170us cudaEventCreateWithFlags
  127. 0.00% 26.015us 1 26.015us 26.015us 26.015us cudaMemcpy
  128. 0.00% 18.299us 21 871ns 546ns 1.7640us cudaDeviceGetAttribute
  129. 0.00% 9.9600us 10 996ns 276ns 3.1900us cuDeviceGetCount
  130. 0.00% 9.1240us 2 4.5620us 3.1170us 6.0070us cudaGetDevice
  131. 0.00% 7.3820us 10 738ns 401ns 1.5590us cuDeviceGet
  132. 0.00% 4.7260us 4 1.1810us 496ns 2.3530us cuDriverGetVersion
  133. 0.00% 4.2060us 2 2.1030us 1.8410us 2.3650us cuDeviceGetPCIBusId
  134. 0.00% 3.8840us 2 1.9420us 1.5750us 2.3090us cuDevicePrimaryCtxSetFlags
  135. 0.00% 3.2630us 2 1.6310us 1.5480us 1.7150us cuInit
  136. 0.00% 2.8190us 8 352ns 263ns 503ns cuCtxGetDevice
  137. 0.00% 1.8750us 1 1.8750us 1.8750us 1.8750us cudaGetDeviceCount
  138. 0.00% 1.7210us 2 860ns 829ns 892ns cuDeviceComputeCapability
  139. 0.00% 1.6040us 4 401ns 299ns 623ns cuDeviceCanAccessPeer
  140. 0.00% 1.0870us 2 543ns 363ns 724ns cuCtxGetCurrent
  141. 0.00% 985ns 2 492ns 486ns 499ns cudaFree
  142.  
  143. real 0m21.865s
  144. user 0m20.820s
  145. sys 0m7.352s
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!