Advertisement
mmmskumara

Untitled

Sep 21st, 2019
140
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 3.90 KB | None | 0 0
  1. ==12492== Profiling application: ../../../quick.cuda taxol.in
  2. ==12492== Profiling result:
  3. Type Time(%) Time Calls Avg Min Max Name
  4. GPU activities: 83.64% 355.792s 1 355.792s 355.792s 355.792s getGrad_kernel(void)
  5. 16.24% 69.0687s 21 3.28899s 1.35947s 5.58191s get2e_kernel(void)
  6. 0.09% 370.43ms 750 493.91us 1.2480us 4.3047ms [CUDA memcpy HtoD]
  7. 0.02% 88.859ms 211 421.13us 3.3600us 1.0880ms [CUDA memcpy DtoH]
  8. 0.01% 39.845ms 189 210.82us 209.98us 221.47us volta_dgemm_64x64_nn
  9. 0.00% 266.66us 189 1.4100us 1.3120us 2.6880us [CUDA memset]
  10. API calls: 99.46% 424.861s 22 19.3118s 1.35948s 355.792s cudaEventSynchronize
  11. 0.17% 709.10ms 728 974.04us 3.7810us 467.42ms cudaMalloc
  12. 0.16% 678.82ms 915 741.88us 4.8820us 4.4808ms cudaMemcpy
  13. 0.09% 399.89ms 1 399.89ms 399.89ms 399.89ms cudaThreadSynchronize
  14. 0.06% 262.00ms 1 262.00ms 262.00ms 262.00ms cudaThreadExit
  15. 0.05% 234.51ms 1067 219.79us 363ns 2.5014ms cudaFree
  16. 0.01% 24.362ms 211 115.46us 15.456us 13.855ms cudaLaunch
  17. 0.00% 2.8880ms 1 2.8880ms 2.8880ms 2.8880ms cudaDeviceSetLimit
  18. 0.00% 2.7162ms 185 14.681us 113ns 567.06us cuDeviceGetAttribute
  19. 0.00% 2.6835ms 2 1.3418ms 1.3413ms 1.3423ms cudaGetDeviceProperties
  20. 0.00% 1.8916ms 189 10.008us 7.2710us 18.207us cudaMemsetAsync
  21. 0.00% 1.6248ms 46 35.320us 8.3240us 105.74us cudaMemcpyToSymbol
  22. 0.00% 1.4777ms 2 738.83us 715.13us 762.52us cuDeviceTotalMem
  23. 0.00% 705.71us 189 3.7330us 2.5910us 7.7930us cudaEventQuery
  24. 0.00% 668.07us 4536 147ns 88ns 6.4260us cudaSetupArgument
  25. 0.00% 489.53us 233 2.1000us 1.2240us 13.968us cudaEventRecord
  26. 0.00% 247.57us 2 123.78us 117.88us 129.69us cuDeviceGetName
  27. 0.00% 171.09us 211 810ns 316ns 28.126us cudaConfigureCall
  28. 0.00% 121.31us 44 2.7570us 626ns 11.330us cudaEventCreate
  29. 0.00% 120.36us 22 5.4700us 2.9920us 11.025us cudaEventElapsedTime
  30. 0.00% 83.703us 44 1.9020us 521ns 15.354us cudaEventDestroy
  31. 0.00% 61.168us 211 289ns 139ns 3.9310us cudaGetLastError
  32. 0.00% 35.346us 32 1.1040us 624ns 9.2630us cudaFuncSetAttribute
  33. 0.00% 12.709us 1 12.709us 12.709us 12.709us cudaSetDevice
  34. 0.00% 11.845us 16 740ns 392ns 3.0620us cudaEventCreateWithFlags
  35. 0.00% 6.7690us 11 615ns 232ns 3.8530us cudaDeviceGetAttribute
  36. 0.00% 5.4750us 1 5.4750us 5.4750us 5.4750us cudaDeviceSetCacheConfig
  37. 0.00% 5.4580us 4 1.3640us 365ns 3.0850us cudaDeviceGetLimit
  38. 0.00% 2.6010us 3 867ns 228ns 1.9970us cuDeviceGet
  39. 0.00% 2.5900us 1 2.5900us 2.5900us 2.5900us cudaGetDevice
  40. 0.00% 2.4310us 2 1.2150us 212ns 2.2190us cudaGetDeviceCount
  41. 0.00% 2.0550us 4 513ns 136ns 1.2910us cuDeviceGetCount
  42. 0.00% 1.0830us 1 1.0830us 1.0830us 1.0830us cuInit
  43. 0.00% 536ns 1 536ns 536ns 536ns cuDriverGetVersion
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement