==4532== NVPROF is profiling process 4532, command: ../../../quick.cuda taxol.in
==4532== Profiling application: ../../../quick.cuda taxol.in
==4532== Profiling result:
            Type  Time(%)      Time     Calls       Avg       Min       Max  Name
 GPU activities:   64.27%  69.5700s        21  3.31286s  1.37252s  5.62752s  get2e_kernel(void)
                   35.28%  38.1905s         1  38.1905s  38.1905s  38.1905s  getGrad_kernel(void)
                    0.34%  363.17ms       728  498.86us  1.2800us  4.1780ms  [CUDA memcpy HtoD]
                    0.08%  83.780ms       211  397.06us  3.2320us  605.41us  [CUDA memcpy DtoH]
                    0.04%  39.838ms       189  210.78us  209.86us  220.03us  volta_dgemm_64x64_nn
                    0.00%  261.73us       189  1.3840us  1.2800us  2.3040us  [CUDA memset]
      API calls:   97.84%  107.761s        22  4.89822s  1.37252s  38.1906s  cudaEventSynchronize
                    0.67%  739.79ms       728  1.0162ms  3.8630us  499.78ms  cudaMalloc
                    0.60%  663.60ms       915  725.24us  5.1140us  4.3307ms  cudaMemcpy
                    0.40%  445.82ms         1  445.82ms  445.82ms  445.82ms  cudaThreadSynchronize
                    0.23%  254.79ms         1  254.79ms  254.79ms  254.79ms  cudaThreadExit
                    0.21%  233.40ms      1067  218.74us     351ns  2.4427ms  cudaFree
                    0.02%  24.505ms       211  116.14us  15.590us  13.952ms  cudaLaunch
                    0.00%  2.8748ms         1  2.8748ms  2.8748ms  2.8748ms  cudaDeviceSetLimit
                    0.00%  2.7054ms       185  14.624us     111ns  559.04us  cuDeviceGetAttribute
                    0.00%  2.6833ms         2  1.3416ms  1.3225ms  1.3608ms  cudaGetDeviceProperties
                    0.00%  2.0213ms       189  10.694us  7.6320us  18.982us  cudaMemsetAsync
                    0.00%  1.4761ms         2  738.07us  715.81us  760.33us  cuDeviceTotalMem
                    0.00%  1.2836ms        24  53.485us  11.467us  101.84us  cudaMemcpyToSymbol
                    0.00%  709.20us       189  3.7520us  2.7590us  7.4540us  cudaEventQuery
                    0.00%  681.55us      4536     150ns      93ns  6.3430us  cudaSetupArgument
                    0.00%  475.25us       233  2.0390us  1.1530us  5.8870us  cudaEventRecord
                    0.00%  255.71us         2  127.85us  126.36us  129.35us  cuDeviceGetName
                    0.00%  133.08us       211     630ns     315ns  5.3630us  cudaConfigureCall
                    0.00%  126.83us        44  2.8820us     696ns  11.622us  cudaEventCreate
                    0.00%  126.18us        22  5.7350us  3.3420us  10.259us  cudaEventElapsedTime
                    0.00%  76.669us        44  1.7420us     595ns  7.5510us  cudaEventDestroy
                    0.00%  52.794us       211     250ns     144ns  3.3230us  cudaGetLastError
                    0.00%  35.441us        32  1.1070us     573ns  9.6210us  cudaFuncSetAttribute
                    0.00%  11.464us        16     716ns     404ns  3.3300us  cudaEventCreateWithFlags
                    0.00%  10.563us         1  10.563us  10.563us  10.563us  cudaSetDevice
                    0.00%  7.2510us        11     659ns     236ns  3.9760us  cudaDeviceGetAttribute
                    0.00%  5.7240us         4  1.4310us     339ns  3.4780us  cudaDeviceGetLimit
                    0.00%  4.7540us         1  4.7540us  4.7540us  4.7540us  cudaDeviceSetCacheConfig
                    0.00%  3.1970us         1  3.1970us  3.1970us  3.1970us  cudaGetDevice
                    0.00%  2.4190us         3     806ns     215ns  1.7770us  cuDeviceGet
                    0.00%  2.0320us         2  1.0160us     286ns  1.7460us  cudaGetDeviceCount
                    0.00%  1.9670us         4     491ns     136ns  1.3460us  cuDeviceGetCount
                    0.00%     875ns         1     875ns     875ns     875ns  cuInit
                    0.00%     662ns         1     662ns     662ns     662ns  cuDriverGetVersion