FP32转FP16能否加速libtorch调用

FP32转FP16能否加速libtorch调用

###1. PYTORCH 采用FP16后的速度提升问题

pytorch可以使用half()函数将模型由FP32迅速简洁的转换成FP16.但FP16速度是否提升还依赖于GPU。以下面的代码为例,

  1. import time 
  2.  
  3. import torch 
  4. from torch.autograd import Variable 
  5. import torchvision.models as models 
  6.  
  7. import torch.backends.cudnn as cudnn 
  8. cudnn.benchmark = True 
  9.  
  10. net = models.resnet18().cuda() 
  11. inp = torch.randn(64, 3, 224, 224).cuda() 
  12.  
  13. for i in range(5): 
  14. net.zero_grad() 
  15. out = net.forward(Variable(inp, requires_grad=True)) 
  16. loss = out.sum() 
  17. loss.backward() 
  18.  
  19. torch.cuda.synchronize() 
  20. start=time.time() 
  21. for i in range(100): 
  22. net.zero_grad() 
  23. out = net.forward(Variable(inp, requires_grad=True)) 
  24. loss = out.sum() 
  25. loss.backward() 
  26. torch.cuda.synchronize() 
  27. end=time.time() 
  28.  
  29. print("FP32 Iterations per second: ", 100/(end-start)) 
  30.  
  31. net = models.resnet18().cuda().half() 
  32. inp = torch.randn(64, 3, 224, 224).cuda().half() 
  33.  
  34. torch.cuda.synchronize() 
  35. start=time.time() 
  36. for i in range(100): 
  37. net.zero_grad() 
  38. out = net.forward(Variable(inp, requires_grad=True)) 
  39. loss = out.sum() 
  40. loss.backward() 
  41. torch.cuda.synchronize() 
  42. end=time.time() 
  43.  
  44. print("FP16 Iterations per second: ", 100/(end-start)) 

在1080Ti上的性能对比:

  1. FP32 Iterations per second: 10.37743206218922 
  2. FP16 Iterations per second: 9.855269155760238 
  3. FP32 Memory:2497M 
  4. FP16 Memory:1611M 

可以发现FP16显著的降低了显存,但是速度没有提升,反而有些许下降。
然后观察在 V100 上的性能对比:

  1. FP32 Iterations per second: 16.325794715481173 
  2. FP16 Iterations per second: 24.853492643300903 
  3. FP32 Memory: 3202M 
  4. FP16 Memory: 2272M 

此时显存显著降低且速度也提升较明显。
关于pytorch 中采用FP16有时速度没有提升的问题,参考https://discuss.pytorch.org/t/cnn-fp16-slower-than-fp32-on-tesla-p100/12146
image.png

###2. Libtorch采用FP16后的速度提升问题
我们在V100上测试FP16是否能提升libtorch的推理速度。
####2.1 下载libtorch

  1. wget https://download.pytorch.org/libtorch/cu101/libtorch-cxx11-abi-shared-with-deps-1.6.0%2Bcu101.zip 
  2. unzip libtorch-cxx11-abi-shared-with-deps-1.6.0+cu101.zip 

在pytorch官网找到对应版本的libtorch,libtorch一般会向下支持,我这里的libtorch版本1.6.0, pytorch安装的是1.1.0

####2.2 pytorch生成trace.pt

  1. import torch 
  2. import torchvision.models as models 
  3. net = models.resnet18().cuda() 
  4. net.eval() 
  5. inp = torch.randn(64, 3, 224, 224).cuda() 
  6. traced_script_module = torch.jit.trace(net, inp) 
  7. traced_script_module.save("RESNET18_trace.pt") 
  8. print("trace has been saved!") 

####2.3 libtorch 调用trace

  1. #include<iostream> 
  2. #include<vector> 
  3. #include<torch/script.h> 
  4. #include <cuda_runtime_api.h> 
  5. using namespace std; 
  6.  
  7. int main() 
  8. { 
  9. at::globalContext().setBenchmarkCuDNN(true); 
  10.  
  11. std::string model_file = "/home/zwzhou/Code/test_libtorch/RESNET18_trace.pt"; 
  12. torch::Tensor inputs = torch::rand({64, 3, 224, 224}).to(at::kCUDA); 
  13. torch::jit::script::Module net = torch::jit::load(model_file); // load model 
  14. net.to(at::kCUDA); 
  15. auto outputs = net.forward({inputs}); 
  16. cudaDeviceSynchronize(); 
  17. auto before = std::chrono::system_clock::now(); 
  18. for (int i=0; i<100; ++i) 
  19. {  
  20. outputs = net.forward({inputs}); 
  21. } 
  22. cudaDeviceSynchronize(); 
  23.  
  24. cudaDeviceSynchronize(); 
  25. auto after = std::chrono::system_clock::now(); 
  26. std::chrono::duration<double> all_time = after - before; 
  27. std::cout<<"FP32 iteration per second: "<<(100/all_time.count())<<"\n"; 
  28.  
  29. net.to(torch::kHalf); 
  30. cudaDeviceSynchronize(); 
  31. before = std::chrono::system_clock::now(); 
  32. for (int i=0; i<100; ++i) 
  33. { 
  34. outputs = net.forward({inputs.to(torch::kHalf)}); 
  35. } 
  36. cudaDeviceSynchronize(); 
  37. after = std::chrono::system_clock::now(); 
  38. std::chrono::duration<double> all_time2 = after - before; 
  39. std::cout<<"FP16 iteration per second: "<<(100/all_time2.count())<<"\n"; 
  40.  
  41. } 

####2.4 编写CMakeLists.txt

  1. cmake_minimum_required(VERSION 3.0 FATAL_ERROR) 
  2. project(FP_TEST) 
  3.  
  4. set(CMAKE_PREFIX_PATH "/home/zwzhou/packages/libtorch/share/cmake/Torch") 
  5. set(DCMAKE_PREFIX_PATH /home/zwzhou/packages/libtorch) 
  6.  
  7. find_package(Torch REQUIRED) 
  8. add_executable(mtest ./libtorch_test.cpp) 
  9. target_link_libraries(mtest ${TORCH_LIBRARIES}) 
  10. set_property(TARGET mtest PROPERTY CXX_STANDARD 14) 

####2.5 测评时间

  1. cd build 
  2. cmake .. 
  3. make 
  4. ./mtest 

####2.6 输出时间

  1. FP32 iteration per second: 60.6978 
  2. FP16 iteration per second: 91.5507 

可以发现,libtorch版本比pytorch版本速度提升比较明显;另外,可以看出在V100上FP16同样能够提升libtorch的推理速度。

####2.7 注意事项
CPU上tensor不支持FP16,所以CUDA上推理完成后转成CPU后还需要转到FP32上。
https://discuss.pytorch.org/t/runtimeerror-add-cpu-sub-cpu-not-implemented-for-half-when-using-float16-half/66229

posted @ 2020-09-07 11:51  一只有恒心的小菜鸟  阅读(1686)  评论(0编辑  收藏  举报