PyCUDA+Threading = Invalid Handles on kernel invocations

The reason is context affinity. Every CUDA function instance is tied to a context, and they are not portable (the same applies to memory allocations and texture references). So each context must load the function instance separately, and then use the function handle returned by that load operation.

If you are not using metaprogramming at all, you might find it simpler to compile your CUDA code to a cubin file, and then load the functions you need from the cubin to each context with driver.module_from_file. Cutting and pasting directly from some production code of mine:

  

   

    

     

    
    

     

      # Context establishment
     
    
   

    

     

    
    

     

      try:
     
    
   

    

     

    
    

     
 if (autoinit):
     
    
   

    

     

    
    

     

       import pycuda.autoinit
     
    
   

    

     

    
    

     
 self.context = None
     
    
   

    

     

    
    

     
 self.device = pycuda.autoinit.device
     
    
   

    

     

    
    

     
 self.computecc = self.device.compute_capability()
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       driver.init()
     
    
   

    

     

    
    

     
 self.context = tools.make_default_context()
     
    
   

    

     

    
    

     
 self.device = self.context.get_device()
     
    
   

    

     

    
    

     
 self.computecc = self.device.compute_capability()
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 # GPU code initialization
     
    
   

    

     

    
    

     
 # load pre compiled CUDA code from cubin file
     
    
   

    

     

    
    

     
 # Select the cubin based on the supplied dtype
     
    
   

    

     

    
    

     
 # cubin names contain C++ mangling because of
     
    
   

    

     

    
    

     
 # templating. Ugly but no easy way around it
     
    
   

    

     

    
    

     
 if self.computecc == (1,3):
     
    
   

    

     

    
    

     
 self.fimcubin = "fim_sm13.cubin"
     
    
   

    

     

    
    

     

       elif self.computecc[0] == 2:
     
    
   

    

     

    
    

     
 self.fimcubin = "fim_sm20.cubin"
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       raise NotImplementedError("GPU architecture not supported")
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       fimmod = driver.module_from_file(self.fimcubin)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       IterateName32 = "_Z10fimIterateIfLj8EEvPKT_PKiPS0_PiS0_S0_S0_jjji"
     
    
   

    

     

    
    

     

       IterateName64 = "_Z10fimIterateIdLj8EEvPKT_PKiPS0_PiS0_S0_S0_jjji"
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 if (self.dtype == np.float32):
     
    
   

    

     

    
    

     

       IterateName = IterateName32
     
    
   

    

     

    
    

     

       elif (self.dtype == np.float64):
     
    
   

    

     

    
    

     

       IterateName = IterateName64
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       raise TypeError
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 self.fimIterate = fimmod.get_function(IterateName)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      except ImportError:
     
    
   

    

     

    
    

     

       warn("Could not initialise CUDA context")
     
    
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/79705500