matlab中cuda编程中分配grid和block dimension的时候的注意事项

这两天在MATLAB里面用CUDA, 结果老是不对, 找了半天才发现, 原来是分配的问题

所以提醒小伙伴们, 分配的时候先看下你的GPU性能

>> gpuDevice

ans = 

  CUDADevice (具有属性):

                      Name: 'Quadro K2000'
                     Index: 1
         ComputeCapability: '3.0'
            SupportsDouble: 1
             DriverVersion: 7.5000
            ToolkitVersion: 7.5000
        MaxThreadsPerBlock: 1024
          MaxShmemPerBlock: 49152
        MaxThreadBlockSize: [1024 1024 64]
               MaxGridSize: [2.1475e+09 65535 65535]
                 SIMDWidth: 32
               TotalMemory: 2.1475e+09
           AvailableMemory: 1.6566e+09
       MultiprocessorCount: 2
              ClockRateKHz: 954000
               ComputeMode: 'Default'
      GPUOverlapsTransfers: 1
    KernelExecutionTimeout: 1
          CanMapHostMemory: 1
           DeviceSupported: 1
            DeviceSelected: 1

MaxThreadsPerBlock: 1024

其中这段话关键, 如果你是block是二维的话,那么你的threadsPerBlock.x * threadsPerBlock.y 不能大于1024.

我用dim3 threadsPerBlock(256, 256); 试了半天, 最终返回的矩阵都是全零矩阵, 所以希望大家注意