matlab gpu加速

gpuDevice

ans = 

  CUDADevice (具有属性):

                      Name: 'GeForce RTX 2060 SUPER'
                     Index: 1
         ComputeCapability: '7.5'
            SupportsDouble: 1
             DriverVersion: 10.2000
            ToolkitVersion: 7.5000
        MaxThreadsPerBlock: 1024
          MaxShmemPerBlock: 49152
        MaxThreadBlockSize: [1024 1024 64]
               MaxGridSize: [2.1475e+09 65535 65535]
                 SIMDWidth: 32
               TotalMemory: 8.5899e+09
           AvailableMemory: 6.9322e+09
       MultiprocessorCount: 34
              ClockRateKHz: 1650000
               ComputeMode: 'Default'
      GPUOverlapsTransfers: 1
    KernelExecutionTimeout: 1
          CanMapHostMemory: 1
           DeviceSupported: 1
            DeviceSelected: 1

>> gpuDeviceCount

ans =

     1

从 gpuArray 转换为 double 时出现以下错误:
无法从 gpuArray 转换为 double。

出错 FD (line 7)
            set(:,m,:) = downsample(signal(:,m:end)',dura_k)';

测试:

t = tic;
gridSize = 200;
maxIterations = 10000;
x = linspace(1, 100, gridSize);
y = linspace(1, 100, gridSize);
[xGrid, yGrid] = meshgrid(x, y);
z0 = xGrid + 1i*yGrid;

count = ones(size(z0), 'gpuArray');
z = z0;
for n = 0:maxIterations
    z = z.*z + z0;
    inside = abs(z)<=2;
    inside = count + inside;
end
count = log(count);

gpuTime = toc(t)

>> testgpu

gpuTime =

  164.4075

>> testgpu

cpuTime =

    2.4311

最后

以上就是结实鲜花为你收集整理的matlab gpu加速的全部内容，希望文章能够帮你解决matlab gpu加速所遇到的程序开发问题。

如果觉得靠谱客网站的内容还不错，欢迎将靠谱客网站推荐给程序员好友。