function allocationBenchmark(arrSz)
if nargin < 1
arrSz = 1000;
end
t = [];
disp('--------------- Allocations in RAM ---------------')
t(end+1) = timeit(@()v1(arrSz), 1);
t(end+1) = timeit(@()v2(arrSz), 1);
t(end+1) = timeit(@()v3(arrSz), 1);
t(end+1) = timeit(@()v4(arrSz), 1);
t(end+1) = timeit(@()v5(arrSz), 1);
t(end+1) = timeit(@()v6(arrSz), 1);
t(end+1) = timeit(@()v7(arrSz), 1);
t = 1E3 * t;
disp(t); disp(" ");
[~,I] = min(t);
disp("Conclusion: method #" + I + " is the fastest on the CPU!"); disp(" ");
if gpuDeviceCount == 0, return; end
t = [];
disp('--------------- Allocations in VRAM --------------')
t(end+1) = NaN;
t(end+1) = gputimeit(@()v2gpu(arrSz), 1);
t(end+1) = gputimeit(@()v3gpu(arrSz), 1);
t(end+1) = gputimeit(@()v4gpu(arrSz), 1);
t(end+1) = gputimeit(@()v5gpu(arrSz), 1);
t(end+1) = gputimeit(@()v6gpu(arrSz), 1);
t(end+1) = gputimeit(@()v7gpu(arrSz), 1);
t = 1E3 * t;
disp(t); disp(" ");
[~,I] = min(t);
disp("Conclusion: method #" + I + " is the fastest on the GPU!");
end
function out = v1(M)
out(1:M, 1:M) = pi;
end
function out = v2(M)
scalar = pi;
out = scalar(ones(M));
end
function out = v3(M)
out = zeros(M, M) + pi;
end
function out = v4(M)
out = repmat(pi, [M, M]);
end
function out = v5(M)
out = ones(M) .* pi;
end
function out = v6(M)
out = zeros(M);
out(:) = pi;
end
function out = v7(M)
out = repelem(pi,M,M);
end
function out = v2gpu(M)
scalar = gpuArray(pi);
out = scalar(gpuArray.ones(M));
end
function out = v3gpu(M)
out = gpuArray.zeros(M, M) + gpuArray(pi);
end
function out = v4gpu(M)
out = repmat(gpuArray(pi), [M, M]);
end
function out = v5gpu(M)
out = gpuArray.ones(M) .* gpuArray(pi);
end
function out = v6gpu(M)
out = gpuArray.zeros(M);
out(:) = gpuArray(pi);
end
function out = v7gpu(M)
out = repelem(gpuArray(pi),M,M);
end
运行上述代码(例如输入
5000
),将得到以下结果:
--------------- Allocations in RAM ---------------
110.4832 328.1685 48.7895 47.9652 108.8930 93.0481 47.9037
Conclusion: method #7 is the fastest on the CPU!
--------------- Allocations in VRAM --------------
NaN 37.0322 17.9096 14.2873 17.7377 16.1386 16.6330
Conclusion: method #4 is the fastest on the GPU!
这告诉我们在每种情况下使用最好的(或等效的)方法。
single
精度运行GPU计算会带来速度优势,但对于我的目的来说,这是无关紧要的,因为我需要更高的精度。您是否怀疑如果使用single
精度,基准测试将产生不同的结果(在最佳方法方面)?如果是这样-更有理由编写基准测试代码。 - Dev-iL