OSX and Mac Performance

I have two apple computers and thought it would be an interesting to compare performance (computer spec below)

COMPUTER A

• Model Name: Mac Pro
• Model Identifier: MacPro6,1
• Processor Name: 6-Core Intel Xeon E5
• Processor Speed: 3.5 GHz
• Number of Processors: 1
• Total Number of Cores:6
• L2 Cache (per Core): 256 KB
• L3 Cache: 12 MB
• Memory: 64 GB

COMPUTER B

• Model Name: MacBook Air
• Model Identifier: MacBookAir6,2
• Processor Name: Intel Core i7
• Processor Speed: 1.7 GHz
• Number of Processors: 1
• Total Number of Cores:2
• L2 Cache (per Core): 256 KB
• L3 Cache: 4 MB
• Memory: 8 GB

I use a simple fft() in a loop to test performance

function [ X ] = test( x )
a = 1:10000000;
for i = a
    fft(x);
end
end

The performance is measured by timeit()

>> x = randn(8,1)
>> temp = @() test(x)
>> timeit(temp)

Computer A = 15.1 seconds Computer B = 11.1 seconds

The MacBook Air spanks the Mac Pro for performance

Why is this the case?

[Ken Atwell]

That is not much of an FFT. What if the vector is of a more realistic size, a say 1K or 2K?

Answer 1

[Nelson Mark]

This is interesting and caught my eye because I'm thinking of buying a Mac Pro. Would you be willing to run some additional benchmarks on some different types of computations? e.g., generate 10000 X 5 random matrices, then doing least squares of column 1 on columns 2-5, 1000 times.

[John D'Errico]

This is not an answer. Please don't add answers just to make a comment, certainly not on a question that has seen no activity for nearly a year.