Recent posts
https://software.intel.com/en-us/recent/787337
enCost of covariance matrix estimation
https://software.intel.com/en-us/forums/intel-math-kernel-library/topic/342666
<p>Hello,</p>
<p>I'm having a bit of trouble finding some informations about some BLAS functions. I want to estimate a covariance matrix from a set of K vectors (of length N).Two ways for doing that:</p>
<p>- put all the vectors x_k into a matrix X (size N*K) and use zgemm to do X*X^{H} so computational cost = 8*K*N²</p>
<p>- use zher K times updating each time the matrix with x_k*x_k^{H} --> what's the cost of that ?</p>
<p>Also, i'm a bit lost when talking about computing power calculation. If, for a given matrix-matrix multiplication, I need 200 GFlop per second (calculated with 8*K*N² / the time I have to do it). Can I compare these 200 GFlops to theorical power of my CPU ? Because i always see that the power of CPUs/GPUs is given in MAD GFlops. Does this mean that i can divide the 200 GFlops by 2 because one multiplication+addition is done per cycle ??</p>
<p>Thank you.</p>
<p>Jean-François</p>
</p>
Thu, 29 Nov 12 05:09:39 -0800Jean-françois D.342666