Research Article
Effective SIMD Vectorization for Intel Xeon Phi Coprocessors
Algorithm 3
Small matrix multiplication summation.
| real, dimension(4,4):: A, B, C | | real sum | | integer j, l, i | | do j = 1, 4 | | do l = 1, 4 | | sum = 0.0 | | do i = 1, 4 | | sum = sum + A(i,l) B(i,j) | | enddo | | C(l,j) = sum | | enddo | | enddo |
|