• proposal
• Cache friendly programming
• Performance Optimization of Sparse Kernels in TOPS
• BLAS overview
• BLAS C interface
• SSE HOWTO
• AltiVec/SSE Migration Guide: Data Types and Intrinsics
• SSE Performance Programming

#!/usr/bin/ruby

# Direct Iterative Method for Matrix-Matrix Multiply
# C = C + A * B
# A: m x n
# B: n x p
# C: m x p

a = [[1.0, 3.0], [2.0, 4.0]] # 1 3
                             # 2 4

b = [[5.0, 7.0], [6.0, 8.0]] # 5 7 
                             # 6 8

c = [[9.0, 11.0], [10.0, 12.0]] # 9  11
                                # 10 12

m = n = p = 2

0.upto(m-1) do |i|
  0.upto(p-1) do |j|
    0.upto(n-1) do |k|
      c[i][j] = c[i][j] + a[i][k]*b[k][j]
    end
  end
end

# C + A * B =  32 42 
#              44 58