Go backward to Cyclic Distribution of Columns Go up to Top Go forward to Memory Access Analysis

Row Based Cyclic Distribution

for all P_m do in parallel
  for i = m to n by p do
    for j = i to n do
      C[i,j] = 0
      for k = 1 to n do
        C[i,j] = C[i,j] + A[i,k]*B[k,j]
      end
    end
  end
end

• Synchronization overhead O(p)
• Total complexity O(n³/p+p)

Memory contention is ignored in this analysis!