System | Parameter | Value | Notes |
2-Spin | State space dimension | 16 × 500 | Sparse matrix representation fits into the L2 cache—polyadic processing is slower, memory footprint improvement is not significant |
nnz(L) and wct(Lv)a, sparse | 116,000, 0.5 ms | ||
nnz(L) and wct(Lv)a, polyadic | 12,000, 5 ms | ||
4-Spin | State space dimension | 256 × 500 | Sparse matrix representation exceeds L2 cache, parity on the wall clock time, significant memory advantage for the polyadic format |
nnz(L) and wct(Lv)a, sparse | 2,600,000, 13 ms | ||
nnz(L) and wct(Lv)a, polyadic | 14,000, 18 ms | ||
6-Spin | State space dimension | 4096 × 500 | Sparse matrix representation is in the gigabytes, polyadic processing is faster and offers a vast memory footprint advantage |
nnz(L) and wct(Lv)a, sparse | 37,000,000, 227 ms | ||
nnz(L) and wct(Lv)a, polyadic | 87,000, 185 ms |
aIntel Xeon E5-2698, single core.