Table 2: Hardware utilization comparisons for both implementations using kintex7-xc7k480t-3ffg1156 chip.

Precision (Bits) 8-bit 16-bit 32-bit 64-bit 128-bit 256-bit 512-bit 1024-bit
SQL_MUL_CSA Registers 144(0%) 281(0%) 554(0%) 1,123(1%) 2211(1%) 4387(1%) 8739(1%) 17443(2%)
LUTs 114(0%) 175(0%) 334(0%) 673(1%) 1113(1%) 1908(1%) 3802(1%) 7557(2%)
SQL_MUL_CLA Registers 202(0%) 370(0%) 706(1%) 1,442(1%) 2722(1%) 5410(1%) 10786(2%) 21538(3%)
LUTs 147(0%) 271(0%) 548(1%) 1,102(1%) 1968(1%) 3913(1%) 8377(3%) 16677(5%)