An 8x8 Self-healing approximate multiply–accumulate (MAC) Verilog implementation based on the MACISH work by G. A. Gillani et al. [1], K. Raben approx. multipliers VHDL implementation [2] and the verilog mac implementation by Intel [3].
Default Config: // ISH_1 | M4 M1 M1 M1 | M1 M1 M4 M1 | M1 M1 M1 M1 | M3 M4 M1 M4 |
Sources:
[1] - G. A. Gillani, M. A. Hanif, B. Verstoep, S. H. Gerez, M. Shafique and A. B. J. Kokkeler, "MACISH: Designing Approximate MAC Accelerators With Internal-Self-Healing," in IEEE Access, vol. 7, pp. 77142-77160, 2019, doi: 10.1109/ACCESS.2019.2920335. https://ieeexplore.ieee.org/abstract/document/8727537
[2] - Raben, K.T. (2019) Comparing selfh-healing techniques in approximate MAC accelerators. https://essay.utwente.nl/77449/1/Raben_BA_EEMCS.pdf