The EvoApproxLibLITE is the lightweight version of our library of approximate circuits with formally guaranteed error parameters. Hardware as well as software models are provided for each circuit.

Circuit name MAE WCE MRE EP power area Download model
mul8x6u_049 0.00 % 0.00 % 0.00 % 0.00 % 0.267 538.3 Verilog fileC filePython PYX
mul8x6u_5EZ [1] 0.0015 % 0.0061 % 0.058 % 25.00 % 0.260 511.5 Verilog fileC filePython PYX
mul8x6u_5TS [1] 0.0045 % 0.012 % 0.16 % 37.11 % 0.255 493.7 Verilog fileC filePython PYX
mul8x6u_4TY [1] 0.014 % 0.037 % 0.47 % 62.50 % 0.249 481.0 Verilog fileC filePython PYX
mul8x6u_629 [1] 0.028 % 0.10 % 0.83 % 79.69 % 0.234 444.9 Verilog fileC filePython PYX
mul8x6u_5HD [1] 0.12 % 0.43 % 2.81 % 95.75 % 0.191 409.2 Verilog fileC filePython PYX
mul8x6u_5Y1 [1] 0.31 % 1.21 % 6.26 % 95.89 % 0.139 298.0 Verilog fileC filePython PYX
mul8x6u_2HT 0.96 % 3.88 % 15.15 % 97.55 % 0.074 183.0 Verilog fileC filePython PYX
mul8x6u_0MH 2.90 % 11.38 % 35.91 % 97.96 % 0.025 87.3 Verilog fileC filePython PYX
mul8x6u_045 7.98 % 30.23 % 64.72 % 98.02 % 0.00089 7.0 Verilog fileC filePython PYX
mul8x6u_51C [1] 24.51 % 98.05 % 100.00 % 98.05 % 0.000 0.0 Verilog fileC filePython PYX

Reported error parameters: MAE - Mean Absolute Error (Mean Error Magnitude), WCE - Worst-Case Absolute Error (Error Magnitude / Error Significance), MSE - Mean Squared Error, MRE - Mean Relative Error (Mean Relative Error Distance), WCRE - Worst-Case Relative Error, EP - Error Probability (Error Rate)  |  Reported design parameters: power - power consumption in mW, area - area on the chip in um2, dly - delay, all values obtained using Synopsys DC (45 nm PDK, 1 V, 25 ℃)  |  Error parameters marked by were verified using a formal technique analyzing all possible input combinations. There is a formal guarantee that the error is not worse than the shown value. The exact values are included at the beginning of each C file and Verilog file.

COMPARISON

Comparison with the complete EvoApproxLib dataset on various metrics. The first plot shows the performance wrt. the parameters used for pareto filtration. The black dots are the circuits included in this dataset. The blue dots are parameters of the circuits included in the full version of EvoApproxLib. Note that the parameters of the accurate implementation shown in the figure correspond with those exhibiting the lowest power consumption.

REFERENCES
  1. V. Mrazek, L. Sekanina and Z. Vasicek, Libraries of Approximate Circuits: Design and Application in CNN Accelerators