Computational species "bw filter simplified less" (CID=45741e3fbcf4024b:1db78910464c9d05)

Notes

Some cost-aware experiments (execution time, size, energy) performed by Grigori Fursin. It supports our research on code optimization and compiler benchmarking (regression detection).

This application is a threshold filter - it is used in image converting and in neuron activation functions.

Computational species: threshold calculation (part of image filter or neuron activation function)

Used artifacts

  • Systems:
    • S1 = Dell Laptop Latitude E6320, Processor=P1, Memory = 8Gb, Storage=256Gb (SSD), Max power consumption=52W, Cost=800 euro (CID=cb7e6b406491a11c:0d84339816de0271)
    • S2 = Samsung Mobile Galaxy Duos GT-S6312, Processor=P2, Memory = 0.8Gb, Storage=4Gb, Battery=1300 mAh / 3.9V / up to 250 hours, Max power consumption~5W, Cost=120 euro (CID=cb7e6b406491a11c:a9740acbe06bcd1e)
    • S3 = Polaroid Tablet Executive 9", Processor=P3, Memory=1Gb, Storage=16Gb, Battery=3500 mAh / 3.9V / up to 80 hours, Max power consumption~, Cost=80 euro ()
  • Compilers:
    • LLVMXYZ = LLVM X.Y.Z
    • GCCXYZ = GCC X.Y.Z
    • MGCCXYZ = MingW X.Y.Z
    • SGCCXYZ = Sourcergy GCC X.Y.Z. for ARM
    • MX = Microsoft Visual Studio compilers X
    • IX = Intel X
  • Number of run-time code repetitions (for example, processing steps in neural networks):
    • R1 = 4000
    • R2 = 1000
    • R3 = 400
  • Total number of computations (processed neurons or pixels)
    • T1 ~ 9.6E9
    • T2 ~ 2.4E9
    • T3 ~ 1.0E9

Notes

Energy: 1Wh = 3600 joules

W = mAh * V / 1000 = 1300 * 3.9 / 1000 ~ 5W


(C) 2011-2014 cTuning foundation