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

• Datasets:
  • D1 = image raw fgg office day gray (CID=8a7141c59cd335f5:c8848a1b1fb1775e), size=1536x1536~2.4E6 (pixels or neurons)
  • D2 = image raw fgg office night gray (CID=8a7141c59cd335f5:0045c9b59e84318b), size=1536x1536~2.4E6

• 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 ()

• Processors:
  • P1 = Intel Core i5-2540M, 2.60GHz, 2 cores (CID=54cd38490124ef51:425ae4e3483c82e8)
  • P2 = Qualcomm MSM7625A FFA, ARM Cortex A5, ARMv7, 1 GHz, 1 core (CID=54cd38490124ef51:ae17889f40209ae7)
  • P3 =
• Processor mode:
  • B1 = 32 bit
  • B2 = 64 bit

• OSs:
  • O1 = Windows 7 Pro SP1 (CID=c4d3ce728f46eea2:10c4f7484446b689)
  • O2 = OpenSuse 12.1, Kernel 3.1.10 (CID=c4d3ce728f46eea2:29ce89f1a1446e89)
  • O3 = Android 4.1.2, Kernel 3.4.0 (CID=c4d3ce728f46eea2:e734c48d5a5824c1)
  • O4 = Android 4.

• 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