| Line 7: | Line 7: | ||
This application is a threshold filter - it is used in image converting and in neuron activation functions. | This application is a threshold filter - it is used in image converting and in neuron activation functions. | ||
| − | == Used artifacts == | + | Computational species: threshold calculation (part of image filter or neuron activation function) |
| + | |||
| + | == Used artifacts<br/> == | ||
*Datasets: | *Datasets: | ||
| − | **D1 = image raw fgg office day gray ({{CREF|8a7141c59cd335f5:c8848a1b1fb1775e}}) | + | **D1 = image raw fgg office day gray ({{CREF|8a7141c59cd335f5:c8848a1b1fb1775e}}), size=1536x1536~2.4E6 (pixels or neurons) |
| − | **D2 = image raw fgg office night gray ({{CREF|8a7141c59cd335f5:0045c9b59e84318b}}) | + | **D2 = image raw fgg office night gray ({{CREF|8a7141c59cd335f5:0045c9b59e84318b}}), size=1536x1536~2.4E6 |
*Systems: | *Systems: | ||
| − | **S1 = Dell Latitude E6320, Memory = 8Gb, | + | **S1 = Dell Laptop Latitude E6320, Processor=P1, Memory = 8Gb, Storage=256Gb (SSD), Max power consumption=52W, Cost=800 euro ({{CREF|cb7e6b406491a11c:0d84339816de0271}}) |
| − | **S2 = Samsung Galaxy Duos GT-S6312, Memory = 0.8Gb, Storage=4Gb, Battery=1300 mAh / 3.9V / up to 250 hours, Max power consumption~5W, Cost=120 euro ({{CREF|cb7e6b406491a11c:a9740acbe06bcd1e}}) | + | **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 ({{CREF|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: | *Processors: | ||
**P1 = Intel Core i5-2540M, 2.60GHz, 2 cores ({{CREF|54cd38490124ef51:425ae4e3483c82e8}}) | **P1 = Intel Core i5-2540M, 2.60GHz, 2 cores ({{CREF|54cd38490124ef51:425ae4e3483c82e8}}) | ||
**P2 = Qualcomm MSM7625A FFA, ARM Cortex A5, ARMv7, 1 GHz, 1 core ({{CREF|54cd38490124ef51:ae17889f40209ae7}}) | **P2 = Qualcomm MSM7625A FFA, ARM Cortex A5, ARMv7, 1 GHz, 1 core ({{CREF|54cd38490124ef51:ae17889f40209ae7}}) | ||
| + | **P3 = | ||
*Processor mode: | *Processor mode: | ||
| − | ** | + | **B1 = 32 bit |
| − | ** | + | **B2 = 64 bit |
*OSs: | *OSs: | ||
| Line 28: | Line 32: | ||
**O2 = OpenSuse 12.1, Kernel 3.1.10 ({{CREF|c4d3ce728f46eea2:29ce89f1a1446e89}}) | **O2 = OpenSuse 12.1, Kernel 3.1.10 ({{CREF|c4d3ce728f46eea2:29ce89f1a1446e89}}) | ||
**O3 = Android 4.1.2, Kernel 3.4.0 ({{CREF|c4d3ce728f46eea2:e734c48d5a5824c1}}) | **O3 = Android 4.1.2, Kernel 3.4.0 ({{CREF|c4d3ce728f46eea2:e734c48d5a5824c1}}) | ||
| + | **O4 = Android 4. | ||
*Compilers: | *Compilers: | ||
| Line 37: | Line 42: | ||
**IX = Intel X | **IX = Intel X | ||
| − | * | + | *Number of run-time code repetitions (for example, processing steps in neural networks): |
**R1 = 4000 | **R1 = 4000 | ||
| − | **R2 = 400 | + | **R2 = 1000 |
| + | **R3 = 400 | ||
| + | *Total number of computations (processed neurons or pixels) | ||
| + | **T1 ~ 9.6E9 | ||
| + | **T2 ~ 2.4E9 | ||
| + | **T3 ~ 1.0E9 | ||
== Notes == | == Notes == | ||
Revision as of 14:33, 22 August 2014
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
