Difference between revisions of "Application Processor Benchmarks"
From HBMobile
Jump to navigationJump to searchTomCooksey (talk | contribs) |
TomCooksey (talk | contribs) |
||
| Line 1: | Line 1: | ||
To get a feel for the performance of the various application processors avaliable on the market, we have benchmarked as many as we can get access to. The tool we have used to benchmark the processors is [http://www.tux.org/~mayer/linux/bmark.html nbench] 2.2.2, as it is easy to cross-compile and only depends on libc. | To get a feel for the performance of the various application processors avaliable on the market, we have benchmarked as many as we can get access to. The tool we have used to benchmark the processors is [http://www.tux.org/~mayer/linux/bmark.html nbench] 2.2.2, as it is easy to cross-compile and only depends on libc. | ||
| − | DISCLAIMER: These are simple synthetic benchmarks and may not represent "real-world" performance. The results may also not match different configurations than those tested (e.g. if different memory is used). | + | DISCLAIMER: These are simple synthetic benchmarks and may not represent "real-world" performance. The results may also not match different configurations than those tested (e.g. if different memory is used). The results we've got so far also seem to differ to other (probably more professional) results. E.g. The Synchromesh Computing [http://www.synchromeshcomputing.com/SynchromeshComputingFTF-Presentation-Benchmarking.ppt benchmarks] |
| + | |||
= Overview of Results = | = Overview of Results = | ||
Revision as of 10:01, 4 July 2007
To get a feel for the performance of the various application processors avaliable on the market, we have benchmarked as many as we can get access to. The tool we have used to benchmark the processors is nbench 2.2.2, as it is easy to cross-compile and only depends on libc.
DISCLAIMER: These are simple synthetic benchmarks and may not represent "real-world" performance. The results may also not match different configurations than those tested (e.g. if different memory is used). The results we've got so far also seem to differ to other (probably more professional) results. E.g. The Synchromesh Computing benchmarks
Overview of Results
| TEST | i.MX31 (532Mhz) | PXA255 (400Mhz) | PXA270 (600Mhz) |
|---|---|---|---|
| NUMERIC SORT | 133.72 | 152.44 | 198.12 |
| STRING SORT | 8.1317 | 10.753 | 17.469 |
| BITFIELD | 4.3146e+07 | 3.6149e+07 | 6.6802e+07 |
| FP EMULATION | 30.475 | 13.023 | 41.583 |
| ASSIGNMENT | - | - | 1.2438 |
| FOURIER | 147.52 | - | - |
| IDEA | 396.2 | 393.08 | 538.49 |
| HUFFMAN | 171.95 | 21.716 | 302.12 |
| NEURAL NET | 0.22022 | - | - |
| LU DECOMPOSITION | 7.1372 | - | - |
