spectral-norm benchmark N=550
Each chart bar shows how many times more Code, one ↓ spectral-norm program used, compared to the program that used least Code.
These are not the only programs that could be written. These are not the only compilers and interpreters. These are not the only programming languages.
Column × shows how many times more each program used compared to the benchmark program that used least.
| sort | sort | sort | ||||
| × | Program Source Code | CPU secs | Elapsed secs | Memory KB | Code B | ≈ CPU Load |
|---|---|---|---|---|---|---|
| 1.0 | Python 3 #2 | 0.11 | 0.11 | ? | 394 | 100% 0% 0% 0% 0% 0% 8% 0% |
| 1.0 | Nuitka #2 | 0.10 | 0.11 | ? | 394 | 8% 0% 91% 0% 0% 0% 0% 0% |
| 1.0 | Python development version #2 | 0.10 | 0.10 | ? | 394 | 0% 0% 100% 0% 0% 0% 10% 0% |
| 1.1 | Numba #2 | 1.31 | 1.34 | 131,484 | 416 | 15% 9% 10% 8% 8% 9% 13% 99% |
| 1.3 | Nuitka #6 | 2.11 | 2.11 | 11,264 | 498 | 100% 0% 0% 0% 2% 0% 0% 0% |
| 1.3 | Python development version #6 | 2.16 | 2.17 | 8,872 | 498 | 0% 0% 100% 0% 2% 0% 0% 1% |
| 1.3 | RustPython #6 | 54.47 | 54.49 | 15,896 | 498 | 0% 1% 1% 1% 0% 1% 100% 1% |
| 1.3 | MicroPython #6 | 6.21 | 6.22 | 4,200 | 498 | 0% 100% 0% 0% 0% 0% 0% 1% |
| 1.3 | Python 2 #6 | 2.36 | 2.36 | 6,640 | 498 | 0% 0% 0% 0% 1% 100% 0% 0% |
| 1.3 | PyPy 2 #6 | 0.17 | 0.17 | ? | 498 | 0% 100% 0% 19% 6% 12% 0% 0% |
| 1.3 | Pyston #6 | 1.30 | 1.30 | 8,048 | 498 | 0% 99% 2% 0% 0% 0% 1% 2% |
| 1.3 | Graal #6 | 8.10 | 2.65 | 921,616 | 498 | 8% 0% 65% 70% 69% 1% 96% 2% |
| 1.3 | Python 3 #6 | 2.15 | 2.16 | 10,384 | 498 | 100% 1% 0% 0% 0% 0% 0% 0% |
| 1.3 | Jython #6 | 10.41 | 7.38 | 3,660 | 498 | 10% 10% 9% 8% 58% 6% 26% 17% |
| 1.3 | PyPy 3 #6 | 0.18 | 0.18 | ? | 498 | 0% 100% 15% 0% 0% 0% 6% 0% |
| 1.5 | Python development version #5 | 2.21 | 0.60 | 56,516 | 575 | 41% 46% 33% 48% 54% 67% 53% 42% |
| 1.5 | PyPy 3 #5 | 2.24 | 1.30 | 90,768 | 575 | 48% 29% 23% 24% 18% 16% 14% 16% |
| 1.5 | Nuitka #5 | 2.61 | 0.70 | 58,040 | 575 | 46% 53% 41% 30% 38% 67% 55% 64% |
| 1.5 | Python 3 #5 | 2.48 | 0.65 | 55,220 | 575 | 59% 50% 20% 38% 59% 56% 55% 55% |
| 1.5 | Jython #8 | 8.79 | 5.59 | 3,540 | 594 | 23% 31% 26% 41% 10% 8% 8% 11% |
| 1.5 | Nuitka #8 | 2.12 | 2.13 | 11,392 | 594 | 0% 0% 1% 0% 0% 0% 0% 100% |
| 1.5 | RustPython #8 | 66.80 | 66.81 | 15,136 | 594 | 1% 100% 1% 0% 0% 1% 0% 0% |
| 1.5 | Graal #8 | 1.97 | 0.96 | 729,476 | 594 | 26% 26% 57% 35% 19% 12% 1% 36% |
| 1.5 | Python 2 #8 | 2.70 | 2.71 | 6,592 | 594 | 0% 0% 0% 100% 0% 2% 1% 0% |
| 1.5 | Pyston #8 | 1.43 | 1.43 | 8,160 | 594 | 3% 1% 0% 1% 1% 1% 1% 100% |
| 1.5 | Python development version #8 | 2.15 | 2.15 | 9,364 | 594 | 0% 0% 0% 0% 1% 0% 2% 100% |
| 1.5 | Python 3 #8 | 2.21 | 2.21 | 10,452 | 594 | 0% 0% 0% 100% 0% 0% 0% 1% |
| 1.5 | PyPy 3 #8 | 0.09 | 0.09 | ? | 594 | 0% 18% 100% 0% 11% 0% 0% 11% |
| 1.5 | PyPy 2 #8 | 0.09 | 0.09 | ? | 594 | 0% 0% 0% 100% 18% 0% 0% 0% |
| 1.5 | Pyston #5 | 1.40 | 0.39 | 43,572 | 595 | 55% 68% 57% 37% 37% 37% 37% 39% |
| 1.5 | Python 2 #5 | 4.23 | 1.13 | 11,728 | 595 | 78% 71% 51% 30% 25% 35% 40% 59% |
| 1.5 | PyPy 2 #5 | 1.12 | 0.70 | 333,172 | 595 | 32% 30% 46% 26% 10% 6% 13% 8% |
| 1.6 | Python 3 #3 | 0.32 | 0.33 | 1,792 | 642 | 100% 3% 0% 0% 0% 0% 3% 0% |
| 1.6 | Nuitka #3 | 0.31 | 0.35 | 3,456 | 642 | 100% 0% 0% 0% 0% 0% 0% 6% |
| 1.6 | Python development version #3 | 0.31 | 0.32 | 2,560 | 642 | 6% 0% 0% 100% 0% 6% 3% 0% |
| 1.7 | Numba | 1.39 | 1.41 | 130,424 | 667 | 21% 13% 15% 17% 14% 18% 99% 14% |
| missing benchmark programs | ||||||
| IronPython | No program | |||||
| Cython | No program | |||||
| Shedskin | No program | |||||
| Grumpy | No program | |||||
spectral-norm benchmark : Eigenvalue using the power method
diff program output N = 100 with this output file to check your program is correct before contributing.
We are trying to show the performance of various programming language implementations - so we ask that contributed programs not only give the correct result, but also use the same algorithm to calculate that result.
Each program should calculate the spectral norm of an infinite matrix A, with entries a11=1, a12=1/2, a21=1/3, a13=1/4, a22=1/5, a31=1/6, etc
For more information see challenge #3 in Eric W. Weisstein, "Hundred-Dollar, Hundred-Digit Challenge Problems" and "Spectral Norm".
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/Hundred-DollarHundred-DigitChallengeProblems.html
http://mathworld.wolfram.com/SpectralNorm.html
Thanks to Sebastien Loisel for this benchmark.