performance measurements
Each table row shows performance measurements for this Numba program with a particular command-line input value N.
| N | CPU secs | Elapsed secs | Memory KB | Code B | ≈ CPU Load |
|---|---|---|---|---|---|
| 550 | 1.31 | 1.34 | 131,484 | 416 | 15% 9% 10% 8% 8% 9% 13% 99% |
Read the ↓ make, command line, and program output logs to see how this program was run.
Read spectral-norm benchmark to see what this program should do.
notes
spectral-norm Numba #2 program source code
# The Computer Language Benchmarks Game
# http://benchmarksgame.alioth.debian.org/
#
# Contributed by Sebastien Loisel
# Fixed by Isaac Gouy
# Sped up by Josh Goldfoot
# Dirtily sped up by Simon Descarpentries
# Sped up with numpy by Kittipong Piyawanno
# 2to3
from numba import jit
from sys import argv
from numpy import *
@jit(forceobj=True)
def spectralnorm(n):
u = matrix(ones(n))
j = arange(n)
eval_func = lambda i : 1.0 / ((i + j) * (i + j + 1) / 2 + i + 1)
M = matrix([eval_func(i) for i in arange(n)])
MT = M.T
for i in range (10):
v = (u*MT)*M
u = (v*MT)*M
print("%0.9f" % (sum(u*v.T)/sum(v*v.T))**0.5)
spectralnorm(int(argv[1]))
make, command-line, and program output logs
Wed, 12 Jan 2022 12:00:30 GMT COMMAND LINE: /usr/bin/python3 spectralnorm.numba-2.numba 550 PROGRAM OUTPUT: 1.274224125