I've got starbench working inside autoconf. I'm half inclined to promote
it out of obsolete. IRAF tests won't run.
On one of our JAC machines I get:
Benchmark ucpu (sec) kcpu (sec) Elapsed (min:sec)
--------- ---------- ---------- -----------------
FFT 0.22 0.03 0:00.27
SLA 0.56 0.00 0:00.55
KAPPA 0.88 0.35 0:02.30
PISA 0.46 0.13 0:01.10
SPECDRE 0.59 0.23 0:01.28
CCDPACK 0.76 0.21 0:01.69
and the pisa test is failing for some reason I'm not sure about. Haven't
looked into why the file output for the pisa test does not match.
STARBENCH is an amazing mismatch of perl + csh + awk. I can't help but
think a simple little perl script would have been easier.
I haven't worked out how to get the starMark rating from "scan". I think
it's failing because the PISA test fails.
The only other outstanding issue is that the sysinfo command does not
contain all the information it used to.
The one obvious problem is that on this 3GHz machine with 16GB of RAM
the benchmark does not last any where near long enough. 2.3 seconds for
the KAPPA test is the longest. The FFT test is significantly faster than
the example in SSN23.
(http://docs.jach.hawaii.edu/star/ssn23.htx/node10.html). The test machine
is 6000 bogomips compared to 1980 bogomips in ssn23.
--
Tim Jenness
JAC software
http://www.jach.hawaii.edu/~timj
|