Hi John,
Finally, for today, here is the 1-CPU AlphaServer ES40 6/833. This
run used the previously approved version from
http://www.cs.virginia.edu/stream/stream_mail/2000/0023.html
Yes, I know it's a little odd that my colleague used an OpenMP version
on a single-CPU test, but I don't think that should invalidate the
result. I hope you agree.
Thanks
-john
Script started on Fri Dec 15 11:52:55 2000
# ./mcc_omp_20000613
n, offset, ntimes
4008399,0,10
----------------------------------------------
Double precision appears to have 16 digits of accuracy
Assuming 8 bytes per DOUBLE PRECISION word
----------------------------------------------
Array size = 4008399
Offset = 0
The total memory requirement is 91.74 MB
You are running each test 10 times
The *best* time for each test is used
----------------------------------------------------
Your clock granularity/precision appears to be 900 microseconds
The tests below will each take a time on the order
of 41000 microseconds
(= 46 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
----------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
----------------------------------------------------
Function Rate (MB/s) RMS time Min time Max time
Copy: 1341.7235 0.0495 0.0478 0.0596
Scale: 1314.2292 0.0497 0.0488 0.0498
Add: 1370.3928 0.0705 0.0702 0.0719
Triad: 1429.4439 0.0679 0.0673 0.0683
AvgBW: 1363.9474
Sum of a is = 4.622889697963963E+018
Sum of b is = 9.245779396823594E+017
Sum of c is = 1.232770586200085E+018
# exit
#
script done on Fri Dec 15 11:53:11 2000
This archive was generated by hypermail 2b29 : Sun Apr 29 2001 - 22:34:10 CDT