John,
I got the binary files from your VA web page. I ran the regular one
first, with lots of normal stuff open
and running (Sarafi - browser, and the Mail client) and then I shut
down everything else.... and got
identical results:
Power Mac with the 5200 rpm disk (80 gig) ~1.4 gHz cpu, about one
month old.
Hardware Overview:
Machine Model: PowerBook5,3
CPU Type: PowerPC G4 (1.1)
Number Of CPUs: 1
CPU Speed: 1.33 GHz
L2 Cache (per CPU): 512 KB
Memory: 1 GB
Bus Speed: 167 MHz
Boot ROM Version: 4.71f1
Serial Number: V740847UP21
Software:
System Software Overview:
System Version: Mac OS X 10.3.3 (7F44)
Kernel Version: Darwin 7.3.0
Boot Volume: Macintosh HD
Computer Name: Tony Sturges’ Computer
User Name: Tony Sturges (tony)
============
Stream PPC base . out
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 400000, Offset = 0
Total memory required = 9.2 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 12 microseconds.
Each test below will take on the order of 9310 microseconds.
(= 775 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: 565.3211 0.0125 0.0113 0.0158
Scale: 534.4021 0.0126 0.0120 0.0135
Add: 599.1761 0.0165 0.0160 0.0172
Triad: 596.8293 0.0173 0.0161 0.0224
==============================================================
then i ran your optimized one- PPC601 Opt. out; I don't know if this
means it is optimized for
some Power PC cpu other than the G4 (I know from nothing about the
Macs) It ran a good bit
faster that the first one, but 'way short of the 2000 estimate I saw on
your web page for peak
megaflops. ??
==============================================================
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 400000, Offset = 0
Total memory required = 9.2 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 12 microseconds.
Each test below will take on the order of 9404 microseconds.
(= 783 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: 760.6370 0.0092 0.0084 0.0116
Scale: 755.9650 0.0099 0.0085 0.0160
Add: 809.1706 0.0123 0.0119 0.0131
Triad: 916.9930 0.0108 0.0105 0.0113
Received on Sun Mar 28 20:38:14 2004
This archive was generated by hypermail 2.1.8 : Sat Apr 03 2004 - 14:56:51 CST