performance right?
|
View:
New views
3 Messages
—
Rating Filter:
Alert me
|
 |
performance right?
by Mathew Yeates
::
Rate this Message:
I got the following results from "make time". Does this look right? I
was thinking that the "reference" and "present" columns would be different. Maybe I don't understand what is being measured. Mathew ------------------------------------------------------------------------- SF.Net email is sponsored by: The Future of Linux Business White Paper from Novell. From the desktop to the data center, Linux is going mainstream. Let it simplify your IT future. http://altfarm.mediaplex.com/ad/ck/8857-50307-18918-4 _______________________________________________ Math-atlas-devel mailing list Math-atlas-devel@... https://lists.sourceforge.net/lists/listinfo/math-atlas-devel |
|
|
Re: performance right?
by Mathew Yeates
::
Rate this Message:
Mathew Yeates wrote:
> I got the following results from "make time". Does this look right? I > was thinking that the "reference" and "present" columns would be > different. Maybe I don't understand what is being measured. > > Mathew > > doh! here are the numbers Reference clock rate=2394Mhz, new rate=2660Mhz Refrenc : % of clock rate achieved by reference install Present : % of clock rate achieved by present ATLAS install single precision double precision ******************************** ******************************* real complex real complex --------------- --------------- --------------- --------------- Benchmark Refrenc Present Refrenc Present Refrenc Present Refrenc Present ========= ======= ======= ======= ======= ======= ======= ======= ======= kSelMM 535.0 521.4 525.4 497.5 311.5 297.0 298.0 283.5 kGenMM 175.5 163.8 175.5 166.6 160.5 153.7 165.4 151.3 kMM_NT 145.2 123.7 149.3 131.4 135.3 116.1 132.3 122.1 kMM_TN 163.2 141.3 161.1 158.4 148.7 133.2 146.0 145.9 BIG_MM 510.1 499.5 504.0 518.4 307.7 269.3 293.0 289.9 kMV_N 113.5 70.6 216.9 122.0 58.9 38.4 97.4 52.9 kMV_T 89.9 63.1 94.6 85.0 47.2 34.2 74.1 54.5 kGER 154.2 141.3 119.4 98.8 29.1 24.1 46.8 39.7 ------------------------------------------------------------------------- SF.Net email is sponsored by: The Future of Linux Business White Paper from Novell. From the desktop to the data center, Linux is going mainstream. Let it simplify your IT future. http://altfarm.mediaplex.com/ad/ck/8857-50307-18918-4 _______________________________________________ Math-atlas-devel mailing list Math-atlas-devel@... https://lists.sourceforge.net/lists/listinfo/math-atlas-devel |
|
|
Re: performance right?
by Clint Whaley
::
Rate this Message:
Mathew,
> I got the following results from "make time". Does this look right? I > was thinking that the "reference" and "present" columns would be > different. Maybe I don't understand what is being measured. This number look reasonable to me. The reference install is on a slower machine, and you will typically get less % of a higher peak . . . Also, that's my home machine (I think: Core2Duo, right?), and it was built from parts by me, and appears to have faster memory access than a lot of preassembled machines . . . Cheers, Clint ************************************************************************** ** R. Clint Whaley, PhD ** Assist Prof, UTSA ** www.cs.utsa.edu/~whaley ** ************************************************************************** ------------------------------------------------------------------------- SF.Net email is sponsored by: The Future of Linux Business White Paper from Novell. From the desktop to the data center, Linux is going mainstream. Let it simplify your IT future. http://altfarm.mediaplex.com/ad/ck/8857-50307-18918-4 _______________________________________________ Math-atlas-devel mailing list Math-atlas-devel@... https://lists.sourceforge.net/lists/listinfo/math-atlas-devel |
| Free embeddable forum powered by Nabble | Forum Help |
