Some speed tests on QL hardware

Nagging hardware related question? Post here!
User avatar
bwinkel67
Gold Card
Posts: 327
Joined: Thu Oct 03, 2019 2:09 am

Some speed tests on QL hardware

Postby bwinkel67 » Fri Mar 27, 2020 12:46 am

A discussion on a different thread lead to some timings being run by Steve Poole with the table below. Thought I'd share with everyone since I found them useful:



stevepoole wrote:Hi Bwinkel69,
You may be interested in some more timing figures for the QL :

Code: Select all

CONFIGURATION                   CYCLES/SEC     +/- %    SPEED      REMARKS
---------------------------     -----------    ------   ------     ------------------------------------------------------
Ql 128ko JS                     ?              ?        ?          I don't wish to unplug my SuperGoldCard !
SGC QL under QDOS               1864           .25      x1         No extra multitasking from me.
SGC QL with SMSQ/E              8440           .11      x4.5       " " ROMdisc and Hermes.
Compaq, 1core, QPC2, 2.8Ghz     173894         37.2     x93        Very variable timings due to monocore multitasking.
Asus, 3core, QPC2, 1.9Ghz       138683         4.0      x90        Triple core means better variability when multitasking.
"     "      "     "            ?              ?        ?          C++ code runs 400 tmes faster than superbasic version !


Here is the program I used for the timings :

Code: Select all

100 ::
110 REMark Code_timer_bas by S.Poole, v25mar2020
120 REMark empty=168316 on QPC2 3core at 1.9Ghz...
125 CLEAR: overhead=93195: REMark {if d<>date: end if}...
130 CLS: y=PI: sum=0: Max=0: min=1E15: secs=10
135 z='3.141592654': BORDER 0
140 d=DATE: FOR wait=0 TO 1E9: IF d<>DATE: d=DATE: EXIT wait
150 :
160 FOR COUNTs=1 TO secs
170   FOR cycles=0 TO 1E9
180     IF d<>DATE: d=DATE: EXIT cycles
190     REMark
200   END FOR cycles
210   sum=sum+cycles: AT 1,1: PRINT secs-COUNTs!!!
220   IF cycles>Max: Max=cycles
230   IF cycles<min: min=cycles
240 END FOR COUNTs
250 dif=Max-min: hlf=dif/2: pc=(hlf*100)/Max
260 PRINT INT(sum/secs)!!'+/-'!pc;'%': BEEP 3276,1
270 ::
280 DEFine FuNction pie
290   RETurn 3.141593
300 END DEFine


I tested each basic operator for 600 seconds, to avoid bias from mutitasking, several times, with and without web access....
Usually, figures are fairly OK using 10 seconds !

The code to test, for example x=0, is placed between lines 180 and 200. The overhead is a constant and is best ignored.
You may wish to compare the timings with your QL configuration ...

The C++ speed was obtained using the transcribed 'QPC2 Travelleing Salesman Program', some 80ko long...
How does the bare 128ko QL fare ?

Regards,
Steve.


I will try and run this on my unexpanded QL when I get a minute.
Last edited by bwinkel67 on Fri Mar 27, 2020 8:02 am, edited 1 time in total.


stevepoole
Gold Card
Posts: 301
Joined: Mon Nov 24, 2014 2:03 pm

Re: Some speed tests on QL hardware

Postby stevepoole » Fri Mar 27, 2020 7:37 am

Hi All,

In the retabbing by Bwinkel67, read ' +/-% ' column. Many thanks for the retabbing.

Steve.


User avatar
bwinkel67
Gold Card
Posts: 327
Joined: Thu Oct 03, 2019 2:09 am

Re: Some speed tests on QL hardware

Postby bwinkel67 » Fri Mar 27, 2020 8:03 am

stevepoole wrote:Hi All,

In the retabbing by Bwinkel67, read ' +/-% ' column. Many thanks for the retabbing.

Steve.


Fixed.


stevepoole
Gold Card
Posts: 301
Joined: Mon Nov 24, 2014 2:03 pm

Re: Some speed tests on QL hardware

Postby stevepoole » Sat Mar 28, 2020 10:48 am

Hi All,

Just got a result from a friend with an AMD, w10, 1.46Ghz, Qemulator :
fast mode gets 16551 loops, 128k mode gets 141. ( speed factor of x117 ! )


What speed does a real 128k QL achieve ? (In order to define speed factor = 1...)

Regards,
Steve.



Who is online

Users browsing this forum: No registered users and 3 guests