Jump to content
IGNORED

Benchmarking...


vol

Recommended Posts

3 minutes ago, ParanoidLittleMan said:

I did not mean that Atari's 50066 Hz was bad for sound quality or like - just that was not compatible.

I agree that this frequency is very unusual, I don't know of any other system which uses it.

Link to comment
Share on other sites

3 minutes ago, ParanoidLittleMan said:

I did not mean that Atari's 50066 Hz was bad for sound quality or like - just that was not compatible.

I remember that I tested the DMA sound on different machines and that the actuel frequencies were not exactly the same on a TT and on a STE.

I made tests (a large sound that I played with DMA measuring the time).

It appeared that on a TT (compared to a STE):

    remplace 12517 with 12584,
    remplace 25033 with 25169,
    remplace 50066 with 50337.

Then, I went on investigating...

The DMA sound seems to be driven by a clock derived from the CPU clock.

On the TT, the crystal is at 32 215 906 Hz (the double of the VME clock that is documented to be 16.107953 MHz).

and:

 

32 215 906 / 2560 = 12584

32 215 906 / 1280 = 25169

32 215 906 / 640  = 50337

 

That looks correct to me.

 

So, the DMA on the STE must derive from the CPU clock, something like:

8 010 880 / 640 = 12517

A CPU clock at 8,01088 MHz.

 

Guillaume.

Link to comment
Share on other sites

4 hours ago, vol said:

Thank you very much.  Your Atari is the fastest in my tables that have just been updated.  It is interesting that the 68020 and 68030 show almost identical performance.

 

Just wait until someone with a 50mhz Pak 68/3 board with FAST RAM, or a

TT030 with a working Cattamaran @48mzh and FAST RAM runs this, won't

be in front long...  :)

 

Link to comment
Share on other sites

Yes, I expected that someone will see that those 50066, 25033 freqs are just divided from main, roughly 32 MHz clock, or rather from roughly 8 MHz for CPU. That way Atari saved on one crystal.

I had no clue about exact clock in TTs, and will avoid to listen music, played so rushed on it ?

 

And to add that freqs are for sure not exactly same in NTSC  (America) and PAL (Europe) STEs (as it is with STFMs too) . There is slight diff. , and the reason is avoiding interference with color carrier in NTSC or PAL encoder.  I googled little, but instead exact crystal freqs found another sad example how some 'experts' are poor with knowledge: https://comp.sys.atari.st.narkive.com/vUJrGBhT/atari-st-crystal-frequencies

 

Link to comment
Share on other sites

21 hours ago, vol said:

...

Thank you very much.  Your Atari is the fastest in my tables that have just been updated.  It is interesting that the 68020 and 68030 show almost identical performance.

As I know 68030 is 68020 with added PMMU unit. And maybe with more flexible data lines - can be set for 32, 16 and ? 8 bit wide bus. 

What hurts is that was launched later than 80386 - so blame not only Atari, but Motorola too for losing market .

And about prices:  PCs with 32 bit 80386 were too expensive, even around 1993, 80386SX was what was sold then more .

Link to comment
Share on other sites

19 minutes ago, ParanoidLittleMan said:

Yes, I expected that someone will see that those 50066, 25033 freqs are just divided from main, roughly 32 MHz clock, or rather from roughly 8 MHz for CPU. That way Atari saved on one crystal.

I had no clue about exact clock in TTs, and will avoid to listen music, played so rushed on it ?

 

And to add that freqs are for sure not exactly same in NTSC  (America) and PAL (Europe) STEs (as it is with STFMs too) . There is slight diff. , and the reason is avoiding interference with color carrier in NTSC or PAL encoder.  I googled little, but instead exact crystal freqs found another sad example how some 'experts' are poor with knowledge: https://comp.sys.atari.st.narkive.com/vUJrGBhT/atari-st-crystal-frequencies

 

If you want to test the actual DMA soudnfrequencies on one particular machine, you can use my little tool !

 

Guillaume.

dmasound.zip

Link to comment
Share on other sites

On 5/4/2021 at 7:56 PM, DarkLord said:

 

Just wait until someone with a 50mhz Pak 68/3 board with FAST RAM, or a

TT030 with a working Cattamaran @48mzh and FAST RAM runs this, won't

be in front long...  :)

 

I happen to have that exact TT setup. Next time I am in Maine I’ll give it a try.

  • Like 1
Link to comment
Share on other sites

6 hours ago, ParanoidLittleMan said:

Hurra ! Instead Amiga vs ST war we have now TT vs Paked Stacy war ?   Sorry, could not resist ?

Serious mode on: That PAK 68/3 in Stacy - is it using regular ST video/graphic HW or there is some added graphic module, card - like Nova  ?

 

Funny.  :)

 

Nothing special about the video hardware. It's the stock monochrome LCD screen that comes with a STacy.

 

640 x 400 resolution.

 

Link to comment
Share on other sites

10 hours ago, ParanoidLittleMan said:

Hurra ! Instead Amiga vs ST war we have now TT vs Paked Stacy war ?   Sorry, could not resist ?

Serious mode on: That PAK 68/3 in Stacy - is it using regular ST video/graphic HW or there is some added graphic module, card - like Nova  ?

The Atari ST is just a bit faster than the Amiga but the Amiga has its advantages too. ;)  It is interesting that this resembles the situation with the Atari 800 and Commodore 64.  History repeated itself. :) It is also interesting that the Apple II and first Macs were slower than the Commodore 64 and Amiga and had less impressive graphics/sound than the Atari 800 and Atari ST but Apple beat Commodore and Atari.

Edited by vol
Link to comment
Share on other sites

An Amiga guy has been able to do an almost impossible thing and find a way to make the algorithm implementation faster a little.  He also helped to prove that the 68020/30 code is actually faster than the 68000 code now.  So please help me again.  Run pi-st and pi-st30 on your hardware for me (100/1000/3000 digits).  I am sure that further improvements are impossible so this is rather my last request. 

pi-st-6.zip

Edited by vol
Link to comment
Share on other sites

Okay, here are my results (still on my STacy, equipped with a Pak 68/3 board running at 40mhz, FPU 40mhz, 4 megs of ST RAM, TOS v3.06)

 

Pi-ST TOS:

 

100 - .04

1000 - 1.59

3000 - 13.02

 

Pi-ST30 TOS:

 

100 - .04

1000 - 1.58

3000 - 12.96

 

Hope this helps.  :)

 

  • Like 1
Link to comment
Share on other sites

Pi-pack #55 has been released and the tables are updated! :) It doesn't contain more speed optimized programs for the Atari ST.  So for the benchmarks the attached programs may be used.

BTW I am curious about NVDI.  Is it popular among the Atari ST users? Is it compatible with all Atari software?

On 5/17/2021 at 5:02 AM, DarkLord said:

Okay, here are my results (still on my STacy, equipped with a Pak 68/3 board running at 40mhz, FPU 40mhz, 4 megs of ST RAM, TOS v3.06)

 

Pi-ST TOS:

100 - .04

1000 - 1.59

3000 - 13.02

 

Pi-ST30 TOS:

100 - .04

1000 - 1.58

3000 - 12.96

Thank you very much.  Your results have corrected much my estimations. PI-ST30 shows better results than PI-ST! :) 

It is sad that there are still no other results. :( It seems I am out of luck here. :( Maybe I should go to Atari Forum...  People there helped me to get results from the Falcon.  However they ran only PI-ST30 and skipped PI-ST. :( I am still gathering results for the Atari Falcon (PI-ST), TT (STRAM and TTRAM), MegaSTE @16Mhz, other popular Atari hardware based on 68030+ released before 1997.  Any help is welcome!  Thanks a million in advance.

 

Link to comment
Share on other sites

I would say NVDI is pretty popular. I've got it here (although I don't

usually activate it during benchmark tests unless requested to do so)

and it runs fine on all my machines (Falcon, STacy, Mega STe, Mega ST)

 

It does make the desktop seem much faster. I'm sure it's listed on the

Atari ST Essentials Software List at Atari Forum. I'd probably go so far

as to call it a staple.

 

HTHs.  :)
 

  • Like 1
Link to comment
Share on other sites

OK, Here my runs.

 

TT@48mhz w/normal boot (NVDI). PI-ST.TOS:

  100 - 0.02

  1000 - 1.34

  3000 - 11.66

TT@48mhz w/normal boot (NVDI). PI-ST30.TOS:

  100 - 0.03

  1000 - 1.34

  3000 - 11.67

TT@48mhz w/clean boot. PI-ST.TOS:

  100 - 0.05

  1000 - 1.63

  3000 - 12.54

TT@48mhz w/clean boot. PI-ST30.TOS:

  100 - 0.05

  1000 - 1.63

  3000 - 12.54

 

So I see no difference between the two programs.

 

For Reference. TT@32mhz w/clean boot. PI.ST.TOS:

  100 - 0.06

  1000 - 2.08

  3000 - 16.56

  • Like 1
Link to comment
Share on other sites

2 hours ago, mdivancic said:

OK, Here my runs.

 

TT@48mhz w/normal boot (NVDI). PI-ST.TOS:

  100 - 0.02

  1000 - 1.34

  3000 - 11.66

TT@48mhz w/normal boot (NVDI). PI-ST30.TOS:

  100 - 0.03

  1000 - 1.34

  3000 - 11.67

TT@48mhz w/clean boot. PI-ST.TOS:

  100 - 0.05

  1000 - 1.63

  3000 - 12.54

TT@48mhz w/clean boot. PI-ST30.TOS:

  100 - 0.05

  1000 - 1.63

  3000 - 12.54

 

So I see no difference between the two programs.

 

For Reference. TT@32mhz w/clean boot. PI.ST.TOS:

  100 - 0.06

  1000 - 2.08

  3000 - 16.56

Thank you very much.  Please inform me what exactly is your TT system @48MHz?  What card does it use?

Did you run PI-ST30.TOS on the TT@32MHz?

It is very strange for me that there is no difference between the two programs.  Let's look at the next table.

                      68020       68030
  moveq.l #0,d0       0-2-3       2-2
  move.l d0,d1        0-2-3       2-2
  lsl.l #3,d0         1-4-4       4-4
  sub.l d0,d1         0-2-3       2-2
  add.l d0,d0         0-2-3       2-2
  sub.l d0,d1         0-2-3       2-2
  sub.l d0,d1         0-2-3       2-2
  lsl.l #8,d1         1-4-4       4-4
  sub.l d1,d0         0-2-3       2-2
                      2-22-29     22-22

  mulu d1,d0          25-27-28    28-28

PI-ST30 uses MULU-optimization, it uses a longer sequence of instructions instead of MULU (D1=10000).  Timings clearly show that we must get at least 6 cycles gain for the 68030...  Does your system use the 68030?

Link to comment
Share on other sites

2 hours ago, mdivancic said:

I used V6, was that the latest version? The TT has a CaTTram accelerator which boost the CPU frequency to 48 mhz. I did not run PI-ST30.TOS at 32 mhz, didn’t see any reason to do so. Yes the cpu is a 68030.

The latest version is on github.  However the speed must remain the same as with V6.  It was not easy to find any information about the CaTTamaran accelerator - I has been able to find only this page in Polish dedicated to it - is it your card?  You wrote "a CaTTram accelerator" so I have some doubts.  I assume that this accelerator doesn't have TTRAM but your system may have it.  Could you provide this detail too? 

The reason to run PI-ST30 was in my request. :) I want to understand timings of the 68030 - it is not easy.  It seems I need to start a new topic about oddities of these timings.  I really can't understand while PI-ST and PI-ST30 show the same time.  My current guess is the MULU.W instruction may be faster than 28 cycles on the 68030 in some cases.

Edited by vol
Link to comment
Share on other sites

1 hour ago, vol said:

The latest version is on github.  However the speed must remain the same as with V6.  It was not easy to find any information about the CaTTamaran accelerator - I has been able to find only this page in Polish dedicated to it - is it your card?  You wrote "a CaTTram accelerator" so I have some doubts.  I assume that this accelerator doesn't have TTRAM but your system may have it.  Could you provide this detail too? 

The reason to run PI-ST30 was in my request. :) I want to understand timings of the 68030 - it is not easy.  It seems I need to start a new topic about oddities of these timings.  I really can't understand while PI-ST and PI-ST30 show the same time.  My current guess is the MULU.W instruction may be faster than 28 cycles on the 68030 in some cases.

The CaTTamaran was an accelerator made here in Canada back in 1994 by Cybercube Research Limited (sometimes referred to as CyRel).  It is a small board that is fitted to the ST-RAM card and connects to various pins on the mainboard via wires.  It does not have its own RAM, it's only function is to increase the clock cycles of the 68030 processor and FPU by 150% (48MHz).  The speeds that mdivancic reported at 32Mhz and 48Mhz confirm that my CaTTamaran is either not functioning or hooked up properly.  It was pre-installed in the machine when I bought it 20 years ago and it's possible it has never been working for me.

  • Like 1
Link to comment
Share on other sites

I remember CaTTamarans were a big hit back then because it increased the speed of the TT to 48 MHz and it only cost $99. Unfortunately, people started complaining that it started damaging TTs, so (at least) my local dealer stopped selling and installing them because of that. I wouldn't be surprised if your CaTTamaran failed. Maybe it would be good to remove it?

  • Like 1
Link to comment
Share on other sites

The CaTTamaran is working fine. I get the expected results when I run GemBench or other programs. I have 16mb of TT ram and 4 mb of ST ram. Plus I can switch between 32/48 without a problem. In fact you can see a speed increase in the results above. Also the CaTTamaran doesn’t boast the TT’s video speed. I do need to pull my TT apart and do some work. I need a new RTC battery and I want to print a new hard drive bay cover so I can access the SD card in my SCSI2SD. I can double check the install at this time. 

 

I ran the test again with the program set to run in TT Ram.

 

TT@48mhz w/clean boot. PI-ST30.TOS:

  100 - 0.05

  1000 - 1.45

  3000 - 10.99

  • Like 1
Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...
  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...