Overview Features Coding ApolloOS Performance Forum Downloads Products Order Contact

Welcome to the Apollo Forum

This forum is for people interested in the APOLLO CPU.
Please read the forum usage manual.
Please visit our Apollo-Discord Server for support.



All TopicsNewsPerformanceGamesDemosApolloVampireAROSWorkbenchATARIReleases
Performance and Benchmark Results!

Vampire : Again Record Breaking

Gunnar von Boehn
(Apollo Team Member)
Posts 6207
22 Jan 2018 15:09


Improved Speed on VAMP 2 GOLD 2.7 (high clocked)

maximum memory Speed

memory Speed with truecolor WB on



Vojin Vidanovic

Posts 770
22 Jan 2018 20:00


Great "old Amiga 500"! Memory performance is nice, now effort can be put elsewhere :-)
   
  I just wonder how v2 is pimped to 106.4Mhz (X15) when standard one was 78Mhz (X11). Its really a nice clock jump and I hope it can be standard on v4 Vamps.
   
  And voila, officially we brake the first pure 100Mhz barrier with quite improved MIPS per Mhz performance.
   
  Past results from
  CLICK HERE  were
 

  AMIGA BUSTEST  -  READL  Score
  ------------------------------------------
     
  VAMPIRE 2                    658.9 / 529.5 MB/sec  (world record!)
     
  x1000 AMIGA-1 PA6T 1800 MHz  285.6 MB/sec
  MOS IBook  PPC G4 1400 MHz  185.4 MB/sec
  MOS MacMini PPC G4 1500 MHz  184.3 MB/sec
  OS4 SAM PPC 460    1100 MHz  109.7 MB/sec
  OS4 SAM PPC 440    667 MHz    91.1 MB/sec
  OS4 Peg2 PPC G4    1000 MHz    80.6 MB/sec 
         
  CyberStormPPC 68060@50        55.1 MB/sec
  Apollo 1240  68040@40        47.8 MB/sec
  FPGA ARCADE                    29.0 MB/sec 
  Blizzard 1230 68030@50        24.3 MB/sec
  Typhoon MK2 68030@40          18.8 MB/sec
  AMIGA 4000 68040@25            11.5 MB/sec
  AMIGA 1200 ACA 1220            10.9 MB/sec
  Zeus 68000 50 Mhz              9.1 MB/sec
 



Thierry Atheist

Posts 644
23 Jan 2018 00:50


Vojin Vidanovic wrote:
I just wonder how v2 is pimped to 106.4Mhz (X15) when standard one was 78Mhz (X11). Its really a nice clock jump and I hope it can be standard on v4 Vamps.

Since the Vampire 4 is supposed to be 30% faster than the 78 MHz V2 and 106.4 MHz is 36.4% faster than the 78 MHz Vampire, that means that the Vampire 2 X15 is 4.93% faster than a Vampire 4!!!



Mallagan Bellator

Posts 393
23 Jan 2018 01:41


I really like reading about those performance updates. Thanks Gunnar ;) it’s really awesome!

Something I’ve been wondering for a while, but not been able to figure out. Is this Apollo team the same guys who made and sold the old apollo accelerators way back? Or totally unrelated?


Gregthe Canuck

Posts 274
23 Jan 2018 02:57


Unrelated.

Apollo = Core,  Vampire = Accelerator




Vojin Vidanovic

Posts 770
23 Jan 2018 04:44


Thierry Atheist wrote:

  Since the Vampire 4 is supposed to be 30% faster than the 78 MHz V2 and 106.4 MHz is 36.4% faster than the 78 MHz Vampire, that means that the Vampire 2 X15 is 4.93% faster than a Vampire 4!!!

Or better, if v4 is  pimped to this +36,4% freq, and is 30% faster with RAM and cache, you get your faster Vamp dream for free (for now!)



Vojin Vidanovic

Posts 770
23 Jan 2018 04:53


Mallagan Bellator wrote:

  Something I’ve been wondering for a while, but not been able to figure out. Is this Apollo team the same guys who made and sold the old apollo accelerators way back? Or totally unrelated?

No, but they were partially same people working on "one side of Natami". Its just name of Greek God that relates them to e.g. Apollo 2030 Turbo and ACT Elektronik, Germany (producer or 90s cards).



Thierry Atheist

Posts 644
23 Jan 2018 08:25


Vojin Vidanovic wrote:
Thierry Atheist wrote:
Since the Vampire 4 is supposed to be 30% faster than the 78 MHz V2 and 106.4 MHz is 36.4% faster than the 78 MHz Vampire, that means that the Vampire 2 X15 is 4.93% faster than a Vampire 4!!!

Or better, if v4 is  pimped to this +36,4% freq, and is 30% faster with RAM and cache, you get your faster Vamp dream for free (for now!)

Hi Vojin!

Now THAT would be.... TOTALLY TOTALLY EXCELLENT!!!!!


Vojin Vidanovic

Posts 770
23 Jan 2018 10:25


Thierry Atheist wrote:

    Hi Vojin!
   
    Now THAT would be.... TOTALLY TOTALLY EXCELLENT!!!!!
   

   
    Hope to see it v4 results this year ... Example is this READL score
   
    VAMPIRE 2 X15 GOLD2.7      658.9 MB/s    (this new record)
    VAMPIRE 2 X11 GOLD2.5      529.5 MB/sec  (world record 2017!)
   
    would expect V4 X11 GOLD3 to be at least 600-640MB/s, due to better cache and DDR3 RAM (which should be RAMs transfer limit also). But great efficiency of memory controller.
   
    Current perf. advertised is CPU score jump from 200Mhz 060 (v2 Vamp) to 250MHz 68060 (v4 vamp).
   
    First v4 Sysinfo Nov 017 by Renaud Schweingruber were 92 MIPS and 37.7 MFLOPS (Vampire v4 X11)
   
    One in all, we can only hope to see future v4 marks.


Tango One

Posts 102
23 Jan 2018 13:28


Can we see some benchmark from V4. ?


Vojin Vidanovic

Posts 770
23 Jan 2018 13:30


tango one wrote:

  Can we see some benchmark from V4. ?
 

 
  The first, one and only is the Sysinfo test result on an video of V4 X11 seems to be booting on an A500+ and currently (Nov 2017) sees only 128mb RAM
  EXTERNAL LINK 
  So my guess is a lot of tuning is needed before public, but it lives!
 
  And MFLOPS result is stronger then on v2 with 2.7 core (full h/w FPU)


Martin Soerensen

Posts 232
23 Jan 2018 14:37


Nice one. I guess that if you stuck this in an A1000, that would probably also make it the world's fastest A1000? :)


Vojin Vidanovic

Posts 770
23 Jan 2018 15:12


Martin Soerensen wrote:

  Nice one. I guess that if you stuck this in an A1000, that would probably also make it the world's fastest A1000? :)
 

 
  You lucky one, having the original lady, even its oldest one!
 
  Well, yes, first v4 models seems to be "Vampire 500 V4" for A500, A1000 and 2000 with adaptor (as with  current Vampire 500 V2) , bringing "world fastests A500/A1000/A2000" once again..
 
  Its also featured at "products page" just not yet widely avail :-)
  CLICK HERE 

posts 13