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!

Can You Beat This Score?page  1 2 3 

Chris H

Posts 65
15 Nov 2016 12:52


Even with the possible max clock rates cyclone iii or most other fpga's delivers, Apollo core will not reach that limitation whith its actual instruction set in my opinion. But you are right, speaking of an (speculative but surely in future possible) apollo-core asic design, this would be a topic.


Markus (mfro)

Posts 99
16 Nov 2016 07:54


Chris Holzapfel wrote:

  Even with the possible max clock rates cyclone iii or most other fpga's delivers, Apollo core will not reach that limitation whith its actual instruction set in my opinion. But you are right, speaking of an (speculative but surely in future possible) apollo-core asic design, this would be a topic.
 

 
  Would disagree here. With simple enough logic, the Cyclone III can easily reach timing at 200 MHz and more. If complexity wouldn't affect clock rate, there would be a x28 (or more) core.
 
  Achievable clock rate also heavily depends on the fill rate of the chip. As the Cyclone III has its PLLs located on the corners of the chip, clock networks can relatively easy be routed within the corresponding quadrant and you can still reach like 100Mhz.
 
  As soon as you need more chip area for your design, Fmax starts to drop drastically.


Gunnar von Boehn
(Apollo Team Member)
Posts 6207
16 Nov 2016 18:06


Someone was so nice to send me result of the EFIKA.
  Many thanks for this..
 
 
 
  EFIKA
  POWERPC 5200B @ 400 Mhz
 

 
 

  SORTBENCH 1.1 (Gunnar von Boehn)
  Its a CPU benchmark that stresses CPU, DCache and branch prediction.
  -------------------------------------------------------------
  1 K Element :  361.20 MB/sec
  2 K Element :  360.60 MB/sec
  4 K Element :  357.53 MB/sec
  8 K Element :  219.96 MB/sec
  16 K Element :  194.20 MB/sec
  32 K Element :  189.11 MB/sec
 



Gunnar von Boehn
(Apollo Team Member)
Posts 6207
16 Nov 2016 23:48


Continues improvement on the memory controller
did also performance of the Core is again.





Amiga 4Life

Posts 101
18 Nov 2016 06:25


thank you...


Mo Retro

Posts 241
18 Nov 2016 15:04


Whenever you think they've squeezed everything out of it, they come with an announcement that they got more out of it. :D

Hat off for Apollo Team. :D


Szyk Cech

Posts 191
18 Nov 2016 17:24


I am wonder how is this possible that one man is smarter than whole old Motorola staff?!?
It seems that it is kind of fun for him what is headache for others...


Wawa T

Posts 695
18 Nov 2016 20:55


moto has practically not developed this architecture since decades, with all respect to gunnar, the team and their professionality, i dont think they are doing whats impossible. its simply a well carried out focused project.

posts 48page  1 2 3