6502.org Forum  Projects  Code  Documents  Tools  Forum
It is currently Wed Oct 02, 2024 4:32 am

All times are UTC




Post new topic Reply to topic  [ 5 posts ] 
Author Message
PostPosted: Sat Jan 05, 2019 8:13 pm 
Offline
User avatar

Joined: Thu Dec 11, 2008 1:28 pm
Posts: 10943
Location: England
Found in Pete Foley's online resumé, under Other Projects:
Quote:
A RISC based implementation of the Apple II 6502 Processor: In mid ’85 I performed an analysis that showed a simple RISC style implementation of a 16‐bit binary compatible superset of the 8‐bit microprocessor used in the Apple II 6502, along with some judicious use of on‐chip caching, could substantially improve performance – to the point of potentially outperforming the 68000 used in the Mac, and given the simplicity of the 6502 the implementation was “doable” by a small team. This was a more direct approach than emulating 6502 compiled binaries by a different processor as was done some four years later in the Mobius project in the Advanced Technology Group (ATG). I set about completing a feasibility study that went through several revisions (Turbo‐I and Turbo‐II), which included a complete micro‐architecture design of the processor along with resource usage diagrams for every clock phase of every instruction. When the design seemed solid and I was ready to move on to an implementation, I sought the counsel and the support of my mentors in the IC Technology group (to whom I owe a huge debt of gratitude), Bob Bailey and Walt Peschke. As usual, when they felt it was time to impart some wisdom upon me, they said, “Pete, lets go for a walk”. As we walked around the local residential neighborhood in Cupertino they explained to me that marketing/sales/biz dev would have no idea what to do (how to position, etc) with such a thing and I would just end up with a black eye. Of course they were right and I stopped working on it.

via this discussion on Hacker News.

Edit: fix linkrot


Last edited by BigEd on Wed Mar 16, 2022 5:51 pm, edited 2 times in total.

Top
 Profile  
Reply with quote  
PostPosted: Sat Jan 05, 2019 8:15 pm 
Offline
User avatar

Joined: Thu Dec 11, 2008 1:28 pm
Posts: 10943
Location: England
Some interesting (unrelated) comments about his time on the Newton project here.

Edit: fix linkrot


Last edited by BigEd on Wed Mar 16, 2022 5:52 pm, edited 1 time in total.

Top
 Profile  
Reply with quote  
PostPosted: Tue Jan 08, 2019 3:01 pm 
Offline

Joined: Fri Apr 06, 2018 4:20 pm
Posts: 94
Sounds a lot like this site's 65org16 core with some cache.

I am not opposed to cache, but if you added cache to any 80s processor it would have sped things up considerably (especially X86 and 68K which accessed main memory every four cycles, being able to access cache every cycle would have been huge). You lose the deterministic nature of timing, but it seems the only way to get around the expensive, fast memory that the 65xx processors required.

If you weren't concerned about multitasking, I've always thought simply putting the Zero Page and Stack on chip would allow the 6502 to go quite fast.


Top
 Profile  
Reply with quote  
PostPosted: Tue Jan 08, 2019 8:53 pm 
Offline

Joined: Mon May 21, 2018 8:09 pm
Posts: 1462
If you call 250ns access times (for a 2MHz Phi2 clock) "fast" and "expensive"…

At the time, RAM was actually faster than CPU logic, so micros of the time were quite happy to access the RAM twice per cycle, once for the CPU and once for the video output. This involved a full RAS-CAS-refresh cycle twice per CPU cycle, and the BBC Micro (which ran at 2MHz and had a lot of goodies) was still reasonably affordable.

Not too long afterwards, 70ns FPM DRAM modules were in regular use in PCs and Macs.


Top
 Profile  
Reply with quote  
PostPosted: Tue Jan 08, 2019 8:59 pm 
Offline
User avatar

Joined: Thu Dec 11, 2008 1:28 pm
Posts: 10943
Location: England
There is still a family difference between the micros which expect to work with single-cycle memory and those which take a faster CPU clock and use several cycles for a memory access.

For explorations around making faster 6502 implementations by accelerating zero page and stack, these days on-chip memory of that size is no obstacle at all, but it was (I think) well after the 70s that you could casually have 512 bytes of RAM on board your micro. So, back then, we could consider small caches and buffers, but now we could have 16-bit access to zero page and to stack, decouple instruction fetch from decode, and quite possibly get major speedups.

That said, such ideas have been discussed before and not yet implemented. Maybe some day someone will feel they have the interest and expertise.


Top
 Profile  
Reply with quote  
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 5 posts ] 

All times are UTC


Who is online

Users browsing this forum: Google [Bot] and 8 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to: