Welcome, Guest. Please login or register.

Author Topic: Lets talk about A1222 - Tabor  (Read 40217 times)

Description:

0 Members and 1 Guest are viewing this topic.

Offline yssing

  • Hero Member
  • *****
  • Join Date: Apr 2002
  • Posts: 1517
    • Show only replies by yssing
    • http://www.yssing.org
Re: Lets talk about A1222 - Tabor
« Reply #29 on: October 23, 2017, 10:02:38 AM »
Well i was hoping for more..
 

Offline kamelito

Re: Lets talk about A1222 - Tabor
« Reply #30 on: October 23, 2017, 12:20:07 PM »
Daniel aka Daytona wrote in the youtube message stream that for now he didn't encounter any performance issue with the Tabor while porting Wings and Tower 57
Kamelito
 

Offline Niding

  • Hero Member
  • *****
  • Join Date: Sep 2004
  • Posts: 566
    • Show only replies by Niding
Re: Lets talk about A1222 - Tabor
« Reply #31 on: October 23, 2017, 12:25:14 PM »
@kamelito

Indeed. If there are anyone on the amigascene I will listen to, its Daniel. Ive never encountered anyone that is to such a degree a "cut the bull%&$#?@!%&$#?@!%&$#?@!%&$#?@!" kinda guy. And its very refreshing.

He did comment that he wasnt overly excited by the CPU choice, but at the end of the day he seemed content with the performance of the Tabor.

Maybe he will chime in with his own comments regarding this.
 

Offline Iggy

  • Hero Member
  • *****
  • Join Date: Aug 2009
  • Posts: 5348
    • Show only replies by Iggy
Re: Lets talk about A1222 - Tabor
« Reply #32 on: October 23, 2017, 01:57:29 PM »
Quote from: Niding;832092
@kamelito

Indeed. If there are anyone on the amigascene I will listen to, its Daniel. Ive never encountered anyone that is to such a degree a "cut the bull%&$#?@!%&$#?@!%&$#?@!%&$#?@!" kinda guy. And its very refreshing.

He did comment that he wasnt overly excited by the CPU choice, but at the end of the day he seemed content with the performance of the Tabor.

Maybe he will chime in with his own comments regarding this.


It would be refreshing, as even I don't appreciate a constant stream of negativity.
And I've repeatedly said I wouldn't continue to post the facts contained in my last post, as it is a bit pointless. This IS happening.
And HEY, I still get what I want, so WTF, eh?

If its adequate for YOUR uses, and it fits your budget, I'd say go for it.
Do NOT make your choices based on mine.
We are very likely to have different goals and preferences.
"Not making any hard and fast rules means that the moderators can use their good judgment in moderation, and we think the results speak for themselves." - Amiga.org, terms of service

"You, got to stem the evil tide, and keep it on the the inside" - Rogers Waters

"God was never on your side" - Lemmy

Amiga! "Our appeal has become more selective"
 

Offline Daytona675x

  • Newbie
  • *
  • Join Date: Oct 2014
  • Posts: 46
    • Show only replies by Daytona675x
    • http://www.goldencode.de
Re: Lets talk about A1222 - Tabor
« Reply #33 on: October 23, 2017, 02:41:17 PM »
@kamelito
Quote
Daniel aka Daytona wrote in the youtube message stream that for now he didn't encounter any performance issue with the Tabor while porting Wings and Tower 57
That's not entirely correct ;) I did not mention Wings in that context. It was about T57, at least I meant it to be about T57 only.
Of course I encountered performance issues - but I was able to solve them by coming up with the native SPE build of T57. With that build there are no performance issues :)

@Niding
Quote
He did comment that he wasnt overly excited by the CPU choice, but at the end of the day he seemed content with the performance of the Tabor.
Right, of course I'd prefer a CPU with a std. FPU, who wouldn't. First of all that SPE thingy means lots of trouble.
The AOS4 pre-release version I got contains a first version of the FPU emulation. It's performance is good enough as long as not too much FPU code has to be emulated. But most important: it works reliable.

However, at this moment I am only happy with the Tabor's float-performanceif the code is either SPE native or only contains few FPU instructions to be emulated.

But, luckily, Thomas Frieden is working on, let's call it "FPU turbo emulation" (I don't know how much I'm allowed to say) and I know that he's making good progress with that. I'm pretty confident that this thing will solve most performance issues with non-native code.

And that's what I mean with "at the end of the day":
While at the moment the performance is fine for my T57 adventure, I'm confident that once Thomas finishes the work on emu-v2 it will also be good for most other float-hungry non-native stuff.
I'd suggest to give the Tabor a chance to show its full potential, and that means:

let the Hyperion guys first finish their work on the OS and don't be so negative yet. I bet they weren't overly excited by the CPU choice neither - but they are actually solving those issues, I guess some moral support won't hurt :)

The Tabor's CPU is pretty fast so IMHO chances are good that at the end of the day we'll end up with a system that performs ~ up to 1.5 times as fast as the 460 for native- or int-code and around 460-speed for code with rather huge amounts of code to be emulated in one way or the other.
Don't nail me on any of this though, it's just my opinion / my guess based on what I saw / experienced / know so far. We'll see.

So much to my opinion. Regarding those two games on Tabor:

T57: when using SPE directly then the performance is nice. When using std. FPU commands then performance is low, although not as low as one might expect considering all those exceptions and emulated FPU commands.

Wings: I didn't even try it on Tabor yet :) The problem with Wings is that it's based on good old Warp3D. So internally it does looooots of vertex transformations and stuff like that. This would be too much to ask from the current FPU emulation.
Now you might say: then do like you did for T57 and compile it for SPE.
Unfortunately that isn't that easy as it is for T57.
To make a long story short: compiled for SPE = code without those 32 FPU registers (SPE uses the GPRs). And this becomes a problem when calling library functions (e.g. Warp3D) which expect floats in FPU registers...
So either the game's float-code was emulated - then the data ended up in the emulated registers and all is good - but slow.
Or the game's float-code was SPE native - then the data ended up in a GPR - but the lib-function expects it inside an (emulated) FPU rgister, where it never appeared.
With T57 it was much easier because I do almost everything in software myself and the few libs I rely on aren't critical (or I wrote replacement functions).
I'll wait for the new turbo-emu before playing around with Wings on Tabor.
AmigaOS 4.1 FE (sam440ep, sam460ex, X5000, Tabor,  R200 / RadeonHD), MorphOS 3.9 (PowerMac G4 733MHz R200), AROS (x86), A1200 (060 80MHz Indivision MK2), A600 Vampire2 / Furia, A500, CDTV
[Dev Videos][Facebook][Old Wings Development Diary]
 

Offline Iggy

  • Hero Member
  • *****
  • Join Date: Aug 2009
  • Posts: 5348
    • Show only replies by Iggy
Re: Lets talk about A1222 - Tabor
« Reply #34 on: October 23, 2017, 04:47:02 PM »
The man does have a point about the performance of the e500V2 core outside of floating point.
Its basically the same as any other e500, and actually may outperform the e600 core (aka G4) on some functions.

Freescale cpus continued to progress after the goal of an e700 core was dropped, and many of the features intended for that product ended up being incorporated into later e500s, the e5500, and the e6500.

The e500V2 was never intended for floating point intensive applications, but it can serve in mixed integer/floating point applications.
"Not making any hard and fast rules means that the moderators can use their good judgment in moderation, and we think the results speak for themselves." - Amiga.org, terms of service

"You, got to stem the evil tide, and keep it on the the inside" - Rogers Waters

"God was never on your side" - Lemmy

Amiga! "Our appeal has become more selective"
 

Offline dirkzwager

  • Newbie
  • *
  • Join Date: Oct 2017
  • Posts: 46
    • Show only replies by dirkzwager
Re: Lets talk about A1222 - Tabor
« Reply #35 on: October 23, 2017, 04:49:31 PM »
Quote from: Daytona675x;832098
@kamelito

let the Hyperion guys first finish their work on the OS and don't be so negative yet. I bet they weren't overly excited by the CPU choice neither - but they are actually solving those issues, I guess some moral support won't hurt :)



I will be very happy with the tabor.
D'ont understand me wrong but when i wisch a really fast system i stay with my mac or pc.
I think the footprint of the os ( amiga os ) is small and that is a big benefit. Of corse the internet ask more and more but the Amiga works well with:):) the software for .... the Amiga. There is no PhotoShop of Imovie etc ....
Amiga 4000/040 with picasso 4, Amiga 500 with ACA 500 plus, Powerbook G4 17* 1,67 Mhz and MorphOs,
 

Offline woof

  • Jr. Member
  • **
  • Join Date: Feb 2003
  • Posts: 94
    • Show only replies by woof
    • http://uae.is.free.fr
Re: Lets talk about A1222 - Tabor
« Reply #36 on: October 25, 2017, 01:16:15 PM »
>becomes a problem when calling library functions (e.g. Warp3D) which expect floats in FPU registers...
???!!!
You talk about Warp3D 68k that was using registers
but as Warp3D for OS4 got an "interface" it can be called with parameters on the stack as normal C functions , no?

Edit: Just checked Warp3D 68k = it dont use fpu registers when calling functions but cpu registers only

Alain Thellier
« Last Edit: October 25, 2017, 01:31:12 PM by woof »
 

Offline Daytona675x

  • Newbie
  • *
  • Join Date: Oct 2014
  • Posts: 46
    • Show only replies by Daytona675x
    • http://www.goldencode.de
Re: Lets talk about A1222 - Tabor
« Reply #37 on: October 25, 2017, 05:03:25 PM »
@Thellier
:confused: 68k? Interface?? Stack??? "Normal C functions"????
I talk about the PPC ABI used in AOS4.
In one single thing you're right though: *calling* *Warp3D* functions is not critical at all.
However this is not because floats aren't passed through registers, they are of course. It is because floats / doubles aren't passed by value in Warp3D - and this is even true for functions that only want single float / double values (which is a design specialty of W3D that I had forgotten about). Which is why in that particular case they aren't passed through float registers indeed. So I could give Wings a SPE try indeed (although the results are probably not satisfying because with some bad luck there are double-based memcpys inside the W3D driver).
However, the ABI incompatibility I explained remains and causes trouble, of course. Just replace "Wings" by the name of your favorite 3D game and replace "e.g. Warp3D" by "MiniGL" (which has tons of functions that expect floats by value) in my explanation and you have a better example why simple re-compiling often won't work.

@Iggy
Yup.  IMHO chances are good that the pretty high performance of that thing in  combination with Thomas Frieden's optimizations save the day :)

@dirkzwanger
Yes,  and let's not forget that this thing is meant to be an entry level  system. So if real fpu-hungry *non*-native stuff runs "okay", then it  should be fine. And let's also not forget that real critical stuff (e.g.  minigl) can certainly be modified to at least do a high amount of work  in native code.

All in all: let's wait and see and be optimistic (and there's certainly reason to be optimistic) :)
« Last Edit: October 26, 2017, 04:52:05 AM by Daytona675x »
AmigaOS 4.1 FE (sam440ep, sam460ex, X5000, Tabor,  R200 / RadeonHD), MorphOS 3.9 (PowerMac G4 733MHz R200), AROS (x86), A1200 (060 80MHz Indivision MK2), A600 Vampire2 / Furia, A500, CDTV
[Dev Videos][Facebook][Old Wings Development Diary]
 

Offline Iggy

  • Hero Member
  • *****
  • Join Date: Aug 2009
  • Posts: 5348
    • Show only replies by Iggy
Re: Lets talk about A1222 - Tabor
« Reply #38 on: October 25, 2017, 07:10:15 PM »
Quote from: Daytona675x;832165
@Thellier
:confused: 68k? Interface?? Stack??? "Normal C functions"????
I talk about the PPC ABI used in AOS4.

@Iggy
Yup.  IMHO chances are good that the pretty high performance of that thing in  combination with Thomas Frieden's optimizations save the day :)

@dirkzwanger
Yes,  and let's not forget that this thing is meant to be an entry level  system. So if real fpu-hungry *non*-native stuff runs "okay", then it  should be fine. And let's also not forget that real critical stuff (e.g.  minigl) can certainly be modified to at least do a high amount of work  in native code.

All in all: let's wait and see and be optimistic (and there's certainly reason to be optimistic) :)


Well...I didn't say high performance,  but we do have to consider that the majority of all code is not floating point.
And when coded for natively, the e500V2 core should certainly be adequate to the application.
We'll have to see what Thomas pulls out of his...hat? But I wouldn't worry to much about the performance hit in software that can't be recompiled (think about that, how much is there?), and it still just a part of the performance equation.
Factor in stronger integer performance than the SAM460, and things aren't that grim.
"Not making any hard and fast rules means that the moderators can use their good judgment in moderation, and we think the results speak for themselves." - Amiga.org, terms of service

"You, got to stem the evil tide, and keep it on the the inside" - Rogers Waters

"God was never on your side" - Lemmy

Amiga! "Our appeal has become more selective"
 

Offline number6

Re: Lets talk about A1222 - Tabor
« Reply #39 on: October 25, 2017, 10:38:43 PM »
@thread

Steven has offered to answer questions as best he can concerning Tabor:

AmiWest 2017 clarifications

#6
 

Offline kreciuTopic starter

Re: Lets talk about A1222 - Tabor
« Reply #40 on: October 25, 2017, 11:41:55 PM »
What really turned off my enthusiasm toward A1222 after AmiWest was general enthusiasm toward emulation of AmigaOS4.1 as a GOOD method of running AmigaOS. So, what is a point of developing ANY hardware for AmigaOS4.1? That was my impression.
Re-A1200inE/BOX/3.2/AmigaOS3.2/TF1260@66Mhz/256Mb/MediatorTX/R9200SE/SpiderUSB/LAN/SB128/16Gb-CF/DVD-ROM/FDD-HD
 

Offline Hans_

Re: Lets talk about A1222 - Tabor
« Reply #41 on: October 25, 2017, 11:51:50 PM »
Quote from: kreciu;832184
What really turned off my enthusiasm toward A1222 after AmiWest was general enthusiasm toward emulation of AmigaOS4.1 as a GOOD method of running AmigaOS. So, what is a point of developing ANY hardware for AmigaOS4.1? That was my impression.


I don't think there was a general enthusiasm toward emulation at the show. I do like the ALICE laptop, and Ken's speech at the banquet was really interesting. However, I still prefer real hardware (and the ability to run 3D apps/games at speed). That's why I've got my own PORtable Tabor Incorporating Amigaone laptop project. I like the A1222/Tabor because it's small enough to make a laptop/luggable with real hardware possible.

Hans
http://hdrlab.org.nz/ - Amiga OS 4 projects, programming articles and more. Home of the RadeonHD driver for Amiga OS 4.x project.
 

Offline utri007

Re: Lets talk about A1222 - Tabor
« Reply #42 on: October 26, 2017, 06:10:09 AM »
I'm going to get A1222, in any case it will be upgrade for my Sam 440ep Flex.
« Last Edit: October 29, 2017, 03:41:31 PM by eliyahu »
ACube Sam 440ep Flex 800mhz, 1gb ram and 240gb hd and OS4.1FE
A1200 Micronic tower, OS3.9, Apollo 060 66mhz, xPert Merlin, Delfina Lite and Micronic Scandy, 500Gb hd, 66mb ram, DVD-burner and WLAN.
A1200 desktop, OS3.9, Blizzard 060 66mhz, 66mb ram, Ide Fix Express with 160Gb HD and WLAN
A500 OS2.1, GVP+HD8 with 4mb ram, 1mb chip ram and 4gb HD
Commodore CDTV KS3.1, 1mb chip, 4mb fast ram and IDE HD
 

Offline woof

  • Jr. Member
  • **
  • Join Date: Feb 2003
  • Posts: 94
    • Show only replies by woof
    • http://uae.is.free.fr
Re: Lets talk about A1222 - Tabor
« Reply #43 on: October 26, 2017, 09:00:43 AM »
Hi
@Daytona675x
 
You are certainly a good coder but you have difficulties to admit when you are wrong
"calling library functions (e.g. Warp3D) which expect floats in FPU registers"
is just a wrong statement as Warp3D (both OS3 and OS4 versions) never used FPU registers for calling functions

>MiniGL (which has tons of functions that expect floats by value)
True but there are not "expecting floats in FPU registers" too


Greetings
Alain Thellier
 

Offline AdvancedFollower

  • Newbie
  • *
  • Join Date: Oct 2017
  • Posts: 39
    • Show only replies by AdvancedFollower
    • https://roughlyit.hopto.org/
Re: Lets talk about A1222 - Tabor
« Reply #44 from previous page: October 29, 2017, 03:37:36 PM »
Quote from: kreciu;832184
What really turned off my enthusiasm toward A1222 after AmiWest was general enthusiasm toward emulation of AmigaOS4.1 as a GOOD method of running AmigaOS. So, what is a point of developing ANY hardware for AmigaOS4.1? That was my impression.

I've been running AmigaOS 4.1 in WinUAE for a while, and I wouldn't call the experience "good". Biggest limitation is slow/limited I/O, and lack of hardware 3D and compositing. In terms of raw CPU performance, my Ryzen 1800X desktop is about 50% of the X5000 performance running Sortbench, but I/O and video are very slow compared to real hardware so the overall experience is slow, choppy and limited.

I think they're just trying to expand the reach of OS4 by having a cheap, convenient method of running AmigaOS 4. Plus the Alice laptop is nearly finished while the A1222 is not.

Of course in theory, emulation could be expanded until it becomes really good. Implement pass-through for the GPU and storage, with the only emulated part being the PPC CPU itself rather than trying to emulate a full A4000 with Blizzard PPC. But that doesn't seem to be the route they are going.
« Last Edit: October 29, 2017, 03:39:49 PM by AdvancedFollower »