Apollo Team announces the Vampire V4

[grond]

Originally Posted by kipper2k

fanning the flames just makes it worse, it's a shame we All cant play nice

It was a JOKE! I was trying to be funny. Obviously I failed.

[kipper2k]

Originally Posted by grond

It was a JOKE! I was trying to be funny. Obviously I failed.

I am not just referring to you Grond, reading all the banter that is going on is annoying at times, if people like it, good... buy , if they don't then stop bashing in public and don't buy

[Mr-Z]

Originally Posted by grond

It took me some time to understand that the joke wasn't obvious and some people wouldn't see that my comment wasn't an attack on Mr-Z who knows me well from the Apollo Team channel on freenode.

I was just loosely referring to a thread in another Amiga forum where some people go as far as to demand that the core also has to crash in places where the 060 crashes to be called "compatible".

I do not feel attacked at all, no offense taken
Only thing i mean with compatible was that the capture devices takes low resolutions by today's standards (like 640x480 etc).

[NovaCoder]

I haven't bothered to read all of this thread but I think some people are getting way too hung up on compatibility. Even real Amiga HW models aren't really that compatible with each other, esp. when you take into account different versions of OS libraries and the various patches/hacks that people run....

[Overflow]

Gunnar made a general comment about the direction and intent of the Apollo core, which will adress relatively frequently asked questions;

Is was always clear that: APOLLO's roadmap includes to run everything any 68K can run. This means also including running Linux.

But we have a clear policy about future features:
We _NEVER_ promise the users features that are not available today but only on our roadmap.
Users always only guarantee stuff working today 100%.

This means even if we might even run internally Linux for testing.
As long we are not sure we can release it now.
Our official answer will always be "no you can not run Linux".

http://www.apollo-core.com/knowledge...6&x=1&z=Jg0cBR

[Locutus]

Originally Posted by Overflow

Gunnar made a general comment about the direction and intent of the Apollo core, which will adress relatively frequently asked questions;
http://www.apollo-core.com/knowledge...6&x=1&z=Jg0cBR

And just a short while ago MMU comments were shot down with 'If you want to run Linux look elsewere' (sorry, i'm not going to hunt down exact copy pasta comments)

EDIT: Actually do have some pasta:



And this is why Apollo will never be a developer friendly platform, everything changes like the wind.

[Overflow]

Originally Posted by Locutus

And just a short while ago MMU comments were shot down with 'If you want to run Linux look elsewere' (sorry, i'm not going to hunt down exact copy pasta comments)

And this is why Apollo will never be a developer friendly platform, everything changes like the wind.

Ive been reading forums far too much, and the general sense I get from it is; people nag nag nag until Gunnar looses his cool. He says "NO FPU for you!". Then someone steps up outside the team and accelerates the FPU progress.

You could say that Gunnar needs to count to 10 every now and then, but when people prefere to focus on the shortcomings in a negative way instead of appriciating the work that has been done SO FAR, then I would have lost my patience far more frequent and earlier (I think).

So Gunnar isnt a perfect public relations guy, but an engineer/coder. Tbh the hardcore computer guys Ive met thru the decades have never fit the "PR" friendly mold.

Take kolla. I actually find quite a few of his posts intresting, and he raises decent questions. But like quite a few others, he often have to add a negative jab before he presses "post reply", for what? The reciver of said post will now have a negative attitude when replying, instead of an objective one.
And we end up with 10 pages of hostility. This happens in thread after thread. Again, maybe cause computer savvy people aint as good with humans as they are with compilers? (See, I did a jab too).

[Samurai_Crow]

I don't know how Gunnar wants to run Linux, but I was under the impression that having a fancy, full featured MMU would lengthen the pipeline and kill much of the performance gains enjoyed by the Apollo core.

If it is possible to get AmosPro running well enough on it that I can make games and other stuff, I will be happy because it is still an Amiga. As for running Linux, I am content with a RasPi or ODroid and don't think it's worth the effort to get Linux on the Vampire. AROS is a better goal since the license battles between Hyperion and Cloanto make things bad for the whole Amiga community.

[grond]

Originally Posted by Samurai_Crow

I don't know how Gunnar wants to run Linux, but I was under the impression that having a fancy, full featured MMU would lengthen the pipeline and kill much of the performance gains enjoyed by the Apollo core.

Why should Gunnar care if people want to lose performance when running a memory-protected OS? In my opinion the MMU would not slow down anything when unused. It's basically just slower memory from the point of view of the CPU Cache because the additional latency gets added between cache and the actual memory.

[grond]

Originally Posted by Locutus

And just a short while ago MMU comments were shot down with 'If you want to run Linux look elsewere'

And is this not a reasonable statement when looking at the current state of the core?

[Overflow]

And Gunnar has had 2 cups of coffe today it seems. He decided to go into more details about the MMU mechanics of legacy and Apollo;

http://www.apollo-core.com/knowledge...11026&z=U8rPdR

The MMU topic seems to be confusing.

Lets us try to explain it.

An MMU is a piece of logic which allows to do three things.
a) It allows to map blocks of memory to another address.
A typical used block size is 4 KB.
Modern MMU also support bigger blocks e.g 64KB or 1MB.
Support for bigger blocks gives for some applications advantages.

b) the MMU allows to control cache setting for blocks.

c) The MMu allows to write/protect memory

APOLLO 68080 has a build in MMU.

Where is the difference between APOLLO and previous 68K CPUs?

Previous 68K CPUs did NOT come with a memory controller inside the CPU.
This means the memory access logic, the memory layout and control of this was always done OUTSIDE of the CPU.
This means while the CPU could inside change their logical view of the addresses with the MMU - it did not have any understanding of how this is mapped outside - as this understanding was controlled by the mainboard chips of the system.

Also the other way around - if the mainboard chips did do some DMA access - they could not know how these areas are mapped inside the CPU MMU.

This old concept did create many problems.
You all have seen those on the AMIGA.

DMA channels on the AMIGA did always work on physical address.
While programs would work on virtual addresses.
This mismatch was not solvable on AMIGA.
If an application was requesting DMA and was using its virtual view of addresses this was leading to crashes.

APOLLO fixes this problem.

APOLLO has the SAGA DMA channels inside the CPU core.
This means both DMA and CPU can use the same representation of the world.
This does solve a number of old problems.
The CPU does see automatically if DMA channels update memory which is cached by the CPU caches.
This means the CPU has always a coherent view of the memory.
This solves many old DMA issues and also allow the usage of APOLLO with many CPU cores. All CPU cores and the DMA engines share one coherent view of the world.

Another big difference to old 68K CPUs is that old 68K CPUs
did only support 1 bus.

APOLLO is designed as a system supporting several memory controllers.

Old MMUs did had a linear address view in 1 dimension.
APOLLO has a multidimensional view.

All these concepts which APOLLO offers are new to the 68K world.
These concepts do exist already today in other enterprise systems.

Coherent multi core systems supporting several memory channels or memory hierarchies are state of the art today.
Apollo is from ground up designed to support this too.

AMIGA OS is not designed for this today.
AMIGA OS can not easily use SMP.
AMIGA OS can not control NUMA memory views.

To provide a old fashioned 1 dimensional memory view to old AMIGA MMU applications - a clean solution would be to provide an sub MMU with 1 dimension inside the multidimensional MMU view.

This feature would transparently support old applications.
This can be done but is _NOT_ in planned for any releases coming soon.

[Overflow]

Direct streaming of youtube video (no convertion to mpeg1).
NetSurf 3.7 (14 November).
Core 2.7 beta with Hard FPU.

[ Show youtube player ]

Minislug is also updated. Now works with 24/32bit depth

https://usercontent.irccloud-cdn.com...119_100937.jpg

https://usercontent.irccloud-cdn.com...119_101151.jpg

[Mr-Z]

Sweet stuff

[Overflow]

The second link contains updated information in TXT format, with examples;

GOLD 2.7 will come with AMMX2 instruction set.

Please find here a preview of the AMMX Quickreference chart:
www.apollo-core.com/AMMXQuickRef.pdf


And a longer reference in TXT
www.apollo-core.com/AMMX.doc.txt


Please mind that the documentation is not final, AMMX2 includes a few more instructions for which documentation has to be written still.

[kolla]

Thierry wishes for Apollo Core in NeXT Cube, or running NeXTSTEP on Apollo Core, but cannot state strongly enough how useless a MMU is - any MMU. Gunnar steps in to calm everyone down by saying Linux may happen, but not now. Everyone is nodding in agreement.

[Samurai_Crow]

Originally Posted by kolla

Thierry wishes for Apollo Core in NeXT Cube, or running NeXTSTEP on Apollo Core, but cannot state strongly enough how useless a MMU is - any MMU. Gunnar steps in to calm everyone down by saying Linux may happen, but not now. Everyone is nodding in agreement.

Sort of. Gunnar wants to have hardware based memory protection so it affects chipset DMA as well.

[Miggy4eva]

Originally Posted by Overflow

Direct streaming of youtube video (no convertion to mpeg1).
NetSurf 3.7 (14 November).
Core 2.7 beta with Hard FPU.

[ Show youtube player ]

Minislug is also updated. Now works with 24/32bit depth

https://usercontent.irccloud-cdn.com...119_100937.jpg

https://usercontent.irccloud-cdn.com...119_101151.jpg

THIS is just amazing, it blows my mind to think that we could be watching youtube and browsing the internet on a machine made in 1985. There would not be a single other machine from that time capable of the same even with upgrades

[Overflow]

http://www.apollo-core.com/knowledge.php?b=4&note=11558

Last night we started to play around with some texture mapping code.

Here is a very early result:
www.apollo-core.com/gfx/V3_demo34.mp4

The screen is rendered in 640 pixel width.
The texture routine uses bilinear texture filtering.
https://en.wikipedia.org/wiki/Bilinear_filtering

[Overflow]

Some uploads to Vimeo.

Unique “Singularities” Amiga AGA Demo (Vampire 600 V2)

GOLD3 internal beta core for Vampire FPGA Accelerator. Realtime capture from Amiga 600 (HDMI, both audio and video 720x576@50) with StarTech PEXHDCAP.



http://www.pouet.net/prod.php?which=69702




Unique “Subside” Amiga AGA Demo (Vampire 600 V2)

GOLD3 internal beta core for Vampire FPGA Accelerator. This demo runs in 640x160 HAM8 screen (15bit). Realtime capture from Amiga 600 (HDMI 720x576@50) with StarTech PEXHDCAP.



http://ada.untergrund.net/?p=demo&i=853
http://www.pouet.net/prod.php?which=67140

[spudje]

A progress update from the Apollo guys would be nice. The Q4 release is clearly not realistic anymore...