Possible new tech info soon

[Carn]

One of my friends works at a gaming company where they just received two PS3 devkits..I can't promise anything but I'll try to get some info out :)

[Viano]

ok, here is my phone number...

[Smokey]

ok, here is my phone number...
and mine.......:)

[Domination]

Wouldn't that be violating an NDA - your friend, I mean? Anyhow, I hope it doesn't cause any problem.

[RavenFox]

Yeah Carn if what your saying is true is best not to try and get any info from him thats worth his job. Then again he shouldnt be saying anything that would break his NDA. Oh yeah here's my # to...

[Carn]

I'm very aware of NDA's etc, I'm not going to push for info but all little things should be cool tho.

[Carn]

haha he just said that they are setting it up next to his table

[Old_Timer!]

Well at least he can tell you if they have a working model of the new Dual Shock controller, and if this is the final PS3 Dev Model with all tech included (Cell+RSX+Blu-Ray Drive+HDD)

[koldfuzion]

beans. Please. Spill some.

[OmniCloud]

beans. Please. Spill some.
DITTO!

[Old_Timer!]

Hey Cpi when are you guys getting your Devkits? and have you heard anything good from your associated that have them.

[Hawk]

Great Carn!
There are only few things we'd like to know:drool:
- How much memory and the clock frequencies?
- RSX compared to other graphics card?
- Cells ability to render graphics with RSX?
- Any spec upgrades?
- Speed of BD-drive?
- SPE-unit compared to Ageias Physx-card?
- How many SPEs are usable?
- What game are they designing? A video capture of it would be nice.
- PS3 price tag?

:laugh: :laugh: :laugh:

[cpiasminc]

Hey Cpi when are you guys getting your Devkits? and have you heard anything good from your associated that have them.
Will probably be on the order of months. Last I heard, the only news is that they'd been ordered or are being ordered. Since pretty much everybody is apparently getting one, it's kind of a tall order as this is a fairly larger studio than where I was working at before.

[venomv]

Where do you work?

[section]

Will probably be on the order of months.
Aw shucks, so we can't actually start the "are we there yet" iterations about the actual specs of PS3 you wouldn't tell us anyway :)

Oh well, then we'll only have to do with the local forums where we can just guess this and that, which won't probably be true anyway.. Woe the life of a fellow nerd :D

[xbdestroya]

Where do you work?

Venom don't you think that question's a little too... direct?

I mean if Cpi wanted to make public where he worked, I think he could have easily done so by now.

[venomv]

Well I though maybe he has said before and I missed, I wouldn't press him if he said he didn't wanna say. And yes I thought that as I posted it, but is there a better way to say it, it comes out pretty direct no matter how you word it.

[cliffbo]

Carn could you send me your friends name and address, I'd like to thank him personal for his contributions if or when they arrive. and of course maybe a few well placed death threats could winkle out just a few more tidbits.

[venomv]

Carn could you send me your friends name and address, I'd like to thank him personal for his contributions if or when they arrive. and of course maybe a few well placed death threats could winkle out just a few more tidbits.

Lol, yeah, I'm sure he wants to give you his name now.

[satriales]

Reminds me of last summer when I was working at Criterion. It was a Saturday and the place was nearly empty. When I sat at my desk I noticed a huge box next to me that had already been opened, but I couldn't tell what was in it. Seeing as there was hardly anyone about I took a closer look and read the paper work.... It was a Xbox 360 Devkit! At the time no-one knew much about the 360 so it was exciting to see one so early and to hold the new controller. I don't work there anyore though so there's no chance of me getting an early glimpse at the PS3.

[cliffbo]

Lol, yeah, I'm sure he wants to give you his name now.

it was worth a try :shrug:

[cpiasminc]

Venom don't you think that question's a little too... direct?

I mean if Cpi wanted to make public where he worked, I think he could have easily done so by now.
The only reason I don't reveal where I work at a given moment is because of the fact that I'm often working on things that are under wraps and because I'm on the engine & tools side of things, I tend to be working on things that affect many projects years down the road. Even if you check my resume online, it only shows up to the last company I was working at up until right now. When things get announced and such, then I go ahead and bear all... in any case, the ops and mods for the most part know where I'm currently working, and I trust them to keep it quiet until I say otherwise.

In addition, if I ever let anything slip about the work I'm doing without approval, then the fact that I don't let out who I'm working for means that nothing major really gets out... except maybe to the industry recruiters out there who just seem to always know things before anyone else does.

In case it's any indication, I'm marginally inebriated at the moment as the office here has just been stuffed with dozens of bottles of Veuve, and I just had a full bottle of it myself, and got another free bottle to take home and, had another 5 glasses of wine on top of it. Anybody who has guesses based on that can PM me your guesses, but do not post on a public thread.

And I'm still writing a TDD in the middle of it. (Yes, I'm no lightweight). And I can still answer techie questions on 5 forums to boot!! HA!!! Okay... like I said, I'm marginally inebriated at the moment. But don't even kid yourself to think that suggests that there I'm an open bag of beans waiting to be spilled.

[version]

heard from a sony member , that different between ps2 and ps3 similar than c64 and pc
WTF
and ps3 not ready yet

[cpiasminc]

Depends on how far down the line "PC" you're talking about. For instance, C64 always had built-in sound hardware (The good ol' SID chip), while the PC didn't have audio hardware even close to what the C64 had for several years, and lacked the power to do anything about it. It wasn't even until the 8088 that you supported more RAM on the PC than on the C64 (a whopping 256k).

[Crossbar]

Depends on how far down the line "PC" you're talking about. For instance, C64 always had built-in sound hardware (The good ol' SID chip), while the PC didn't have audio hardware even close to what the C64 had for several years, and lacked the power to do anything about it. It wasn't even until the 8088 that you supported more RAM on the PC than on the C64 (a whopping 256k).
Hmm, may I ask what kind of PC you are thinking of that existed before the 8088 based one? I always thought that IBM created the original PC?

[cpiasminc]

Nope... IBM created the first machine to be commercially labeled as a PC. The AppleII's predate the 8088 PC... which itself is predated by the MITS Altair, which is also predated by the Scelbi-8H... Hell... Xerox had the Alto back in 1973, and that actually had a mouse and GUI and everything. If you're talking about the earliest "PC", I think the earliest you can go back is probably the Simon.

But even otherwise, the ones I had in mind were Intel's SIM4 microcomputers based on the 4004. Although I think the first time the actual term "personal computer" came up, it was in regards to one of HP's desktop all-in-ones. I don't remember if it was the 9100 series or the 9800 series offhand.

[Crossbar]

Nope... IBM created the first machine to be commercially labeled as a PC. The AppleII's predate the 8088 PC... which itself is predated by the MITS Altair, which is also predated by the Scelbi-8H... Hell... Xerox had the Alto back in 1973, and that actually had a mouse and GUI and everything. If you're talking about the earliest "PC", I think the earliest you can go back is probably the Simon.

But even otherwise, the ones I had in mind were Intel's SIM4 microcomputers based on the 4004. Although I think the first time the actual term "personal computer" came up, it was in regards to one of HP's desktop all-in-ones. I don't remember if it was the 9100 series or the 9800 series offhand.
LOL with that wide definition of PC and versions quote "heard from a sony member , that different between ps2 and ps3 similar than c64 and pc" the PS3 may turn out to be a reincarnation of PSone. This may drive version even more crazy (if possible).

[makeitlookreal]

Has anyone happened to come across any new technical information? I had hoped that some of the NDA's would have expired and at least a few of the developers could start talking. I hope we don't have to wait all the way to E3 to just get some new tech info.

[Viano]

lol

[Z]

wait 15 days more. check the timer in my sig. :)

[version]

clr

[Smokey]

thats kicken version

[version]

Table 4. SPU instruction class and timings

Pipe Instruction class Execution timing

0 Single precision floating point 6 cycles
Double precision floating point 7 cycles (6 cycle issue stall)
Integer multiply, integer/float conversion, interpolate 7 cycles
Load immediate, logical operations, integer add/subtract, sign extend, count leading zeros, select bits, carry/borrow generate 2 cycles
Element rotate/shift, special byte operations 4 cycles
1 Loads/stores, branch hints, channel operations, move to/from SPR 6 cycles
Shuffle bytes, quadword rotate/shift, estimate, gather, form select mask, generate insertion control, branch 4 cycles

[venomv]

I had hoped that some of the NDA's would have expired and at least a few of the developers could start talking.

Maybe we can hope for that to happen post-E3.

[frosty]

All the tech beans will be spilled at E3, IMO, with the price being dropped @ TGS.

[LiquidEagle]

That's what I'm expecting too, frosty, it's gonna be a terrible, rumor-filled timespan in between E3 & TGS if things go down that way :(. Sony will reveal all this amazing technology they're developing and this hardware capable of so many things, and I think that time is going to leave things wide open for people like Microsoft or "analysts" to make up wild pricing plans as their predictions to scare people off.

[frosty]

well, to remedy that sony could first blow everyone away with ps3's power @ e3, then announce that it won't be priced higher than $xxx dollars, without dropping a specific price. Leaving them some room for error and squashing some rumors at the same time.

[cpiasminc]

I had hoped that some of the NDA's would have expired and at least a few of the developers could start talking.
I'm not sure if this is true universally or not, but most NDAs I've ever seen don't have an explicit statute of limitations or are stated as having an indeterminate length of binding. You can talk about things that are already announced only because once they become public knowledge, they're no longer considered "confidential and protected."

0 Single precision floating point 6 cycles
Double precision floating point 7 cycles (6 cycle issue stall)
Integer multiply, integer/float conversion, interpolate 7 cycles
Load immediate, logical operations, integer add/subtract, sign extend, count leading zeros, select bits, carry/borrow generate 2 cycles
Element rotate/shift, special byte operations 4 cycles
1 Loads/stores, branch hints, channel operations, move to/from SPR 6 cycles
Shuffle bytes, quadword rotate/shift, estimate, gather, form select mask, generate insertion control, branch 4 cycles

These are what? latency? throughput? Stages in execution? What specific ops are you referring to when you say simply "single precision floating point"? I find it difficult to believe that any and all ops have the same latency/throughput.

[Crossbar]

These are what? latency? throughput? Stages in execution? What specific ops are you referring to when you say simply "single precision floating point"? I find it difficult to believe that any and all ops have the same latency/throughput.
Those numbers made little sense to me as well. Just another random post.

[version]

Five minutes with: Mark Nutter and Max Aguilar on the Cell BE memory model
Nothing to fear but fear itself

18 Apr 2006

The Power Architecture™ PowerPC® core and the Cell Broadband Engine™ (Cell BE) PPE unit: how different are they? Find out why there is "nothing to fear" from Cell BE programming, after all.
developerWorks: We're taking Five Minutes of Mark Nutter's and Max Aguilar's time to talk about the memory model of the Cell BE processor. Max and Mark work in the IBM Systems & Technology Group on Cell BE software development.

dW: The Cell BE processor PPE core is not based on any existing PowerPC core. Is that correct?

Mark Nutter: The PPU is very similar to other PowerPC cores. The only difference now is that we have these additional supplementary processors, and they actually have their own MMU.

dW: Sometimes there's discussion of how close is the Cell PPE to a PowerPC core. I know that there's a lot of emphasis that Cell is PowerPC-compliant. It's not an out-of-order execution unit, so how different is it?

Max Aguilar: I think we could start by going all the way back to 601 and the PowerPC architecture, and look from there all the way through POWER5™ and such, and you could say that to a certain extent there's been more or less in-order or out-of-order execution in memory communication. There is variability within that PowerPC architecture for in-order or out-of-order execution.

dW: But it hasn't affected the actual ability to run code.

Aguilar: Right, because each processor that takes the out-of-order execution is responsible for producing internally the correct results, and analyzing register dependencies and whatnot.

Nutter: For reference [see Resources for a link --eds], you may want to look at the MMU description for the SPEs, because that's the important piece, choosing, again, the same address translation machinery and storage protection machinery that the PowerPC core uses. They are fully PowerPC [ISA] compliant, so when you issue MFC/DMAs, it steps through the same address translation and protection mechanism that the PowerPC core steps through.

dW: So there is really nothing to fear about Cell.

Aguilar: As a PowerPC programmer no, other than the fact that it's not a high-performance PowerPC core in the POWER5 vein.

dW: Now if we take and we start with, say, the PowerPC Architecture Book III and we look at that memory model from there, where do we go differently with the Cell BE processor?

Nutter: From the SPU's perspective, its loads and stores are relative to the local storage area. Internal to the SPU there is no address translation or local memory protection. So there is no segment or page or any of that.

dW: Could this create a situation in which an SPE is writing to real memory that is not owned by the thread using the SPE?

Aguilar: No. From the SPU's perspective, the only way that it accesses system memory is through an MFC/DMA.

Nutter: And for MFC/DMA accesses to main memory, all of the TLB and SLB translations take effect. Each MFC includes its own MMU, which is compatible with the PowerPC semantics. So the usual rules are applied.

dW: What about the reverse, from a PPE to SPE or to a global memory?

Nutter: From the PPE to an SPE, there are two convenient ways to do this. The first is load store to or from a memory mapped local storage area. The second is to use the PowerPC side of the DMA queue in the MFC engine.

dW: When you're doing a memory mapped local store, who is responsible for configuring and discovery of those memory regions?

Nutter: The operating system, usually at an application's request.

Aguilar: We really don't advise people to memory map local store into the PPE's effective address space

Nutter: Or to make heavy use of it if they do.

dW: You recommend going with the DMA?

Aguilar: Yes. The DMA is definitely the way you want to transfer, because when you access the local store it's done through MMIO, very slow compared to the MFC/DMA.

dW: That's a big clarification, that the recommended approach is using the DMA approach as opposed to the global memory mapping.

Nutter: Let's consider for a moment an application that might need to copy the content to the local store from the PPE side. One way it could do that would be to call memcpy on that memory map local storage area, and essentially copy all 256 kilobytes with any other anonymous memory chunk in the system. That would be very slow relative to the DMA engine. It would have, potentially, various side effects -- depending on the memory target where you were copying to, it would potentially displace contents of the L2, and so on. So every load and store to an MMIO region is something to be avoided, if you can do it, and certainly to avoid 256 kilobytes worth of that.

dW: Alex Chow's pipeline abstraction [see Resources --eds] uses Local Store to Local Store. Who handles that transference from one SPE's LS to another LS? Is that in the SPU executable code, or is that handled at the operating system level?

Nutter: Local storage area could be memory mapped into an effective address space. We also mentioned that an SPU transfers either to its local store from EA or visa versa. The piece that we didn't tie together for you there, but we are now, hopefully, is that you can transfer to another SPU's local storage area that has been memory mapped.

So you essentially are just treating the target local store as an effective address, and the SPU program initiates the transfer, and it's actually a very high bandwidth on-chip, and it stays entirely on-chip transfer. It's actually 10x or more, the kind of improvement over what you would see if you were having to spill out to memory.

dW: In the case of a pipeline model, there are two (or more) approaches. One is where only the resulting data is pipelined and the executable code already resides on the next SPE in the pipe, and the other is where both data and executable code are written to the next SPE. Are the execute and write protections on memory segments enforced when writing from one SPE to another, and if so, how?

Nutter: Yes. As we mentioned before, MFC/DMA commands targeting effectively addressed memory go through address translation and protection. This is true both for accesses to regular memory and for accesses to memory-mapped I/O. MFC/DMA commands targeting another SPU's local storage area are just like any other memory access, from the MMU's point of view.

dW: Does staying within the Element Interconnect Bus (EIB) by pipelining to another SPE require some pre-knowledge by the compiler to take advantage of the performance gain?

Nutter: Somebody, either the programmer or ideally the compiler, has to communicate where the target local storage area is and organize the data flow, so whether that's the PPE side of the application or an automated compiler toolchain is the piece that has to be tied together for the SPU.

dW: With the GCC toolchain, what abstractions does it support out of the box?

Aguilar: It's a low-level compiler, in the sense that it compiles to the SPU or to the PPE ISA, but it doesn't do any of the higher-level abstraction or tying together of the programming model. For instance, what we're talking about here is the "task parallel programming" model in the pipeline. That [GCC] compiler right now doesn't have a great deal of abstraction capability in it for handling that automatically. So the programmers have to set that up for themselves.

A good way to think about this is that depending on your workload, the programming model you choose to break up your workload is kind of the flexibility we're giving the programmers here. For example, if it makes sense for you to break down your workload and have multiple SPUs executing on different chunks of work, then a parallel programming model makes sense.

There are other programming models where we take work and pass it from one SPU to another in a serial fashion, and that may be another way to break up your workload. What we've done in the SDK is given the programmer flexibility that would suggest the programming models, so that they can decide how they feel their workload would take greatest advantage of the Cell processor.

dW: Thank you for your time and responses.

[jaxmkii]

Where do you work?DO NOT TELL HIM!

if hes is going to tell us something best not to give ANY personal info

think about it as long as he has never given any personal info on where he lives/works hes ok.

with 14,000 devs kits out there how many devs work on each one!

if he was to leak to a member of this board and that meber was to post it. and the information would be specks only. nothing that would be specfic to his role or company or game he was working on. how could sony track it?

[satriales]

if he was to leak to a member of this board and that meber was to post it. and the information would be specks only. nothing that would be specfic to his role or company or game he was working on. how could sony track it?
I'm sure there are ways. I know of a couple of gametesters who got fired for posting on forums about games they were working on. One idiot even wrote a review on Amazon months before the game was released. It didn't take them long to track him down and fire him.

[jaxmkii]

leaking about a one game are specific...

1 game = how many possible testers?

it was all ready narrowd down for them

but PS3 dev kit how many have seen them around the world? im willing to bet 100,000 or more

im suprised there has not been any leaks allready

[cpiasminc]

I still avoid any specific numbers that aren't already known. I generally don't even mention titles I've been working on until they're released. It's less about Sony tracking it, as that's not very difficult since they can request IP access records from admins. The point is that an NDA is just that...

Even the technical matters you see are either already known, can be derived by intuition, or I can make educated guesses.

[Carn]

ah bummer; my friend got at his office this morning and they moved the set :(

[venomv]

I'm sure there are ways. I know of a couple of gametesters who got fired for posting on forums about games they were working on. One idiot even wrote a review on Amazon months before the game was released. It didn't take them long to track him down and fire him.

They probaly asked the owners of the forums to release the names of the posters, I'm sure they could get them easiely through legal action of some sort, so they probably just gave it to them.

[Carn]

Nothing new; but the "controller prototypes" are Wireless DualShock2's.

[VG Aficionado]

Nothing new; but the "controller prototypes" are Wireless DualShock2's.Hmmm, interesting. I wonder whether they actually feature any new button or function or they're totally representative of the final controller feature-wise. I wish to be pleasantly surprised.

[Carn]

as far as I know there arent any new buttons on it

[Z]

Nothing new; but the "controller prototypes" are Wireless DualShock2's.
I don't see why make any wirelss prototyps when you already have current Dualshock2s that fit the purpose perfectly. Rev has wired remotes. PS3 has always been shown to use PS2 pads. it is half a year till launch. they will ship the final pad when it is finished. there is no reason to send them half baked prototypes.

[VG Aficionado]

They may use wireless DS2's just for the sake of testing battery life and other minor things according to usage.

[Sephiroth_VII]

Couldn't such things be tested in a lab? On a devkit, wireless controllers won't make much of a difference. Not to doubt you, Carn, but as of now, this smells of BS.

[version]

http://www.watch.impress.co.jp/game/docs/20060426/3dhd.htm

[Carn]

I just tell what I get told guys..all I heard was "They seem to be wireless dualshock 2 controllers", I have no idea if they are real "prototypes" or just modified DS2s to test thigns with.

[CARTIER90]

I have to say, I never found FPS games on a console easy to control compared to the old Kboard / Mouse setup....I know that the PS3 will support such a setup - I just hope they will with ALL games !.

[VG Aficionado]

I have to say, I never found FPS games on a console easy to control compared to the old Kboard / Mouse setup....I know that the PS3 will support such a setup - I just hope they will with ALL games !.Oh yeah, the next Tekken must be a bliss using M+K... [/sarcasm] Why did you have to bring that out of the blue? This is the wrong thread to discuss M+K, there's another one where that's being discussed.

[CARTIER90]

aaaaaalrighty then VG....just with all the talk of FPS's and controllers..aaagh ! I need a m+k keyboard.

[Z]

of course a lab would be much better than sending things out to various places around the world and collecting feedback and changing the models.
on the battery subject; they said the pad would last an entire gaming day. that is 24 hours.:XD:

I just tell what I get told guys..all I heard was "They seem to be wireless dualshock 2 controllers", I have no idea if they are real "prototypes" or just modified DS2s to test thigns with.
no worries mate, we are just talking about the logic behind such a move since we don't have anything better to do. I wanted to start singing exclusively for this forum but I was threaten to be banned! it's jealousy I tell you!