• Hey, guest user. Hope you're enjoying NeoGAF! Have you considered registering for an account? Come join us and add your take to the daily discourse.

Xbox One hardware breakdown by ExtremeTech.com after HotChips reveal

kensama

Member
if you believe its thread worthy then make a new thread... no one should hold you back fellow Gaffer :)

of course give mention to kensama for finding it first I guess

Oh for me it's not important to be mentionned or not you know.
I share some information, when i think it's not already posted.
 

KidBeta

Junior Member
I disagree completely, and I'll just leave it at that. :)



Does it technically even need to be able to touch ESRAM directly if the data that's present in ESRAM is still able to make it's way to the CPU utilizing that Host Guest GPU MMU? Keep in mind, that ESRAM is likely very closely coupled with the GPU, so if the GPU in anyway is able to pass information to the CPU, then surely that means data which was present in ESRAM can be handled by the CPU without first having to be present inside main ram.

And what about being able to pass pointers between the CPU and GPU?

Yes it has to be able to touch the eSRAM, as I said if you can't touch the eSRAM then how is it going to get in its cache?.

Being able to pass pointers between the CPU and GPU means that the they share the same address space, that doesn't mean that the CPU is going to be able to directly read the eSRAM.
 

strata8

Member
So the X1 CPU is clocked at 1,9ghz? I thought it was much less.

Do we know what the PS4 is clocked at?

It was semi-confirmed in that Killzone SF slide from a while back:
G9WmPO0.jpg

487,710 cycles/305 microseconds = 1599 cycles per microsecond = 1599,000,000 cycle per second = 1.6 GHz.

The slide is pretty old though (pre-E3?).
 

Mula

Member

is this right ?

As far as arrangements go there are four 256b wide banks for a total of 1024b or 128B wide memory. A little math gets you to a speed of 1.59375GHz, lets call it 1.6GHz because the peak bandwidth is unlikely to be 204.00000GBps. Why is this important? What was that GPU frequency again? 800MHz you say? Think that is half of the memory speed for no real reason? If you said yes you are wrong. With the rumored bump of GPU speeds from 800MHz to 831MHz, this may also bump the internal memory bandwidth up by a non-trivial amount. In any case now you know the clocks.
 

ElTorro

I wanted to dominate the living room. Then I took an ESRAM in the knee.

I can't make sense of many paragraphs, and their math voodoo is all over the place. What's the general reputation of SemiAccurate?

I saw that as well, looks there there was a few spelling errors in the article. MS has confirmed 853mhz.

They also talk about "209GB/s" of theoretical peak bandwidth which is another typo. I don't know where that 831mhz is coming from. It's clearly wrong, and the GPU clock is not even a rumor anymore.
 

Dodecagon

works for a research lab making 6 figures
Not saying everything in that article is accurate, but as an industry professional, I know semiaccurate is well respected and charlie in particular. I was shown the site by co-workers.
 
Its Semi Accurate, which is pretty much Charlie Demerjian's attempt to go independent after his stint with The Inquirer.

He's got some industry contacts but they're notoriously unreliable. He gets stuff right occasionally but there's so much white noise that there's no point reading most of the shit he writes. He also likes maintaining silly one-sided feuds against companies like nVidia and Apple.

So basically Semi Accurate is kind of rubbish. I dunno who his contacts are but I don't think for one second that Apple ever imagined using AMD's APUs in their Macbook Air (yes this was an actual article).
 

twobear

sputum-flecked apoplexy
Are the audio processors available to developers or are they just for handling Kinect stuff behind the scenes?

Its Semi Accurate, which is pretty much Charlie Demerjian's attempt to go independent after his stint with The Register.

He's got some industry contacts but they're notoriously unreliable. He gets stuff right occasionally but there's so much white noise that there's no point reading most of the shit he writes. He also likes maintaining silly one-sided feuds against companies like nVidia and Apple.

So basically Semi Accurate is kind of rubbish. I dunno who his contacts are but I don't think for one second that Apple ever imagined using AMD's APUs in their Macbook Air (yes this was an actual article).
Interesting that you didn't mention the slew of enormously negative MS articles he's put out recently.
 
I don't read the site and I don't read what he writes because most of it is clickbait. What are you insinuating here? That I'm dismissing Semi Accurate because they said something positive about the Xbox One?

If so, then I'm not dismissing Semi Accurate because of that reason. I'm dismissing them because they're actually...well...semi accurate at best and the writer has some serious problems. Like read everything he's written about nVidia. He's got contacts somewhere but he's historically tried his best to play red army vs. green army whenever possible.
 

ElTorro

I wanted to dominate the living room. Then I took an ESRAM in the knee.
Are the audio processors available to developers or are they just for handling Kinect stuff behind the scenes?

Decoding/encoding and mixing of will certainly be of use in games. Apparently, the feature set is similar to what was available on the 360, most probably more capable in terms of number and quality of simultaneous audio streams.

Durango supports two audio rendering APIs for typical game use along with a variant of the Windows 8 Media Foundation API for playback of user music:

XAudio2, a game-focused audio library already available on Xbox 360 and Windows operating systems (Windows XP to Windows 8), is generally recommended for most title development.

WASAPI (Windows Audio Session API) can be used for any custom, exclusively software-implemented pipeline. WASAPI provides audio endpoint functionality only. Decompression, sample-rate conversion, mixing, and digital-signal processing, as well as interactions with Durango’s audio hardware components, must be implemented by the client. WASAPI is most typically used by audio middleware solutions.

http://www.vgleaks.com/durango-sound-of-tomorrow/
http://msdn.microsoft.com/en-us/library/windows/desktop/ee415813(v=vs.85).aspx (XAudio2 API)
http://msdn.microsoft.com/en-us/library/windows/desktop/dd371455(v=vs.85).aspx (WSAPI)
 

twobear

sputum-flecked apoplexy
I don't read the site and I don't read what he writes because most of it is clickbait. What are you insinuating here? That I'm dismissing Semi Accurate because they said something positive about the Xbox One?

If so, then I'm not dismissing Semi Accurate because of that reason. I'm dismissing them because they're actually...well...semi accurate at best and the writer has some serious problems. Like read everything he's written about nVidia. He's got contacts somewhere but he's historically tried his best to play red army vs. green army whenever possible.

The MS articles are interesting actually because six months ago they seemed enormously histrionic but in retrospect they seem fantastically prescient.
 

sevanig

Banned
No I believe he was calling B3D a xbox fanboy haven, which would be correct, as the site has turned into total shit over the years. Sad to see such a great site in the past devolve into such useless shit. Used to be my favorite place for graphics tech talk.

Too rite mate, I use to enjoy going to the forums back in the day... :(
 

Klocker

Member
Are the audio processors available to developers ...snip
.

Yes and bkilian who worked on the Bone audio chip said it is an order of magnitude more powerful in that regard over 360 as well as it has it's own processor where 360 needed to leverage xenon threads


Oh and an interesting discussion on audio chip on everyone most hated site now evidently with lots of nuggets throughout


Also interesting about the video planes from semi-accurate article

With the exception of the Audio Out/Resize/Composting block the other units are plumbing, at least from a users perspective. Game developers may swoon over dual swizzle copy units but for those more interested in the other end of the controller, meh. The Audio Out/Resize/Composting bit however is quite interesting, at least the latter two functions are. Resize does what it sounds, it can resize and scale a video stream on the fly but more importantly is separate from the GPU cores and the video encode/decode blocks.

This says Microsoft is quite serious about video, it will allow for effectively ‘free’ PiP and tiling of video stream limited only by the scaler’s power. While this is doable with the GPU itself it would be intrusive and suck performance from the running tasks. Same with the compositing unit, this is amazingly useful for things like programming overlays, seamless PiP, video conferencing, tasks switching, and most obviously to stuff annoying adds all over your screen until you beg for mercy. Somehow we don’t think the bean counters at MS will care though, but that is just our impression.

In short Microsoft put in some serious hardware to have multiple layers of overlays, scaling of video streams to use with it, and a lot of related hardware to ensure that they can pull off video tricks that are simply not possible to do with modern hardware. The fact that it is separate from the rest of the system also points to the company grasping its uses long before the hardware was started. This is a serious video machine whose power is unlikely to be solely used for the benefit of the consumer without causing any performance degradation on running tasks. It also meshes directly with several of those hidden bits SemiAccurate has heard about. Do not discount this as trivial, it is a fundamental design premise, if not the fundamental design premise of the system, and one that explains the need for dedicated coherent links between the GPU and I/O blocks


To translate from technical minutia to English, good code = 204GBps, bad code = 109GBps, and reality is somewhere in between. Even if you try there is almost no way to hit the bare minimum or peak numbers. Microsoft sources SemiAccurate talked to say real world code, the early stuff that is out there anyway, is in the 140-150GBps range, about what you would expect. Add some reasonable real-world DDR3 utilization numbers and the total system bandwidth numbers Microsoft threw around at the launch seems quite reasonable. This embedded DRAM is however not a cache in the traditional PC sense, not even close.S|A
 

neodeano

Member
I'll see if I can get Charlie to comment on his 1.9GHz guesstimate. He's still on my Skype after I worked with him at the Inq. Please don't hold that against me.
 
Yes and bkilian who worked on the Bone audio chip said it is an order of magnitude more powerful in that regard over 360 as well as it has it's own processor where 360 needed to leverage xenon threads


Oh and an interesting discussion on audio chip on everyone most hated site now evidently with lots of nuggets throughout


Also interesting about the video planes from semi-accurate article

Lost of interesting stuff in there. Damn shame I can't stay to read it :(
 

vpance

Member
Microsoft sources SemiAccurate talked to say real world code, the early stuff that is out there anyway, is in the 140-150GBps range*

*For alpha transparencies

They're just reiterating on what was told to DF.
 

astraycat

Member
I can't make sense of many paragraphs, and their math voodoo is all over the place. What's the general reputation of SemiAccurate?



They also talk about "209GB/s" of theoretical peak bandwidth which is another typo. I don't know where that 831mhz is coming from. It's clearly wrong, and the GPU clock is not even a rumor anymore.

Their math is just poor.

What they should do is 128B * 853MHz = 109GB/s, lines up with all the given numbers.

Instead, they're doing (204GB/s) / (128B/c) ~= 1.59GHz, which is a nonsensical number. Why would the clock rate of the ESRAM controller be at such an oddball number compared to the main clock, which has been confirmed to be 853MHz?

I think it's worth noting as well that the (204GB/s) / (853MHz) ~= (192GB/s) / (800MHz), which is the number from DF that caused a previous shitstorm of speculation. The 204GB/s has simply gone up from the 192GB/s with the 853MHz clock speed. These SemiAccurate guys need to get their act together.
 

Surface of Me

I'm not an NPC. And neither are we.
Their math is just poor.

What they should do is 128B * 853MHz = 109GB/s, lines up with all the given numbers.

Instead, they're doing (204GB/s) / (128B/c) ~= 1.59GHz, which is a nonsensical number. Why would the clock rate of the ESRAM controller be at such an oddball number compared to the main clock, which has been confirmed to be 853MHz?

I think it's worth noting as well that the (204GB/s) / (853MHz) ~= (192GB/s) / (800MHz), which is the number from DF that caused a previous shitstorm of speculation. The 204GB/s has simply gone up from the 192GB/s with the 853MHz clock speed. These SemiAccurate guys need to get their act together.

They do only claim to be semi-accurate.
 

ToyBroker

Banned
I wouldn't say SemiAccurate is very reliable. NO one has reported on that 1.9ghz figure and the dude seems like kind of a prick on Twitter--a number of people have already questioned/called him out on it and he responded Phil Fish style pretty much.
 

heelo

Banned
Are the audio processors available to developers or are they just for handling Kinect stuff behind the scenes?


Interesting that you didn't mention the slew of enormously negative MS articles he's put out recently.

(1) My understanding was that all of Kinect's processing was located inside the Kinect box.

(2) CD has been absolutely brutal towards MS over the past couple years (at least), but to be honest I think it's less about one-sided vendettas and more about acerbic criticism being his writing "voice."
 
Top Bottom