102 * 2 != 192 for starters...
-
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.
DigitalFoundry: X1 memory performance improved for production console/ESRAM 192 GB/s)
- Thread starter ekim
- Start date
- Status
102 * 2 != 192 for starters...
zomgbbqftw
Banned
LabouredSubterfuge
Member
I'll let others talk for me:
Short answer is that different GPU architectures make the flop comparison not very useful. So you'd have a point if the two consoles had different GPU architectures, but they don't, so you don't.
Don't be upset.
Vestal
Gold Member
Im guessing he is referring to the general response from various users saying this is PR Bullshit..
Which would be ridiculous to think that MS would bullshit their own devs in regards to what the machine could do.. I mean do any of you know the implications of something like that?
Hm... Let me think. Looking at the accurate articles from DF in the last years... I'm inclined to trust them.
Looking at the track record of maltrain... Nothing.
Why should I swallow some random comment from a gaffer over a detailed article from a reliable website?
still finding it odd DF are the only ones reporting this
LabouredSubterfuge
Member
What the fuck are we talking about? You are coming up with random math as an argument? Seriously?
lol that's not math, that's a fairy tale. It's like saying I can benchpress 200 pounds, squat 300 pounds, and deadlift 500 pounds, THAT MEANS IM STRONG ENOUGH TO LIFT 1000 POUNDS.
Tripolygon
Banned
Reading that article it seems that the only information coming out of Microsoft is this:
They appear to have arrived at that number by combining peak theoretical read/write speed, so I think you guys are right about them downgrading the ESRAM to 96GB/s, else they would surely be telling developers 204MB/s? the 88% has probably come from the EuroGamer editor seeing the 102>192 increase without knowing about the rumoured downgrade?
They appear to have arrived at that number by combining peak theoretical read/write speed, so I think you guys are right about them downgrading the ESRAM to 96GB/s, else they would surely be telling developers 204MB/s? the 88% has probably come from the EuroGamer editor seeing the 102>192 increase without knowing about the rumoured downgrade?
Well, for start... give me a name of ONE DEV who received this info. I don't see any. So we know nothing. I only see "theoretically possible" things that, by logic and math, sounds like bullshit and a reliable media as Digital Foundry shouldn't be on board of this until THEY PROBE the thing for themselves as they usually do.
pretty sure the only thing anyone is claiming as "unrealistically optimistic" is the 192GB/s number (which even DF provides a much more real world number). As for why MS would provide that type of number when describing the performance gain?? Who knows?
Interfectum
Member
I bought some flops off the street the other day... good shit man. 2TBs will lay you out for an evening.
And I find it odd that DF are linked to continuously for their mythbusting of MS's cloud claims and then when they report something postive they're absolutely definitely in MS's pocket and they're totally lying about it. *shrug* But without any proof or even evidence, the claim is pure, unrefined FUD.
Yeah. And the news says that GPU remains 800MHz.
I don't understand some people make an effort to discredit the information, it seems that the good news bothers them.
LabouredSubterfuge
Member
Were they double precision? That shit is intense.
neobiz
Member
I dig your avatar and you seem to be rational. lol
Do not ever post anything that can be construed as any kind of insider info unless you're absofuckinglutely sure. Check it twice, then don't post it. There be sharks in these waters.
Vestal
Gold Member
Incorrect analogy.. More like you can flex dumbells of 250 pounds on each arm and squat 500 pounds thus total power of 1000 pounds.
Interfectum
Member
Shits hot man... like boy band hot.
lastflowers
Banned
Can people just be happy that there is a possibility that the xbone is a little bit better than before? Can't that only benefit everyone?
You were the one talking about that AMD Flops are different from Nvidia Flops... No one doubted that comparing Flops to deduct actual performance is a stupid thing because its mostly about how effective the actual architecture is.
Interfectum
Member
I don't think any (sane) people are 'unhappy' about this. More skeptical than anything.
link1201
Member
Ok, that is what I thought. I was worried I was going crazy...I could see the PR spin angle if this was a MN or Xbox new wire announcement etc, but this is the word they are getting from DEVs.
No? It's explained in the next paragraph. But jumping-to-conclusions Is easier it seems.
AgentP
Thinks mods influence posters politics. Promoted to QAnon Editor.
102.4 * 1.88 = 192.5 (88% increase).
dragonelite
Member
normal folks with their double the 1% buys dem extended format.
This is not "random math" - but thank you for the accusation...
102GB/s was the embedded memory peak bandwith up until today.
800mhz*128byte * 1 (read or write operation) =102,4GB/s
800mhz*128byte * 2 (1 read and 1 write operation) =204,8GB/s
DF stating the new peak memory bandwith beeing 192GB/s while maintainig 800mhz clockspeed just doesn't add up...
nothing at all is explained in that article... I mean nothing. this entire thread is assumption based, as is the article itself aside from the 192GB/s number (which is second hand to begin with). Let's not kid ourselves otherwise.
This isn't entirely true, just highly unlikely. If MS was assuming a 12% deadlock scenario, or say an 88% likelihood of being able to get an extra read or write in pre- or post- clock cycle, then it's possible that's where they got that number from.. but yeah.. highly unlikely.
Sure. Still, an increase in "88%" is weird to put it mildly. You can't change the way an interconnect works (or discover that it works differently) by chance. This just doesn't happen. I guess the article oversimplifies the issue, or does not have the whole story. For instance, was bidirectional communication possible before and if not, why not?
Well if you want this dev fired, ask DF to out him... I really recommend to read the whole article.
zomgbbqftw
Banned
Let's go through this logically, I'll lay it out so everyone can understand.
Previously MS engineers though read/write was only unidirectional, and the APU to ESRAM bandwitdth was pegged at 102GB/s, the reality was that it was bidirectional, regardless of what they thought which meant it was actually 204GB/s which lines up perfectly to 800MHz for the GPU.
Now we have information saying that MS engineers have discovered that information is bidirectional (not that it is now, just that they found out it is) and the consolidated read/write bandwidth is 192GB/s which is 96GB/s in each direction. That figure is lower than the old 102GB/s figure and it implies a GPU clock of 750MHz.
So yes, 192 is higher than 102, but it is not comparable as the latter is unidirectional bandwidth and the former is bidirectional. The fact that MS engineers didn't know or realise that you could run read/write operations simultaneously is irrelevant because it was still possible, this is not a new addition, more a new discovery. Think of it like a scientific discovery, just because an apple fell on Newton it doesn't mean he invented gravity, it existed before that, he just discovered it.
So we've actually gone from 204GB/s to 192GB/s or on the old measure, 102GB/s to 96GB/s, it's not that hard to understand. Leadbetter has this one wrong and he should try to correct it.
NoirVisage
Banned
That's what he's not getting, and what I assumed DF was above.
LukasTaves
Member
It's not like Ps4 and Xbone gpus are exactly the same either. Ms deliberated decided to trade gpu processing power for more onchip memory. That alone gives differences in architecture that could unbalance the flops to performance ratio.
sis i think its more some of this stuff just isnt adding up. seems more speculation/rumor than confirmation to me. after all that has happened surely you cant blame ppl for being skeptical
Demanding negative proof. Huh. I can't even tell if something's sarcastic anymore.
Tripolygon
Banned
Thats the beauty of the math. You can buy 3 Toyota Camry rated at 268hp each, add them all together and they will be more powerful than a Pagani Zonda Revolucion.
Magnific0giganticus
Banned
Where's cboat when you need him?
Crazy Buttocks On A Train, I summon thee!
Crazy Buttocks On A Train, I summon thee!
LabouredSubterfuge
Member
I was explaining to the poster that comparing flops on two different architectures is a fools errand but that comparing flops on two extremely similar architectures is not so much.
esram especially if its only 32mb is irelevant these days
It could be used for a ping pong game running one algorithm based on a single C++ class file. But for complex gaming having1000s of things on screen , it is basically useless
I am sure that before responding to me , you do realize that whenever a thread unloads its resources or is killed by kernel , then there is cache penalty and we are talking a meagre 32mb which cant be used concurrently by all routines.
Again - it's not mentioned that the ESRam can now be utilized fully bi-directional.
Please explain to me how a "partialy" 88% bidirectional bus works...
By this logic, caches are irrelevant because they are only 2MB-6MB in size.
What's so useless about using eSRAM like the eDRAM in the Xbox 360? You put the framebuffer in it, apply effects like anti-aliasing or particles, then pass it off to be displayed.
Edit: I am assuming that it's similar to the 360's eDRAM in that it has logic units surrounding it rather than just being a chunk of fast memory.
umm.. the two GPUs are identical architectures.. absolutely. The only "not identical" part are the number of compute units on each GPU and the included on-die eSRAM. Both of those have no bearing on the actual performance of the GPU. It's still X total CU's running at Y clock speed under the same architecture.
edit - and no, they didn't trade processing power for "on-chip memory". They traded processing power for a faster cache to offset the slower ram they had to stick with due to deciding on 8GB very early on.
And frankly, I am ECSTATIC that they decided on 8GB so early.. had Sony's luck not come up and we were looking at 4GB in PS4 right now... almost every comparison thread to date would be a much more interesting and contentious story.
This is exactly what I am not getting. I am not assuming that somebody at Microsoft wants to be disingenuous, just that the story the article tells doesn't make much sense, technically. There must be some sort of oversimplification.
Thanks for the explanation, this makes sense.
I don't know how this works - I'm quoting the article.
- Status