Well then, why don't you list some consumer workloads that require 8+ core CPUs that don't also benefit from having a dGPU and we can determine how important that market is?
That 40TOPs numbers is reached by a combination of CPU and NPU TOPs, it's not just NPU. The NPU only makes up a small...
In AMD's case most systems that will be running without a dGPU will likely be mobile APU based anyway.
Mobile APUs are generally better suited to office PC style usecases than stuff like Raphael. They idle lower, those kinds of office style PC have no real usecase for the handful of cores you...
Integer scores are up but FP results seem to be down a bit.
The AES score is disastrous on both scores, it's dragging down the average significantly. Here's a breakdown with a PHX result that's actually quite similar to the one @Gideon posted earlier:
I'm not sure about that result you're looking at, but a 7950X at 3.1GHz on Linux scores ~2200pts (EDIT: wrong number, ~1300pts). If you use that as a basis, you get 22.3% IPC uplift.
To be fair he's not wrong on one thing: a lot of PHX devices come with memory frequency settings available to play around with. I've seen it in some reviews of handhelds, and I'm sure my Win Mini has it too.
And not just a toggle between different rated frequencies, an input box for frequency...
It's not just X Plus, also one of the X Elite SKUs gets it's boost clock removed, which is mega annoying. I really wish there was a different name for that SKU, maybe it should have been the "X Pro" instead. Because losing nearly 20% ST clocks vs the top end X Elite is easily a whole...
You're looking at the wrong mobile part.
Strix Halo is probably a better glimpse as to where the future of desktop lies. Albeit I imagine a future desktop part would run a much smaller IOD with a much smaller iGPU than STX-Halo will have, the fundamentals will probably be the same.
This patent reminds me a lot of A10 Fusion, where the little cores ended up being almost transparent to software because if a workload was heavy enough it would transition from the little cores to the big cores, and primarily use those instead (not sure how that was determined by the...
Cinebench tracks well with SPEC?
Interesting claim. Any reason you posted the charts for Zen 3 over Zen 2 instead of Zen 4 over Zen 3?
Oh, that's why. The ST perf in R20 gain (16.5%) was barely over than the clock gain (16.3%) from Zen 3 to Zen 4. There was a ~13% uplift in IPC that seems...
If the final retail price for a 9950X is $999, ODMs won't be paying anywhere near that much. You have no clue how large the disparity is between retail sold parts and the prices ODMs pay.
No, I don't think ODMs will be paying less for Strix Halo than they will for Fire Range. I just also don't...
Wait a second, who told you that? I wasn't aware that was rumoured already.
(Please don't take this as a confirmation of a leak or something like that, I've just not seen anyone say that on Twitter or anywhere else is all).
Strix Halo will never be sold via retail directly due to the 256b memory bus.
It will always have to go through ODMs. That's still treated as "sold through ODMs", not sold through retail. You're not making sense.
Once again, you're correlating ODM prices with retail prices, whilst...
So if you agree that you can't compare the price an ODM pays for STX-Halo to the retail price of a 9950X, then we agree that STX-Halo cannot be used to determine if a $999 MSRP is realistic or not. That's the next logical step, no?
You can't simultaneously say this whilst also claiming this:
If you recognise the pricing for ODMs is totally detached from the pricing of consumer retail parts.
It's just an alternative approach to chip design. Adding more stuff on die and creating a larger core also increases power usage. Targeting lower clock speeds means your caches run slower etc. There's loads of tradeoffs taking place here, it's what makes it so damned hard.
Zen 4C doesn't gain...
It is true that those performance predictions are out of date, it's untrue that they're likely based on 20A silicon. Firstly, Intel barely expects any difference between 20A and Intel 3 results, secondly even back then the node choices would have been made.
Nobody's claiming or expecting that...
I've literally seen the performance projections. Just like the slides from Igor on ARL, there's also one for LNL's iGPU compared to MTL-U (which caps out at 64EUs/4Xe cores). Even then Time Spy performance is less than a 2x gain (I'm not giving an exact number, I had too many people complain at...
I mean I think it'd be both lower effort to develop and much easier to run to just have an app with that information and a regular search bar on your mobile phone. And cheaper to the store as well, they don't have to fit a computer to the end of every aisle.
Battery life there shouldn't be too surprising, Teams is the literal best case workload for AMD vs their competitors and they're comparing against M3 Pro, which does sport worse battery life than the base M3. Across an average of multiple tests Hawk Point wouldn't look that good, but I mean...
I'm 100% certain whoever said that is wrong, sorry.
I'm sure Lunar Lake will be a huge step up over what Intel has now for 15W iGPU performance, but at this power level they're currently quite far behind the competition. Also 3050 performance tier is far, far, far too ambitious.
Yeah I expect Kraken to be a bit smaller than PHX, but not by much. Just basically offer similar levels of MT and iGPU performance (better at lower power, worse at higher power if I were to guess) with a better NPU and ST performance. So similar price for an overall mostly improved product.
64b, that's the limit Mendocino had so I'd be downright shocked if Sonoma Valley didn't have it too. They share the same socket after all, 64b LPDDR5 is almost certainly a platform limitation.
G14 2024 (1.5KG) is lighter than the Macbook Pro 14 with M3 Max (1.62KG). If the same device were to run STX-Halo instead, I'd expect some minor weight savings due to only one combined heatsink for the APU package would be needed rather than one seperate for APU and dGPU like right now. Also a...
Not going to spill the beans but it's safe to assume it won't use the basic organic substrates that AMD uses for their desktop packages. A package like that would be awful for a mobile platform, and unlike Dragon/Fire Range Strix Halo is designed for laptops first, not a desktop part repurposed...
Are you asking seriously or are you trying to waste people's time with the full knowledge there are laptops that run significantly higher GPU power limits than the entire Strix Halo package, much less including CPU power consumption.
125W total system power fits relatively small notebooks quite...
Phoenix2 and Mendo aren't the same price bracket, Mendocino is a cheaper part. Sonoma Valley is a direct replacement for the same socket as Mendocino, so it should be considerably cheaper than PHX2.
MTL actually launched late Q4 as well, iirc mid-December.
Lunar Lake isn't that, it's launching in Q3, similar timeframe to X Elite. You're just better off assuming both parts are the same timeframe for the most part. Also Kraken is the mainstream part sure, but both LNL and X Elite are more...
Ampere isn't the best option if what you want is a high performance core anyway. The custom cores designed for AmpereOne were targeting only a very modest improvement over N1 with the main goal being making the core more area efficient more than anything else.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.