No?View attachment 101375
So Hawk Point -> Strix Point, TDP went up.
Such is the magnitude of RDOA3 failure, yes.It looks like RDNA3.5 is a bigger increase over RDNA3 then RDNA3 was over RDNA2.
They probably did. Just a year later compared to their own roadmaps. They need to speed up their cadence, 22 months for second gen in a row feels kind of ehhhh?you know I think Hulk is right, AMD delivered what they wanted with Zen 5, we just had the wrong expectations.
Guess they weren't feeling any heat from Intel. I suspect it was ready to launch any moment since August 2023 but Intel botched the 14th gen release with refreshed crap so AMD must've been like, why bother?Just a year later compared to their own roadmaps.
I think you said this wrong.Guess they weren't feeling any heat from Intel. I suspect it was ready to launch any moment since August 2023 but Intel botched the 14th gen release with refreshed crap so AMD must've been like, why bother?
Afaik, Prior to this leak, RDNA3 being broken was only rumors and speculation. This is the first real confirmation.Such is the magnitude of RDOA3 failure, yes.
So at 5.5Ghz the INT score would be ~ 3800, assuming the clock was correctly reported. That can't be right.ASUSTeK COMPUTER INC. ProArt P16 H7606WI_H7606WI_00067221D - Geekbench
Benchmark results for an ASUSTeK COMPUTER INC. ProArt P16 H7606WI_H7606WI_00067221D with an AMD Ryzen AI 9 HX 170 w/ Radeon 880M processor.browser.geekbench.com
Not sure if frequency is reported correctly.
I heard AMD missed the target by at least 30%, and all that hard work into saving die space really screwed them over.Afaik, Prior to this leak, RDNA3 being broken was only rumors and speculation. This is the first real confirmation.
Even if you fully believed the "RDNA3 is bugged rumors" (which I was skeptical of). It's still wild to see just how much missed potential there is. The performance delta is bigger than the bugged GTX 480 and the fixed GTX 580.
Basically the 7800XT=6800XT plus a few percent, so same tier virtually no improvement.I heard AMD missed the target by at least 30%, and all that hard work into saving die space really screwed them over.
Being a CEO of Tenstorrent.So. What is Jim Keller doing these days....
It's not quite that linear of a scaling, but yes.So at 5.5Ghz the INT score would be ~ 3800, assuming the clock was correctly reported. That can't be right.
It's the same FP8 socket so yes, all it takes is an AGESA update, fresh solder balls and there you go.In fact, the leak above comes from GPD itself, they are comparing the AI 370 to the Phoenix 8840 as a direct drop-in replacement in their GPD Duo, same TDP options.
Yeah but that's a 5yo dGP.then we are very close to 2060 mobile performance, and Zen 6 APUs might actually be within the range of that performance.
I think we should set our sights quite a bit higher for HT hao SKUI would like to point out one thing.
If the scores for Strix Point arer correct, and there is zero reason for them to be fake, or mistaken, then we are very close to 2060 mobile performance, and Zen 6 APUs might actually be within the range of that performance.
2060 is 6000 pts in 3D Mark TS. With 24 CUs/12 WGPs, and any form of SLC/Infinity cache - we might get it in an APU.
Babysitting Raja Koduri.So. What is Jim Keller doing these days....
Im not talking about Halo products, I am talking about "normal" products .I think we should set our sights quite a bit higher for HT hao SKU
By the way, read this: https://tenstorrent.com/research/the-ojo-yoshi-report-jim-kellers-journey-from-cpus-to-ceo/So. What is Jim Keller doing these days....
That's KRK lands, even where you least expect it.no 8C cut down version
This confirms that LionCove is the result of Jim Keller's activities at Intel.By the way, read this: https://tenstorrent.com/research/the-ojo-yoshi-report-jim-kellers-journey-from-cpus-to-ceo/
Super interesting, especially the bits about AMD and Intel.
Every AMD part since RMB (VGH, really) ships with the tumor.Does Strix point ship with Pluton?