- Mar 3, 2017
- 1,747
- 6,598
- 136
PPA-wise it does not crimes but 1t CAGR is severely lacking.
Yes, completely unrelated people.(granted that was a GPU).
That's not a good benchmark.It's not horrible against the x86 competition
Z4 was surprisingly alright so better be something decent.Kind of curious how well the uarch is going to age with Zen6 as only a minor rev, though.
It was the italian guy and i also mentioned it here on the forum.Must state the obvious obligatory different GPUs, but further than that-- does anyone remember some techtuber/leaker saying they saw something really weird in CP2077 with either Zen 5 or 9700X (dont remember which)? Somebody help me, I cant recall who it was but I distinctly remember it. This could be what they were alluding to.
I hope they iron out whatever kinks it now has come second gen FWIW. Would be a shame to waste an unconventional design.It's not horrible against the x86 competition. Kind of curious how well the uarch is going to age with Zen6 as only a minor rev, though.
I hope they iron out whatever kinks it now has come second gen FWIW. Would be a shame to waste an unconventional design.
Wouldn't be the first time though. *cough*
It was the italian guy and i also mentioned it here on the forum.
Also dude you still on the copium train... 6800xt doesnt magicaly net 60% better minimum fps and 15% avg. Also i just benched with fsr off and exact same settings as the chinese i have even better scores then previous screenshot... Cant find the HUB video where he compared amd vs nvidia with cpu limited scenarios and i think it was somwhere in 5-10% range.
it’s seems the M4 has the highest overall ST performance increase this year, kinda funny considering how Apples CPU team is slowly growing again after the exodus.So it seems everyone is flopping except Apple.
it’s seems the M4 has the highest overall ST performance increase this year, kinda funny considering how Apples CPU team is slowly growing again after the exodus.
But it funny how the X Elite couldn’t even match M1 in terms of IPC, looks like there is more to Apples cores than Gerard Williams.
Oh it will, but that's the LNL selling point altogether.so Lunar Lake has to beat that and it will be difficult.
Same settings as the leaked 9700X cyberpunk bench. (I even picked the best one for 9700x). AMD official slides showed watchdog -6% vs 5800x3d stock vs 9700x stock. So it wouldnt be crazy to assume that it could also be slower in cyberpunk.Whoa, whoa, whoa mon frere, what copium? Im not making excuses, just pointing out its not exactly apples to apples-- in any case thats completely secondary to my point about the Italian guys comment about CP2077. What more do you know about that? I could care less about the differences in the GPUs, I know they shouldnt cause those kinds of differences in the averages. Mins can be caused by many, many things. What do you mean you benched? What CPU do you have, X3D or 9700X, lol?
Point is, it seems to me that CP2077 and Zen 5 (desktop at least, Strix seems to perform OK?) seem to not play well together for some reason, is it copium for me to assume that it could be game engine vs brand new architecture related and could possibly be fixed with a game patch or AGESA / driver update, or should I just say "Zen 5 desktop sucks!" and stop asking questions?
it’s seems the M4 has the highest overall ST performance increase this year, kinda funny considering how Apples CPU team is slowly growing again after the exodus.
But it funny how the X Elite couldn’t even match M1 in terms of IPC, looks like there is more to Apples cores than Gerard Williams.
It’s an ~7% IPC increase and 10% clock bump. M4 isn’t groundbreaking yes but it’s an evolution over M3.on tuned SME, sure. This is a stretch. M4 was a fine rev but not with any kind of breakthrough iso-clock increase. It was a clock bump with some tweaks
Qualcomm was also quite misleading but yeah their 2nd gen should be much better.What is surprising here? It's the first uarch from their startup's roadmap. I think people underestimate how much continuity and having past designs to use as foothold and ready tech reservoir is important. It's great achievement they ended up with competitive performance. (people really should completely disregard all that BS about beating everybody 2x over from those old misleading Nuvia blogs).
No. Zen 5 isn’t bulldozer but it’s also not the mythical core that Apple etc will take years to catch up to. That assertion still annoys me.
Yes, I've been having the same feeling lately. Also with RDNA2 being competitive with Ampere as opposed to RDNA3 vs Lovelace, and the almost complete cancellation of RDNA4.I can't help to think that AMD got really lucky with all this Intel situation.
It's not luck, it's Intel pushing their chips beyond any reasonable degree to compete with AMD.Still, let's wait for Zen 5 on the desktop, but I'm not optimistic.
I can't help to think that AMD got really lucky with all this Intel situation.
David Huang was not using an ES. It was a retail sample.Here is what David Huang got for Spec 1t and IPC with an ES sample when equalizing clocks.
View attachment 104081
So a 9.71% IPC increase and the GCC test actually improved by 10.4%. I estimated 7% from Anandtech’s data with a rough calculation of actual clock speed difference but actual clock equalized tests are obviously better. Still a bit underwhelming, but combined with the efficiency increase, it’s an overall good result, just a let down after all the hype. The desktop variant should have higher IPC, it’s just a question of how much.
I feel like there is huge disparity when AMD fails and don’t reach expectations compared to when Intel, Nvidia and Apple fail. Not directing this at you but it’s something I noticed here and other online forums/twitter.Still a bit underwhelming, but combined with the efficiency increase, it’s an overall good result, just a let down after all the hype.
Precisely. I guarantee this forum mocks Lion Cove relentlessly when it launches with similar performance increases.I feel like there is huge disparity when AMD fails and don’t reach expectations compared to when Intel, Nvidia and Apple fail. Not directing this at you but it’s something I noticed here and other online forums/twitter.
The amount of crap Apple got for that 7% IPC improvement over 7 months mind you not even 22 months like AMD is certainly constitutes favouritism. Comments like Apple’s CPU team dead and ARM is dead but when AMD doesn’t reach expectations then its “design is hard”, they focused resources somewhere else, Zen 6 is the one to look out for etc.
10% increase in IPC is 5% YoY, so is AMDs CPU team dead no it’s not, so maybe Kepler and the “x86 gang” should not make statements like how Intel and AMD increase IPC 10% YoY which is certainly not true.
Here is what David Huang got for Spec 1t and IPC with an ES sample when equalizing clocks.
View attachment 104081
So a 9.71% IPC increase and the GCC test actually improved by 10.4%. I estimated 7% from Anandtech’s data with a rough calculation of actual clock speed difference but actual clock equalized tests are obviously better. Still a bit underwhelming, but combined with the efficiency increase, it’s an overall good result, just a let down after all the hype. The desktop variant should have higher IPC, it’s just a question of how much.