- Mar 3, 2017
- 1,626
- 5,910
- 136
How am I to know?So what will we get, and when?
So maybe we’ll get this after all? :How am I to know?
But still you were certain that we won’t get that, since you wrote:What we want: 32% IPC with only 250MHz clock regression launching as soon as this spring
So you must have some idea of what you think we’ll get, and when.What we get: not that and later too
Zen 3 was AMD’s “Conroe” IMO.
Shoot, so were certain Athlon chips. Pentium 4 was running at close to twice the clocks, yet AMD was still winning…
…until the Core series dropped.
Doesn’t that honor technically belong to AMD? Hawk point has “AI” and you could definitely consider that to be a gaming CPU. Zen 5 will also have it and launches before Arrow Lake. (unless something has changed — I haven’t had much time to stay on top of things)
I will actually be glad when consoles get an NPU. It will encourage game developers to use it. I am a PC gamer, but you know we almost always get the shaft when it comes to pushing the limits of tech.
I would also like to see said AI functions used to make game AI smarter, particularly in RTS games. (too bad the genre is on life support)
It is not so much an idea as an anti-idea. I can predict it won't be that because no one has provided any basis to the claims.So maybe we’ll get this after all? :
But still you were certain that we won’t get that, since you wrote:
So you must have some idea of what you think we’ll get, and when.
Though at least with this adroc et al have a chance of being right or close to right.
Yeah, the actual perf is higher, but it sounds like bullshit so no point stating it anywhere near public.I can predict it won't be that because no one has provided any basis to the claims
Ooooooor here is a crazy idea. You can actually use this awesome opportunity to really proof, that you know the performance by posting the "crazy" numbers that noone is going to believe anyway. And if your numbers turn out to be true you have proofen that you are a credible source.Yeah, the actual perf is higher, but it sounds like bullshit so no point stating it anywhere near public.
The point is that the sandbagging is external. In the ideal case any sandbagging leaves room to cover for internal failures. Nobody external would care then. RDNA3's marketing was bad for its broken external promises. Hype trains are disliked for their bad track record of overpromises. AMD's usual sandbagging is kinda refreshing for underpromising and then positively surprising.Yeah I know.
But internally it was very not rosy.
But they always do that.The point is that the sandbagging is external.
"please spoonfeed me".Ooooooor here is a crazy idea. You can actually use this awesome opportunity to really proof, that you know the performance by posting the "crazy" numbers that noone is going to believe anyway. And if your numbers turn out to be true you have proofen that you are a credible source.
So if lots of Zen4 workloads are front end bound , we have a big front end , hopefully super duper prefetch + predictors and we have 50% wider ALU / execution. On your bullish statements im now upping my YOLO prediction from 33% to 41% IPC over Zen4.But they always do that.
RDNA3 not beating it's relatively modest >50% PPW target is the oddity, after all.
"please spoonfeed me".
no? no. get street cred first.
Yay, not the worst guess even!So if lots of Zen4 workloads are front end bound , we have a big front end , hopefully super duper prefetch + predictors and we have 50% wider ALU / execution. On your bullish statements im now upping my YOLO prediction from 33% to 41% IPC over Zen4.
Wouldn't have considered that target modest, so if that's the internal view indeed I'm looking forward to seeing how AMD tackles future consumer graphic gens as a result of that flop.But they always do that.
RDNA3 not beating it's relatively modest >50% PPW target is the oddity, after all.
It's modest given it's a shrink + new uArch.Wouldn't have considered that target modest, so if that's the internal view indeed I'm looking forward to seeing how AMD tackles future consumer graphic gens as a result of that flop.
You plaster a new shiny core onto a rickety antique uncore setup and you win (by a lot).Would someone qualify for me a Conroe moment?
The Conroe moment was when Intel destroyed all of AMD's hopes and dreams for more than a decade. The massive Conroe OC's out of the box that went on over the Intel product cycles for years. I still keep a drawer with my favorite Intel and AMD CPU's.Would someone qualify for me a Conroe moment?
Is it like a Zen moment? Or merely A14 sized?
Well I don't think that'll happen. Is there a better definition that is based on performance without counting on competitor to be too broke to make new cores?The Conroe moment was when Intel destroyed all of AMD's hopes and dreams for more than a decade. The massive Conroe OC's out of the box that went on over the Intel product cycles for years. I still keep a drawer with my favorite Intel and AMD CPU's.
AMD should not have purchased ATI. AMD once owned 33% of GloFlo aka. Global Foundries and spun it off their investment. It's not like AMD wasn't making money. They made big investments that were not smart. AMD was the top of the CPU market for two years. First to 1ghz CPU's, brought 64bit processors to the market when Intel said 32bit was all consumers needed.Well I don't think that'll happen. Is there a better definition that is based on performance without counting on competitor to be too broke to make new cores?
You've already read one.Is there a better definition that is based on performance
Well AMD wasn't, K10 was just underwhelming.to be too broke to make new cores?
So you're celebrating the era where intel used nefarious tactics to stifle competition?The Conroe moment was when Intel destroyed all of AMD's hopes and dreams for more than a decade. The massive Conroe OC's out of the box that went on over the Intel product cycles for years. I still keep a drawer with my favorite Intel and AMD CPU's.
They still do ! But not to the extent they used to.So you're celebrating the era where intel used nefarious tactics to stifle competition?
So you're celebrating the era where intel used nefarious tactics to stifle competition?
Let's not go through these discussions again...AMD should not have purchased ATI.
You've already read one.
So, then, as eek2121 said then Zen 3 was also a Conroe moment. But its supremacy lasted only for a year.You plaster a new shiny core onto a rickety antique uncore setup and you win (by a lot).
But they didn't, not with Conroe et all.So you're celebrating the era where intel used nefarious tactics to stifle competition?
No it wasn't, Zen3 wasn't much of a bigger machine, just a differently balanced one.So, then, as eek2121 said then Zen 3 was also a Conroe moment
No?There are so many designs in flight at Intel now
That's not my problem.I don't see anything dominating like Conroe did for so long.
Intel couldn't control the server market because the Ryzen servers have more cores and are so damn efficient. I am pointing out AMD's pricing strategy like with the pricing of the Zen3 threadrippers. Nobody is buying them because they are $$$$. The first two generations of threadrippers were affordable and priced accordingly throughout the product cycle.They still do ! But not to the extent they used to.