What's points per GHz got to do with it? Different architectures have different ways to get the same answer. Points per watt I'd understand. Otherwise just rank by performance.
Someone binning?This guy from Canada keeps selling 9900Xs for under $400 US. I was tempted, but looks sus as hell. What do yall think?
AMD Ryzen 9 9900X - Ryzen 9 9000 Series Granite Ridge (Zen 5) 12- Core 4.4 GHz | eBay
Find many great new & used options and get the best deals for AMD Ryzen 9 9900X - Ryzen 9 9000 Series Granite Ridge (Zen 5) 12- Core 4.4 GHz at the best online prices at eBay! Free shipping for many products!www.ebay.com
No, it's +7-9 % over Zen 4 (talking only about games).The difference to previous gen is still small after all all those updates, 5-6%. That's equivalent to like, 230 MHz clock increase on some 5.5 GHz part. Worth something like 30-40 extra dollars, but not much more. Currenly 9700X is 80 dollars more expensive than 7700X.
But weren't people already doing that when comparing IvyBridge to Skylake?Arguing whether it's +5% or +8% is actually hilarious.
There can be a different selesction of games resulting in some % difference; windows update can suddenly change something by 2-3%; error margin when running games is not that tight;
If I said to myself in 2018 that we're now arguing whether the new processor was 1.05x faster or 1.08x faster, I'd just laugh.
But weren't people already doing that when comparing IvyBridge to Skylake?
In the instance which you referred to, AMD actually measured iso-clock performance. That is, the two chips which they put into this comparison were operating at a fixed clock rate, the same for both chips.[...] AMD / Intel / Arm calculate generational IPC uplift [...]
The issue is that IPC might be misleading and not exactly what people are looking for. For example in Zen4 case, and avx512 vs avx2, you would have the same throughput, but AVX512 code would retire only half of the instructions the avx2 loop would do, and maybe shave off few cycles saved on the front-end. So for AVX2 code path, the IPC figure would look better while the performance could be actually the same or worse.Truly measuring IPC involves counting both the actual instructions and the actual cycles. Which is possible to do but somehow hardly anybody does.
That's no reason to quote their results incorrectly.Arguing whether it's +5% or +8% is actually hilarious.
It's a range, there were multiple games tested... Also, that value (Zen4->Zen5) only changed by 1 percentage point.There can be a different selesction of games resulting in some % difference; windows update can suddenly change something by 2-3%; error margin when running games is not that tight;
If I said to myself in 2018 that we're now arguing whether the new processor was 1.05x faster or 1.08x faster, I'd just laugh.
In the instance which you referred to, AMD actually measured iso-clock performance. That is, the two chips which they put into this comparison were operating at a fixed clock rate, the same for both chips.
That's not exactly "IPC", but it is still better than
- clock-normalized performance from chips which ran at fixed but different clock rates,
- or worse, clock-"normalized" performance from chips which ran at variable clock rates, normalizing from a measured characteristic clock rate, e.g. the time-averaged clock rate during the test run,
- or worst and outright hilarious, clock-"normalized" performance from chips which ran at variable clock rates, normalized from a completely randomly picked clock rate which has little connection with the clock rates that actually happened during the test.
Truly measuring IPC involves counting both the actual instructions and the actual cycles. Which is possible to do but somehow hardly anybody does.
Are you sure you remember that correctly? Ivy to Skylake is a cumulative effect of two tocks, Haswell and Skylake.But weren't people already doing that when comparing IvyBridge to Skylake?
I was looking up AT review of Skylake before posting Haven't calculated the percentage but the bars looked within 5% range. Anyway my point was, that 5% gaming improvements weren't something unheard of before even across 2 generations. The whole media coverage of Zen5 sounds like it is an utter failure of a chip. Just going by the titles of some videos one could think it's actually worse than Bulldozer for gaming... It's a bit tiring. That's all.Are you sure you remember that correctly? Ivy to Skylake is a cumulative effect of two tocks, Haswell and Skylake.
My intention wasn't to say 5% is meaningless, but tunnel vision on gaming when deciding Zen5 merits is underselling the arch.If you think give or take 5 percentage points doesn't matter here, anything you'll do with those numbers will have enough of an error margin to make any further "calculations" with that number meaningless.
I was looking up AT review of Skylake before posting Haven't calculated the percentage but the bars looked within 5% range. Anyway my point was, that 5% gaming improvements weren't something unheard of before even across 2 generations. The whole media coverage of Zen5 sounds like it is an utter failure of a chip. Just going by the titles of some videos one could think it's actually worse than Bulldozer for gaming... It's a bit tiring. That's all.
Oh, that wasn't reacting to you, but to the previous posts, my bad.My intention wasn't to say 5% is meaningless, but tunnel vision on gaming when deciding Zen5 merits is underselling the arch.
They already dropped the 9950X slightly. With how hard they are hammering on Zen 4 sales at the moment, they should move through the rest of their Zen 4 inventory pretty quickly I'd think and hopefully move on to price dropping Zen 5.I wonder when we will start to see prices drop on some of these Zen 5 SKU's? When Arrow Lake launches perhaps?? IMO they need to do it soon.
I hope they do quite soon. As you can tell, Im looking for any good deals, lol.They already dropped the 9950X slightly. With how hard they are hammering on Zen 4 sales at the moment, they should move through the rest of their Zen 4 inventory pretty quickly I'd think and hopefully move on to price dropping Zen 5.
My 2nd 9950x came from Amazon. It dropped from $649 to $623 before I even got it installed. I sent it back to Amazon saying I got a better price (from them no less) but I still do not have my refund until Sept 14th !I wonder when we will start to see prices drop on some of these Zen 5 SKU's? When Arrow Lake launches perhaps?? IMO they need to do it soon as these launch prices are just too expensive compared to Zen 4.
Chat with amazon. I'm a big spender but prob not near your league. I bet if you complained about the price drop, they'd give you like $50 just to make you happy. I got like $100 for stuff they didn't send in a reasonable window. Amazon if you're reading this, it didn't happen. Go blue origin.My 2nd 9950x came from Amazon. It dropped from $649 to $623 before I even got it installed. I sent it back to Amazon saying I got a better price (from them no less) but I still do not have my refund until Sept 14th !
3% client operating margins.I find this absolutely perplexing. Would think after enough time they'd get their heads together and sort this out. One are where they definitely can learn from Intel's example. Billions on the table, yeesh.
I find this absolutely perplexing. Would think after enough time they'd get their heads together and sort this out. One are where they definitely can learn from Intel's example. Billions on the table, yeesh.