Caporegime
- Joined
- 18 Oct 2002
- Posts
- 30,431
Same, I got a well-priced Strix B650E-I ITX board s/h instead but the HDV was almost bought!
Great VRM's and will take a 16c np
Last edited:
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
AMD Zen 5 rumours
- Thread starter Grim5
- Start date
Great VRM's and will take a 16c np
Looks a good board for the money, I'm going to get her a Strix X650E-F board. I used this board for my sons build at Christmas and was really happy with it, it's as good as my board. I'm going to sell her 3800x, X570 TOMAHAWK board, ram and use the the money towards her new board.
5% total system performance from simply selecting the best ram sticks feels like quite an important choice.
Horrible Ryzen 9 9950X inter-CCD latency which is more than twice vs Ryzen 9 7950X is reportedly getting fixed
One of the issues plaguing the Zen 5 CPUs with dual-CCDs is inter-CCD latency. According to reports, the CCD-to-CCD latency in the Ryzen 9 9950X is ~180 ns, more than double the amount of the Ryzen 9 7950X. Fortunately, AMD is reportedly preparing a fix for the issue.
www.notebookcheck.net
Associate
- Joined
- 29 Jun 2016
- Posts
- 535
Ugh, this is ******* reporting.Horrible Ryzen 9 9950X inter-CCD latency which is more than twice vs Ryzen 9 7950X is reportedly getting fixed
One of the issues plaguing the Zen 5 CPUs with dual-CCDs is inter-CCD latency. According to reports, the CCD-to-CCD latency in the Ryzen 9 9950X is ~180 ns, more than double the amount of the Ryzen 9 7950X. Fortunately, AMD is reportedly preparing a fix for the issue.
The person who wrote the original core-core latency test, Ian Cutress while he was at Anandtech, has said that these results rarely if ever directly apply to performance. He tested them because it was interesting to see how the architecture works and what it's potential weaknesses were. People testing them now, e.g. Chips and Cheese, have re-iterated the same thing. It's interesting, but not likely the cause of "lacking performance".
Sure, there may be some workloads under corner cases that benefit by resolving this, but this is not going to miraculously give this processor a 10% performance improvement. If it does it'll be under specific circumstances and not be a general performance uplift.
Last edited:
I suspect many of these workloads could be found in modern games. Games just started to utilise more than 8 cores. And there is a lot of inter-thread communication there
Normal multicore loads, your video encoding and rendering tasks, barely exchange data between threads. Start on a chunk of work, give it back when done. Won't even notice this latency increase
I'm glad that AMD thinks this is fixable. Secretly hope that SMT thread latency increase would be fixed too.
Over on HardwareLuxx.de, Andreas Schilling has been busy:
www.hardwareluxx.de
Also tested KB5041587 on Win 11 23H2 and Zen 3 3D. Yes Ryzen 5800X3D seems gains.
In fact, possible the biggest gains if my spreadsheet is correct (looking at their min scores - not the less useful avg FPS):
Actually excluded the Intels has there was no with and without Patch, if I do:
If even a 9600X can outperform the i9-14900K while using a fraction of the power? Well Intel might as well go home? Certainly explains why they cranked up the power so much with the 14th gen.
Optimierte Sprungvorhersage: Zen 5 mit Windows-Update KB5041587 getestet - Hardwareluxx
Optimierte Sprungvorhersage: Zen 5 mit Windows 11 24H2 getestet.
www.hardwareluxx.de
In fact, possible the biggest gains if my spreadsheet is correct (looking at their min scores - not the less useful avg FPS):
Actually excluded the Intels has there was no with and without Patch, if I do:
If even a 9600X can outperform the i9-14900K while using a fraction of the power? Well Intel might as well go home? Certainly explains why they cranked up the power so much with the 14th gen.
Man of Honour
Wow, that's a very nice gain for the 5800x3d!! Now all we need is the "patch". When is that supposed to be released?
Outside of gaming there is a vast gulf between the 14900K and 9600X in application performance and with the kind of settings and resolutions people are realistically running even with a 4090 there is hardly any difference between any of these CPUs in gaming as things stand.
Which is why my money is on the 14700K as it is rarely more than a hair behind the top tier CPUs while costing a lot less.
Associate
- Joined
- 28 Sep 2018
- Posts
- 2,386
Yep got a 14700k due to price point and with tuning I’m not missing out on anything.
It's pretty amusing
will be better with future GPU releases that will be fasterLoving how the 5800x3d is performing for such low power consumption what a gaming beast got mine for £200 over a year ago
People won't be buying 6 cores for productivity
It's pretty amusing
I'd imagine by the time there are GPUs out which really contrast the difference all these CPUs will be yesterday's story.
Opps, wrong column used for the AvearageIfs in my spreadsheet.
That was Avg FPS not Min FPS, this is Min:
Seems to be a couple of anomalous results for the 14700K in there - one the lows are really bad and definitely not correct which is pulling down the overall mins and in another case they seem to have the 14900K and 14700K results switched around.
I don't go for the very top end GPU anyway, so nice to have this unexpected free performance so keeps it relevant for longer
Point being if they stripped out the 14900K it would probably still giving comparable gaming performance while also having much lower power consumption with comparable application performance to the 9600X...
Last edited: