AMD Ryzen CPU Core Scaling Performance

[dungeon]

Joker productions ?

https://www.youtube.com/watch?v=nsDjx-tW_WQ&t=1s

Interesting... Joker is running memory at 3000 MHz, that might help to explain the difference in gaming results. I noticed the "MEM" usage on the HUD is different between 1700 and 7700K, not sure how to interpret that.

Hmm... I wasn't able to find any kind of summary of benchmark numbers - all of the comments *about* these videos on other forums suggest that the numbers were pretty close, but there has to be a better way than watching the video and scribbling down numbers.

Fine for gaming, but it would be even better to not compare these since does not make sense comparing and ignoring general all around R7 product anyway.

From pure gaming POV, R5 1400X sounds more appropriate since that should be fastest AMD 4c/8t CPU, as equal number of cores/threads to i7 7700K That should even non OCed have equal fps as that OCed 1700 for these games since none games there uses more than 4 cores anyway.

Sorry to mentioning unreleased products, but i even imagined by watching this R5 1400X stock in action

[dungeon]

Yeah, Joker Productions, that's the name, I didn't even search for any specific, but by video it showed direct overlay of games and MSI Afterburner with FPS, mem usage, CPU usage, GPU usage and so on. From what i saw, it falls in line "similar IPC with different frequencies", same is produced by Guru3D review with CPUz benchmark, so dunno.

What i spotted in that Joker's video that DX11 is fine, but DX12 games tend to be much slower in comparision... wild guess but might be SMT with newer APIs fail somewhat, as like VK in Michael's benchmarks here.

Weird new APIs

[leipero]

The overclocking potential seems to be one of the many open questions. Some appear to think it is limited to +100 MHz (maybe that's just non-X), while elsewhere one reads the 1800X has been overclocked to 5.8 GHz (cooled with liquid nitrogen).

From all things i saw, OC potential isn't that great on Ryzen, but that is to be expected, it's new fab. process, new architecture, Core iX had multiple revisions to come this far (7700k 4.7GHz+).

[dungeon]

From all things i saw, OC potential isn't that great on Ryzen, but that is to be expected, it's new fab. process, new architecture, Core iX had multiple revisions to come this far (7700k 4.7GHz+).

Ryzen is great but this is just R7, rule is that more cores / more threads CPUs can't be clocked as much high as models with lower amount of cores/threads.

It is same for Intel, 6900K isn't shipped with high base clock and it can't go as high as 7700K on OC no way... as that is cut in half cores simply said. Same like this R7 1700 if cut in half would be R5 1400X, same TDP but which would have higher base clock and more OC potentional.

[sarfarazahmad]

Ryzen is great but this is just R7, rule is that more cores / more threads CPUs can't be clocked as much high as models with lower amount of cores/threads.

It is same for Intel, 6900K isn't shipped with high base clock and it can't go as high as 7700K on OC no way... as that is cut in half cores simply said. Same like this R7 1700 if cut in half would be R5 1400X, same TDP but which would have higher base clock and more OC potentional.

yep that would be more suited for gaming. it would be definitely somewhere around 200 USD i think. imagine close to 7700k single threaded performance with OC on 1400x at a close to 200 USD price point. Intel's stands at $340.

[pal666]

Michael , does http://man7.org/linux/man-pages/man1/taskset.1.html to limit available cpus at runtime work worse than bios setting ?

[pal666]

Of course it works. It's the mediocre code created by incompetent game developers that won't scale.

actually workiness of smt depends on task's cache usage. which doesn't necessarily reflect its mediocriness

[pal666]

the majority of the games out there do not scale beyond 4 cores. Rysen R3/5, here I come.

so you will always be playing obsolete games?

[pal666]

Ryzen chips have pretty bad latency to RAM and I'd put my money on this being the problem as the issue seems to be in games, which are more about latency rather than throughput.

this is incorrect. if your application is more about ram latency, you are screwed no matter what.

[pal666]

Well to my understanding, HT works similarly to SMT, and HT was not known to match the performance of an entire CPU core, which is why I'm so impressed AMD did such a good job.

ht and smt are the same and work with same performance