View Single Post
Staro 06.11.2019., 09:51   #367
The Exiled
Moj komp
The Exiled's Avatar
Datum registracije: Feb 2014
Lokacija: Varaždin
Postovi: 1,725
56 core Xeon Platinum 9282 ranges from 8% to 84% better performance (31% higher geomean) than AMD’s 64 core Rome-based system (7742) on leading real-world HPC workloads across manufacturing, life sciences, financial services and earth sciences.
For gaming, 8-cores is the optimal spot for performance scaling in modern PC gaming, and at 8-cores we get the best frequency scaling out of our Coffee Lake products and 14nm process technology today. And clock speed is what feeds the hungry primary threads of game engines today! The first thing I see with this set is that going from 8-cores to 12-cores results in less than 10% scaling in all games, and in that 12-game set, 9 of them improve by 5% or less. What about that 12-core to 16-core jump? Only one game in our results today sees an improvement (Ashes of the Singularity once again) while the other 11 games not only do not scale up in performance, THREE of them actually regress slightly, offering lower performance than a 12-core configuration.
Today something happened that many may not have seen. Intel published a set of benchmarks showing its advantage of a dual Intel Xeon Platinum 9282 system versus the AMD EPYC 7742. Vendors present benchmarks to show that their products are good from time-to-time. There is one difference in this case: we checked Intel’s work and found that they presented a number to intentionally mislead would-be buyers as to the company’s relative performance versus AMD. By Intel using the post-2nd generation Intel Xeon Scalable version of GROMACS but the pre-AMD EPYC 7002 series which had been out for over a month, Intel’s numbers are highly skewed for the Platinum 9282 which only has a 20% lead. One can only conclude that Intel’s “Performance at Intel” blog is not a reputable attempt to present factual information. It is simply a way for Intel to publish misinformation to the market in the hope that people do not do the diligence to see what is backing the claims. Once one does the diligence, things fall apart quickly.
Linux kernel dev Greg Kroah-Hartman reckons Intel Simultaneous Multithreading (SMT) - also known as hyper-threading - should be disabled for security due to MDS (Microarchitectural Data Sampling) bugs. OpenBSD was right, he said. "A year ago they said disable hyper-threading, there's going to be lots of problems here. They chose security over performance at an earlier stage than anyone else. Disable hyper-threading. That's the only way you can solve some of these issues. We are slowing down your workloads. Sorry."
Ryan Shrout i društvo se iz petnih žila trude najbolje što mogu, pa nije čudno da je ovaj materijal ugledal svjetlo dana taman prije sutrašnjeg predstavljanja novih Threadripper 3000 modela.
The Exiled je offline   Reply With Quote