The Intel Core i9-9900K at 95W: Fixing The Power for SFF
by Ian Cutress on November 29, 2018 8:00 AM ESTCPU Performance: Legacy Tests
We have also included our legacy benchmarks, representing a stack of older code for popular benchmarks.
All of our benchmark results can also be found in our benchmark engine, Bench.
3DPM v1: Naïve Code Variant of 3DPM v2.1
The first legacy test in the suite is the first version of our 3DPM benchmark. This is the ultimate naïve version of the code, as if it was written by scientist with no knowledge of how computer hardware, compilers, or optimization works (which in fact, it was at the start). This represents a large body of scientific simulation out in the wild, where getting the answer is more important than it being fast (getting a result in 4 days is acceptable if it’s correct, rather than sending someone away for a year to learn to code and getting the result in 5 minutes).
In this version, the only real optimization was in the compiler flags (-O2, -fp:fast), compiling it in release mode, and enabling OpenMP in the main compute loops. The loops were not configured for function size, and one of the key slowdowns is false sharing in the cache. It also has long dependency chains based on the random number generation, which leads to relatively poor performance on specific compute microarchitectures.
3DPM v1 can be downloaded with our 3DPM v2 code here: 3DPMv2.1.rar (13.0 MB)
x264 HD 3.0: Older Transcode Test
This transcoding test is super old, and was used by Anand back in the day of Pentium 4 and Athlon II processors. Here a standardized 720p video is transcoded with a two-pass conversion, with the benchmark showing the frames-per-second of each pass. This benchmark is single-threaded, and between some micro-architectures we seem to actually hit an instructions-per-clock wall.
Facebook
Twitter
RSS
101 Comments
View All Comments
Alexvrb - Thursday, November 29, 2018 - link
Yes yes, all those office workers running a 9900K would barely notice. Serious, man? The whole reason this issue came to light was because gamers and other demanding users complained that the processor at DEFAULT settings on pretty much any retail board was annihilating TDP, even more noticeably so than their previous flagship. Journalists are lagging well behind, and when they DO bother looking into it, it's very much a "yeah it's true, shrug" article.Gastec - Wednesday, June 19, 2019 - link
Well said, "shrugging". Automagically overclocked CPU's do make benchmark graphs look better and CPUs sell better. Reminds me of one of AngryJoe's video about a certain MMO: "Oh, you want more? That would be $15 please! $15 more, please! That would be another $15!" Same with Intel, you want more performance, that would be 75% to 100% more watts, please! Yeah, I get it. Want 10 Ghz on all cores? 1000 W, what's the problem?koaschten - Thursday, November 29, 2018 - link
Check https://www.youtube.com/watch?v=kmAWqyHdebILindseyLopez - Wednesday, December 19, 2018 - link
nonicolaim - Thursday, November 29, 2018 - link
Missing link to TDP article on first page.Exodite - Thursday, November 29, 2018 - link
Thanks for this!It would be interesting, though perhaps not entirely related to this article in particular, to get a comparison on actual power draw and load temperatures as well. Similar to what you provide in your usual CPU reviews, to get a fair comparison to both the "unlocked" 9900K as well as the other slew of processors in the bench.
I'd imagine the 9900K would look much better on those numbers, though obviously worse on performance, when actually adhering to TDP.
Wingartz - Thursday, November 29, 2018 - link
*You can read it all [here], although what it boils down to is this diagram*[here] doesn't have a link to the article
:nudge> - Thursday, November 29, 2018 - link
For easy comparisons it's great to see Geekbench making an appearanceAlexvrb - Friday, November 30, 2018 - link
*worthless comparisons barely better Dhrystone and WhetstoneSirMaster - Thursday, November 29, 2018 - link
How many people are actually buying a $500 CPU and capping it's power limit to 95W?Can't be many, how about buy a different CPU if you plan on capping it's power limit like that.
I have an SFF mini-ITX build and my old overclocked haswell CPU is running at like 180W and staying cool just fine.