Comments on: Intel Golden Cove Performance x86 Core Detailed

By: Matt

Matt — Thu, 09 Sep 2021 19:37:03 +0000

hoohoo, you are basically accusing Intel of fraud. If you don't believe what they say then it doesn't matter how much they say, you just won't believe them, so why are you expressing it as the results are "meaningless" instead of just saying they are bogus? Best to wait for the processor to come out, then. But, isn't it more likely they did the tests and they just haven't put the information up yet? After all they released a similar graphic before comparing Sunny Cove to Skylake and I'm willing to bet if there was a discrepancy when the product came out people would have noted it. Before you answer, the information is now up. " Testing as of May 28, 2021. Intel® Core i9-11900k, 4x16GB 1R DDR4 UDIMM 2DPC 3200 Max Memory Frequency, Samsung 980 Pro 500GB PCIe SSD, WIN 10 20H2 19042.ent.rx64.789, High Performance Power Plan, 1920x1080 display resolution Alder Lake Desktop S801 , RVP board with 2x16GB 1R DDR5 UDIMM 1DPC, 4400 Max Memory Frequency, Samsung 980 Pro 500GB PCIe SSD, WIN 10 20H2 19042.ent.rx64.508_update.906, High Performance Power Plan, 1920x1080 display resolution Based on overall scores and individual subcomponent scores on: SYSmark 25, CrossMark, PCMark 10, SPEC CPU 2017, WebXPRT 3, Geekbench 5." So the information on the slide is almost complete. What's missing is that the Alder Lake processor is using DDR5 while the 11th gen is using DDR4 and that all those extra bars apparently represent the subtests that comprise the listed tests. But I suppose you will say that since Intel didn't label which bar was which, or Intel hasn't given the specific system specifications involved, they are still lying about something. Why did Intel choose the specific tests they chose, after all? Is the average weighted based on the number of subtests? Is that appropriate? Yes, any internal benchmarks must be taken with a grain of salt. That's true. We must trust the manufacturer if we trust internal benchmarks or performance promises. But this slide isn't any more "meaningless" than any other slide of internal benchmarks. If Intel promises an IPC uplift of a certain amount and that is not in the same ballpark as reality when the processor comes out then it will reflect badly on the company. What's "meaningful" is the promise, not the details behind an internal benchmark.

By: hoohoo

hoohoo — Sat, 04 Sep 2021 08:36:26 +0000

@Matt,

“As it is it is more meaningful than simply a declaration if “19% IPC improvement.” If you go to the link listed…”
“They don’t have Golden Cove results …”

So the unlabelled slide about 19% better perf has no results for the CPU the slide describes.

That is not more meaningful.

By: Matt

Matt — Fri, 03 Sep 2021 13:42:08 +0000

The chart would show more information if they labeled all the bars, but you’d have to zoom in pretty hard to read them. As it is it is more meaningful than simply a declaration if “19% IPC improvement.” If you go to the link listed in the slide http://www.intel.com/ArchDay21Claims you can go down a rabbit hole of the tests being used. They don’t have Golden Cove results but it looks like there are results from prior Xeon generations andyou can see the workloads being run and the server manufacturers and configurations used.

By: KarelG

KarelG — Fri, 03 Sep 2021 08:07:52 +0000

Oh, Intel, please no. You have put link: For workload and configurations visit https://www.intel.com/ArchDay21claims on the slide and the link is account/pw protected. That’s quite a shame.

By: hoohoo

hoohoo — Thu, 02 Sep 2021 23:37:00 +0000

Gotta hand it to Intel Marketing, the “19% Performance Improvement” slide looks as impressive as hell, but when I zoom in and look at it I find it means absolutely nothing.

STH coverage of Intel this time out has been mostly a slide show. I think it is beneath you guys. STH in the past has been one of the places a person could find real analysis.