CPU Performance: Windows 11 vs Windows 10

There are going to be a lot of Windows 11 vs Windows 10 testing over the next few months, based on different CPUs, chipsets, configurations, and even situations where CPUs are replaced and drivers need to be reinstalled to get full performance. Windows 11 is still young, and most of our tests worked (WSL did not, will need to find out why). In this instance both OS installs were fresh and default with all updates and updated drivers. We haven't had time to run our gaming tests, those should come soon.

(1-1) Agisoft Photoscan 1.3, Complex Test(1-2) AppTimer: GIMP 2.10.18(2-1) 3D Particle Movement v2.1 (non-AVX)(2-2) 3D Particle Movement v2.1 (Peak AVX)(2-3) yCruncher 0.78.9506 ST (250m Pi)(2-4) yCruncher 0.78.9506 MT (2.5b Pi)(2-4b) yCruncher 0.78.9506 MT (250m Pi)(2-5) NAMD ApoA1 Simulation(2-6) AI Benchmark 0.1.2 Total(3-1) DigiCortex 1.35 (32k Neuron, 1.8B Synapse)(3-2b) Dwarf Fortress 0.44.12 World Gen 129x129, 550 Yr(3-3) Dolphin 5.0 Render Test(3-4c) Factorio v1.1.26 Test, 20K Hybrid(4-1) Blender 2.83 Custom Render Test(4-2) Corona 1.3 Benchmark(4-3a) Crysis CPU Render at 320x200 Low(4-5) V-Ray Renderer(4-7a) CineBench R23 Single Thread(4-7b) CineBench R23 Multi-Thread(5-1a) Handbrake 1.3.2, 1080p30 H264 to 480p Discord(5-1b) Handbrake 1.3.2, 1080p30 H264 to 720p YouTube(5-1c) Handbrake 1.3.2, 1080p30 H264 to 4K60 HEVC(5-2a) 7-Zip 1900 Compression(5-2b) 7-Zip 1900 Decompression(5-2c) 7-Zip 1900 Combined Score(5-3) AES Encoding(5-4) WinRAR 5.90 Test, 3477 files, 1.96 GB(7-1) Kraken 1.1 Web Test(7-2) Google Octane 2.0 Web Test(7-3) Speedometer 2.0 Web Test(8-1c) Geekbench 5 Single Thread(8-1d) Geekbench 5 Multi-Thread

Windows 11 has a small effect on some of our Multi-Threaded tests, such as y-cruncher, Speedometer, and AES, but for the most part it's quite minimal.

CPU Benchmark Performance: E-Core CPU Benchmark Performance: DDR5 vs DDR4
Comments Locked

474 Comments

View All Comments

  • adamxpeter - Friday, November 5, 2021 - link

    Very poetic post.
  • bananaforscale - Friday, November 5, 2021 - link

    Seems we're actually getting a Zen 3 refresh early next year. Alder Lake's lead also decreases with DDR4, gaming above 1080p (so basically anyone who would buy a 12900K for a gaming rig), it uses more power and with DDR5 you pay extra for memory.

    Yeah, Alder Lake has some advantages. Not sure I'd call it a better overall package at the moment.
  • madseven7 - Saturday, November 6, 2021 - link

    Intel is back at the cost of power. AMD at that power will destroy Intel. Intel basically said screw TDP.
  • Qasar - Saturday, November 6, 2021 - link

    intel has been saying that for 2-3 years now, its the only way their chips can be competitive with zen 2 and 3
  • Maverick009 - Sunday, November 7, 2021 - link

    They really haven't screwed up as you would like to think. I do believe AMD was thrown off some by the unexpected performance in Hybrid design. They still do trade blows between some games, multi-threaded software, and on applications that are just not optimized for Alder Lake.

    What I have noticed though in the days since Alder Lake's NDA went up and reviews came out, is leaks to AMD's next gen Zen CPUs have begun to trinkle out a little more than usual. Yes we have Zen 4 on the way, which will pave the way for DDR5 and PCIe Gen5 along with an uplift in IPC. However the real secret sauce may be in Zen 4D as the platform to build a heavily multi-threaded core package along with SMT enabled, and then Zen 5. The big picture, is AMD's version of a Hybrid CPU may include a combination of Zen 4D big cores and Zen 5 Bigger cores. The Zen 4D are said to possibly carry as many as 16 cores per chiplet, too, so it would speak to a possible heavily multi-threaded efficient CPU, while sacrificing a little bit of single threaded performance to achieve it. The timeframe would also put the new Hybrid CPU on a collision course to battle Raptor Lake.

    For once the CPU market has gotten interesting again, and the consumer ultimately wins here.
  • NikosD - Monday, November 8, 2021 - link

    @reviewers

    Since AVX-512 is working on ADL, it would be useful to test the AVX-512 vs AVX2 power consumption of ADL by running POVRAY using P-cores only and compare that maximum AVX2 power consumption to AVX-512 max power consumption using 3DPM.

    Because max 272W power consumption of POVRAY as reported, includes 48W from E-cores too.
  • mode_13h - Tuesday, November 9, 2021 - link

    > it would be useful to test the AVX-512 vs AVX2 power consumption of ADL by running POVRAY

    I'm not sure of POV-Ray is the best way to stress AVX-512.
  • NikosD - Wednesday, November 10, 2021 - link

    They have already tested max power consumption of AVX-512 using 3DPM.

    I just asked to test POVRAY using P-cores only, for max power consumption of AVX2 in order to compare with 3DPM.
  • usernametaken76 - Monday, November 8, 2021 - link

    lol
  • xhris4747 - Tuesday, November 9, 2021 - link

    They did not take the performance crown gaming is almost tied overall mt is a mixed bag hopefully they use pbo which gives about 27k-30k on c23

Log in

Don't have an account? Sign up now