Deepcool CG560 chassis review
Fractal Design Torrent Black RGB TG review
Core i9 12900K DDR4 3600 vs DDR5 5200 performance review
Corsair H150i Elite LCD review
Seasonic Syncro Q704 chassis + Connect PSU review
Fractal Design Ion+ 2 Platinum 860W PSU Review
Crucial P5 Plus PCIe 4.0 M.2 NVMe review
Fractal Design Lumen S28 RGB review (LCS)
WD Red SN500 NVMe SSD review
Core i9 12900K processor review
Windows 11 is up to 15 percent slower with AMD CPUs, fixes coming in October
AMD acknowledges that Windows 11 is slower than Windows 10 on suitable AMD processors. This is due to issues with the L3 cache and the processor's thread distribution across cores. Microsoft and AMD are now working on fixes that will be available in October.
The L3 cache's latency is three times that of Windows 10. As a result, AMD cautions that applications that are sensitive to memory subsystem access time variances may operate slower than before. Sensitive applications may operate around three to five percent slower than they should. Certain programs, "such as those frequently used in esports," may perform 10 to 15% slower than they did on the previous OS.
The second issue is with CPPC2, which controls which threads are processed by which cores within the UEFI. With Windows 11, threads would no longer be processed automatically by the processor's fastest core. Performance degradation would be noticeable in particular for programs that rely on a single or a few threads. This issue would be most obvious in processors with eight or more cores and a TDP more than 65W.
While Windows updates are required for the L3 cache, AMD updates can resolve the CPPC2 issue. AMD has stated that both patches would be available in October. Affected users are recommended to continue using Windows 10 until then.
Windows 11 was released on Monday evening. On Tuesday, tweakers provided benchmarks for the new operating system. This already shown that the AMD CPU utilized in certain apps performed slower than the CPU used in Windows 10, although the differences were minimal in other applications.
Download: Display Driver Uninstaller (DDU) V18.0.4.4 (with support for Windows 11) - 10/06/2021 09:30 AM
Download Display Driver Uninstaller v18.0.4.4; this new update brings numerous fixes, changes as well as offering Windows 11 support. Download...
Microsoft provides methods for bypassing the TPM 2.0 verification process during the Windows 11 upgrade - 10/06/2021 09:14 AM
Current users of Windows 10 PCs can to upgrade to the latest version of Windows 11. Microsoft has made a support website available on the internet that details the numerous installation choices. Surpr...
Qualcomm Unleashes the Power of Wi-Fi Gaming on Windows 11 PCs - 10/06/2021 08:45 AM
Qualcomm Technologies, Inc., together with ecosystem leaders spanning key platforms and OEMs, is set to redefine wireless expectations for latency-sensitive gaming, productivity and learning applicati...
By default on a new system, Windows 11 will hinder gaming performance. - 10/06/2021 08:42 AM
Despite Microsoft's boasts that "if you're a gamer, Windows 11 was made for you," you should be on the lookout for prebuilt PCs that come preloaded with the new operating system. ...
Download: AMD Radeon Software Adrenalin 21.10.1 drivers for Far Cry 6 and Windows 11 - 10/05/2021 09:28 AM
On Monday, AMD released the newest Adrenalin drivers. Version 20.10.1 beta is Windows 11 ready. "Far Cry 6" gains 10% over the previous driver, while "Battlefield 2042 Open Beta,&qu...
geogan
Senior Member
Posts: 905
Joined: 2010-01-04
Senior Member
Posts: 905
Joined: 2010-01-04
#5953951 Posted on: 10/10/2021 05:27 PM
There are no benchmarks for "snappiness" or "responsiveness". If I click on a taskbar icon in W11 and it opens faster than in W10, why would I need benchmarks? Some of you rely far too heavily on benchmarks, for things benchmarks are a poor representation of..
Because "snappiness" or "responsiveness" is highly subjective and usually not true. I'm not sure if there are benchmarks that measure it... doesn't that PCMark open and close things lots of times to try and measure this? Anyway all I am saying is someone's personal opinion that something "feels faster" is not usually worth the paper its written on.
There are no benchmarks for "snappiness" or "responsiveness". If I click on a taskbar icon in W11 and it opens faster than in W10, why would I need benchmarks? Some of you rely far too heavily on benchmarks, for things benchmarks are a poor representation of..
Because "snappiness" or "responsiveness" is highly subjective and usually not true. I'm not sure if there are benchmarks that measure it... doesn't that PCMark open and close things lots of times to try and measure this? Anyway all I am saying is someone's personal opinion that something "feels faster" is not usually worth the paper its written on.
pegasus1
Senior Member
Posts: 1198
Joined: 2012-11-06
Senior Member
Posts: 1198
Joined: 2012-11-06
#5953957 Posted on: 10/10/2021 05:59 PM
Just because you disagree, it doesn't make you right. If anybody does something enough they get to notice if that thing is suddenly different, it called absence of the normal, presence of the abnormal, or in some circles 'a change to the pattern of life'.
Because "snappiness" or "responsiveness" is highly subjective and usually not true. I'm not sure if there are benchmarks that measure it... doesn't that PCMark open and close things lots of times to try and measure this? Anyway all I am saying is someone's personal opinion that something "feels faster" is not usually worth the paper its written on.
Just because you disagree, it doesn't make you right. If anybody does something enough they get to notice if that thing is suddenly different, it called absence of the normal, presence of the abnormal, or in some circles 'a change to the pattern of life'.
sykozis
Senior Member
Posts: 22012
Joined: 2008-07-14
Senior Member
Posts: 22012
Joined: 2008-07-14
#5954033 Posted on: 10/11/2021 12:22 AM
It's literally impossible to develop a benchmark to measure "responsiveness" or "snappiness"..... PCMark measures application load time. It can't measure how fast the system actually responds to user input. There is no software that can and it's impossible to develop software capable of such.
"snappiness" and "responsiveness" are objective observations based on experience.
Because "snappiness" or "responsiveness" is highly subjective and usually not true. I'm not sure if there are benchmarks that measure it... doesn't that PCMark open and close things lots of times to try and measure this? Anyway all I am saying is someone's personal opinion that something "feels faster" is not usually worth the paper its written on.
It's literally impossible to develop a benchmark to measure "responsiveness" or "snappiness"..... PCMark measures application load time. It can't measure how fast the system actually responds to user input. There is no software that can and it's impossible to develop software capable of such.
"snappiness" and "responsiveness" are objective observations based on experience.
Kool64
Senior Member
Posts: 1128
Joined: 2006-10-21
Senior Member
Posts: 1128
Joined: 2006-10-21
#5954064 Posted on: 10/11/2021 03:45 AM
I've had it on my main rig for over 2 months and I've not noticed anything with my 3700x.
I've had it on my main rig for over 2 months and I've not noticed anything with my 3700x.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 1198
Joined: 2012-11-06
Had it on several machines since day 1, no issues, just moved the taskbar back to the left side and now its like W10 (with Start 10) only slicker.