• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Windows Defender can Significantly Impact Intel CPU Performance, We have the Fix

unclewebb

ThrottleStop & RealTemp Author
Joined
Jun 1, 2008
Messages
7,323 (1.26/day)
my all core clocks of 4700mhz show around mid 46xx in Defender mode -0x222
The actual clocks are consistent. The problem is that Windows Defender and HWiNFO are constantly fighting over control of the monitoring timers. HWiNFO sets the timers to mode 3 so it can accurately determine the effective clocks. Windows Defender comes along and changes the timers back to mode 2. This happens over and over again. Kind of like two people trying to share a single stop watch. This is what prevents HWiNFO from accurately measuring the effective clock speed. The clock speed has not changed. Just the ability to correctly monitor the effective clock speed has changed.

Monitoring software should be able to request exclusive access to these system timers. That would help prevent any fights like this over their use. The shared timer model that Intel uses is flawed.
 
Joined
Feb 20, 2020
Messages
9,340 (6.16/day)
Location
Louisiana
System Name Ghetto Rigs z490|x99|Acer 17 Nitro 7840hs/ 5600c40-2x16/ 4060/ 1tb acer stock m.2/ 4tb sn850x
Processor 10900k w/Optimus Foundation | 5930k w/Black Noctua D15
Motherboard z490 Maximus XII Apex | x99 Sabertooth
Cooling oCool D5 res-combo/280 GTX/ Optimus Foundation/ gpu water block | Blk D15
Memory Trident-Z Royal 4000c16 2x16gb | Trident-Z 3200c14 4x8gb
Video Card(s) Titan Xp-water | evga 980ti gaming-w/ air
Storage 970evo+500gb & sn850x 4tb | 860 pro 256gb | Acer m.2 1tb/ sn850x 4tb| Many2.5" sata's ssd 3.5hdd's
Display(s) 1-AOC G2460PG 24"G-Sync 144Hz/ 2nd 1-ASUS VG248QE 24"/ 3rd LG 43" series
Case D450 | Cherry Entertainment center on Test bench
Audio Device(s) Built in Realtek x2 with 2-Insignia 2.0 sound bars & 1-LG sound bar
Power Supply EVGA 1000P2 with APC AX1500 | 850P2 with CyberPower-GX1325U
Mouse Redragon 901 Perdition x3
Keyboard G710+x3
Software Win-7 pro x3 and win-10 & 11pro x3
Benchmark Scores Are in the benchmark section
Hi,
Yeah I disable the effective clock monitoring
Also in hwinfo settings/ safety uncheck periodic poling as well.
1705778087149.png
 
Joined
Dec 14, 2006
Messages
536 (0.08/day)
System Name Ed-PC
Processor Intel i5-12600k
Motherboard Asus TUF Z690 PLUS Wifi D4
Cooling Noctua NH-14S
Memory Crucial Ballistix DDR4 C16@3600 16GB
Video Card(s) Nvidia MSI 970
Storage Samsung 980, 860evo
Case Lian Li Lancool II mesh Perf
Audio Device(s) onboard
Power Supply Corsair RM750x
Software Win10 Pro 64bit
The actual clocks are consistent. The problem is that Windows Defender and HWiNFO are constantly fighting over control of the monitoring timers. HWiNFO sets the timers to mode 3 so it can accurately determine the effective clocks. Windows Defender comes along and changes the timers back to mode 2. This happens over and over again. Kind of like two people trying to share a single stop watch. This is what prevents HWiNFO from accurately measuring the effective clock speed. The clock speed has not changed. Just the ability to correctly monitor the effective clock speed has changed.

Monitoring software should be able to request exclusive access to these system timers. That would help prevent any fights like this over their use. The shared timer model that Intel uses is flawed.
Yeah, I saw the fighting happening while running HWinfo64, so the effective clock is just a reporting issue caused by defender counters.
 
Last edited:

sodium

New Member
Joined
Jun 15, 2023
Messages
11 (0.04/day)
Just updating as of the date of this post the defender bug is still a problem so I guess it's never going to get fixed. optimized defaults in bios, 12700k and 4800 JEDEC DDR5. Fully updated windows 11 home 23H2, OS build 22631.3296. Latest bios/ME firmware on MSI Z690. The motherboard doesn't matter with this bug since the same CPU in an ASROCK motherboard had the same problem.

Cinebench R23.200
21382 - the bug is active, effective clock speeds in hwinfo are all throttling slightly lower than normal.
22620 - bug is fixed by simply opening and then closing Throttlestop. Effective clock speeds are now reaching advertised default boost.
 

unclewebb

ThrottleStop & RealTemp Author
Joined
Jun 1, 2008
Messages
7,323 (1.26/day)
bug is fixed by simply opening and then closing ThrottleStop.
If Windows Defender Boost is checked in the ThrottleStop 9.6 Options window, you should continue to get maximum performance whether ThrottleStop is running or not. If you do a sleep resume cycle, you will need to start ThrottleStop again.

I prefer to just leave ThrottleStop running in the background with it minimized to the system tray. Being able to see the CPU temperature in the system tray helps me keep an eye on things. That makes it easier to see when some background process has gone rogue. ThrottleStop is very efficient. If you want to absolutely minimize CPU usage, press the Stop Data button. CPU usage will be close to zero with reduced data monitoring.
 
Top