Poor power efficiency with B660/B760* boards and active** Full-Speed USB devices

Dan0987 · ‎01-22-2024

Hi,

The CPU spends a significant amount of time in higher C-states after connecting a Full-Speed (12Mbit/s) USB device, significantly affecting power consumption. The deeper the Package C-state was in prior to connecting the Full-Speed USB device, the greater the difference in power consumption.

* the problem has been observed on motherboards with B660 and B760 chipsets, but it is possible that other 600 and 700 series chipsets are also affected.

** applies to connected and not suspended devices

Here are some numbers produced on a Linux system with an i5-13500 and a Gigabyte B660 AORUS MASTER DDR4 and various USB devices, but it appears that MS Windows is also affected:

Baseline. System at idle. Total power consumption: ~ 5.3 W

C2 (pc2)	0,6%
C3 (pc3)	0,7%
C6 (pc6)	0,3%
C7 (pc7)	0,0%
C8 (pc8)	0,0%
C9 (pc9)	0,0%
C10 (pc10)	97,5%

Baseline + Logitech M90 mouse (Low-Speed, 1.5 Mbit/s). Total power consumption: ~ 6.5 W

T:  Bus=01 Lev=01 Prnt=02 Port=06 Cnt=01 Dev#= 18 Spd=1.5  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
P:  Vendor=046d ProdID=c05a Rev=63.00
S:  Manufacturer=Logitech
S:  Product=USB Optical Mouse
C:  #Ifs= 1 Cfg#= 1 Atr=a0 MxPwr=100mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=usbhid
E:  Ad=81(I) Atr=03(Int.) MxPS=   4 Ivl=10ms

C2 (pc2)	5,0%
C3 (pc3)	1,1%
C6 (pc6)	0,3%
C7 (pc7)	0,0%
C8 (pc8)	0,0%
C9 (pc9)	0,0%
C10 (pc10)	92,7%

Baseline + Flash Drive (High-Speed, 480 Mbit/s). Total power consumption: ~ 6 W

T:  Bus=01 Lev=01 Prnt=02 Port=06 Cnt=01 Dev#= 16 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=0781 ProdID=5583 Rev=01.00
S:  Manufacturer=SanDisk
S:  Product=Ultra Fit
S:  SerialNumber=<redacted>
C:  #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=224mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

C2 (pc2)	0,8%
C3 (pc3)	1,0%
C6 (pc6)	0,3%
C7 (pc7)	0,0%
C8 (pc8)	0,0%
C9 (pc9)	0,0%
C10 (pc10)	96,9%

Baseline + spinning 5 TB 2,5" HDD powered from the USB port. (SuperSpeed, 5 Gbit/s). Total power consumption: ~ 8.6 W

T:  Bus=02 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#=  4 Spd=5000 MxCh= 0
D:  Ver= 3.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 9 #Cfgs=  1
P:  Vendor=1058 ProdID=2665 Rev=20.07
S:  Manufacturer=Western Digital
S:  Product=My Passport 2665
S:  SerialNumber=<redacted>
C:  #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=896mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage
E:  Ad=02(O) Atr=02(Bulk) MxPS=1024 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS=1024 Ivl=0ms

C2 (pc2)	0,8%
C3 (pc3)	1,0%
C6 (pc6)	0,2%
C7 (pc7)	0,0%
C8 (pc8)	0,0%
C9 (pc9)	0,0%
C10 (pc10)	97,1%

And now, for comparison, some Full-Speed (12 Mbit/s) USB devices:

Baseline + Keyboard. Total power consumption: ~ 11.5 W

T:  Bus=01 Lev=01 Prnt=18 Port=07 Cnt=01 Dev#= 17 Spd=12   MxCh= 0
D:  Ver= 1.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=04d9 ProdID=a131 Rev=01.04
S:  Manufacturer=HOLTEK
S:  Product=USB-HID Keyboard
C:  #Ifs= 4 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=01 Driver=usbhid
E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=1ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
E:  Ad=04(O) Atr=03(Int.) MxPS=  64 Ivl=1ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 2 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 3 Alt= 0 #EPs= 2 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
E:  Ad=06(O) Atr=03(Int.) MxPS=  64 Ivl=1ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=1ms

C2 (pc2)	51,4%
C3 (pc3)	1,1%
C6 (pc6)	0,1%
C7 (pc7)	0,0%
C8 (pc8)	0,1%
C9 (pc9)	0,0%
C10 (pc10)	46,2%

Baseline + Logitech G700 mouse. Total power consumption: ~ 11.5 W

T:  Bus=01 Lev=01 Prnt=02 Port=06 Cnt=01 Dev#= 12 Spd=12   MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS= 8 #Cfgs=  1
P:  Vendor=046d ProdID=c531 Rev=21.00
S:  Manufacturer=Logitech
S:  Product=USB Receiver
C:  #Ifs= 2 Cfg#= 1 Atr=a0 MxPwr=98mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=usbhid
E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=1ms
I:  If#= 1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=00 Driver=usbhid
E:  Ad=82(I) Atr=03(Int.) MxPS=  20 Ivl=1ms

C2 (pc2)	51,5%
C3 (pc3)	0,7%
C6 (pc6)	0,1%
C7 (pc7)	0,0%
C8 (pc8)	0,1%
C9 (pc9)	0,0%
C10 (pc10)	46,7%

Baseline + Razer DAV2Pro mouse. Total power consumption: ~ 11.5 W

T:  Bus=01 Lev=01 Prnt=02 Port=06 Cnt=01 Dev#= 14 Spd=12   MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1532 ProdID=007d Rev=01.00
S:  Manufacturer=Razer
S:  Product=Razer DeathAdder V2 Pro
S:  SerialNumber=000000000000
C:  #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=100mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=02 Driver=usbhid
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 1 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=01 Driver=usbhid
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 2 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=01 Prot=01 Driver=usbhid
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 3 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=01 Driver=usbhid
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=1ms
I:  If#= 4 Alt= 0 #EPs= 1 Cls=03(HID  ) Sub=00 Prot=01 Driver=usbhid
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=1ms

C2 (pc2)	51,5%
C3 (pc3)	0,9%
C6 (pc6)	0,2%
C7 (pc7)	0,0%
C8 (pc8)	0,1%
C9 (pc9)	0,0%
C10 (pc10)	46,3%

Related issue: High power consumption when using USB1.1 serial devices under Linux.

Any information on this and possible workarounds would be greatly appreciated.

Best regards,

Daniel

ACarmona_Intel · ‎01-29-2024

Hello Dan0987,

We greatly appreciate your posts in our Intel communities.

We understand that you are having issues with your system, as it is having a poor power efficiency with B660/B760* boards and active** Full-speed USB devices

In order for me to isolate the issue and provide the best solution, kindly provide the following information:

When did the issue start?
Was the system working fine before?
Have you made any changes, like software, settings, drivers, recent installations, or hardware upgrades, that resulted in this issue?
Have you tried to swap the processor for another motherboard? Does the issue still persist?

Thank you, and have a great day ahead!

Best regards,

Carmona A.

Intel Customer Support Technician

Dan0987 · ‎01-30-2024

Hi Carmona,

Thank you for the reply. I observed the issue shortly after purchase, in June 2023, if I remember correctly. Nothing has changed since then. BIOS/microcode released during that period had no impact on it. The issue is reproducible on various Linux distributions and MS Windows. I tried swapping the motherboard to ASUS TUF GAMING B760M-PLUS - the issue still persisted. Other than that, I didn't make any hardware changes. I haven't tested any other CPU.

Best regards,

Daniel

ACarmona_Intel · ‎01-31-2024

Hello Dan0987,

Thank you for the information provided.

We will do further research on this matter and post the response on this thread once it is available.

Have a fantastic day, and thank you very much for your patience and understanding!

Best regards,

Carmona A.

Intel Customer Support Technician

alex3305 · ‎02-01-2024

Dear @ACarmona_Intel,

Please also take the time to read the previous thread (https://community.intel.com/t5/Processors/High-power-consumption-when-using-USB1-1-serial-devices-under/m-p/1516435) as was linked in the OP. As this issue, or something related, was reported by multiple users.

ACarmona_Intel · ‎02-04-2024

Hello Dan0987,

Thank you for patiently waiting on our response.

We understand that you are experiencing a high C state after connecting a full-speed (12 mbit/s) USB device.

To further explain, C-states are power-saving modes that lower the CPU's voltage and clock speed when it is not in use. Higher C-states indicate more power savings, but also more delay to resume normal operation.

In order for us to continue working on our issue, please provide the following information:

Does this only occur with the i5-13500 processor?
What are the other brands and models of the motherboards you have used?
What is the exact name of the Linux distribution and Windows OS you have used?

Also, we would like to let you know that we've explored the other forums, and the suggestion is to contact Linux. However, we have to further examine our issue, and we can do that by obtaining more details, which you can only provide, so we can come up with appropriate answer.

By the way, you may check out these links for additional information on the issue that we have:

Thank you, and have a great day ahead!

Best regards,

Carmona A.

Intel Customer Support Technician

Dan0987 · ‎02-04-2024

Hi Carmona,

Thank you for pointing out my mistake. My apologies for the confusion. Unfortunately, it seems that I cannot correct the original post. My goal, of course, is to keep the package C-State as high (deep) as possible, when 12 Mbps USB devices are connected, as is the case with USB devices of other speeds.

Personally, I have only tested the i5-13500 on:

Gigabyte B660 AORUS MASTER DDR4 (two different units)
TUF GAMING B760M-PLUS WIFI D4

The operating systems I tested on:

Arch Linux (no version, it's a rolling release distribution) kernels 6.4 - 6.7
Windows 11 23H2

Best regards,

Daniel

alex3305 · ‎02-05-2024

Hi @ACarmona_Intel,

I also want to chip in, because of my very similar issue. Or maybe the same. This is with a Gigabyte B760M GAMING X DDR4 with unRAID on Linux kernel 5.19 to 6.1.

ACarmona_Intel · ‎02-05-2024

Hello Dan0987,

Thank you for the information provided.

Again, we will do further research on this matter and post the response on this thread once it is available.

By the way, Have you tested another processor to rule out our issue?

Thank you so much for your understanding and patience, and have a wonderful day!

Best regards,

Carmona A.

Intel Customer Support Technician

ACarmona_Intel · ‎02-08-2024

Hello Dan0987,

Again, thank you so much for patiently waiting on our response.

Our engineers have already discussed the concerns we have, and to further get to the root cause of our issue, may we know the brand and type of USB device you are using?

And please verify if these are all accurate, and kindly provide the specific brand and type:

Logitech M90 mouse
SanDisk Flash Drive
Western Digital spinning 5 TB, 2.5" HDD

Full-Speed (12 Mbit/s) USB devices:
HOLTEK Keyboard
Logitech G700 mouse
Razer DAV2Pro mouse

Furthermore, what method are you using to measure the power consumption? And what is the effect of this higher power consumption on your computer?

By the way, we would also like to inform you that the maximum power consumption for a USB port is 500 mA, and it should not affect anything.

Thank you, and have a great day ahead!

Best regards,

Carmona A.

Intel Customer Support Technician

Dan0987 · ‎02-08-2024

Hi Carmona,

Here are the full names of the devices, but I believe that the issue should be easily reproducible with any 12 Mbps USB device, certainly with the HID class devices.

Devices with no significant impact on the package C-State.

Logitech M90 (PN 910-001794)
SanDisk Ultra Fit USB 3.0 16GB
Western Digital My Passport 5TB WD50NDZW-11BHVS1

Devices that significantly affect the package C-State.

MODECOM Volcano Blade (HOLTEK) keyboard
Logitech G700 (PN 910-001761)
Razer DeathAdder V2 Pro (PN RZ01-033501)

I use a Kill-A-Watt like device to measure the power consumption. I have not noticed any impact on the computer itself.

Best regards,

Daniel

alex3305 · ‎02-09-2024

Hi @ACarmona_Intel,

Thank you for your reply. For me, it were different devices than @Dan0987 mentioned.

USB devices that had a negative impact on power consumption:

SONOFF Zigbee 3.0 USB Dongle Plus-P
Conbee II
Z-Wave.me UZB Z-Wave Controller Plus

USB devices that didn't have an impact on power consumption:

WD Passport 2TB (USB 3)
WD Gaming Drive works with PS4 4TB (USB 3)
OEM 2.5" HDD enclosure with a Crucial BX500 1TB (USB 3)
Philips 16GB USB drive (USB 2.0)

I measured an increase of somewhere between 6W - 7W when these devices were connected and in use. It also didn't matter if 1 device or more devices are in use. The power increase is always the same. But far exceeding the expected 500mA USB power rating that you mentioned. That's why I think something else is not working correctly. I measured using a TP-Link Tapo P115 smart plug and a generic power meter akin to the Kill-A-Watt.

The only thing that I could observe is that package C-states weren't going below C2 when the devices were connected and used. The individual cores were going reaching C6-C7 according to Powertop. On my other computer (based on an Intel Celeron J4105), the package C-state reaches C6 just fine with the devices connected and in use. Other than that, no noticeable effect was observed.

ACarmona_Intel · ‎02-11-2024

Hello Alex3305,

Thank you for posting in our Intel communities.

Please file a new case so that we can appropriately support you as well, as there will be differences between your device and Dan0987.

Intel Support: https://www.intel.com/content/www/us/en/support.html

Thank you for your understanding, and have a great day ahead.

Best regards,
Carmona A.
Intel Customer Support Technician

ACarmona_Intel · ‎02-11-2024

Hello Dan0987,

Thank you so much for the response and for recommending to us that the issue will be easily reproducible with any 12 Mbps USB device, certainly with HID-class devices.

By the way, the following information that you have shared was all highly noted.

Again, I will discuss our issue with our engineers and post the response on this thread once it is available.

We really appreciate your patience and understanding, and have a great day!

Best regards,

Carmona A.

Intel Customer Support Technician

ACarmona_Intel · ‎02-18-2024

Hello Dan0987,

I have some new information from our investigation, and we need some more details from you to give you a precise answer. Please do, answer, and provide the following:

Follow the steps on the Logitech website for your G700 mouse and inform us if you notice any difference. Here is the link: https://support.logi.com/hc/en-gb/articles/360023247114-Expected-battery-life-of-the-G700-gaming-mouse
Can you please explain why you think it is a processor issue?
Have you contacted the USB manufacturers to find out the reason and their recommendations? We believe some I/O driver or I/O device settings might be the problem.

Please let us know so we can determine the root cause of this issue.

Thank you, and have a great day ahead!

Best regards,

Carmona A.

Intel Customer Support Technician

Dan0987 · ‎02-19-2024

Hi @ACarmona_Intel,

Thank you for taking the time to investigate this issue. Here are the answers to your questions.

Follow the steps on the Logitech website for your G700 mouse and inform us if you notice any difference. Here is the link: https://support.logi.com/hc/en-gb/articles/360023247114-Expected-battery-life-of-the-G700-gaming-mouse

These tips relate to the battery performance of the mouse itself. I don't have to switch on the mouse at all. The issue is reproducible even when just the receiver is connected.

Can you please explain why you think it is a processor issue?

Actually, I suspect the problem is on the chipsets side or its drivers (supplied by Intel, I presume). I've read from other users that the problem can be worked around by using a PCIe USB controller (i.e. bypassing the chipset). Unfortunately I don't own one to confirm. Apologies if this is the wrong forum, but I have not found a more appropriate one for this problem.

Have you contacted the USB manufacturers to find out the reason and their recommendations? We believe some I/O driver or I/O device settings might be the problem.

No, I haven't. It's highly unlikely that the problem lies with the USB devices. Unfortunately, I don't have another modern system to test, but I have read feedback from other users that the problem doesn't occur on other platforms.

Best regards,

Daniel

ACarmona_Intel · ‎02-20-2024

Hello Dan0987,

Thank you so much for providing us with a detailed response.

We will do further research again based on the responses that you have provided, and then we will post the response on this thread once it is available.

Thank you, and have a great day!

Best regards,

Carmona A.

Intel Customer Support Technician

Benderu23 · ‎02-24-2024

I'm glad I found this discussion because I also noticed the same thing with my system.
About my general conditions:
I previously used an old Intel NUC7OJYHN with Pentium Silver J5040 as a home server.
Then a Proxmox with Homeassistant and the SONOFF Zigbee USB stick controlled via Zigbee2MQTT. Power consumption 12 watts regardless of whether the USB stick is plugged in or not.
Now I want to move everything to a new mini PC.
For this I bought an HP Pro Mini G9 and use the same Proxmox version there and took over the VM image from the old server 1:1.
When the new server starts, the power consumption is initially 10 watts --> OK. But if the Zigbee stick is then addressed via Zigbee2MQTT, the power consumption increases to 19 watts and the CPU temperature rises from 34 to 44 degrees Celsius.
If I stop Zigbee2MQTT again (Homeassistant still running), the consumption drops back to 10 watts and the temperature drops again.
The CPU-Usage doesn't really change during this time, only the power consumption.
I tried to use the USB device via Windows and Linux without a VM, but I always get the same result as soon as the USB stick is addressed.
I also completely reinstalled Homeassistant and used the ZHA module instead of Zigbee2MQTT. The same error pattern here too.
The only solution was to connect the Sonoff Zigbee USB stick to another computer and connect it via the network to Zigbee2MQTT using the Linux program “ser2net”. Then the power consumption remains constant at 10 watts and 34 degrees even when Zigbee2MQTT is working.
So the same conditions just without USB-Connection, then everything seems to be OK.

I don't use a mouse, keyboard or other USB devices on the PC

Here are the specs from HP for my new home server. The i3-12100T is installed with 16 GB RAM and an M.2 SSD
The chipset on the motherboard appears to be the Q670.
https://h20195.www2.hp.com/v2/GetPDF.aspx/c08161382.pdf

ACarmona_Intel · ‎02-25-2024

Hello Benderu23,

Thank you for posting in our Intel communities.

There will be differences between your device and Dan0987; therefore, please file a new case so that we can properly support you.

Intel Support: https://www.intel.com/content/www/us/en/support.html

Thank you for your understanding, and have a great day ahead.

Best regards,
Carmona A.
Intel Customer Support Technician

ACarmona_Intel · ‎02-25-2024

Hello Dan0987,

Thank you for patiently waiting on our response.

To help us find out the root cause of the issue, we would appreciate it if you could answer the following questions:

• What prompted you to measure the power consumption?

• Did you experience any throttling in the system?

• Was there any deterioration in the system's performance? Except for the difference in power consumption.

We also want to assure you that as long as the system is functioning according to the specifications and without any warnings or errors, you can use it as it is. If you encounter any issue with the Intel product in the system, we are always ready to assist you with our support process.

Thank you, and have a great day ahead!

Best regards,

Carmona A.

Intel Customer Support Technician

Dan0987 · ‎02-26-2024

Hi @ACarmona_Intel,

Thank you for investigating this issue. Regarding your questions.

• What prompted you to measure the power consumption?

Energy prices in Europe have recently soared, making the replacement of energy inefficient equipment a necessity. I measured all devices that could significantly affect my electricity bill. One of the main motivations for the computer upgrade was energy efficiency.

• Did you experience any throttling in the system?

I don't think so. I replaced the original CPU cooler with a Thermalright Peerless Assassin 120, which should be more than adequate. The motherboard power section heatsink also seems to be more than sufficient.

• Was there any deterioration in the system's performance? Except for the difference in power consumption.

I don't know. If that happened, it escaped my attention.

I realize that a few watts may seem insignificant, but considering that this issue could affect tens or even hundreds of thousands of users, a significant amount of energy is potentially wasted. I believe this is something worth investigating and fixing if possible.

Best regards,

Daniel