knotgerman

Enable and test. That should be all that is needed. If you can find a "Multi-VC" toggle, try enabling that as well. "Energy Efficient P-state" - unknown what that is but may be for newer LPe cores on say Panther Lake laptop chips. DLMR was added to bios a while back. Tried every single SCEHUB/SCEWIN binary out there including the latest MSI ones. Got close a few times but none worked.

Powertop "arrow lake" patch does nothing. acpi_C1 = C6, C2 = C8, C3 = C10. That's it. I already posted about it being stuck in C2 with the "patch." C-states work; the reporting is just wrong. pcm should work just like powertop should work. Intel doesn't care about arrow lake desktop. File a bug and see what Intel says. My guess is nothing. r8169 kernel driver. You have ASPM fully enabled on the ethernet. Your lspci looks identical to mine. S0ix enablement should allow for deep power savings. I think the issue is pcie roots aren't turning off. I am not risking my mb editing EFI manually. More: https://z8.re/blog/aspm.html https://krasovs.ky/2025/01/11/power-saving.html Official intel s0ix: https://github.com/intel/S0ixSelftestTool Asrock can do it. Tried a few times but gave up.

Yes. powertop will never work so give up. You can read my previous posts. Cx_ACPI = C6/C8/C10. Read the intel docs--they aren't fixing it and the reporting will stay broken. RTL8125 works fine with ASPM fully enabled. Same chip and same MB as me. I can't get lower than 12W, so you beat me with 8-9W. Getting S0ix enabled is the "holy grail" to hit the same low power as Alder Lake/12th gen; however, you seem to be almost there... somehow. # lspci -vv | awk '/ASPM/{print $0}' RS= | grep --color -P '(^[a-z0-9:.]+|ASPM )'Can you post the above?

Intel seems to have listed specs for arrow lake finally: You will never reach C10 without PSR or display off. AFAIK DP/eDP is required for PSR. https://edc.intel.com/content/www/us/en/design/products/platforms/details/arrow-lake-s/core-ultra-200s-series-processors-datasheet-volume-1-of-2/package-c-states/ PKG C10 Display in PSR or powered, ff all VRs at PS4 or LPM + crystal clock off. The processor will enter Package C10 when: All IA cores in C10 + Processor Graphic cores in RC6. The platform components/devices allow proper LTR for entering Package C10. Single display, 60Hz max, and PSR on for C10: https://edc.intel.com/content/www/us/en/design/products/platforms/details/arrow-lake-s/core-ultra-200s-series-processors-datasheet-volume-1-of-2/package-c-states-and-display-resolutions/ PSR off? Max C8 forever. Powertop reporting only 3 states and intel saying it won't be fixed ever: https://edc.intel.com/content/www/us/en/design/products/platforms/details/arrow-lake-s/core-ultra-200s-series-processors-datasheet-volume-1-of-2/processor-ia-core-c-state-rules/ C6-C10 MWAIT(C6/C8/10) or IO read=P_LVL3//6/8 Graphics tweaks https://edc.intel.com/content/www/us/en/design/products/platforms/details/arrow-lake-s/core-ultra-200s-series-processors-datasheet-volume-1-of-2/memory-power-savings-technologies/ Memory Power Savings Technologies Display Power Savings Technologies Processor Graphics Core Power Savings Technologies Intel lpmd does not exist for Arrow Lake: 🤣 https://github.com/intel/intel-lpmd/issues/97

Intel is lazy so they will never fix intel_idle. Note: acpi_idle gives lower power consumption powertop will never work; see #1. Read above thread, and it explains c-states are working; reporting is just busted. zero OEM's will enable S0 on their Arrow Lake motherboards. Try reaching anyone at Asus and ask for S0 be an option in BIOS. 7-10w drop just from that. Every single intel microcode improvement drives up power consumption; roll back your BIOS and watch your power drop.

Yet again, intel is too lazy to fix intel_idle so all working c-states are just dumped into three. 13th gen did the same thing at first. grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/name /sys/devices/system/cpu/cpu0/cpuidle/state0/name:POLL /sys/devices/system/cpu/cpu0/cpuidle/state1/name:C1_ACPI /sys/devices/system/cpu/cpu0/cpuidle/state2/name:C2_ACPI /sys/devices/system/cpu/cpu0/cpuidle/state3/name:C3_ACPI AFAIK, there are zero arrow lake boards that have S0ix enabled through bios or via a beta bios. Mine is "0" i.e. disabled. I have an Asus board and there is no way to talk to asus engineers to even get S0ix enabled.

OEM's have S0ix enabled for such low "Long Idle" + 12VO. "Short Idle" = intel's bad microcode chasing benchmarks. 22W desktop idle for OEM's is IMHO bad. Dell USFF desktop: https://www.energystar.gov/productfinder/product/certified-computers/details/3892093 300T (13th gen) Category I1: Long Idle (watts) Field details: 2.2 Category I1: Short Idle (watts) Field details: 6.4 265T (15th gen/ARL desktop) Category I2: Long Idle (watts) Field details: 2.1 Category I2: Short Idle (watts) Field details: 5.8 Like I said, "Low Power S0 Idle" enabled should get all arrow lake boards down to ~10W.

Once S0ix is enabled, it should drop most arrow lake desktops down to 10w. The problem is turning it on. Asrock is the only OEM I know of that you can beg for beta BIOS with stuff turned on. Beg them to provide you with beta bios and it turned on. Find a version of SCEWIN that actually works to turn it on. Manually edit efi variables and risk bricking your MB Don't have #1, #2 didn't work, and I'm not risking my MB to attempt #3.

Same thing happened for a short while for 13th gen. The c-states work; the reporting doesn't because Intel does not care to fix intel_idle and instead use acpi_idle. https://www.energystar.gov/productfinder/product/certified-computers/details/3999745 Workstations: Long Idle (watts) Field details: 6.6w Workstations: Short Idle (watts) Field details: 44.5w https://www.energystar.gov/productfinder/product/certified-computers/details/3798818 Category I2: Long Idle (watts) Field details: 2.2w Category I2: Short Idle (watts) Field details: 22.6w https://www.energystar.gov/productfinder/product/certified-computers/details/3892312 Category D2: Long Idle (watts) Field details: 3.7w Category D2: Short Idle (watts) Field details: 22.6 OEM's have 12VO psu's and likely S0ix enabled. The best I can do is 12w under the same "Long Idle" conditions i.e. let your desktop idle with monitor blanked.

Go read the link and what I actually wrote: "All of the c-states are just condensed into 3."

No. The correct c-state reporting won't work until intel fixes intel_idle. There might be fixes for kernel 6.19 or whatever number comes after that. https://forums.unraid.net/topic/176866-intel-15th-gen-arrow-lake-thoughts/page/6/#findComment-1566181

I reverted back to intel_idle as there does not seem to be a discernible difference over time. I think hybrid core handing is not optimized. 6.15 - SLPC low power GuC mode 6.16 - EAS support (didn't do much for me) 6.19 - ACPI_idle (and intel_idle) should be improved: https://www.phoronix.com/news/Linux-ACPI-CPU-Idle-Hybrid

C-states work. intel_idle is busted which means powertop is busted. The best you can do is 90-100% C3_ACPI i.e. you hit C10. This is across all arrow lake boards. Every single bios update has raised power consumption. Roll your bios back through each microcode and watch idle power drop. For me, anything beyond 0x116 is unacceptable. Sounds like you are on the latest. I believe the absolute floor for (at the wall) idle power is 10w for desktop arrow lake. I gave up at 16w and moved on.

$ apt install acpica-tools $ acpidump -b -n FACP $ iasl -d facp.dat Use the above to pull the values for your board and convert to text. All desktop boards should have that setting but it is off for some reason.

https://github.com/amitxv/SCEWIN Has anyone been able to get SCEWIN working on arrow lake? It complains about missing a driver or it just does a soft lock when trying to read values.

- No realtek 2.5G - limited sata - arrow lake too expensive for such application - PCIe 5 will eat power if used. + DDR5 low power 6th-12th gen is a better choice. Arrow lake is very efficient at idle e.g. 2.1w for 265T (5.8w with monitor attached): https://www.energystar.gov/productfinder/product/certified-computers/details/3892093 The problem is neither Intel nor any OEM's care at all about LGA arrow lake.

grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/name /sys/devices/system/cpu/cpu0/cpuidle/state0/name:POLL /sys/devices/system/cpu/cpu0/cpuidle/state1/name:C1_ACPI (C1) /sys/devices/system/cpu/cpu0/cpuidle/state2/name:C2_ACPI (C7) /sys/devices/system/cpu/cpu0/cpuidle/state3/name:C3_ACPI (C10) grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/desc /sys/devices/system/cpu/cpu0/cpuidle/state0/desc:CPUIDLE CORE POLL IDLE /sys/devices/system/cpu/cpu0/cpuidle/state1/desc:ACPI FFH MWAIT 0x0 /sys/devices/system/cpu/cpu0/cpuidle/state2/desc:ACPI FFH MWAIT 0x21 /sys/devices/system/cpu/cpu0/cpuidle/state3/desc:ACPI FFH MWAIT 0x60 All of the c-states are just condensed into 3. cat /sys/devices/system/cpu/cpuidle/current_driver acpi_idle I laughed out loud here. Switching to acpi_idle is a 2-3w drop over intel_idle. I'm seeing dips down to 16.5w.

powertop will not report correct c-states until intel_idle is fixed. File a bug with intel and see if you can get them to care about their own products. Intel explained why raptor lake didn't get support initially; they found no real improvement over ACPI. If you hit C3_ACPI with greater than 85%, you are getting C8 at least. BGA vs LGA. LGA Ultra 7 265T https://www.energystar.gov/productfinder/product/certified-computers/details/3999018 3.3w idle (AIO screen off) LGA Ultra 7 265T https://www.energystar.gov/productfinder/product/certified-computers/details/3892093 2.1w idle The issue is intel is chasing gaming benchmarks on PC desktops and dragging those that want low idle with them.

The issue isn't whether or not C-states are working (they are) it's just they are not reported in a human readable format that is tweaked by intel. AFAIK, raptor lake reports correctly now in powertop although some still report it as broken. GitHubAdd Intel Arrow Lake support by nasahlpa · Pull Request #...This commit adds the model numbers for Intel Arrow Lake (ARL) processors. The only boards worth testing for lower idle would be an H810 system; Asrock and Asus both have them. My theory is that arrow lake can't go below 10w due to the chiplet vs monolith design at least for LGA socket. AMD has this issue but they are way worse at 2-3x higher idle than arrow lake. ARL-U has no issues hitting low idle (<10w).

powertop will always be broken because intel_idle doesn't report arrow lake correctly. No one is buying arrow lake and intel doesn't care it seems. (raptor lake got the same treatment but was eventually fixed). "C3_ACPI" @ ~95% is the best I can get which looks like C8. 6.15.2 kernel is required to fix idle power regressions. Every single BIOS update has made idle power higher. 0x116 is good and 0x114 is better but has less performance. 0x116 = 19-20w 6.15.2+ = 17.5w 6.15 SLPC power profile = 16.5w Monitor blanked = 14.5w Booted headless = 12.5w AFAIK, 10w is the floor with arrow lake.

1. Latest bios drives up power consumption on that board. Downgrade: 2. SN850x has high idle power consumption; move this to chipset m.2 slots if you haven't already. 3. Use usb attached to chipset (USB ports with "*" in bios tell you which to use) 4. powertop is broken and likely won't get fixed anytime soon. 5. 2.5gbe must have aspm manually enabled

Anyone notice idle power consumption keeps going up each BIOS update? Easiest way to delineate is by microcode: 0x117 = 22-23w 0x116 = 19-20w 0x114 = 15-16w I assume Intel is trying to placate benchmarks/gamers and ignoring idle power. Is anyone else getting hit by this on Asus or other brands? Almost a 10w jump. 😠

Just use the T-series specs and match them on K- CPUs. https://www.intel.com/content/www/us/en/products/sku/241065/intel-core-ultra-7-processor-265t-30m-cache-up-to-5-30-ghz/specifications.html The "sweet spot" for arrow lake efficiency (30-65W) is even below T-series TDP. IIRC in how the clusters are laid out, the 245k can actually be faster for certain applications. I only bought the 245k because of a cheap bundle. At idle, you won't notice any appreciable difference between any of these chips. True, but the #1 issue you will have is no one owns this platform. Good luck finding anyone to discuss anything related to arrow lake beyond overclocking/gaming. I can't find anyone else on the internet to even discuss chasing ultra low idle power consumption on this platform.

Can those buying into arrow lake post power consumption numbers to get a baseline of what is possible? I can't break through 16W at the wall. OT: For Americans who do not have a microcenter nearby, newegg has 265k+asus z890m combo for $100 off ($436.57) right now. Also other 265k combos as well.

Answering my own question: https://www.tomshardware.com/pc-components/power-supplies/cooler-master-mwe-gold-850-v3-power-supply-review ++ Confirmed efficiency at low idle. +/- Peak is only 40% (340W) +/- Efficiency drops quickly over 40% and even faster when hot - Fan noise at max (I'm never going to ever hit that) - Fan spins up sooner when hot Recommended for up to 350W. 850W version is quieter and more efficient that 750W version. Unknown whether cooler master does component swaps to cheapen PSU over time. Perhaps someone else can comment on that.