Motherboards With Broken ASPM On Linux

Written by Michael Larabel in Hardware on 10 October 2011 at 09:28 AM EDT. 40 Comments
HARDWARE
One of the many OpenBenchmarking.org features that haven't yet been fully taken advantage is the opportunities presented by the vast collection of system hardware/software information and logs that have been submitted to this collaborative testing platform from Phoronix Media. OpenBenchmarking.org is much more than just being a storage place for benchmark results. After writing a simple plug-in this morning, here's a list of many motherboards that have broken PCI-E Active State Power Management support from their BIOS, which can lead to greatly increased power consumption under Linux.

When writing a simple OpenBenchmarking.org plug-in this morning to take advantage of some of the data at hand, it needed just 30 seconds to auto-generate a list of all unique motherboards that don't properly support Active State Power Management. From the data available by OpenBenchmarking.org, there were about 4200 systems being reported with broken ASPM from the BIOS.

Active State Power Management is one of the power savings features in PCI Express, which can cause excessive power consumption under Linux and there's still no proper fix for better handling the ASPM support in situations where the BIOS doesn't properly advertise the feature, i.e. "ACPI FADT declares the system doesn't support PCIe ASPM", although the power savings mode will properly function in most cases.

For many systems, this can be worked around by setting "pcie_aspm=force" when booting the system, but that's assuming the user knows about the problem with their system in the first place.

The list below is what was generated by OpenBenchmarking.org for detected motherboards that are PCI Express enabled, but where the Fixed ACPI Description Table (FADT) claims that the Active State Power Management feature is not supported. To ensure some quality, each motherboard in the list had at least two unique submissions where ASPM could be detected as not working due to the ACPI table.

The list is not exhaustive since it's also up to those that have used the Phoronix Test Suite and opted-in to submit data to OpenBenchmarking.org, but it at least shows some of the motherboard vendors who frequently have bad BIOS implementations. One of the interesting findings is that there's even multiple Intel-branded motherboards that should support ASPM (e.g. the modern Cougar Point Intel DP67BG) but where the ACPI FADT says otherwise. Some recent server motherboards from Intel (e.g. S5520HCT) aren't even setting this feature that's part of the PCI Express specification.

ASUS G53JW v1.0
ASUS G73Jh v1.0
ASUS G73Jw v1.0
ASUS K42F v1.0
ASUS K43E v1.0
ASUS K52JT v1.0
ASUS K52Jc v1.0
ASUS K52Jr v1.0
ASUS K53E v1.0
ASUS K72Jr v1.0
ASUS M50Vm v1.0
ASUS N61Jq v1.0
ASUS U36JC v1.0
ASUS U6S v1.0
ASUS UL30A v1.0
ASUS UL30VT v1.0
ASUS X55SR v1.0
Acer Aspire 5741G
Acer Aspire 5742G
Acer H57M01
Acer JE50_HR
Acer JM41_CP
Acer Mantasta
Apple Mac-942C5DF58193131B
Apple Mac-F222BEC8 v1.0
Dell 01CTXG
Dell 01RP13
Dell 01V648
Dell 02P9X9
Dell 033FF6
Dell 03PH4G
Dell 05XKKK
Dell 0675PR
Dell 06D7TR
Dell 0CK703
Dell 0CRH6C
Dell 0D883F
Dell 0DFRFW
Dell 0DT097
Dell 0H603H
Dell 0H61FC
Dell 0HH807
Dell 0HN7XN
Dell 0J4TFW
Dell 0M858N
Dell 0MD99X
Dell 0N582M
Dell 0N5KHN
Dell 0NR282
Dell 0RF703
Dell 0RW199
Dell 0RW203
Dell 0T656F
Dell 0T6M8G
Dell 0TP412
Dell 0V52N7
Dell 0WF810
Dell 0WG855
Dell 0XHKPT
Dell 0XPDFK
EVGA X58 Classified 4-Way SLI
FUJITSU D2619
FUJITSU D2799
Gigabyte EP45-UD3LR
Gigabyte EP45T-DS3R
Gigabyte P55A-UD3
Gigabyte X38-DQ6
Gigabyte X48T-DQ6
HP 0AC0
HP 0AE8h
HP 0AECh
HP 0B4Ch
HP 1405
HP 1409 v50.19
HP 1411
HP 1448 v65.36
HP 1448 v65.37
HP 144A
HP 1486
HP 1521
HP 1601 v58.28
HP 161C
HP 1630
HP 1657 v10.25
HP 172B
HP 308A
HP 30E7
HP 7008
HP ProLiant DL360 G7
HP ProLiant DL580 G7
HP ProLiant SL390s G7
Intel D510MO
Intel DH57JG
Intel DP55SB
Intel DP55WG
Intel DP67BG
Intel DX58OG
Intel S2600CP v..........
Intel S5500BC
Intel S5500WB
Intel S5520HC
Intel S5520HCT
Intel S5520UR
LENOVO 1706W3Q
LENOVO 20078JU
LENOVO 2007EH7
LENOVO 2241BN5
LENOVO 2522K3G
LENOVO 25379UG
LENOVO 2537EU2
LENOVO 2613EJU
LENOVO 27327KG
LENOVO 2746P3G
LENOVO 2901CTO
LENOVO 2924WJ4
LENOVO 3323PMG
LENOVO 4180D27
LENOVO 4239CTO
LENOVO 4270CTO
LENOVO 42862AU
LENOVO 4290RV5
LENOVO 4290W1A
LENOVO 4290W1B
LENOVO 4313CTO
LENOVO 43149VG
LENOVO 4314D4G
LENOVO 4318CTO
LENOVO 431924G
LENOVO 43494JG
LENOVO 4349WK8
LENOVO 636438G
LENOVO 6459CTO
LENOVO 6464W71
LENOVO 64741AG
LENOVO 7417TPF
LENOVO 7439WB7
LENOVO 7443E4G
LENOVO 7443RQ6
LENOVO 7668CTO
LENOVO 7732CTO
LENOVO 7742NCG
LENOVO 79ETE5WW (2.25 )
LENOVO 8741A11
MSI MS-16F1
PEGATRON G60JX v1.0
POSITIVO H24ZC
Packard Bell BV PB5M
Packard Bell FMP55
RadiSys Hawk Claw
SAMSUNG R780
Sony VAIO
Supermicro X8DA3 v1.3
TOSHIBA Portable PC

If you're interested in the Linux power situation, check out last week's article providing an update on the Linux power situation in Ubuntu. On the topic of OpenBenchmarking.org, over the weekend it was also useful in providing the first Linux information on AMD Trinity APUs that will be released in 2012.

Many more interesting OpenBenchmarking.org features are on the way as I continue working to exploit the true power of the platform and the vision for this unique system.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week