Show Your Support: This site is primarily supported by advertisements. Ads are what have allowed this site to be maintained on a daily basis for the past 18+ years. We do our best to ensure only clean, relevant ads are shown, when any nasty ads are detected, we work to remove them ASAP. If you would like to view the site without ads while still supporting our work, please consider our ad-free Phoronix Premium.
Trying To Run The Intel Core i7 5775C On Linux
While I was so excited to get my hands on the i7-5775C for Linux testing, so far I haven't been able to get any results. At first I was going to test the i7-5775C with a new build using a Gigabyte GA-Z79-HD3P motherboard. After updating to the latest BIOS revision that claims Broadwell support (BIOS F3), the system wouldn't boot. With the i7-5775C installed, the system powers on for a few seconds, resets itself as apparent from the fans, and keeps doing this in a continuous cycle without POSTing or any activity. A Core i7 4790K meanwhile in the same system powers up just fine.
After that I turned to an ASRock Z97 Extreme6 motherboard -- upgraded to the latest BIOS (v2.30) -- and it too plays happy with the Intel Devil's Canyon CPU. The Core i7 5775C booted up just fine so I figured we were off to the races. However, when booting up to the same install as was fine with the i7-4790K, stability problems were evident within minutes when attempting to put the CPU under stress. My easy reproducible case is just running phoronix-test-suite benchmark build-linux-kernel and it will never succeed.
Played around with the Linux 3.19 kernel, Linux 4.1.0 stable, and even Linux 4.2 Git to no avail. I also swapped out the memory and tried enabling/disabling the XMP profiles thinking maybe memory was initially the stability culprit. I also tried booting without the X.Org Server running and even under nomodeset thinking perhaps the Iris 6200 graphics were running into an issue. However, the repeated trend when the system would hang (not accessible remotely) and the intel_idle driver would frequently be cited.
I then tried disabling the intel_idle driver, but now the dump stack involves ACPI CPU idle.
I reached out to the intel_idle maintainer Len Brown and others to see if they had any leads, but given the US holiday weekend, I don't expect much activity this weekend. Just posting this brief update in case anyone has encountered a similar problem or ideas. I'm quite excited to get the Core i7 5775C up for Linux benchmarking. I'm even half-tempted to see if the CPU plays nicely under FreeBSD to try to isolate it as a software or hardware trouble.