On Tue, 06 Sep 2016, Jonas Zierer wrote: > I'm running Ubuntu on my Dell E7440 (CPU: i7-4600U CPU @ 2.10GHz, > sig=0x40651) and have exactly the same problem. I updated the microcode
It might be, or it might not be exactly the same problem. Do you have *exactly* the same problem as the one reported on the outdated microcode for the E5v3, which only shows up during a microcode update ? -- for this one, removing intel-microcode makes the problem disappear. Or do you have *exactly* the problem as reported for the Core i7-4850K in the Intel forum, which shows up during boot **without** any microcode updates, based on the type of memory/bus current limiters that are set by the BIOS into the processor? -- for this one, it will happen no matter what (including in Microsoft Windows). If it doesn't strictly match the behavior listed above, it is a different problem than the one reported in this bug report. > using iucode_tools to the most recent version (7/14/2016) but the problem > persists > > [ 0.000000] microcode: CPU0 microcode updated early to revision 0x1f, > date = 2016-04-01 ... > [ 0.718311] microcode: CPU0 sig=0x40651, pf=0x40, revision=0x1f > [ 0.718316] microcode: CPU1 sig=0x40651, pf=0x40, revision=0x1f > [ 0.718324] microcode: CPU2 sig=0x40651, pf=0x40, revision=0x1f > [ 0.718331] microcode: CPU3 sig=0x40651, pf=0x40, revision=0x1f This is a different microcode, for a different processor than the ones reported in this bug report and the intel forum. I searched the specification update for Haswell-U (Core i7-4600U), available here: www.intel.com/content/dam/www/public/us/en/documents/specification-updates/4th-gen-core-family-mobile-specification-update.pdf But could not find any erratum that matched the one in Hawell-E/EP that was documented, and fixed by Intel. There are some *different* errata that might affect the processor speed in your processor: HSM149, HSM118 (could cause thermal throttling to engage), and HSM58, but they should all have been fixed quite a while ago... > is it possible that the problem was fixed for only some CPUs? Yes, the issue was fixed for Haswell-E/EP, where it was listed as erratum... but AFAIK it was neither reported, nor fixed for any other processor type, not even on the other processors with the Haswell microarchitecture. Since it is not listed by Intel as a known erratum for your Haswell-U processor, it gets a lot more difficult to know what it might be. Can you ask other users of your laptop, preferably including people that use it with Microsoft Windows, whether they have the same issue or not? -- Henrique Holschuh
