Hacker News: infberg

New comment by infberg in "GPT-5.6"

infberg — Thu, 09 Jul 2026 17:14:05 +0000

Do you have a source for that?

New comment by infberg in "Amazon EC2 M9g Instances"

infberg — Thu, 11 Dec 2025 10:51:21 +0000

Hey, big fan of the vantage instance finder. Would it be possible to add instance type labels similar to what AWS calls them on their website - "storage-optimized", "general-purpose" etc.?

I find this often useful to quickly compare similar instance types, e.g.: m7g vs. m8g vs. m9g.

New comment by infberg in "Dell deletes Latitude CPU Throttling issue after link is posted here"

infberg — Mon, 14 Feb 2022 20:08:06 +0000

Not sure whether you are aware but this issue seems to affect different vendors like Lenovo as well who can't find a solution neither.

The same issue is being reported all over lenovo linux forums as well and for example on https://github.com/erpalma/throttled/issues/255 you see lots of lenovo people reporting the same.

I personally suffer the same issue on my X1G9, the best fix so far is the unload/load all related kernel modules one which makes throttling at least only drop to 1.2 Ghz.

New comment by infberg in "Faster software through register based calling"

infberg — Thu, 25 Nov 2021 10:54:22 +0000

https://devblogs.microsoft.com/dotnet/loop-alignment-in-net-...

Is a good post in regards to code alignment effects.

New comment by infberg in "Bubble sort slower with -O3 than -O2 with GCC"

infberg — Sun, 17 Oct 2021 16:31:55 +0000

Care to explain? -O3 generates larger code than -O2?

New comment by infberg in "It’s Not Always iCache"

infberg — Mon, 12 Jul 2021 21:43:27 +0000

I agree with you that one can very often get distraced by single events, however knowing that you are frontend/backend bound isn't all that more helpful either.

For frontend you can guess that PGO, BOLT, huge tables might probably help but it's still a blind guess without knowing what to look at next.

Intel's TMA is the only helpful thing here really. Bit sad that AMD and ARM don't provide a way to calculate something TMA-like themselves.