Hacker News Reader

Hacker News

Comment by MindTooth | Hacker News Reader

Parent Full thread

MindTooth

Here are some of Linux stuff: https://www.phoronix.com/scan.php?page=article&item=amd-linu...

View on HN

Kernel 5.4 compiled under 24 seconds. Insane.

Compile on boot

This comment made my day :)

That was already a thing back in 2004: https://bellard.org/tcc/tccboot.html

15 seconds to compile and run a Linux kernel of the time (64MB RAM required!).

That is insane. I'm surprised it can even go that low, I would have expected it to hit an IO bottleneck before then (large object files/linking/source reads, etc).

Even with a fast SSD on my lowly i7, I often wind up sitting at IO or lock contention instead of actual CPU bottlenecks (although it could be argued faster CPU = faster lock release = faster compilation).

They used a Samsung Pro NVMe which should be able to hold almost all of the linux kernel sources in it's read cache without that many issues.

NVMes are magic. Just the same improvement that SSDs have over HDDs. Probably the only upgrade worth getting for my home PC at this point.

Technically, 100%. I'm full SSD right now though which has a seriously noticeable difference from from HDD but for what I do most days NVME isn't justifiable. I see others who can take advantage of the speeds and do so with huge returns.

I do have 2 super SFF HP boxes that only take NVME in the M.2 drive so have one on hand but it isn't installed at the moment.

PCI-ex version 4, double the xfer rate. It can handle a massive 16 GB/s. Are there even disks that can handle that speed?

not yet.

https://www.aorus.com/AORUS-Gen4-AIC-SSD-8TB

15000MB/sec, available now for $3119 AUD.

That's just four SSDs mounted on one riser card with a fan. If you're going to count the aggregate bandwidth of an array, then the question's almost meaningless.

The entire Linux kernel source tree will trivially fit in tmpfs in RAM.

On one of these systems I'm fairly sure you could just whack the entire thing in /tmp and -j64 it, the compile artifacts aren't that big either.

I've done builds in /dev/shm/ on Xeon and Threadripper with only a trivial speed-up. If it can fit in tempfs, make/cc can just load it all into RAM anyway, so I guess you only reduce the build time by the time it takes for the first read. Which would explain why '-j' on a big codebase tends to trigger my OOM killer.

With half the cores of the upcoming (early 2020) 3990X ...

Now there is no excuse to not Install Gentoo.

Hah! There is something cathartic about recompiling the world with -march=native even if it makes no noticable difference.

Would the best use of this CPU be in a group or multi-group build+integration server? It's $2000 for the CPU alone, so this can't be general-use.

I also imagine it'd be useful as a rendering machine for small to medium media companies.

Reply on news.ycombinator.com