Was Collecting SBUs now, Fast compile engines

Ian Molton spyro at armlinux.org
Fri Jun 7 13:33:05 PDT 2002


On Fri, 07 Jun 2002 22:16:02 +0200
Björn Lindberg <d95-bli.no at spam.nada.kth.se> wrote:

> 
> IMO, compiling is mainly dependent on processor speed and cache
> size/speed as Ian says. Next comes RAM bandwidth, and lastly HDD
> performance. The last part is "proven" by the fact that the HDD is
> usually not working very hard at all during compiles, while the CPU
> is.

Actually, you got the last two things backward.

caching, both on the CPU and in the OS come first, and yes, the OSs
memory cache is in RAM, but even the slowest RAM is faster than a
harddisc.

thing is, the data has to get INTO those caches, so unless you have
compiled the software already, all that data is sitting on the harddisc,
not in memory.

the fastest cache in the world cant deliver data it simply doesnt have.

so, in order of importance:

1) CPU caching
2) L2/3 cache (if any)
3) OS RAM cache (note: NOT RAM bandwidth - even the DRAM in my 15 yo
acorn would do here)
4) HDD performance, ***especially*** seek time, far more than
throughput.
5) memory bandwidth

RAM is already so fast, its irrelevant (almost).
-- 
Unsubscribe: send email to listar at linuxfromscratch.org
and put 'unsubscribe lfs-chat' in the subject header of the message



More information about the lfs-chat mailing list