[LLVMdev] [cfe-dev] RFC: Upcoming Build System Changes

David A. Greene greened at obbligato.org
Tue Nov 1 18:09:26 PDT 2011


Óscar Fuentes <ofv at wanadoo.es> writes:

> Let me guess: you are starting from a cold cache. Other than a
> difference caused by the OS, that's the only thing that could explain
> it.

Nope.  This is the best of several runs for both.

> The format used by your `time' is not familiar to me, so excuse me if I
> make a question related to your measures:

> LLVM: 4.32user 2.47system 0:03.21elapsed 211%CPU
> Cray: 2.88user 1.06system 0:04.94elapsed 79%CPU
>
> Looks like the Cray build is using less CPU but takes 1.7 seconds more
> than LLVM of wall clock time. But then you note that the LLVM build uses
> a lot more I/O. How can this be? It looks as if the LLVM build were much
> more parallel. Is this explained because the shell scripts you mention
> above introduce serialization points?

Good question.  I don't have enough detail to be sure.  I was just
looking at user time.  Wallclock time includes a whole bunch of
OS-related things, but it certainly is useful to look at.

> And the decisive question: is 3.2 seconds considered an annoying amount
> of time for you deciding to support a substantial change on the LLVM
> build, but 4.94 seconds is not annoying enough to get rid of those shell
> scripts? :-)

I'm more about maintainability but I have noted the long empty LLVM
build times to be annoying, yes.

                             -Dave




More information about the llvm-dev mailing list