[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1335541737.2463.135.camel@laptop>
Date: Fri, 27 Apr 2012 17:48:57 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Arnaldo Carvalho de Melo <acme@...radead.org>
Cc: Ingo Molnar <mingo@...nel.org>, linux-kernel@...r.kernel.org,
David Ahern <dsahern@...il.com>,
Frederic Weisbecker <fweisbec@...il.com>,
Hagen Paul Pfeifer <hagen@...u.net>,
Mike Galbraith <efault@....de>,
Namhyung Kim <namhyung@...il.com>,
Paul Mackerras <paulus@...ba.org>,
Stephane Eranian <eranian@...gle.com>,
Linus Torvalds <torvalds@...ux-foundation.org>
Subject: Re: [GIT PULL 0/4] perf/annotate loop detection V2, fixes
On Fri, 2012-04-27 at 12:31 -0300, Arnaldo Carvalho de Melo wrote:
> > So the forward conditional jumps get moved by one character to
> > the right and get prefixed with '.', which has the following
> > effects:
> >
> > - the flow of all the 'other', register modifying and loop
> > instructions can be seen more clearly
> >
> > - the 'exception' forward conditional jumps get moved into the
> > visual background, slightly.
> >
> > - blocks of instructions with no branches amongst them are more
> > clearly visible.
> >
> > If '.' is too aggressive or too confusing then some other
> > (possibly graphical) character could be used as well?
>
> Yeah, there are some unused graphical chars. But perhaps we should just
> use ↓ again?
>
> 0.00 │┌─→ c0: cmp %rax,%rbx
> 0.00 ││ mov %rax,%rcx
> 0.00 ││ ↓ ↓je 5dd
> 0.00 ││ cc: test %rcx,%rcx
> 0.00 ││ ↓ ↓je da
> 0.00 ││ mov 0x8(%rcx),%esi
> 0.00 ││ shr $0x4,%esi
> 0.00 ││ sub $0x2,%esi
> 0.00 ││ da: mov %rcx,0x10(%rbx)
> 0.00 ││ mov %rcx,%rax
> 0.00 ││ cmpl $0x0,%fs:0x18
> 0.00 ││ ↓ ↓je ed
> 0.00 ││ lock cmpxchg %rbx,(%rdx)
> 0.00 ││ cmp %rax,%rcx
> ││
> 0.00 │└──────↑ } jne c0
>
> Does it still stands out? I think so, we expect a letter there,
> something very different is there, matching the other down arrowsome
> columns to the left.
That just looks daft.. what's wrong with the single up/down arrow?
Also, can we keep all this on the list please?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists