[PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-11-18 Thread Andi Kleen
From: Andi Kleen The uncore PMU has a lot of duplicated PMUs for different subsystems. When expanding an uncore alias we usually end up with a large number of identically named aliases, which makes perf stat output difficult to read. Automatically sum them up in perf stat,

[PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-11-18 Thread Andi Kleen
From: Andi Kleen The uncore PMU has a lot of duplicated PMUs for different subsystems. When expanding an uncore alias we usually end up with a large number of identically named aliases, which makes perf stat output difficult to read. Automatically sum them up in perf stat, unless --no-merge is

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Andi Kleen
On Mon, Oct 17, 2016 at 07:28:36PM +0200, Jiri Olsa wrote: > On Mon, Oct 17, 2016 at 09:30:17AM -0700, Andi Kleen wrote: > > > this leads to my next question: why this merging should be default? > > > > It's the right default for uncore, and it doesn't do anything for > > non uncore because these

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Andi Kleen
On Mon, Oct 17, 2016 at 07:28:36PM +0200, Jiri Olsa wrote: > On Mon, Oct 17, 2016 at 09:30:17AM -0700, Andi Kleen wrote: > > > this leads to my next question: why this merging should be default? > > > > It's the right default for uncore, and it doesn't do anything for > > non uncore because these

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Mon, Oct 17, 2016 at 09:30:17AM -0700, Andi Kleen wrote: > > this leads to my next question: why this merging should be default? > > It's the right default for uncore, and it doesn't do anything for > non uncore because these usually don't have duplicated event aliases > over different PMUs.

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Mon, Oct 17, 2016 at 09:30:17AM -0700, Andi Kleen wrote: > > this leads to my next question: why this merging should be default? > > It's the right default for uncore, and it doesn't do anything for > non uncore because these usually don't have duplicated event aliases > over different PMUs.

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Andi Kleen
> this leads to my next question: why this merging should be default? It's the right default for uncore, and it doesn't do anything for non uncore because these usually don't have duplicated event aliases over different PMUs. -Andi

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Andi Kleen
> this leads to my next question: why this merging should be default? It's the right default for uncore, and it doesn't do anything for non uncore because these usually don't have duplicated event aliases over different PMUs. -Andi

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: SNIP > > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 688dea7cb08f..76304f27c090 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -140,6 +140,7 @@ static

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: SNIP > > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 688dea7cb08f..76304f27c090 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -140,6 +140,7 @@ static

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: SNIP > + OPT_BOOLEAN(0, "no-merge", _merge, "Do not merge identical named > events"), > OPT_STRING('x', "field-separator", _sep, "separator", > "print counts with custom separator"), > OPT_CALLBACK('G',

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: SNIP > + OPT_BOOLEAN(0, "no-merge", _merge, "Do not merge identical named > events"), > OPT_STRING('x', "field-separator", _sep, "separator", > "print counts with custom separator"), > OPT_CALLBACK('G',

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: > From: Andi Kleen > > The uncore PMU has a lot of duplicated PMUs for different subsystems. > When expanding an uncore alias we usually end up with a large > number of identically named aliases, which makes perf

Re: [PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-17 Thread Jiri Olsa
On Thu, Oct 13, 2016 at 02:15:29PM -0700, Andi Kleen wrote: > From: Andi Kleen > > The uncore PMU has a lot of duplicated PMUs for different subsystems. > When expanding an uncore alias we usually end up with a large > number of identically named aliases, which makes perf stat > output difficult

[PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-13 Thread Andi Kleen
From: Andi Kleen The uncore PMU has a lot of duplicated PMUs for different subsystems. When expanding an uncore alias we usually end up with a large number of identically named aliases, which makes perf stat output difficult to read. Automatically sum them up in perf stat,

[PATCH 07/10] perf, tools: Collapse identically named events in perf stat

2016-10-13 Thread Andi Kleen
From: Andi Kleen The uncore PMU has a lot of duplicated PMUs for different subsystems. When expanding an uncore alias we usually end up with a large number of identically named aliases, which makes perf stat output difficult to read. Automatically sum them up in perf stat, unless --no-merge is