[PATCH -tip] perf_counter tools: shorten names for events

[PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On AMD box:
$ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null

Before :

 Performance counter stats for 'ls -lR /usr/include/':

      248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
        1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
         153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
         423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
         302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
      251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
        5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
          93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
        6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
         609485  L2-Cache-Load-Misses  (scaled from 23.45%)
        6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
      248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
        5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
      257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
           6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
      109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
        5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)

    0.413702461  seconds time elapsed.

After :

 Performance counter stats for 'ls -lR /usr/include/':

      259250339  L1-d-load-refs        (scaled from 22.73%)
        1187200  L1-d-load-miss        (scaled from 23.01%)
         150454  L1-d-store-refs       (scaled from 23.01%)
         494252  L1-d-prefetch-refs    (scaled from 23.29%)
         362661  L1-d-prefetch-miss    (scaled from 23.73%)
      247343449  L1-i-load-refs        (scaled from 23.71%)
        4804990  L1-i-load-miss        (scaled from 23.85%)
         108711  L1-i-prefetch-refs    (scaled from 23.83%)
        6260313  L2-load-refs          (scaled from 23.82%)
         605425  L2-load-miss          (scaled from 23.82%)
        6898075  L2-store-refs         (scaled from 23.96%)
      248334160  d-TLB-load-refs       (scaled from 23.95%)
        3812835  d-TLB-load-miss       (scaled from 23.87%)
      253208496  i-TLB-load-refs       (scaled from 23.73%)
           5873  i-TLB-load-miss       (scaled from 23.46%)
      110891027  Branch-load-refs      (scaled from 23.21%)
        5529622  Branch-load-miss      (scaled from 23.02%)

    0.374790195  seconds time elapsed.

Reported-by : Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 tools/perf/util/parse-events.c |   20 ++++++++++----------
 1 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 06af2fa..5c4b532 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,23 +71,23 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
-	{ "L1-data",		"l1-d",		"l1d"			},
-	{ "L1-instruction",	"l1-i",		"l1i"			},
+	{ "L1-d",		"l1d"					},
+	{ "L1-i",		"l1i"					},
 	{ "L2",			"l2"					},
-	{ "Data-TLB",		"dtlb",		"d-tlb"			},
-	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
+	{ "d-TLB",		"dtlb",					},
+	{ "i-TLB",		"itlb",					},
 	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
 };
 
 static char *hw_cache_op[][MAX_ALIASES] = {
-	{ "Load",		"read"					},
-	{ "Store",		"write"					},
-	{ "Prefetch",		"speculative-read", "speculative-load"	},
+	{ "load",		"read"					},
+	{ "store",		"write"					},
+	{ "prefetch",		"speculative-read", "speculative-load"	},
 };
 
 static char *hw_cache_result[][MAX_ALIASES] = {
-	{ "Reference",		"ops",		"access"		},
-	{ "Miss"							},
+	{ "refs",		"ops",		"access"		},
+	{ "miss"							},
 };
 
 char *event_name(int counter)
@@ -123,7 +123,7 @@ char *event_name(int counter)
 		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
 			return "unknown-ext-hardware-cache-result";
 
-		sprintf(name, "%s-Cache-%s-%ses",
+		sprintf(name, "%s-%s-%s",
 			hw_cache[cache_type][0],
 			hw_cache_op[cache_op][0],
 			hw_cache_result[cache_result][0]);
-- 
1.6.0.6

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

Hello Ingo,

On Tue, 2009-06-23 at 17:58 +0530, Jaswinder Singh Rajput wrote:
> On AMD box:
> $ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null
> 
> Before :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
>         1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
>          153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
>          423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
>          302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
>       251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
>         5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
>           93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
>         6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
>          609485  L2-Cache-Load-Misses  (scaled from 23.45%)
>         6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
>       248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
>         5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
>       257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
>            6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
>       109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
>         5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)
> 
>     0.413702461  seconds time elapsed.
> 
> After :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       259250339  L1-d-load-refs        (scaled from 22.73%)
>         1187200  L1-d-load-miss        (scaled from 23.01%)
>          150454  L1-d-store-refs       (scaled from 23.01%)
>          494252  L1-d-prefetch-refs    (scaled from 23.29%)
>          362661  L1-d-prefetch-miss    (scaled from 23.73%)
>       247343449  L1-i-load-refs        (scaled from 23.71%)
>         4804990  L1-i-load-miss        (scaled from 23.85%)
>          108711  L1-i-prefetch-refs    (scaled from 23.83%)
>         6260313  L2-load-refs          (scaled from 23.82%)
>          605425  L2-load-miss          (scaled from 23.82%)
>         6898075  L2-store-refs         (scaled from 23.96%)
>       248334160  d-TLB-load-refs       (scaled from 23.95%)
>         3812835  d-TLB-load-miss       (scaled from 23.87%)
>       253208496  i-TLB-load-refs       (scaled from 23.73%)
>            5873  i-TLB-load-miss       (scaled from 23.46%)
>       110891027  Branch-load-refs      (scaled from 23.21%)
>         5529622  Branch-load-miss      (scaled from 23.02%)
> 
>     0.374790195  seconds time elapsed.
> 
> Reported-by : Ingo Molnar <mingo@elte.hu>
> Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
> ---

Is this looks OK to you.

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> After :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       259250339  L1-d-load-refs        (scaled from 22.73%)
>         1187200  L1-d-load-miss        (scaled from 23.01%)
>          150454  L1-d-store-refs       (scaled from 23.01%)
>          494252  L1-d-prefetch-refs    (scaled from 23.29%)
>          362661  L1-d-prefetch-miss    (scaled from 23.73%)
>       247343449  L1-i-load-refs        (scaled from 23.71%)
>         4804990  L1-i-load-miss        (scaled from 23.85%)
>          108711  L1-i-prefetch-refs    (scaled from 23.83%)
>         6260313  L2-load-refs          (scaled from 23.82%)
>          605425  L2-load-miss          (scaled from 23.82%)
>         6898075  L2-store-refs         (scaled from 23.96%)
>       248334160  d-TLB-load-refs       (scaled from 23.95%)
>         3812835  d-TLB-load-miss       (scaled from 23.87%)
>       253208496  i-TLB-load-refs       (scaled from 23.73%)
>            5873  i-TLB-load-miss       (scaled from 23.46%)
>       110891027  Branch-load-refs      (scaled from 23.21%)
>         5529622  Branch-load-miss      (scaled from 23.02%)

here's an edited version of my suggestions:

>       259250339  dL1-loads              (scaled from 22.73%)
>         1187200  dL1-load-misses        (scaled from 23.01%)
>          150454  dL1-stores             (scaled from 23.01%)
>          494252  dL1-prefetches         (scaled from 23.29%)
>          362661  dL1-prefetch-misses    (scaled from 23.73%)
>       247343449  iL1-loads              (scaled from 23.71%)
>         4804990  iL1-load-misses        (scaled from 23.85%)
>          108711  iL1-prefetches         (scaled from 23.83%)
>         6260313  LLC-loads              (scaled from 23.82%)
>          605425  LLC-load-misses        (scaled from 23.82%)
>         6898075  LLC-stores             (scaled from 23.96%)
>       248334160  dTLB-loads             (scaled from 23.95%)
>         3812835  dTLB-load-misses       (scaled from 23.87%)
>       253208496  iTLB-loads             (scaled from 23.73%)
>            5873  iTLB-load-misses       (scaled from 23.46%)
>       110891027  branches               (scaled from 23.21%)
>         5529622  branch-misses          (scaled from 23.02%)

We can leave out 'refs' i think - without any qualification 
statements like '247343449 iL1-loads' are still unambigious i think.

Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
matters. Also, note that it's LLC (Last Level Cache), not L2.

( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
  have a L3 too. )

Note, branches are special - we dont really have 'branch loads', 
branches are executions. 'Branches' and 'Branch-misses' are the 
right term.

Do you agree?

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> 
> > After :
> > 
> >  Performance counter stats for 'ls -lR /usr/include/':
> > 
> >       259250339  L1-d-load-refs        (scaled from 22.73%)
> >         1187200  L1-d-load-miss        (scaled from 23.01%)
> >          150454  L1-d-store-refs       (scaled from 23.01%)
> >          494252  L1-d-prefetch-refs    (scaled from 23.29%)
> >          362661  L1-d-prefetch-miss    (scaled from 23.73%)
> >       247343449  L1-i-load-refs        (scaled from 23.71%)
> >         4804990  L1-i-load-miss        (scaled from 23.85%)
> >          108711  L1-i-prefetch-refs    (scaled from 23.83%)
> >         6260313  L2-load-refs          (scaled from 23.82%)
> >          605425  L2-load-miss          (scaled from 23.82%)
> >         6898075  L2-store-refs         (scaled from 23.96%)
> >       248334160  d-TLB-load-refs       (scaled from 23.95%)
> >         3812835  d-TLB-load-miss       (scaled from 23.87%)
> >       253208496  i-TLB-load-refs       (scaled from 23.73%)
> >            5873  i-TLB-load-miss       (scaled from 23.46%)
> >       110891027  Branch-load-refs      (scaled from 23.21%)
> >         5529622  Branch-load-miss      (scaled from 23.02%)
> 
> here's an edited version of my suggestions:
> 
> >       259250339  dL1-loads              (scaled from 22.73%)
> >         1187200  dL1-load-misses        (scaled from 23.01%)
> >          150454  dL1-stores             (scaled from 23.01%)
> >          494252  dL1-prefetches         (scaled from 23.29%)
> >          362661  dL1-prefetch-misses    (scaled from 23.73%)
> >       247343449  iL1-loads              (scaled from 23.71%)
> >         4804990  iL1-load-misses        (scaled from 23.85%)
> >          108711  iL1-prefetches         (scaled from 23.83%)
> >         6260313  LLC-loads              (scaled from 23.82%)
> >          605425  LLC-load-misses        (scaled from 23.82%)
> >         6898075  LLC-stores             (scaled from 23.96%)
> >       248334160  dTLB-loads             (scaled from 23.95%)
> >         3812835  dTLB-load-misses       (scaled from 23.87%)
> >       253208496  iTLB-loads             (scaled from 23.73%)
> >            5873  iTLB-load-misses       (scaled from 23.46%)
> >       110891027  branches               (scaled from 23.21%)
> >         5529622  branch-misses          (scaled from 23.02%)
> 
> We can leave out 'refs' i think - without any qualification 
> statements like '247343449 iL1-loads' are still unambigious i think.
> 

Looks good.

> Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
> matters. Also, note that it's LLC (Last Level Cache), not L2.
> 
> ( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
>   have a L3 too. )
> 

Ok, I will fix it and also set the alias.

> Note, branches are special - we dont really have 'branch loads', 
> branches are executions. 'Branches' and 'Branch-misses' are the 
> right term.
> 
> Do you agree?
> 

Event we used for (BPU, READ, ACCESS) is 'branch instructions retired'

So 'branch loads' we mean 'branch instruction loaded and retired'

I like all of them : 'branch loads', 'branch retired' or 'branches'

Please let me know, which one is best option so that I can prepare the
patch.

Thanks,
--
JSR 

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Wed, 2009-06-24 at 03:42 +0530, Jaswinder Singh Rajput wrote:

> > Note, branches are special - we dont really have 'branch loads', 
> > branches are executions. 'Branches' and 'Branch-misses' are the 
> > right term.
> > 
> > Do you agree?
> > 
> 
> Event we used for (BPU, READ, ACCESS) is 'branch instructions retired'
> 
> So 'branch loads' we mean 'branch instruction loaded and retired'
> 
> I like all of them : 'branch loads', 'branch retired' or 'branches'
> 
> Please let me know, which one is best option so that I can prepare the
> patch.
> 

Or if branches is special and following values are always invalid :

 (BPU, WRITE, ACCESS)
 (BPU, WRITE, MISS)
 (BPU, PREFETCH, ACCESS)
 (BPU, PREFTECH, MISS)

then can we move BPU to some other category from Hardware cache
counters.

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> > 
> > > After :
> > > 
> > >  Performance counter stats for 'ls -lR /usr/include/':
> > > 
> > >       259250339  L1-d-load-refs        (scaled from 22.73%)
> > >         1187200  L1-d-load-miss        (scaled from 23.01%)
> > >          150454  L1-d-store-refs       (scaled from 23.01%)
> > >          494252  L1-d-prefetch-refs    (scaled from 23.29%)
> > >          362661  L1-d-prefetch-miss    (scaled from 23.73%)
> > >       247343449  L1-i-load-refs        (scaled from 23.71%)
> > >         4804990  L1-i-load-miss        (scaled from 23.85%)
> > >          108711  L1-i-prefetch-refs    (scaled from 23.83%)
> > >         6260313  L2-load-refs          (scaled from 23.82%)
> > >          605425  L2-load-miss          (scaled from 23.82%)
> > >         6898075  L2-store-refs         (scaled from 23.96%)
> > >       248334160  d-TLB-load-refs       (scaled from 23.95%)
> > >         3812835  d-TLB-load-miss       (scaled from 23.87%)
> > >       253208496  i-TLB-load-refs       (scaled from 23.73%)
> > >            5873  i-TLB-load-miss       (scaled from 23.46%)
> > >       110891027  Branch-load-refs      (scaled from 23.21%)
> > >         5529622  Branch-load-miss      (scaled from 23.02%)
> > 
> > here's an edited version of my suggestions:
> > 
> > >       259250339  dL1-loads              (scaled from 22.73%)
> > >         1187200  dL1-load-misses        (scaled from 23.01%)
> > >          150454  dL1-stores             (scaled from 23.01%)
> > >          494252  dL1-prefetches         (scaled from 23.29%)
> > >          362661  dL1-prefetch-misses    (scaled from 23.73%)
> > >       247343449  iL1-loads              (scaled from 23.71%)
> > >         4804990  iL1-load-misses        (scaled from 23.85%)
> > >          108711  iL1-prefetches         (scaled from 23.83%)
> > >         6260313  LLC-loads              (scaled from 23.82%)
> > >          605425  LLC-load-misses        (scaled from 23.82%)
> > >         6898075  LLC-stores             (scaled from 23.96%)
> > >       248334160  dTLB-loads             (scaled from 23.95%)
> > >         3812835  dTLB-load-misses       (scaled from 23.87%)
> > >       253208496  iTLB-loads             (scaled from 23.73%)
> > >            5873  iTLB-load-misses       (scaled from 23.46%)
> > >       110891027  branches               (scaled from 23.21%)
> > >         5529622  branch-misses          (scaled from 23.02%)
> > 
> > We can leave out 'refs' i think - without any qualification 
> > statements like '247343449 iL1-loads' are still unambigious i think.
> > 
> 
> Looks good.
> 
> > Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
> > matters. Also, note that it's LLC (Last Level Cache), not L2.
> > 
> > ( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
> >   have a L3 too. )
> > 
> 
> Ok, I will fix it and also set the alias.
> 
> > Note, branches are special - we dont really have 'branch loads', 
> > branches are executions. 'Branches' and 'Branch-misses' are the 
> > right term.
> > 
> > Do you agree?
> > 
> 
> Event we used for (BPU, READ, ACCESS) is 'branch instructions 
> retired'
> 
> So 'branch loads' we mean 'branch instruction loaded and retired'
> 
> I like all of them : 'branch loads', 'branch retired' or 
> 'branches'

There's two things:

Firstly, there are "loads" are when data is loaded into the CPU. It 
has a very firm meaning.

Secondly, the "loading an instruction into the CPU" idiom you 
mention is not really correct - what we generally say is to "fetch 
an instruction".

In that sense using 'branch loads' is confusing, and that's why i 
corrected it. 'branches' is perfectly fine shortcut for 'branch 
instructions executed'. (or branch instructions fetched and retired)

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Wed, 2009-06-24 at 10:40 +0200, Ingo Molnar wrote:
> * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> 
> > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > > * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> > > 
> > > here's an edited version of my suggestions:
> > > 
> > > >       259250339  dL1-loads              (scaled from 22.73%)
> > > >         1187200  dL1-load-misses        (scaled from 23.01%)
> > > >          150454  dL1-stores             (scaled from 23.01%)
> > > >          494252  dL1-prefetches         (scaled from 23.29%)
> > > >          362661  dL1-prefetch-misses    (scaled from 23.73%)
> > > >       247343449  iL1-loads              (scaled from 23.71%)
> > > >         4804990  iL1-load-misses        (scaled from 23.85%)
> > > >          108711  iL1-prefetches         (scaled from 23.83%)
> > > >         6260313  LLC-loads              (scaled from 23.82%)
> > > >          605425  LLC-load-misses        (scaled from 23.82%)
> > > >         6898075  LLC-stores             (scaled from 23.96%)
> > > >       248334160  dTLB-loads             (scaled from 23.95%)
> > > >         3812835  dTLB-load-misses       (scaled from 23.87%)
> > > >       253208496  iTLB-loads             (scaled from 23.73%)
> > > >            5873  iTLB-load-misses       (scaled from 23.46%)
> > > >       110891027  branches               (scaled from 23.21%)
> > > >         5529622  branch-misses          (scaled from 23.02%)
> > > 
> > > We can leave out 'refs' i think - without any qualification 
> > > statements like '247343449 iL1-loads' are still unambigious i think.
> > > 
> > 
> > Looks good.
> > 
> > > Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
> > > matters. Also, note that it's LLC (Last Level Cache), not L2.
> > > 
> > > ( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
> > >   have a L3 too. )
> > > 
> > 
> > Ok, I will fix it and also set the alias.
> > 
> > > Note, branches are special - we dont really have 'branch loads', 
> > > branches are executions. 'Branches' and 'Branch-misses' are the 
> > > right term.
> > > 
> > > Do you agree?
> > > 
> > 
> > Event we used for (BPU, READ, ACCESS) is 'branch instructions 
> > retired'
> > 
> > So 'branch loads' we mean 'branch instruction loaded and retired'
> > 
> > I like all of them : 'branch loads', 'branch retired' or 
> > 'branches'
> 
> There's two things:
> 
> Firstly, there are "loads" are when data is loaded into the CPU. It 
> has a very firm meaning.
> 
> Secondly, the "loading an instruction into the CPU" idiom you 
> mention is not really correct - what we generally say is to "fetch 
> an instruction".
> 
> In that sense using 'branch loads' is confusing, and that's why i 
> corrected it. 'branches' is perfectly fine shortcut for 'branch 
> instructions executed'. (or branch instructions fetched and retired)
> 


OK, We will show :
'branch loads'           -> 'branches'
'branch load-misses'     -> 'branch-misses'

now issue is how we can show :

'branch stores'          ->  ?
'branch store-misses'    ->  ?

'branch prefetches'      ->  ?
'branch prefetch-misses' ->  ?

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> On Wed, 2009-06-24 at 10:40 +0200, Ingo Molnar wrote:
> > * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> > 
> > > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > > > * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> > > > 
> > > > here's an edited version of my suggestions:
> > > > 
> > > > >       259250339  dL1-loads              (scaled from 22.73%)
> > > > >         1187200  dL1-load-misses        (scaled from 23.01%)
> > > > >          150454  dL1-stores             (scaled from 23.01%)
> > > > >          494252  dL1-prefetches         (scaled from 23.29%)
> > > > >          362661  dL1-prefetch-misses    (scaled from 23.73%)
> > > > >       247343449  iL1-loads              (scaled from 23.71%)
> > > > >         4804990  iL1-load-misses        (scaled from 23.85%)
> > > > >          108711  iL1-prefetches         (scaled from 23.83%)
> > > > >         6260313  LLC-loads              (scaled from 23.82%)
> > > > >          605425  LLC-load-misses        (scaled from 23.82%)
> > > > >         6898075  LLC-stores             (scaled from 23.96%)
> > > > >       248334160  dTLB-loads             (scaled from 23.95%)
> > > > >         3812835  dTLB-load-misses       (scaled from 23.87%)
> > > > >       253208496  iTLB-loads             (scaled from 23.73%)
> > > > >            5873  iTLB-load-misses       (scaled from 23.46%)
> > > > >       110891027  branches               (scaled from 23.21%)
> > > > >         5529622  branch-misses          (scaled from 23.02%)
> > > > 
> > > > We can leave out 'refs' i think - without any qualification 
> > > > statements like '247343449 iL1-loads' are still unambigious i think.
> > > > 
> > > 
> > > Looks good.
> > > 
> > > > Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
> > > > matters. Also, note that it's LLC (Last Level Cache), not L2.
> > > > 
> > > > ( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
> > > >   have a L3 too. )
> > > > 
> > > 
> > > Ok, I will fix it and also set the alias.
> > > 
> > > > Note, branches are special - we dont really have 'branch loads', 
> > > > branches are executions. 'Branches' and 'Branch-misses' are the 
> > > > right term.
> > > > 
> > > > Do you agree?
> > > > 
> > > 
> > > Event we used for (BPU, READ, ACCESS) is 'branch instructions 
> > > retired'
> > > 
> > > So 'branch loads' we mean 'branch instruction loaded and retired'
> > > 
> > > I like all of them : 'branch loads', 'branch retired' or 
> > > 'branches'
> > 
> > There's two things:
> > 
> > Firstly, there are "loads" are when data is loaded into the CPU. It 
> > has a very firm meaning.
> > 
> > Secondly, the "loading an instruction into the CPU" idiom you 
> > mention is not really correct - what we generally say is to "fetch 
> > an instruction".
> > 
> > In that sense using 'branch loads' is confusing, and that's why i 
> > corrected it. 'branches' is perfectly fine shortcut for 'branch 
> > instructions executed'. (or branch instructions fetched and retired)
> > 
> 
> 
> OK, We will show :
> 'branch loads'           -> 'branches'
> 'branch load-misses'     -> 'branch-misses'
> 
> now issue is how we can show :
> 
> 'branch stores'          ->  ?
> 'branch store-misses'    ->  ?
> 
> 'branch prefetches'      ->  ?
> 'branch prefetch-misses' ->  ?

there's no such thing as a 'branch store'. Instructions are not 
stored. We shouldnt display those.

They are prefetched sometimes speculatively ... not sure there are 
events for them ... are there?

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Wed, 2009-06-24 at 20:07 +0200, Ingo Molnar wrote:
> * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> 
> > 
> > OK, We will show :
> > 'branch loads'           -> 'branches'
> > 'branch load-misses'     -> 'branch-misses'
> > 
> > now issue is how we can show :
> > 
> > 'branch stores'          ->  ?
> > 'branch store-misses'    ->  ?
> > 
> > 'branch prefetches'      ->  ?
> > 'branch prefetch-misses' ->  ?
> 
> there's no such thing as a 'branch store'. Instructions are not 
> stored. We shouldnt display those.
> 
> They are prefetched sometimes speculatively ... not sure there are 
> events for them ... are there?
> 

yes, you are right there is no such events.

But I need to test and display all.

If I need to to need to handle branch as special case, then better to
make separate array for branches and remove from hw_cache array.

Is it OK.

Thanks,

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> * Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:
> 

> here's an edited version of my suggestions:
> 
> >       259250339  dL1-loads              (scaled from 22.73%)
> >         1187200  dL1-load-misses        (scaled from 23.01%)
> >          150454  dL1-stores             (scaled from 23.01%)
> >          494252  dL1-prefetches         (scaled from 23.29%)
> >          362661  dL1-prefetch-misses    (scaled from 23.73%)
> >       247343449  iL1-loads              (scaled from 23.71%)
> >         4804990  iL1-load-misses        (scaled from 23.85%)
> >          108711  iL1-prefetches         (scaled from 23.83%)
> >         6260313  LLC-loads              (scaled from 23.82%)
> >          605425  LLC-load-misses        (scaled from 23.82%)
> >         6898075  LLC-stores             (scaled from 23.96%)
> >       248334160  dTLB-loads             (scaled from 23.95%)
> >         3812835  dTLB-load-misses       (scaled from 23.87%)
> >       253208496  iTLB-loads             (scaled from 23.73%)
> >            5873  iTLB-load-misses       (scaled from 23.46%)
> >       110891027  branches               (scaled from 23.21%)
> >         5529622  branch-misses          (scaled from 23.02%)
> 
> We can leave out 'refs' i think - without any qualification 
> statements like '247343449 iL1-loads' are still unambigious i think.
> 
> Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
> matters. Also, note that it's LLC (Last Level Cache), not L2.
> 
> ( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
>   have a L3 too. )
> 
> Note, branches are special - we dont really have 'branch loads', 
> branches are executions. 'Branches' and 'Branch-misses' are the 
> right term.
> 

[PATCH] perf_counter tools: shorten names for events

Special handling for branches as branches are special
we don't really have 'branch loads', branches are executions.
'Branches' and 'Branch-misses' are the right term.

On AMD box:
$ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null

Before :

 Performance counter stats for 'ls -lR /usr/include/':

      248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
        1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
         153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
         423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
         302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
      251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
        5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
          93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
        6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
         609485  L2-Cache-Load-Misses  (scaled from 23.45%)
        6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
      248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
        5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
      257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
           6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
      109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
        5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)

    0.413702461  seconds time elapsed.

After :

 Performance counter stats for 'ls -lR /usr/include/':

      283542921  dL1-loads             (scaled from 23.28%)
        1848314  dL1-load-misses       (scaled from 22.94%)
         168963  dL1-stores            (scaled from 22.94%)
         739249  dL1-prefetches        (scaled from 22.45%)
         501021  dL1-prefetch-misses   (scaled from 22.25%)
      275037259  iL1-loads             (scaled from 23.40%)
        6030825  iL1-load-misses       (scaled from 23.26%)
         166760  iL1-prefetches        (scaled from 24.31%)
        7224781  LLC-loads             (scaled from 24.76%)
         821097  LLC-load-misses       (scaled from 24.07%)
        7070549  LLC-stores            (scaled from 24.45%)
      251586242  dTLB-loads            (scaled from 24.65%)
        5127780  dTLB-load-misses      (scaled from 23.99%)
      276782014  iTLB-loads            (scaled from 23.77%)
          16787  iTLB-load-misses      (scaled from 23.72%)
      123408502  branches              (scaled from 22.88%)
        5843856  branch-misses         (scaled from 22.87%)

    1.417039891  seconds time elapsed.

Reported-by : Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 tools/perf/util/parse-events.c |   45 ++++++++++++++++++++++++++-------------
 1 files changed, 30 insertions(+), 15 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 06af2fa..fa6e2e5 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,23 +71,23 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
-	{ "L1-data",		"l1-d",		"l1d"			},
-	{ "L1-instruction",	"l1-i",		"l1i"			},
-	{ "L2",			"l2"					},
-	{ "Data-TLB",		"dtlb",		"d-tlb"			},
-	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
-	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
+ { "dL1",	"L1-d",		"l1d",					},
+ { "iL1",	"L1-i",		"l1i",					},
+ { "LLC",	"L2",							},
+ { "dTLB",	"d-tlb",						},
+ { "iTLB",	"i-tlb",						},
+ { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
 };
 
 static char *hw_cache_op[][MAX_ALIASES] = {
-	{ "Load",		"read"					},
-	{ "Store",		"write"					},
-	{ "Prefetch",		"speculative-read", "speculative-load"	},
+ { "load",	"loads",	"read",					},
+ { "store",	"stores",	"write",				},
+ { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
 };
 
 static char *hw_cache_result[][MAX_ALIASES] = {
-	{ "Reference",		"ops",		"access"		},
-	{ "Miss"							},
+ { "refs",	"ops",		"access",				},
+ { "misses",	"miss",							},
 };
 
 char *event_name(int counter)
@@ -123,10 +123,25 @@ char *event_name(int counter)
 		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
 			return "unknown-ext-hardware-cache-result";
 
-		sprintf(name, "%s-Cache-%s-%ses",
-			hw_cache[cache_type][0],
-			hw_cache_op[cache_op][0],
-			hw_cache_result[cache_result][0]);
+		/*
+		 * special handling for branches
+		 * we are only interested in BPU, READ
+		 */ 
+		if (cache_type == PERF_COUNT_HW_CACHE_BPU && cache_op)
+			return "unknown";
+		else if (cache_type == PERF_COUNT_HW_CACHE_BPU) {
+			if (cache_result)
+				sprintf(name, "%s-%s", hw_cache[cache_type][0],
+					hw_cache_result[cache_result][0]);
+			else
+				sprintf(name, "%s", hw_cache[cache_type][1]);
+		} else if (cache_result)
+			sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
+				hw_cache_op[cache_op][0],
+				hw_cache_result[cache_result][0]);
+		else
+			sprintf(name, "%s-%s", hw_cache[cache_type][0],
+				hw_cache_op[cache_op][1]);
 
 		return name;
 	}
-- 
1.6.0.6

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Thomas Gleixner]

On Thu, 25 Jun 2009, Jaswinder Singh Rajput wrote:
> On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> 
>       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
>       283542921  dL1-loads             (scaled from 23.28%)

Where is the point of this? dL1-loads is a completely non intuitive
artificial abbreviation.
 
Changing "L1-data-Cache-Load-Referencees" to "L1-dcache-loads" or
something similar provides a short but sufficiently self explaining
explanation of the counter.

I don't want to use a abbreviations dictionary to decode a perf
report.

Thanks,

	tglx

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Wed, 2009-06-24 at 23:00 +0200, Thomas Gleixner wrote:
> On Thu, 25 Jun 2009, Jaswinder Singh Rajput wrote:
> > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > 
> >       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
> >       283542921  dL1-loads             (scaled from 23.28%)
> 
> Where is the point of this? dL1-loads is a completely non intuitive
> artificial abbreviation.
>  
> Changing "L1-data-Cache-Load-Referencees" to "L1-dcache-loads" or
> something similar provides a short but sufficiently self explaining
> explanation of the counter.
> 
> I don't want to use a abbreviations dictionary to decode a perf
> report.

Of course we need to shorten the event names, currently they are too
long and need at least 45 characters only for names, how can we show
another useful info on the screen.

Please suggest some better short names for :

  L1-data-Cache-Load-Reference                  [Hardware cache event]
  L1-data-Cache-Load-Miss                       [Hardware cache event]
  L1-data-Cache-Store-Reference                 [Hardware cache event]
  L1-data-Cache-Store-Miss                      [Hardware cache event]
  L1-data-Cache-Prefetch-Reference              [Hardware cache event]
  L1-data-Cache-Prefetch-Miss                   [Hardware cache event]
  L1-instruction-Cache-Load-Reference           [Hardware cache event]
  L1-instruction-Cache-Load-Miss                [Hardware cache event]
  L1-instruction-Cache-Store-Reference          [Hardware cache event]
  L1-instruction-Cache-Store-Miss               [Hardware cache event]
  L1-instruction-Cache-Prefetch-Reference       [Hardware cache event]
  L1-instruction-Cache-Prefetch-Miss            [Hardware cache event]
  L2-Cache-Load-Reference                       [Hardware cache event]
  L2-Cache-Load-Miss                            [Hardware cache event]
  L2-Cache-Store-Reference                      [Hardware cache event]
  L2-Cache-Store-Miss                           [Hardware cache event]
  L2-Cache-Prefetch-Reference                   [Hardware cache event]
  L2-Cache-Prefetch-Miss                        [Hardware cache event]
  Data-TLB-Cache-Load-Reference                 [Hardware cache event]
  Data-TLB-Cache-Load-Miss                      [Hardware cache event]
  Data-TLB-Cache-Store-Reference                [Hardware cache event]
  Data-TLB-Cache-Store-Miss                     [Hardware cache event]
  Data-TLB-Cache-Prefetch-Reference             [Hardware cache event]
  Data-TLB-Cache-Prefetch-Miss                  [Hardware cache event]
  Instruction-TLB-Cache-Load-Reference          [Hardware cache event]
  Instruction-TLB-Cache-Load-Miss               [Hardware cache event]
  Instruction-TLB-Cache-Store-Reference         [Hardware cache event]
  Instruction-TLB-Cache-Store-Miss              [Hardware cache event]
  Instruction-TLB-Cache-Prefetch-Reference      [Hardware cache event]
  Instruction-TLB-Cache-Prefetch-Miss           [Hardware cache event]
  Branch-Cache-Load-Reference                   [Hardware cache event]
  Branch-Cache-Load-Miss                        [Hardware cache event]
  Branch-Cache-Store-Reference                  [Hardware cache event]
  Branch-Cache-Store-Miss                       [Hardware cache event]
  Branch-Cache-Prefetch-Reference               [Hardware cache event]
  Branch-Cache-Prefetch-Miss                    [Hardware cache event]

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Roland Dreier]

 >   L1-data-Cache-Load-Reference                  [Hardware cache event]
 >   L1-instruction-Cache-Load-Reference           [Hardware cache event]

obvious place to start is to change "data-Cache" and "instruction-Cache"
to "dcache" and "icache" which are still easy to figure out without
needing to look anything up.  And "Reference" can become "ref" with
minimal loss of clarity too.  So we could get down to

    L1-icache-load
    L1-icache-load-miss
    L1-icache-store-miss
    L1-icache-prefetch
    L1-icache-prefetch-miss

and so on.

 >   Data-TLB-Cache-Load-Reference                 [Hardware cache event]

Could become

    dTLB-load
    dTLB-load-miss
    iTLB-load

etc.

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Roland Dreier <rdreier@cisco.com> wrote:

>  >   Data-TLB-Cache-Load-Reference                 [Hardware cache event]
> 
> Could become
> 
>     dTLB-load
>     dTLB-load-miss
>     iTLB-load

I already went through this and suggested shorter names, that was 
the motivation of this patch.

The new names i suggested two days ago can be found below.

	Ingo

----- Forwarded message from Ingo Molnar <mingo@elte.hu> -----

Date: Tue, 23 Jun 2009 21:56:56 +0200
From: Ingo Molnar <mingo@elte.hu>
To: Jaswinder Singh Rajput <jaswinder@kernel.org>
Subject: Re: [PATCH -tip] perf_counter tools: shorten names for events
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Peter Zijlstra <peterz@infradead.org>,
	LKML <linux-kernel@vger.kernel.org>


* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> After :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       259250339  L1-d-load-refs        (scaled from 22.73%)
>         1187200  L1-d-load-miss        (scaled from 23.01%)
>          150454  L1-d-store-refs       (scaled from 23.01%)
>          494252  L1-d-prefetch-refs    (scaled from 23.29%)
>          362661  L1-d-prefetch-miss    (scaled from 23.73%)
>       247343449  L1-i-load-refs        (scaled from 23.71%)
>         4804990  L1-i-load-miss        (scaled from 23.85%)
>          108711  L1-i-prefetch-refs    (scaled from 23.83%)
>         6260313  L2-load-refs          (scaled from 23.82%)
>          605425  L2-load-miss          (scaled from 23.82%)
>         6898075  L2-store-refs         (scaled from 23.96%)
>       248334160  d-TLB-load-refs       (scaled from 23.95%)
>         3812835  d-TLB-load-miss       (scaled from 23.87%)
>       253208496  i-TLB-load-refs       (scaled from 23.73%)
>            5873  i-TLB-load-miss       (scaled from 23.46%)
>       110891027  Branch-load-refs      (scaled from 23.21%)
>         5529622  Branch-load-miss      (scaled from 23.02%)

here's an edited version of my suggestions:

>       259250339  dL1-loads              (scaled from 22.73%)
>         1187200  dL1-load-misses        (scaled from 23.01%)
>          150454  dL1-stores             (scaled from 23.01%)
>          494252  dL1-prefetches         (scaled from 23.29%)
>          362661  dL1-prefetch-misses    (scaled from 23.73%)
>       247343449  iL1-loads              (scaled from 23.71%)
>         4804990  iL1-load-misses        (scaled from 23.85%)
>          108711  iL1-prefetches         (scaled from 23.83%)
>         6260313  LLC-loads              (scaled from 23.82%)
>          605425  LLC-load-misses        (scaled from 23.82%)
>         6898075  LLC-stores             (scaled from 23.96%)
>       248334160  dTLB-loads             (scaled from 23.95%)
>         3812835  dTLB-load-misses       (scaled from 23.87%)
>       253208496  iTLB-loads             (scaled from 23.73%)
>            5873  iTLB-load-misses       (scaled from 23.46%)
>       110891027  branches               (scaled from 23.21%)
>         5529622  branch-misses          (scaled from 23.02%)

We can leave out 'refs' i think - without any qualification 
statements like '247343449 iL1-loads' are still unambigious i think.

Plus we can abbreviate dL1/iL1/dTLB/iTLB. The capitalization 
matters. Also, note that it's LLC (Last Level Cache), not L2.

( Sidenote: L2 can still be an alias for LLC, even though some CPUs 
  have a L3 too. )

Note, branches are special - we dont really have 'branch loads', 
branches are executions. 'Branches' and 'Branch-misses' are the 
right term.

Do you agree?

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Thomas Gleixner <tglx@linutronix.de> wrote:

> On Thu, 25 Jun 2009, Jaswinder Singh Rajput wrote:
> > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > 
> >       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
> >       283542921  dL1-loads             (scaled from 23.28%)
> 
> Where is the point of this? dL1-loads is a completely non 
> intuitive artificial abbreviation.

blame me :)

I found L1-data-Cache-Load-References way too long and i asked for 
suggestions and came up with my list of abbreviations.

I found 'dL1' intuitive because we use 'dTLB' and 'iTLB' as well.

How about L1-data-loads ?

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> After :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       283542921  dL1-loads             (scaled from 23.28%)
>         1848314  dL1-load-misses       (scaled from 22.94%)
>          168963  dL1-stores            (scaled from 22.94%)
>          739249  dL1-prefetches        (scaled from 22.45%)
>          501021  dL1-prefetch-misses   (scaled from 22.25%)
>       275037259  iL1-loads             (scaled from 23.40%)
>         6030825  iL1-load-misses       (scaled from 23.26%)
>          166760  iL1-prefetches        (scaled from 24.31%)
>         7224781  LLC-loads             (scaled from 24.76%)
>          821097  LLC-load-misses       (scaled from 24.07%)
>         7070549  LLC-stores            (scaled from 24.45%)
>       251586242  dTLB-loads            (scaled from 24.65%)
>         5127780  dTLB-load-misses      (scaled from 23.99%)
>       276782014  iTLB-loads            (scaled from 23.77%)
>           16787  iTLB-load-misses      (scaled from 23.72%)
>       123408502  branches              (scaled from 22.88%)
>         5843856  branch-misses         (scaled from 22.87%)
> 
>     1.417039891  seconds time elapsed.

ok, this output looks pretty good and intuitive to me (please 
integrate suggestions from Thomas), but the patch itself needs 
another iteration i think:

>  static char *hw_cache[][MAX_ALIASES] = {
> -	{ "L1-data",		"l1-d",		"l1d"			},
> -	{ "L1-instruction",	"l1-i",		"l1i"			},
> -	{ "L2",			"l2"					},
> -	{ "Data-TLB",		"dtlb",		"d-tlb"			},
> -	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
> -	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
> + { "dL1",	"L1-d",		"l1d",					},
> + { "iL1",	"L1-i",		"l1i",					},
> + { "LLC",	"L2",							},
> + { "dTLB",	"d-tlb",						},
> + { "iTLB",	"i-tlb",						},
> + { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
>  };
>  
>  static char *hw_cache_op[][MAX_ALIASES] = {
> -	{ "Load",		"read"					},
> -	{ "Store",		"write"					},
> -	{ "Prefetch",		"speculative-read", "speculative-load"	},
> + { "load",	"loads",	"read",					},
> + { "store",	"stores",	"write",				},
> + { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
>  };
>  
>  static char *hw_cache_result[][MAX_ALIASES] = {
> -	{ "Reference",		"ops",		"access"		},
> -	{ "Miss"							},
> + { "refs",	"ops",		"access",				},
> + { "misses",	"miss",							},
>  };
>  
>  char *event_name(int counter)
> @@ -123,10 +123,25 @@ char *event_name(int counter)
>  		if (cache_result > PERF_COUNT_HW_CACHE_RESULT_MAX)
>  			return "unknown-ext-hardware-cache-result";
>  
> -		sprintf(name, "%s-Cache-%s-%ses",
> -			hw_cache[cache_type][0],
> -			hw_cache_op[cache_op][0],
> -			hw_cache_result[cache_result][0]);
> +		/*
> +		 * special handling for branches
> +		 * we are only interested in BPU, READ
> +		 */ 
> +		if (cache_type == PERF_COUNT_HW_CACHE_BPU && cache_op)
> +			return "unknown";
> +		else if (cache_type == PERF_COUNT_HW_CACHE_BPU) {
> +			if (cache_result)
> +				sprintf(name, "%s-%s", hw_cache[cache_type][0],
> +					hw_cache_result[cache_result][0]);
> +			else
> +				sprintf(name, "%s", hw_cache[cache_type][1]);
> +		} else if (cache_result)
> +			sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
> +				hw_cache_op[cache_op][0],
> +				hw_cache_result[cache_result][0]);
> +		else
> +			sprintf(name, "%s-%s", hw_cache[cache_type][0],
> +				hw_cache_op[cache_op][1]);
>  
>  		return name;

Firstly, please run your patches through checkpatch - it will report 
a real problem in your patch.

Secondly, this special-casing of the BPU isnt very clean in this 
form. The BPU isnt 'special' because it deals with instructions - 
it's special because it's for all practical purposes read-only.

So we should extend our table with a read-only flag, and the BPU and 
the iTLB should be listed as read-only. (iTLB-store-miss is another 
thing that makes no sense) For those we should skip the 'store' 
bits.

That way the generic code does not have this special-case wart 
dependent on PERF_COUNT_HW_CACHE_BPU.

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Thomas Gleixner]

On Thu, 25 Jun 2009, Ingo Molnar wrote:

> 
> * Thomas Gleixner <tglx@linutronix.de> wrote:
> 
> > On Thu, 25 Jun 2009, Jaswinder Singh Rajput wrote:
> > > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > > 
> > >       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
> > >       283542921  dL1-loads             (scaled from 23.28%)
> > 
> > Where is the point of this? dL1-loads is a completely non 
> > intuitive artificial abbreviation.
> 
> blame me :)
> 
> I found L1-data-Cache-Load-References way too long and i asked for 
> suggestions and came up with my list of abbreviations.
> 
> I found 'dL1' intuitive because we use 'dTLB' and 'iTLB' as well.

:)
 
> How about L1-data-loads ?

Yeah, something like that would be nice. The ones Roland
suggested are fine as well.

Thanks,

	tglx

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Thu, 2009-06-25 at 11:33 +0200, Ingo Molnar wrote:

> Firstly, please run your patches through checkpatch - it will report 
> a real problem in your patch.
> 
> Secondly, this special-casing of the BPU isnt very clean in this 
> form. The BPU isnt 'special' because it deals with instructions - 
> it's special because it's for all practical purposes read-only.
> 
> So we should extend our table with a read-only flag, and the BPU and 
> the iTLB should be listed as read-only. (iTLB-store-miss is another 
> thing that makes no sense) For those we should skip the 'store' 
> bits.
> 
> That way the generic code does not have this special-case wart 
> dependent on PERF_COUNT_HW_CACHE_BPU.
> 

I am sorry BPU still needs special handling ;-)

[PATCH] perf_counter tools: shorten names for events

Added new alias for events.

special handling for BPU for :
 'branch loads'       -> 'branches'
 'branch load-misses' -> 'branch-misses'

On AMD box:
$ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null

Before :

 Performance counter stats for 'ls -lR /usr/include/':

      248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
        1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
         153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
         423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
         302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
      251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
        5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
          93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
        6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
         609485  L2-Cache-Load-Misses  (scaled from 23.45%)
        6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
      248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
        5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
      257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
           6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
      109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
        5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)

    0.413702461  seconds time elapsed.

After :

 Peformance counter stats for 'ls -lR /usr/include/':

      266590464  L1d-loads             (scaled from 23.03%)
        1222273  L1d-load-misses       (scaled from 23.58%)
         146204  L1d-stores            (scaled from 23.83%)
         406344  L1d-prefetches        (scaled from 24.09%)
         283748  L1d-prefetch-misses   (scaled from 24.10%)
      249650965  L1i-loads             (scaled from 23.80%)
        3353961  L1i-load-misses       (scaled from 23.82%)
         104599  L1i-prefetches        (scaled from 23.68%)
        4836405  LLC-loads             (scaled from 23.67%)
         498214  LLC-load-misses       (scaled from 23.66%)
        4953994  LLC-stores            (scaled from 23.64%)
      243354097  dTLB-loads            (scaled from 23.77%)
        6468584  dTLB-load-misses      (scaled from 23.74%)
      249719549  iTLB-loads            (scaled from 23.25%)
           5060  iTLB-load-misses      (scaled from 23.00%)
      112343016  branches              (scaled from 22.76%)
        5528876  branch-misses         (scaled from 22.54%)

    0.427154051  seconds time elapsed.

Reported-by : Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 tools/perf/util/parse-events.c |   56 +++++++++++++++++++++++++++------------
 1 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7939a21..993cee4 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,23 +71,23 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
-	{ "L1-data",		"l1-d",		"l1d"			},
-	{ "L1-instruction",	"l1-i",		"l1i"			},
-	{ "L2",			"l2"					},
-	{ "Data-TLB",		"dtlb",		"d-tlb"			},
-	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
-	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
+ { "L1d",	"l1-d",		"L1-data",				},
+ { "L1i",	"l1-i",		"L1-instruction",			},
+ { "LLC",	"L2"							},
+ { "dTLB",	"d-tlb",	"Data-TLB",				},
+ { "iTLB",	"i-tlb",	"Instruction-TLB",			},
+ { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
 };
 
 static char *hw_cache_op[][MAX_ALIASES] = {
-	{ "Load",		"read"					},
-	{ "Store",		"write"					},
-	{ "Prefetch",		"speculative-read", "speculative-load"	},
+ { "load",	"loads",	"read",					},
+ { "store",	"stores",	"write",				},
+ { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
 };
 
 static char *hw_cache_result[][MAX_ALIASES] = {
-	{ "Reference",		"ops",		"access"		},
-	{ "Miss"							},
+ { "refs",	"Reference",	"ops",		"access",		},
+ { "misses",	"miss",							},
 };
 
 #define C(x)		PERF_COUNT_HW_CACHE_##x
@@ -118,6 +118,33 @@ static int is_cache_op_valid(u8 cache_type, u8 cache_op)
 		return 0;	/* invalid */
 }
 
+static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
+{
+	static char name[50];
+
+	/*
+	 * special handling for BPU for :
+	 * 'branch loads'	-> 'branches'
+	 * 'branch load-misses'	-> 'branch-misses'
+	 */
+	if (cache_type == PERF_COUNT_HW_CACHE_BPU) {
+		if (cache_result)
+			sprintf(name, "%s-%s", hw_cache[cache_type][0],
+				hw_cache_result[cache_result][0]);
+		else
+			sprintf(name, "%s", hw_cache[cache_type][1]);
+
+	} else if (cache_result)
+		sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
+			hw_cache_op[cache_op][0],
+			hw_cache_result[cache_result][0]);
+		else
+			sprintf(name, "%s-%s", hw_cache[cache_type][0],
+				hw_cache_op[cache_op][1]);
+
+	return name;
+}
+
 char *event_name(int counter)
 {
 	u64 config = attrs[counter].config;
@@ -137,7 +164,6 @@ char *event_name(int counter)
 
 	case PERF_TYPE_HW_CACHE: {
 		u8 cache_type, cache_op, cache_result;
-		static char name[100];
 
 		cache_type   = (config >>  0) & 0xff;
 		if (cache_type > PERF_COUNT_HW_CACHE_MAX)
@@ -153,12 +179,8 @@ char *event_name(int counter)
 
 		if (!is_cache_op_valid(cache_type, cache_op))
 			return "invalid-cache";
-		sprintf(name, "%s-Cache-%s-%ses",
-			hw_cache[cache_type][0],
-			hw_cache_op[cache_op][0],
-			hw_cache_result[cache_result][0]);
 
-		return name;
+		return event_cache_name(cache_type, cache_op, cache_result);
 	}
 
 	case PERF_TYPE_SOFTWARE:
-- 
1.6.0.6

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Thu, 2009-06-25 at 14:48 +0200, Thomas Gleixner wrote:
> On Thu, 25 Jun 2009, Ingo Molnar wrote:
> 
> > 
> > * Thomas Gleixner <tglx@linutronix.de> wrote:
> > 
> > > On Thu, 25 Jun 2009, Jaswinder Singh Rajput wrote:
> > > > On Tue, 2009-06-23 at 21:56 +0200, Ingo Molnar wrote:
> > > > 
> > > >       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
> > > >       283542921  dL1-loads             (scaled from 23.28%)
> > > 
> > > Where is the point of this? dL1-loads is a completely non 
> > > intuitive artificial abbreviation.
> > 
> > blame me :)
> > 
> > I found L1-data-Cache-Load-References way too long and i asked for 
> > suggestions and came up with my list of abbreviations.
> > 
> > I found 'dL1' intuitive because we use 'dTLB' and 'iTLB' as well.
> 
> :)
>  
> > How about L1-data-loads ?
> 
> Yeah, something like that would be nice. The ones Roland
> suggested are fine as well.
> 

This still looks ugly and lines are again long check for
'L1-dcache-prefetch-misses' and does not solve the purpose :

 Performance counter stats for 'ls -lR /usr/include/':
 
      254259235  L1-dcache-loads       (scaled from 22.69%)
        1129360  L1-dcache-load-misses  (scaled from 23.05%)
         151929  L1-dcache-stores      (scaled from 22.94%)
         395089  L1-dcache-prefetches  (scaled from 23.30%)
         273699  L1-dcache-prefetch-misses  (scaled from 23.19%)
      253780608  L1-icache-loads       (scaled from 23.07%)
        4014781  L1-icache-load-misses  (scaled from 23.16%)
          94336  L1-icache-prefetches  (scaled from 23.66%)
        5553717  LLC-loads             (scaled from 23.70%)
         533195  LLC-load-misses       (scaled from 23.68%)
        5534185  LLC-stores            (scaled from 23.92%)
      252786406  dTLB-loads            (scaled from 23.86%)
        5058100  dTLB-load-misses      (scaled from 24.17%)
      248308183  iTLB-loads            (scaled from 24.55%)
           4627  iTLB-load-misses      (scaled from 24.10%)
      106942084  branches              (scaled from 23.93%)
        5280013  branch-misses         (scaled from 23.06%)

Please check my patch which I send few minutes ago.

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Roland Dreier]

 > > Where is the point of this? dL1-loads is a completely non 
 > > intuitive artificial abbreviation.
 > 
 > blame me :)
 > 
 > I found L1-data-Cache-Load-References way too long and i asked for 
 > suggestions and came up with my list of abbreviations.
 > 
 > I found 'dL1' intuitive because we use 'dTLB' and 'iTLB' as well.
 > 
 > How about L1-data-loads ?

I think L1-dcache is a good compromise between length and ease of
understanding (at least for me).

 - R.

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Roland Dreier]

 > This still looks ugly and lines are again long check for
 > 'L1-dcache-prefetch-misses' and does not solve the purpose :
 > 
 >  Performance counter stats for 'ls -lR /usr/include/':
 >  
 >       254259235  L1-dcache-loads       (scaled from 22.69%)
 >         1129360  L1-dcache-load-misses  (scaled from 23.05%)
 >          151929  L1-dcache-stores      (scaled from 22.94%)
 >          395089  L1-dcache-prefetches  (scaled from 23.30%)
 >          273699  L1-dcache-prefetch-misses  (scaled from 23.19%)
 >       253780608  L1-icache-loads       (scaled from 23.07%)
 >         4014781  L1-icache-load-misses  (scaled from 23.16%)

But even the longest line there (dcache-prefetch-misses) is only 64
columns long, so you could just align the "(scaled" part a little
further to the right and keep the output under, say, 72 columns.

 - R.

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Roland Dreier]

 >       266590464  L1d-loads             (scaled from 23.03%)

IMHO "L1d" is too abbreviated for it to be obvious that it means L1 data
cache.  If you want something really short maybe "L1-d$" might be a
little clearer, but I stil like "L1-dcache" best.

The formatting of aligning things is nice defitely but we could also
shorten lines by saying "scaled from" in fewer characters maybe?  (I
have to admit I don't know what "scaled from X%" means in this case so I
can't suggest something better, but the fact that I can't easily tell
what it means probably suggests that the wording could be improved)

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Thu, 2009-06-25 at 08:05 -0700, Roland Dreier wrote:
> > This still looks ugly and lines are again long check for
>  > 'L1-dcache-prefetch-misses' and does not solve the purpose :
>  > 
>  >  Performance counter stats for 'ls -lR /usr/include/':
>  >  
>  >       254259235  L1-dcache-loads       (scaled from 22.69%)
>  >         1129360  L1-dcache-load-misses  (scaled from 23.05%)
>  >          151929  L1-dcache-stores      (scaled from 22.94%)
>  >          395089  L1-dcache-prefetches  (scaled from 23.30%)
>  >          273699  L1-dcache-prefetch-misses  (scaled from 23.19%)
>  >       253780608  L1-icache-loads       (scaled from 23.07%)
>  >         4014781  L1-icache-load-misses  (scaled from 23.16%)
> 
> But even the longest line there (dcache-prefetch-misses) is only 64
> columns long, so you could just align the "(scaled" part a little
> further to the right and keep the output under, say, 72 columns.
> 

BTW, this is a shorten patch not widen patch ;-)

L1d and L1i is self explanatory.

If iTLB and dTLB are valid then why not L1d and L1i ?

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Roland Dreier <rdreier@cisco.com> wrote:

> 
>  > > Where is the point of this? dL1-loads is a completely non 
>  > > intuitive artificial abbreviation.
>  > 
>  > blame me :)
>  > 
>  > I found L1-data-Cache-Load-References way too long and i asked for 
>  > suggestions and came up with my list of abbreviations.
>  > 
>  > I found 'dL1' intuitive because we use 'dTLB' and 'iTLB' as well.
>  > 
>  > How about L1-data-loads ?
> 
> I think L1-dcache is a good compromise between length and ease of 
> understanding (at least for me).

all of them are caches and dcache is quite ugly as we already have a 
'dcache' in the kernel.

We could do L1-data-loads or just go back to dL1-loads or 
d-L1-loads.

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Roland Dreier <rdreier@cisco.com> wrote:

> 
>  >       266590464  L1d-loads             (scaled from 23.03%)
> 
> IMHO "L1d" is too abbreviated for it to be obvious that it means 
> L1 data cache.  If you want something really short maybe "L1-d$" 
> might be a little clearer, but I stil like "L1-dcache" best.

I find 'dcache' extremely confusing given that we have a dcache in 
Linux already.

	Ingo

[tip:perfcounters/urgent] perf_counter tools: Shorten names for events

[tip-bot for Jaswinder Singh Rajput]

Commit-ID:  e5c59547791f171b280bc4c4b2c3ff171824c1a3
Gitweb:     http://git.kernel.org/tip/e5c59547791f171b280bc4c4b2c3ff171824c1a3
Author:     Jaswinder Singh Rajput <jaswinder@kernel.org>
AuthorDate: Thu, 25 Jun 2009 18:25:22 +0530
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 25 Jun 2009 17:30:23 +0200

perf_counter tools: Shorten names for events

Added new alias for events.

On AMD box:

 $ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null

Before :

 Performance counter stats for 'ls -lR /usr/include/':

      248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
        1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
         153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
         423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
         302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
      251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
        5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
          93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
        6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
         609485  L2-Cache-Load-Misses  (scaled from 23.45%)
        6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
      248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
        5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
      257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
           6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
      109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
        5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)

    0.413702461  seconds time elapsed.

After :

 Peformance counter stats for 'ls -lR /usr/include/':

      266590464  L1-d$-loads           (scaled from 23.03%)
        1222273  L1-d$-load-misses     (scaled from 23.58%)
         146204  L1-d$-stores          (scaled from 23.83%)
         406344  L1-d$-prefetches      (scaled from 24.09%)
         283748  L1-d$-prefetch-misses (scaled from 24.10%)
      249650965  L1-i$-loads           (scaled from 23.80%)
        3353961  L1-i$-load-misses     (scaled from 23.82%)
         104599  L1-i$-prefetches      (scaled from 23.68%)
        4836405  LLC-loads             (scaled from 23.67%)
         498214  LLC-load-misses       (scaled from 23.66%)
        4953994  LLC-stores            (scaled from 23.64%)
      243354097  dTLB-loads            (scaled from 23.77%)
        6468584  dTLB-load-misses      (scaled from 23.74%)
      249719549  iTLB-loads            (scaled from 23.25%)
           5060  iTLB-load-misses      (scaled from 23.00%)
      112343016  branch-loads          (scaled from 22.76%)
        5528876  branch-load-misses    (scaled from 22.54%)

    0.427154051  seconds time elapsed.

Reported-by : Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1245934522.5308.39.camel@hpdv5.satnam>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/parse-events.c |   45 ++++++++++++++++++++++++---------------
 1 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7939a21..430f060 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,23 +71,23 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
-	{ "L1-data",		"l1-d",		"l1d"			},
-	{ "L1-instruction",	"l1-i",		"l1i"			},
-	{ "L2",			"l2"					},
-	{ "Data-TLB",		"dtlb",		"d-tlb"			},
-	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
-	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
+ { "L1-d$",	"l1-d",		"L1-data",				},
+ { "L1-i$",	"l1-i",		"L1-instruction",			},
+ { "LLC",	"L2"							},
+ { "dTLB",	"d-tlb",	"Data-TLB",				},
+ { "iTLB",	"i-tlb",	"Instruction-TLB",			},
+ { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
 };
 
 static char *hw_cache_op[][MAX_ALIASES] = {
-	{ "Load",		"read"					},
-	{ "Store",		"write"					},
-	{ "Prefetch",		"speculative-read", "speculative-load"	},
+ { "load",	"loads",	"read",					},
+ { "store",	"stores",	"write",				},
+ { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
 };
 
 static char *hw_cache_result[][MAX_ALIASES] = {
-	{ "Reference",		"ops",		"access"		},
-	{ "Miss"							},
+ { "refs",	"Reference",	"ops",		"access",		},
+ { "misses",	"miss",							},
 };
 
 #define C(x)		PERF_COUNT_HW_CACHE_##x
@@ -118,6 +118,22 @@ static int is_cache_op_valid(u8 cache_type, u8 cache_op)
 		return 0;	/* invalid */
 }
 
+static char *event_cache_name(u8 cache_type, u8 cache_op, u8 cache_result)
+{
+	static char name[50];
+
+	if (cache_result) {
+		sprintf(name, "%s-%s-%s", hw_cache[cache_type][0],
+			hw_cache_op[cache_op][0],
+			hw_cache_result[cache_result][0]);
+	} else {
+		sprintf(name, "%s-%s", hw_cache[cache_type][0],
+			hw_cache_op[cache_op][1]);
+	}
+
+	return name;
+}
+
 char *event_name(int counter)
 {
 	u64 config = attrs[counter].config;
@@ -137,7 +153,6 @@ char *event_name(int counter)
 
 	case PERF_TYPE_HW_CACHE: {
 		u8 cache_type, cache_op, cache_result;
-		static char name[100];
 
 		cache_type   = (config >>  0) & 0xff;
 		if (cache_type > PERF_COUNT_HW_CACHE_MAX)
@@ -153,12 +168,8 @@ char *event_name(int counter)
 
 		if (!is_cache_op_valid(cache_type, cache_op))
 			return "invalid-cache";
-		sprintf(name, "%s-Cache-%s-%ses",
-			hw_cache[cache_type][0],
-			hw_cache_op[cache_op][0],
-			hw_cache_result[cache_result][0]);
 
-		return name;
+		return event_cache_name(cache_type, cache_op, cache_result);
 	}
 
 	case PERF_TYPE_SOFTWARE:

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Roland Dreier <rdreier@cisco.com> wrote:

>  >       266590464  L1d-loads             (scaled from 23.03%)
> 
> IMHO "L1d" is too abbreviated for it to be obvious that it means 
> L1 data cache.  If you want something really short maybe "L1-d$" 
> might be a little clearer, but I stil like "L1-dcache" best.

i changed it to L1-d$ / L1-i$.

> The formatting of aligning things is nice defitely but we could 
> also shorten lines by saying "scaled from" in fewer characters 
> maybe?  (I have to admit I don't know what "scaled from X%" means 
> in this case so I can't suggest something better, but the fact 
> that I can't easily tell what it means probably suggests that the 
> wording could be improved)

Indeed, the '(scaled from 12.3%)' message should i guess be changed 
to:

  (9.43x scaled)

( and a multiplicative factor is more expressive anyway, than the 
  percentage of from where we scale up. )

	Ingo

Re: [tip:perfcounters/urgent] perf_counter tools: Shorten names for events

[Jaswinder Singh Rajput]

Hello Ingo,

On Thu, 2009-06-25 at 15:33 +0000, tip-bot for Jaswinder Singh Rajput
wrote:
> Commit-ID:  e5c59547791f171b280bc4c4b2c3ff171824c1a3
> Gitweb:     http://git.kernel.org/tip/e5c59547791f171b280bc4c4b2c3ff171824c1a3
> Author:     Jaswinder Singh Rajput <jaswinder@kernel.org>
> AuthorDate: Thu, 25 Jun 2009 18:25:22 +0530
> Committer:  Ingo Molnar <mingo@elte.hu>
> CommitDate: Thu, 25 Jun 2009 17:30:23 +0200
> 
> perf_counter tools: Shorten names for events
> 
> Added new alias for events.
> 
> On AMD box:
> 
>  $ ./perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses -- ls -lR /usr/include/ > /dev/null
> 
> Before :
> 
>  Performance counter stats for 'ls -lR /usr/include/':
> 
>       248064467  L1-data-Cache-Load-Referencees  (scaled from 23.27%)
>         1001433  L1-data-Cache-Load-Misses  (scaled from 23.34%)
>          153691  L1-data-Cache-Store-Referencees  (scaled from 23.34%)
>          423248  L1-data-Cache-Prefetch-Referencees  (scaled from 23.33%)
>          302138  L1-data-Cache-Prefetch-Misses  (scaled from 23.25%)
>       251217546  L1-instruction-Cache-Load-Referencees  (scaled from 23.25%)
>         5757005  L1-instruction-Cache-Load-Misses  (scaled from 23.23%)
>           93435  L1-instruction-Cache-Prefetch-Referencees  (scaled from 23.24%)
>         6496073  L2-Cache-Load-Referencees  (scaled from 23.32%)
>          609485  L2-Cache-Load-Misses  (scaled from 23.45%)
>         6876991  L2-Cache-Store-Referencees  (scaled from 23.71%)
>       248922840  Data-TLB-Cache-Load-Referencees  (scaled from 23.94%)
>         5828386  Data-TLB-Cache-Load-Misses  (scaled from 24.17%)
>       257613506  Instruction-TLB-Cache-Load-Referencees  (scaled from 24.20%)
>            6833  Instruction-TLB-Cache-Load-Misses  (scaled from 23.88%)
>       109043606  Branch-Cache-Load-Referencees  (scaled from 23.64%)
>         5552296  Branch-Cache-Load-Misses  (scaled from 23.42%)
> 
>     0.413702461  seconds time elapsed.
> 
> After :
> 
>  Peformance counter stats for 'ls -lR /usr/include/':
> 
>       266590464  L1-d$-loads           (scaled from 23.03%)
>         1222273  L1-d$-load-misses     (scaled from 23.58%)
>          146204  L1-d$-stores          (scaled from 23.83%)
>          406344  L1-d$-prefetches      (scaled from 24.09%)
>          283748  L1-d$-prefetch-misses (scaled from 24.10%)
>       249650965  L1-i$-loads           (scaled from 23.80%)
>         3353961  L1-i$-load-misses     (scaled from 23.82%)
>          104599  L1-i$-prefetches      (scaled from 23.68%)
>         4836405  LLC-loads             (scaled from 23.67%)
>          498214  LLC-load-misses       (scaled from 23.66%)
>         4953994  LLC-stores            (scaled from 23.64%)
>       243354097  dTLB-loads            (scaled from 23.77%)
>         6468584  dTLB-load-misses      (scaled from 23.74%)
>       249719549  iTLB-loads            (scaled from 23.25%)
>            5060  iTLB-load-misses      (scaled from 23.00%)
>       112343016  branch-loads          (scaled from 22.76%)
>         5528876  branch-load-misses    (scaled from 22.54%)
> 
>     0.427154051  seconds time elapsed.
> 
> Reported-by : Ingo Molnar <mingo@elte.hu>
> Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> LKML-Reference: <1245934522.5308.39.camel@hpdv5.satnam>
> Signed-off-by: Ingo Molnar <mingo@elte.hu>
> 
> 
> ---
>  tools/perf/util/parse-events.c |   45 ++++++++++++++++++++++++---------------
>  1 files changed, 28 insertions(+), 17 deletions(-)
> 
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index 7939a21..430f060 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -71,23 +71,23 @@ static char *sw_event_names[] = {
>  #define MAX_ALIASES 8
>  
>  static char *hw_cache[][MAX_ALIASES] = {
> -	{ "L1-data",		"l1-d",		"l1d"			},
> -	{ "L1-instruction",	"l1-i",		"l1i"			},
> -	{ "L2",			"l2"					},
> -	{ "Data-TLB",		"dtlb",		"d-tlb"			},
> -	{ "Instruction-TLB",	"itlb",		"i-tlb"			},
> -	{ "Branch",		"bpu" ,		"btb",		"bpc"	},
> + { "L1-d$",	"l1-d",		"L1-data",				},
> + { "L1-i$",	"l1-i",		"L1-instruction",			},

You changed, 'L1d' to 'L1-d$' and 'L1i" to 'L1-i$' so above command is
failing.

[PATCH] perf_counter tools: adding alias for L1D and L1I which was removed ny mistake

By mistake  e5c59547791f171 renamed preexisting aliases which leads to failure.

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
---
 tools/perf/util/parse-events.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 430f060..4d042f1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,8 +71,8 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
- { "L1-d$",	"l1-d",		"L1-data",				},
- { "L1-i$",	"l1-i",		"L1-instruction",			},
+ { "L1-d$",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-i$",	"l1-i",		"l1i",		"L1-instruction",	},
  { "LLC",	"L2"							},
  { "dTLB",	"d-tlb",	"Data-TLB",				},
  { "iTLB",	"i-tlb",	"Instruction-TLB",			},
-- 
1.6.0.6

Re: [tip:perfcounters/urgent] perf_counter tools: Shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> - { "L1-d$",	"l1-d",		"L1-data",				},
> - { "L1-i$",	"l1-i",		"L1-instruction",			},
> + { "L1-d$",	"l1-d",		"l1d",		"L1-data",		},
> + { "L1-i$",	"l1-i",		"l1i",		"L1-instruction",	},

Yes, those aliases still make sense indeed, as long as they are not 
the primary alias (which is being displayed).

	Ingo

[tip:perfcounters/urgent] perf_counter tools: Add alias for 'l1d' and 'l1i'

[tip-bot for Jaswinder Singh Rajput]

Commit-ID:  4418351f06d9ce73acc846158c20186965f920f3
Gitweb:     http://git.kernel.org/tip/4418351f06d9ce73acc846158c20186965f920f3
Author:     Jaswinder Singh Rajput <jaswinder@kernel.org>
AuthorDate: Thu, 25 Jun 2009 21:27:42 +0530
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 25 Jun 2009 21:54:53 +0200

perf_counter tools: Add alias for 'l1d' and 'l1i'

Add 'l1d' and 'l1i' aliases again as shortcuts - just dont make them
the primary display alias.

Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1245945462.9157.11.camel@hpdv5.satnam>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/parse-events.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 430f060..4d042f1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,8 +71,8 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
- { "L1-d$",	"l1-d",		"L1-data",				},
- { "L1-i$",	"l1-i",		"L1-instruction",			},
+ { "L1-d$",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-i$",	"l1-i",		"l1i",		"L1-instruction",	},
  { "LLC",	"L2"							},
  { "dTLB",	"d-tlb",	"Data-TLB",				},
  { "iTLB",	"i-tlb",	"Instruction-TLB",			},

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Jaswinder Singh Rajput]

On Thu, 2009-06-25 at 17:34 +0200, Ingo Molnar wrote:
> * Roland Dreier <rdreier@cisco.com> wrote:
> 
> >  >       266590464  L1d-loads             (scaled from 23.03%)
> > 
> > IMHO "L1d" is too abbreviated for it to be obvious that it means 
> > L1 data cache.  If you want something really short maybe "L1-d$" 
> > might be a little clearer, but I stil like "L1-dcache" best.
> 
> i changed it to L1-d$ / L1-i$.
> 
> > The formatting of aligning things is nice defitely but we could 
> > also shorten lines by saying "scaled from" in fewer characters 
> > maybe?  (I have to admit I don't know what "scaled from X%" means 
> > in this case so I can't suggest something better, but the fact 
> > that I can't easily tell what it means probably suggests that the 
> > wording could be improved)
> 
> Indeed, the '(scaled from 12.3%)' message should i guess be changed 
> to:
> 
>   (9.43x scaled)
> 
> ( and a multiplicative factor is more expressive anyway, than the 
>   percentage of from where we scale up. )
> 

Can you please let me know how you get 9.43x from 12.3%

Thanks,
--
JSR

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Jaswinder Singh Rajput <jaswinder@kernel.org> wrote:

> On Thu, 2009-06-25 at 17:34 +0200, Ingo Molnar wrote:
> > * Roland Dreier <rdreier@cisco.com> wrote:
> > 
> > >  >       266590464  L1d-loads             (scaled from 23.03%)
> > > 
> > > IMHO "L1d" is too abbreviated for it to be obvious that it means 
> > > L1 data cache.  If you want something really short maybe "L1-d$" 
> > > might be a little clearer, but I stil like "L1-dcache" best.
> > 
> > i changed it to L1-d$ / L1-i$.
> > 
> > > The formatting of aligning things is nice defitely but we could 
> > > also shorten lines by saying "scaled from" in fewer characters 
> > > maybe?  (I have to admit I don't know what "scaled from X%" means 
> > > in this case so I can't suggest something better, but the fact 
> > > that I can't easily tell what it means probably suggests that the 
> > > wording could be improved)
> > 
> > Indeed, the '(scaled from 12.3%)' message should i guess be changed 
> > to:
> > 
> >   (9.43x scaled)
> > 
> > ( and a multiplicative factor is more expressive anyway, than the 
> >   percentage of from where we scale up. )
> > 
> 
> Can you please let me know how you get 9.43x from 12.3%

it was a guesstimate - the real factor is 8.13x

from X percentage scaling factor you get to the multiplier factor by 
doing:

   100.0 / X

	Ingo

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Anton Blanchard]

Hi,

> IMHO "L1d" is too abbreviated for it to be obvious that it means L1 data
> cache.  If you want something really short maybe "L1-d$" might be a
> little clearer, but I stil like "L1-dcache" best.

There's one problem with L1-d$-* for event names. It took me a few goes
before I realised I was being hit by bash variable expansion:


#  perf stat -e L1-d$-loads ls

 usage: perf stat [<options>] <command>

...


# perf stat -e 'L1-d$-loads' ls

 Performance counter stats for 'ls':

        1273291  L1-d$-loads             

    0.004434037  seconds time elapsed


I also prefer the more verbose L1-dcache-* names, and since we support
aliases its mostly a matter of screen real estate when printing out the
statistics.

Anton

Re: [PATCH -tip] perf_counter tools: shorten names for events

[Ingo Molnar]

* Anton Blanchard <anton@samba.org> wrote:

> 
> Hi,
> 
> > IMHO "L1d" is too abbreviated for it to be obvious that it means L1 data
> > cache.  If you want something really short maybe "L1-d$" might be a
> > little clearer, but I stil like "L1-dcache" best.
> 
> There's one problem with L1-d$-* for event names. It took me a few goes
> before I realised I was being hit by bash variable expansion:
> 
> 
> #  perf stat -e L1-d$-loads ls
> 
>  usage: perf stat [<options>] <command>
> 
> ...
> 
> 
> # perf stat -e 'L1-d$-loads' ls
> 
>  Performance counter stats for 'ls':
> 
>         1273291  L1-d$-loads             
> 
>     0.004434037  seconds time elapsed
> 
> 
> I also prefer the more verbose L1-dcache-* names, and since we 
> support aliases its mostly a matter of screen real estate when 
> printing out the statistics.

ok - mind sending a patch for this?

	Ingo

[PATCH] perf_counter tools: Rename cache events to remove $

[Anton Blanchard]

The cache events contain '$' which will hit shell variable expansion. To
avoid confusion change this to 'cache', ie L1-d$-loads becomes L1-dcache-loads.

Signed-off-by: Anton Blanchard <anton@samba.org>
---

Index: linux.trees.git/tools/perf/util/parse-events.c
===================================================================
--- linux.trees.git.orig/tools/perf/util/parse-events.c	2009-07-06 21:50:53.000000000 +1000
+++ linux.trees.git/tools/perf/util/parse-events.c	2009-07-06 21:51:12.000000000 +1000
@@ -71,8 +71,8 @@
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
- { "L1-d$",	"l1-d",		"l1d",		"L1-data",		},
- { "L1-i$",	"l1-i",		"l1i",		"L1-instruction",	},
+ { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
  { "LLC",	"L2"							},
  { "dTLB",	"d-tlb",	"Data-TLB",				},
  { "iTLB",	"i-tlb",	"Instruction-TLB",			},

[tip:perfcounters/core] perf_counter tools: Rename cache events to remove $

[tip-bot for Anton Blanchard]

Commit-ID:  9590b7ba3fefdfe0c7741f5e2f61faf2ffcea19c
Gitweb:     http://git.kernel.org/tip/9590b7ba3fefdfe0c7741f5e2f61faf2ffcea19c
Author:     Anton Blanchard <anton@samba.org>
AuthorDate: Mon, 6 Jul 2009 22:01:31 +1000
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Fri, 10 Jul 2009 10:04:06 +0200

perf_counter tools: Rename cache events to remove $

The cache events contain '$' which will hit shell variable
expansion. To avoid confusion change this to 'cache', ie
L1-d$-loads becomes L1-dcache-loads.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: Roland Dreier <rdreier@cisco.com>
Cc: Jaswinder Singh Rajput <jaswinder@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <20090706120131.GB4391@kryten>
Signed-off-by: Ingo Molnar <mingo@elte.hu>


---
 tools/perf/util/parse-events.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5184959..518a33a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -71,8 +71,8 @@ static char *sw_event_names[] = {
 #define MAX_ALIASES 8
 
 static char *hw_cache[][MAX_ALIASES] = {
- { "L1-d$",	"l1-d",		"l1d",		"L1-data",		},
- { "L1-i$",	"l1-i",		"l1i",		"L1-instruction",	},
+ { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
+ { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
  { "LLC",	"L2"							},
  { "dTLB",	"d-tlb",	"Data-TLB",				},
  { "iTLB",	"i-tlb",	"Instruction-TLB",			},