Re: [PATCH] perf stat: Add support for s390 transaction counters

> Displaying these different types for s390 is important from my point of > view. Of course, I could create a mapping of TX_NC_TABORT/TX_NC_TEND > to tx-commit/tx-abort. The remaining events would still appear to be specific > to the cpum_cf. If you want more generic metrics you can just use

Re: [PATCH] perf stat: Add support for s390 transaction counters

> Displaying these different types for s390 is important from my point of > view. Of course, I could create a mapping of TX_NC_TABORT/TX_NC_TEND > to tx-commit/tx-abort. The remaining events would still appear to be specific > to the cpum_cf. If you want more generic metrics you can just use

Re: [PATCH] perf stat: Add support for s390 transaction counters

Hi, On Wed, Mar 14, 2018 at 08:43:17AM -0700, Andi Kleen wrote: > > S390 has no support for Elision and uses transaction begin/end/abort > > instructions. The CPU measurement counter facility provides counters for > > transaction end and transaction abort. > > You don't need to implement the

Re: [PATCH] perf stat: Add support for s390 transaction counters

Hi, On Wed, Mar 14, 2018 at 08:43:17AM -0700, Andi Kleen wrote: > > S390 has no support for Elision and uses transaction begin/end/abort > > instructions. The CPU measurement counter facility provides counters for > > transaction end and transaction abort. > > You don't need to implement the

Re: [PATCH] perf stat: Add support for s390 transaction counters

> S390 has no support for Elision and uses transaction begin/end/abort > instructions. The CPU measurement counter facility provides counters for > transaction end and transaction abort. You don't need to implement the el-* events. > I have used this table (taken from

Re: [PATCH] perf stat: Add support for s390 transaction counters

> S390 has no support for Elision and uses transaction begin/end/abort > instructions. The CPU measurement counter facility provides counters for > transaction end and transaction abort. You don't need to implement the el-* events. > I have used this table (taken from

Re: [PATCH] perf stat: Add support for s390 transaction counters

On 03/14/2018 02:18 PM, Arnaldo Carvalho de Melo wrote: > Em Wed, Mar 14, 2018 at 09:34:48AM +0100, Thomas-Mich Richter escreveu: >> On 03/13/2018 04:23 AM, Andi Kleen wrote: >>> Thomas Richter writes: > Right now there is only hard coded support for x86. > >>>

Re: [PATCH] perf stat: Add support for s390 transaction counters

On 03/14/2018 02:18 PM, Arnaldo Carvalho de Melo wrote: > Em Wed, Mar 14, 2018 at 09:34:48AM +0100, Thomas-Mich Richter escreveu: >> On 03/13/2018 04:23 AM, Andi Kleen wrote: >>> Thomas Richter writes: > Right now there is only hard coded support for x86. > >>> That's not true. There is

Re: [PATCH] perf stat: Add support for s390 transaction counters

Em Wed, Mar 14, 2018 at 09:34:48AM +0100, Thomas-Mich Richter escreveu: > On 03/13/2018 04:23 AM, Andi Kleen wrote: > > Thomas Richter writes: > >> Right now there is only hard coded support for x86. > > That's not true. There is support for generic transaction

Re: [PATCH] perf stat: Add support for s390 transaction counters

Em Wed, Mar 14, 2018 at 09:34:48AM +0100, Thomas-Mich Richter escreveu: > On 03/13/2018 04:23 AM, Andi Kleen wrote: > > Thomas Richter writes: > >> Right now there is only hard coded support for x86. > > That's not true. There is support for generic transaction events in perf. > > As far as I

Re: [PATCH] perf stat: Add support for s390 transaction counters

On 03/13/2018 04:23 AM, Andi Kleen wrote: > Thomas Richter writes: > >> Right now there is only hard coded support for x86. > > That's not true. There is support for generic transaction events in perf. > > As far as I can tell your events would map 1:1 to the

Re: [PATCH] perf stat: Add support for s390 transaction counters

On 03/13/2018 04:23 AM, Andi Kleen wrote: > Thomas Richter writes: > >> Right now there is only hard coded support for x86. > > That's not true. There is support for generic transaction events in perf. > > As far as I can tell your events would map 1:1 to the generic tx-* events. > > -Andi >

Re: [PATCH] perf stat: Add support for s390 transaction counters

Thomas Richter writes: > Right now there is only hard coded support for x86. That's not true. There is support for generic transaction events in perf. As far as I can tell your events would map 1:1 to the generic tx-* events. -Andi

Re: [PATCH] perf stat: Add support for s390 transaction counters

Thomas Richter writes: > Right now there is only hard coded support for x86. That's not true. There is support for generic transaction events in perf. As far as I can tell your events would map 1:1 to the generic tx-* events. -Andi

Re: [PATCH] perf stat: Add support for s390 transaction counters

Em Mon, Mar 12, 2018 at 11:38:06AM +0100, Thomas Richter escreveu: > This patch introduces support for s390 transaction counters > displayed with command 'perf stat -T -- sleep 2' > > Right now there is only hard coded support for x86. > > This patch introduces architecture specfic counter >

Re: [PATCH] perf stat: Add support for s390 transaction counters

Em Mon, Mar 12, 2018 at 11:38:06AM +0100, Thomas Richter escreveu: > This patch introduces support for s390 transaction counters > displayed with command 'perf stat -T -- sleep 2' > > Right now there is only hard coded support for x86. > > This patch introduces architecture specfic counter >

[PATCH] perf stat: Add support for s390 transaction counters

This patch introduces support for s390 transaction counters displayed with command 'perf stat -T -- sleep 2' Right now there is only hard coded support for x86. This patch introduces architecture specfic counter tables for x86 and s390. The architecture is queried and the event string for

[PATCH] perf stat: Add support for s390 transaction counters

This patch introduces support for s390 transaction counters displayed with command 'perf stat -T -- sleep 2' Right now there is only hard coded support for x86. This patch introduces architecture specfic counter tables for x86 and s390. The architecture is queried and the event string for