lkml.org 
[lkml]   [2022]   [May]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    SubjectRe: [PATCH 00/20] perf vendors events arm64: Multiple Arm CPUs
    From
    On 2022-05-18 09:15, John Garry wrote:
    > On 17/05/2022 15:32, Robin Murphy wrote:
    >>
    >> On 2022-05-10 11:47, Nick Forrington wrote:
    >>> Add Performance Monitoring Unit event data for the Arm CPUs listed
    >>> below.
    >>>
    >>> Changesets are dependent due to incremental updates to the common events
    >>> file and mapfile.csv.
    >>>
    >>> Data is sourced from https://github.com/ARM-software/data
    >>>
    >>> Nick Forrington (20):
    >>>    perf vendors events arm64: Arm Cortex-A5
    >>>    perf vendors events arm64: Arm Cortex-A7
    >>>    perf vendors events arm64: Arm Cortex-A8
    >>>    perf vendors events arm64: Arm Cortex-A9
    >>>    perf vendors events arm64: Arm Cortex-A15
    >>>    perf vendors events arm64: Arm Cortex-A17
    >>>    perf vendors events arm64: Arm Cortex-A32
    >>
    >> Obligatory question over anything relating to the above CPUs being in
    >> an "arch/arm64" directory... ;)
    >
    > If we were to add to arm32/arm then the common event numbers and maybe
    > other JSONs in future would need to be duplicated.
    >
    > Would there be any reason to add to arm32/arm apart to from being
    > strictly proper? Maybe if lots of other 32b support for other vendors
    > came along then it could make sense (to separate them out).

    That's the heart of the question, really. At best it seems unnecessarily
    confusing as-is. AFAICS either the naming isn't functional, wherein it
    would potentially make the most sense to rename the whole thing
    "pmu-events/arch/arm" if it's merely for categorising Arm architectures
    in general, or it is actually tied to the host triplet, in which case
    the above patches are most likely useless.

    I'd agree that there doesn't seem much point in trying to separate
    things along relatively arbitrary lines if it *isn't* functionally
    necessary - the PMUv2 common events look to be a straightforward subset
    of the PMUv3 ones, but then there's Cortex-A32 anyway, plus most of the
    already-supported CPUs could equally run an AArch32 perf tool as well.

    Thanks,
    Robin.

    \
     
     \ /
      Last update: 2022-05-18 14:45    [W:8.040 / U:0.072 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site