From: Tvrtko Ursulin <tursulin@ursulin.net>
To: Intel-gfx@lists.freedesktop.org
Subject: [PATCH v4 i-g-t 0/7] IGT PMU support
Date: Tue, 10 Oct 2017 10:29:59 +0100 [thread overview]
Message-ID: <20171010093008.22804-1-tvrtko.ursulin@linux.intel.com> (raw)
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
1.
Fixes for intel-gpu-overlay to work on top of the proposed i915 PMU perf API.
2.
New test to exercise the same API.
3.
Update to gem_wsim and media-bench.pl to be able to use engine busyness via PMU
for making balancing decisions.
v2:
* Added gem_wsim and media-bench.pl patches.
* Comments and fixes for the perf_pmu test.
v3:
* A bunch of review feedback implemented.
v4:
* Tests for semaphore waits and event waits.
* Review feedabck.
* RAPL PMU for intel-gpu-overlay.
Tvrtko Ursulin (7):
intel-gpu-overlay: Move local perf implementation to a library
intel-gpu-overlay: Consolidate perf PMU access to library
intel-gpu-overlay: Fix interrupts PMU readout
intel-gpu-overlay: Catch-up to new i915 PMU
tests/perf_pmu: Tests for i915 PMU API
gem_wsim: Busy stats balancers
media-bench.pl: Add busy balancers to the list
benchmarks/Makefile.am | 2 +-
benchmarks/gem_wsim.c | 142 +++++++
lib/Makefile.am | 6 +-
lib/igt_gt.c | 50 +++
lib/igt_gt.h | 38 ++
lib/igt_perf.c | 58 +++
lib/igt_perf.h | 96 +++++
overlay/Makefile.am | 6 +-
overlay/gem-interrupts.c | 25 +-
overlay/gpu-freq.c | 29 +-
overlay/gpu-perf.c | 3 +-
overlay/gpu-top.c | 87 ++---
overlay/perf.c | 26 --
overlay/perf.h | 64 ----
overlay/power.c | 22 +-
overlay/rc6.c | 41 +-
scripts/media-bench.pl | 5 +-
tests/Makefile.am | 1 +
tests/Makefile.sources | 1 +
tests/perf_pmu.c | 957 +++++++++++++++++++++++++++++++++++++++++++++++
20 files changed, 1425 insertions(+), 234 deletions(-)
create mode 100644 lib/igt_perf.c
create mode 100644 lib/igt_perf.h
delete mode 100644 overlay/perf.c
delete mode 100644 overlay/perf.h
create mode 100644 tests/perf_pmu.c
--
2.9.5
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next reply other threads:[~2017-10-10 9:30 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-10 9:29 Tvrtko Ursulin [this message]
2017-10-10 9:30 ` [PATCH i-g-t 1/9] intel-gpu-overlay: Move local perf implementation to a library Tvrtko Ursulin
2017-11-21 19:34 ` [PATCH i-g-t v3 " Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 2/9] intel-gpu-overlay: Consolidate perf PMU access to library Tvrtko Ursulin
2017-10-10 12:21 ` Chris Wilson
2017-10-10 9:30 ` [PATCH i-g-t 3/9] lib/perf: Fix data types and general tidy Tvrtko Ursulin
2017-10-10 12:22 ` Chris Wilson
2017-10-10 9:30 ` [PATCH i-g-t 4/9] intel-gpu-overlay: Fix interrupts PMU readout Tvrtko Ursulin
2017-10-10 12:23 ` Chris Wilson
2017-10-10 14:17 ` [PATCH i-g-t v2 " Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 5/9] intel-gpu-overlay: Catch-up to new i915 PMU Tvrtko Ursulin
2017-11-21 18:20 ` Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 6/9] intel-gpu-overlay: Use RAPL PMU for power reading Tvrtko Ursulin
2017-10-10 11:30 ` [PATCH i-g-t v2 " Tvrtko Ursulin
2017-10-10 12:05 ` [PATCH i-g-t v3 " Tvrtko Ursulin
2017-10-10 12:25 ` Chris Wilson
2017-11-21 19:35 ` [PATCH i-g-t v4 " Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 7/9] tests/perf_pmu: Tests for i915 PMU API Tvrtko Ursulin
2017-10-10 12:37 ` Chris Wilson
2017-10-10 13:38 ` Tvrtko Ursulin
2017-10-10 13:46 ` Chris Wilson
2017-10-10 14:17 ` [PATCH i-g-t v6 " Tvrtko Ursulin
2017-10-10 16:39 ` Chris Wilson
2017-10-11 12:54 ` [PATCH i-g-t v7 " Tvrtko Ursulin
2017-11-21 11:50 ` Chris Wilson
2017-11-21 18:21 ` [PATCH i-g-t v8 " Tvrtko Ursulin
2017-11-21 19:36 ` [PATCH i-g-t v9 " Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 8/9] gem_wsim: Busy stats balancers Tvrtko Ursulin
2017-11-21 19:37 ` [PATCH i-g-t v3 " Tvrtko Ursulin
2017-10-10 9:30 ` [PATCH i-g-t 9/9] media-bench.pl: Add busy balancers to the list Tvrtko Ursulin
2017-11-21 11:51 ` Chris Wilson
2017-10-10 9:42 ` ✗ Fi.CI.BAT: failure for IGT PMU support (rev7) Patchwork
2017-10-10 12:06 ` ✓ Fi.CI.BAT: success for IGT PMU support (rev8) Patchwork
2017-10-10 13:48 ` ✓ Fi.CI.BAT: success for IGT PMU support (rev9) Patchwork
2017-10-10 15:19 ` ✗ Fi.CI.IGT: failure for IGT PMU support (rev8) Patchwork
2017-10-10 18:42 ` ✓ Fi.CI.BAT: success for IGT PMU support (rev11) Patchwork
2017-10-11 1:28 ` ✓ Fi.CI.IGT: " Patchwork
2017-10-11 14:09 ` ✓ Fi.CI.BAT: success for IGT PMU support (rev12) Patchwork
2017-10-11 20:16 ` ✗ Fi.CI.IGT: failure " Patchwork
2017-11-22 11:41 ` ✓ Fi.CI.BAT: success for IGT PMU support (rev18) Patchwork
2017-11-22 11:57 ` Tvrtko Ursulin
2017-11-22 12:47 ` Petri Latvala
2017-11-22 14:31 ` ✓ Fi.CI.IGT: " Patchwork
2017-11-22 14:39 ` Petri Latvala
2017-11-22 14:50 ` Petri Latvala
2017-11-22 17:09 ` Tvrtko Ursulin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171010093008.22804-1-tvrtko.ursulin@linux.intel.com \
--to=tursulin@ursulin.net \
--cc=Intel-gfx@lists.freedesktop.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox