Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: igt-dev@lists.freedesktop.org
Cc: Lionel G Landwerlin <lionel.g.landwerlin@linux.intel.com>
Subject: [igt-dev] [PATCH 26/30] lib/perf: Update MTL OA timestamp and EU thread config
Date: Tue, 14 Feb 2023 13:00:03 -0800	[thread overview]
Message-ID: <20230214210007.2026033-27-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20230214210007.2026033-1-umesh.nerlige.ramappa@intel.com>

MTL has configuration similar to DG2 for OA timestamp and threads per
EU. Update the same for MTL.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
---
 lib/i915/perf.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/lib/i915/perf.c b/lib/i915/perf.c
index d8624dc0..24ef3819 100644
--- a/lib/i915/perf.c
+++ b/lib/i915/perf.c
@@ -432,6 +432,14 @@ intel_perf_for_devinfo(uint32_t device_id,
 		else
 			return unsupported_i915_perf_platform(perf);
 	} else if (devinfo->is_meteorlake) {
+		perf->devinfo.eu_threads_count = 8;
+		/* OA reports have the timestamp value shifted to the
+		 * right by 1 bits, it also means we cannot use the
+		 * top bit for comparison.
+		 */
+		perf->devinfo.oa_timestamp_shift = -1;
+		perf->devinfo.oa_timestamp_mask = 0x7fffffff;
+
 		if (is_mtl_gt2(&perf->devinfo))
 			intel_perf_load_metrics_mtlgt2(perf);
 		else if (is_mtl_gt3(&perf->devinfo))
-- 
2.36.1

  parent reply	other threads:[~2023-02-14 21:00 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-14 20:59 [igt-dev] [PATCH 00/30] Enable OAM support in IGT and GPUvis Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 01/30] i915/perf: Add support for 64-bit OA formats Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 02/30] i915/perf: Define a default engine for OA Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 03/30] i915/perf: Use default engine for sseu tests Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 04/30] i915/perf: Ensure rcs0 is present for gen12-mi-rpc Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 05/30] i915/perf: Use ARRAY_SIZE for buffer-fill test Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 06/30] i915/perf: Add class:instance support to OA tests Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 07/30] i915/perf: Enable tests to run on specific engines Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 08/30] i915/perf: Treat ticks as 64 bit Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 09/30] i915/perf: Treat timestamp as 64 bit value Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 10/30] i915/perf: Add OAM format type Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 11/30] i915/perf: Use a helper for OA format Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 12/30] i915/perf: Add support for oa perf groups Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 13/30] i915/perf: Test concurrent access to OA in different groups Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 14/30] i915/perf: Add OAM support Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 15/30] lib/perf: Make chipsets aware of oa formats Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 16/30] i915/perf: Choose OAM format for media metrics Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 17/30] lib/perf" Set missing metric unit for some counters Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 18/30] lib/perf: Add MTL to supprted HW in oa guid registry Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 19/30] lib/perf: Add support for OAM format in codegen Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 20/30] lib/perf: Update MTL GT2 metrics for OAM Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 21/30] lib/perf: Update MTL GT3 " Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 22/30] i915/perf: Add support for engine specific metrics Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 23/30] i915/perf: Run non-zero-reason on media engines as well Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 24/30] i915/perf: Make sanity check failures descriptive Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 25/30] lib/perf: Enable multi-tile support for perf library Umesh Nerlige Ramappa
2023-02-14 21:00 ` Umesh Nerlige Ramappa [this message]
2023-02-14 21:00 ` [igt-dev] [PATCH 27/30] lib/perf: Add support for MPEC format Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 28/30] lib/perf: Adjust the GPU timestamp for new OA formats Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 29/30] tools/perf: Choose the right card Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 30/30] lib/perf: Apply shift to raw timestamp as well Umesh Nerlige Ramappa
2023-02-14 21:18 ` [igt-dev] ✗ GitLab.Pipeline: warning for Enable OAM support in IGT and GPUvis Patchwork
2023-02-14 21:47 ` [igt-dev] ✓ Fi.CI.BAT: success " Patchwork
2023-02-15  0:48 ` [igt-dev] [PATCH 00/30] " Umesh Nerlige Ramappa
2023-02-15  7:22 ` [igt-dev] ✗ Fi.CI.IGT: failure for " Patchwork

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=20230214210007.2026033-27-umesh.nerlige.ramappa@intel.com \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=lionel.g.landwerlin@linux.intel.com \
    /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