From: Matt Roper <matthew.d.roper@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org, Matt Roper <matthew.d.roper@intel.com>
Subject: [Intel-gfx] [PATCH 0/8] i915: Introduce Xe_HP compute engines
Date: Tue, 7 Sep 2021 10:19:08 -0700 [thread overview]
Message-ID: <20210907171916.2548047-1-matthew.d.roper@intel.com> (raw)
The Xe_HP architecture introduces compute engines as a new engine class.
These compute command streamers (CCS) are similar to the render engine,
except that they're intended for GPGPU usage and lack support for the 3D
pipeline.
The definition of I915_ENGINE_CLASS_COMPUTE is new ABI; see below for a
link to a UMD (compute) merge request that utilizes the new ABI.
This series adds some of the basic enablement for the CCS engines, but
does not yet add them to the engine list for the relevant platforms
(XeHP SDV and DG2); that will be handled in future series.
UMD (compute): https://github.com/intel/compute-runtime/pull/451
Daniele Ceraolo Spurio (1):
drm/i915/xehp: compute engine pipe_control
John Harrison (1):
drm/i915/xehp: Extend uninterruptible OpenCL workloads to CCS
Matt Roper (6):
drm/i915/xehp: Define compute class and engine
drm/i915/xehp: CCS shares the render reset domain
drm/i915/xehp: Add Compute CS IRQ handlers
drm/i915/xehp: CCS should use RCS setup functions
drm/i915/xehp: Define context scheduling attributes in lrc descriptor
drm/i915/xehp: Enable ccs/dual-ctx in RCU_MODE
.../drm/i915/gem/selftests/i915_gem_context.c | 8 ++--
drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 31 ++++++++++-----
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 39 ++++++++++++++++++-
drivers/gpu/drm/i915/gt/intel_engine_types.h | 11 +++++-
drivers/gpu/drm/i915/gt/intel_engine_user.c | 5 ++-
.../drm/i915/gt/intel_execlists_submission.c | 34 +++++++++++++++-
drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 15 +++++++
drivers/gpu/drm/i915/gt/intel_gt_irq.c | 15 ++++++-
drivers/gpu/drm/i915/gt/intel_lrc.c | 4 +-
drivers/gpu/drm/i915/gt/intel_lrc.h | 10 +++++
drivers/gpu/drm/i915/gt/intel_reset.c | 4 ++
drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h | 13 ++++---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 28 ++++++++++++-
drivers/gpu/drm/i915/i915_drv.h | 2 +
drivers/gpu/drm/i915/i915_perf.c | 4 +-
drivers/gpu/drm/i915/i915_reg.h | 20 +++++++++-
include/uapi/drm/i915_drm.h | 1 +
17 files changed, 215 insertions(+), 29 deletions(-)
--
2.25.4
next reply other threads:[~2021-09-07 17:19 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-07 17:19 Matt Roper [this message]
2021-09-07 17:19 ` [Intel-gfx] [PATCH 1/8] drm/i915/xehp: Define compute class and engine Matt Roper
2021-09-08 9:46 ` Tvrtko Ursulin
2021-09-08 16:42 ` Daniel Vetter
2021-09-07 17:19 ` [Intel-gfx] [PATCH 2/8] drm/i915/xehp: CCS shares the render reset domain Matt Roper
2021-09-08 10:07 ` Tvrtko Ursulin
2021-09-08 20:23 ` Matt Roper
2021-09-09 8:11 ` Tvrtko Ursulin
2021-09-08 16:46 ` Daniel Vetter
2021-09-07 17:19 ` [Intel-gfx] [PATCH 3/8] drm/i915/xehp: Add Compute CS IRQ handlers Matt Roper
2021-09-08 10:09 ` Tvrtko Ursulin
2021-09-07 17:19 ` [Intel-gfx] [PATCH 4/8] drm/i915/xehp: CCS should use RCS setup functions Matt Roper
2021-09-08 10:13 ` Tvrtko Ursulin
2021-09-08 13:57 ` Tvrtko Ursulin
2021-09-07 17:19 ` [Intel-gfx] [PATCH 5/8] drm/i915/xehp: compute engine pipe_control Matt Roper
2021-09-07 17:19 ` [Intel-gfx] [PATCH 6/8] drm/i915/xehp: Define context scheduling attributes in lrc descriptor Matt Roper
2021-09-08 14:01 ` Tvrtko Ursulin
2021-09-07 17:19 ` [Intel-gfx] [PATCH 7/8] drm/i915/xehp: Enable ccs/dual-ctx in RCU_MODE Matt Roper
2021-09-08 14:10 ` Tvrtko Ursulin
2021-09-07 17:19 ` [Intel-gfx] [PATCH 8/8] drm/i915/xehp: Extend uninterruptible OpenCL workloads to CCS Matt Roper
2021-09-08 14:15 ` Tvrtko Ursulin
2021-09-07 20:21 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for i915: Introduce Xe_HP compute engines Patchwork
2021-09-07 20:23 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-09-07 20:53 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-09-08 0:00 ` [Intel-gfx] ✓ Fi.CI.IGT: " 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=20210907171916.2548047-1-matthew.d.roper@intel.com \
--to=matthew.d.roper@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--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