Bug 104100

Summary: Nearly 10% performance drop in SynMark CSCloth from "i965: Emit CS stall before MEDIA_VFE_STATE"
Product: Mesa Reporter: Eero Tamminen <eero.t.tamminen>
Component: Drivers/DRI/i965Assignee: Kenneth Graunke <kenneth>
Status: NEW --- QA Contact: Intel 3D Bugs Mailing List <intel-3d-bugs>
Severity: normal    
Priority: medium Keywords: bisected, regression
Version: git   
Hardware: Other   
OS: All   
Whiteboard:
i915 platform: i915 features:

Description Eero Tamminen 2017-12-05 10:56:25 UTC
Following commit drops performance in SynMark CSCloth test, as expected:
-----------------------------------------------------
commit 55a97db52347f62111a24715078c6035380d3e19
Author:     Kenneth Graunke <kenneth@whitecape.org>
AuthorDate: Tue Oct 31 09:57:54 2017 -0700
Commit:     Matt Turner <mattst88@gmail.com>
CommitDate: Mon Dec 4 10:02:46 2017 -0800

    i965: Emit CS stall before MEDIA_VFE_STATE.
    
    This fixes hangs on GFXBench 5's Aztec Ruins benchmark.
    
    Unfortunately, it regresses OglCSCloth performance by about 10%. There
    are some ideas for fixing that.
    
    The Vulkan driver already emits this stall.
    
    Reviewed-by: Matt Turner <mattst88@gmail.com>
-----------------------------------------------------

The drop is:
* 8-9% on SKL GT4e
* 5-6% on KBL GT3e
* 3-4% on SKL & KBL GT2
* within (largish) variance on BDW GT2 & GT3

On HSW GT it would seem to actually improve perf marginally.

Latter is interesting because Kenneth's trial fix for the performance regression (verified to fix it):
https://cgit.freedesktop.org/~kwg/mesa/commit/?h=vfe-stall-3&id=ab9bff0ac43f0d878106ba124e84edca9b359c8a

Is according to Kenneth causing problems on HSW.  Maybe it could be applied only on newer GENs?

Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.