XDC 2019: Final week to submit your talks!

Mark Filion mfilion at collabora.com
Sat Jul 6 01:53:23 UTC 2019

Hi Ray,

Thank you for your submissions. Please make sure to submit the two talks via the form on the XDC website!



On July 5, 2019 5:27:33 p.m. EDT, "Huang, Ray" <Ray.Huang at amd.com> wrote:
>Hi Mark and all,
>I am Ray (Rui) Huang from AMD Linux Graphic Driver team, that work on
>Linux driver support on AMDGPU right now. I wrote PSP and swSMU driver
>in the amdgpu kernel part before, and brought up series of AMDGPU such
>as Vega10, Raven, Raven2, Navi10, and etc. And I am trying to do some
>optimization under drm, ttm driver based on the AMDGPU. It's my honor
>if I have an opportunity to discuss with each X developers in XDC2019.
>My focus is in the kernel side so far, and below is my kernel patches:
>Here are the two Talks that I submits this time, please take a look: 
>Talk1: (Bulk moving mechanism on LRU for DRM/TTM)
>While investigating a performance issue with the F1 2017 game
>benchmark, we identified some bottlenecks related to how ttm and amdgpu
>do buffer validation and LRU handling.  This ultimately lead to a major
>redesign of how we handle buffer migration.  This talk describes
>process that we took to identify and fix the bottleneck and what we
>learned along the way.
>		The Talos Principle(Vulkan)     Clpeak(OCL)            
>BusSpeedReadback(OCL) /unit: ms
>Original                                 		162.1 FPS                   
>42.15 us                0.254 (1K) 0.241 (2K) 0.230(4K) 0.223(8K)
>Bulk Move                             		162.4 FPS                      
>44.48 us                0.260 (1K) 0.274 (2K) 0.249(4K) 0.243(8K)
>Original (move PT bo on LRU)            	147.7 FPS                     
>76.86 us                0.319(1k) 0.314 (2K) 0.308(4K) 0.307(8K)
>Bulk Move (move PT bo on LRU)           	163.5 FPS                     
>40.52 us                0.244(1K) 0.252(2K) 0.213(4K) 0.214(8K)
>0.225(16K)    <-- With the best performance and highest FPS at the same
>Talk2: (Linux AMDGPU new swSMU driver)
>The powerplay driver will be retired. We know there are so many
>duplicated codes and redundant structure such as CGS call and event
>manager, so we decide to write a new driver for the SMU(power)
>component of amdgpu. We try to write a simple and readable framework
>for Linux. The first version of new sw smu driver that is basing on
>vega20. Then do re-arch for linux power codes to use a new sw SMU ip
>block for future asics. So far in the latest two ASICs for amdgpu
>(vega20 and Navi10) will all be implemented by swSMU driver, and all
>future ASICs will all use swSMU framework to implement on power part. 
>Thanks & Best Regards,
>-----Original Message----- 
>From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Mark
>Sent: Monday, July 1, 2019 12:04 PM
>To: events at lists.x.org
>Subject: XDC 2019: Final week to submit your talks!
>It's the final week to submit your talks, workshops or demos for
>CfP ends this coming Sunday, July 7! 
>Have some new developments to share? Facing some challenges with you
>projects? If it's related to open source  graphics, please send it in! 
>amd-gfx mailing list
>amd-gfx at lists.freedesktop.org

Sent from my Android device with K-9 Mail. Please excuse my brevity.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.x.org/archives/events/attachments/20190706/7bcd4bfa/attachment.htm>

More information about the events mailing list