XDC 2019: Final week to submit your talks!

[Huang, Ray]

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:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?qt=author&q=Huang+Rui 

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) 0.204(16K)
Bulk Move                             		162.4 FPS                       44.48 us                0.260 (1K) 0.274 (2K) 0.249(4K) 0.243(8K) 0.228(16K)
Original (move PT bo on LRU)            	147.7 FPS                       76.86 us                0.319(1k) 0.314 (2K) 0.308(4K) 0.307(8K) 0.310(16K)
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 time

Link: https://www.phoronix.com/scan.php?page=news_item&px=AMDGPU-LRU-Bulk-Move 	


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. 

Link: https://www.phoronix.com/scan.php?page=news_item&px=AMD-New-SW-SMU-Driver-Future 


Thanks & Best Regards,
Ray

-----Original Message----- 
From: amd-gfx <amd-gfx-bounces at lists.freedesktop.org> On Behalf Of Mark Filion
Sent: Monday, July 1, 2019 12:04 PM
To: events at lists.x.org
Subject: XDC 2019: Final week to submit your talks!

Hi!

It's the final week to submit your talks, workshops or demos for #XDC2019!! 

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! 

http://xdc2019.x.org 

Best,

Mark

_______________________________________________
amd-gfx mailing list
amd-gfx at lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx