Trying The LLVM SI Machine Instruction Scheduler With Mesa 17.2 + LLVM 5.0

Written by Michael Larabel in Mesa on 18 May 2017 at 08:38 PM EDT. 11 Comments
MESA
A Phoronix reader was recently making comments about the LLVM SI Machine Instruction Scheduler "sisched", so I decided to run some fresh benchmarks of this opt-in feature for RadeonSI Gallium3D.

With a Radeon R9 Fury on the i7-7700K box I decided to run some "sisched" tests using the Padoka PPA built against Mesa 17.2-dev this week with LLVM 5.0 SVN AMDGPU.

It's been over one year since last looking at sisched benchmarks so curiosity was there over the impact with modern Mesa and hardware. This scheduler is designed to boost performance for some workloads.
R9 Fury + mesa 17.2-dev R600_DEBUG=sisched

Though in my tests this week, I didn't see any impact with the tested hardware/software configuration...
R9 Fury + mesa 17.2-dev R600_DEBUG=sisched

Those curious can poke at this result file but it didn't end up yielding any meaningful difference in the tests carried out.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week