About

x264 should see roughly a 2X performance improvement from autovectorization based on data from other architectures.    Based on extrapolation of data from the k230 board it is expected that a uarch which can do 128bit vector ALU ops in a single cycle will see a runtime reduction of 50% for this benchmark.  That translates into a 2X improvement in the spec2017 score for 525.x264_r.

Given that's precisely the goal we were shooting for, this is considered done.

Note that Robin is investigating improving the generated code for the SATD routines.  Esesntially we're doing a lot of byte loads when we should be loading larger values.  This may provide a another small improvement on top of the basic vectorization.

Stakeholders/Partners

Dependencies

Status

Updates

May 9, 2024 

• Note additional opportunities for improvement.

Apr 25, 2024 

• Testing on the k230 board shows "only" a 17% runtime improvement when the target for x264 vectorization is a 50% runtime improvement (which will double the spec score)

• However, it looks like the cost of a vector ALU op is at least 3X LMUL

• So a performant uarch where vector ALU ops of reasonable size (128 bits) are 1c would see the expected 50% runtime improvement.

• Considering this resolved.

Mar 14, 2024 

• Dynamic instruction rates cut by 47%, so in the right ballpark for a 2X performance improvement

  • x86 shows a roughly 88% improvement (ie, runtime nearly cut in half)

  • aarch64 shows roughly a 104% improvement (ie run time cut by more than 50%)

  • 47% reduction in dynamic cycle counts is in the right ballpark

  • Need to do performance testing to reach closure

Dec 29, 2023 

• Project reported as a priority for 1H2024