Comment by forrestthewoods

8 hours ago

auto-vectorization is not nearly as good as you would hope it to be.

The best SIMD optimizations likely require changing your data format from AoS to SoA.

9 comments

forrestthewoods

Reply
ethin  8 hours ago

Either this or you have to do special tricks like pairwise tree reductions and hand-unroll certain portions of loops.

raegis  8 hours ago

What are AoS and SoA?

  • Georgelemental  8 hours ago

    Array of Structs and Struct of Arrays https://en.wikipedia.org/wiki/AoS_and_SoA

    • Rendello  7 hours ago

      A good introduction to SoA (for anyone curious) are the two most famous Data-Oriented Design talks by Mike Acton (game engine dev) [1] and Andrew Kelley (Zig lead dev) [2] respectively.

      I read a book book about DoD [3] really which confused me at first with all its talk about database table design (in a book about a high-performance C++ game engine?), but when it finally clicked it was amazing. The point is that you want to think hard about your access patterns and what could constitute good "primary keys", then model it accordingly. SoA ends up being useful a lot of the time, because having your data in homogeneous arrays/vectors is great for cache locality and branch elimination. Even without SIMD you can get huge speedups from that, but that's also where your compiler (or you as a programmer) can get incredible SIMD gains.

      SoA is not a silver bullet as it may not align well with your access patterns, but it can great to add to your toolkit.

      ---

      Mike Acton: Data-Oriented Design and C++: https://www.youtube.com/watch?v=rX0ItVEVjHc

      Andrew Kelley: A Practical Guide to Applying Data Oriented Design: https://www.youtube.com/watch?v=IroPQ150F6c

      Richard Fabian: Data-Oriented Design: https://www.dataorienteddesign.com/dodbook/

formerly_proven  8 hours ago

And -march=native or at least -march=x86-64-v3 or similar, alternatively identifying relevant functions and manually invoking FMV and uarch specialization via target_clones. Plus non-integer code can generally not be autovectorized in normal-math mode since FP is non-commutative.