Minotaur: A SIMD-Oriented Synthesizing Superoptimizer

05/31/2023

∙

by   Zhengyang Liu, et al.

∙

0

∙

share

Minotaur is a superoptimizer for LLVM's intermediate representation that focuses on integer SIMD instructions, both portable and specific to x86-64. We created it to attack problems in finding missing peephole optimizations for SIMD instructions-this is challenging because there are many such instructions and they can be semantically complex. Minotaur runs a hybrid synthesis algorithm where instructions are enumerated concretely, but literal constants are generated by the solver. We use Alive2 as a verification engine; to do this we modified it to support synthesis and also to support a large subset of Intel's vector instruction sets (SSE, AVX, AVX2, and AVX-512). Minotaur finds many profitable optimizations that are missing from LLVM. It achieves limited speedups on the integer parts of SPEC CPU2017, around 1.3 the test suite for the libYUV library by 2.2 maximum, when targeting an Intel Cascade Lake processor.