AI-PROPELLER uses AlphaEvolve to evolve interprocedural code layout heuristics in Propeller and reports 0.23-1.6% gains on warehouse-scale applications via real hardware measurements.
Mlgo: a machine learning guided compiler optimizations framework
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AutoPass uses evidence from compiler states and runtime feedback to guide LLM agents in tuning LLVM optimizations, delivering 1.043x and 1.117x geometric-mean speedups over -O3 on x86-64 and ARM64.
citing papers explorer
-
AI-PROPELLER: Warehouse-Scale Interprocedural Code Layout Optimization with AlphaEvolve
AI-PROPELLER uses AlphaEvolve to evolve interprocedural code layout heuristics in Propeller and reports 0.23-1.6% gains on warehouse-scale applications via real hardware measurements.
-
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
AutoPass uses evidence from compiler states and runtime feedback to guide LLM agents in tuning LLVM optimizations, delivering 1.043x and 1.117x geometric-mean speedups over -O3 on x86-64 and ARM64.