PolyBench

PolyBench PolyBench is a comprehensive benchmark to facilitate the evaluation of relevant methods on diverse question patterns for augmenting large language models with external knowledge graphs. Dataset Details Curated by: Renjie Liu (https://liu-rj.github.io/) Language: English License: apache-2.0 Dataset Description

Papers using PolyBench (9)

Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimization2025LOOPer: A Learned Automatic Code Optimizer For Polyhedral Compilers2024 · 1 citesHintPilot: LLM-based Compiler Hint Synthesis for Code Optimization2026Bridging the Gap: Empowering Small Models in Reliable OpenACC-based Parallelization via GEPA-Optimized Prompting2026P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code2025ACPO: AI-Enabled Compiler Framework2023Performance Optimization using Multimodal Modeling and Heterogeneous GNN2023 · 12 citesmlirSynth: Automatic, Retargetable Program Raising in Multi-Level IR using Program Synthesis2023 · 5 citesCompiler Auto-tuning through Multiple Phase Learning2023 · 2 cites