Step-TP is a dataset providing grounded, atomic step-level IR transitions and CoT supervision to enable reliable multi-step LLM-guided tensor program optimization instead of end-to-end imitation.
Meta large language model compiler: Foundation models of compiler optimization
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
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.
EggMind automates EqSat strategy synthesis via LLMs and EqSatL, cutting final cost 45.1% and peak RAM 69.1% versus full equality saturation on vectorization benchmarks while transferring to tensor compilers.
SysLLMatic integrates LLMs with performance diagnostics and a 43-pattern catalog to optimize complex software, reporting 1.54x latency and 1.24x energy gains over compilers on large Java systems where prior LLM methods did not scale.
Proposes Software 4.0 as an autopoietic heterarchy of human intelligence, neural AI, and reflective symbolic substrate materialized in the Recognitive platform to enable native structural verification and evolution.
citing papers explorer
-
Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization
Step-TP is a dataset providing grounded, atomic step-level IR transitions and CoT supervision to enable reliable multi-step LLM-guided tensor program optimization instead of end-to-end imitation.
-
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
SWE-RL uses RL on software evolution data to train LLMs achieving 41% on SWE-bench Verified with generalization to other reasoning tasks.
-
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.
-
LLM-Guided Strategy Synthesis for Scalable Equality Saturation
EggMind automates EqSat strategy synthesis via LLMs and EqSatL, cutting final cost 45.1% and peak RAM 69.1% versus full equality saturation on vectorization benchmarks while transferring to tensor compilers.
-
SysLLMatic: Large Language Models are Software System Optimizers
SysLLMatic integrates LLMs with performance diagnostics and a 43-pattern catalog to optimize complex software, reporting 1.54x latency and 1.24x energy gains over compilers on large Java systems where prior LLM methods did not scale.
-
The Biomimetic Architecture of Software 4.0
Proposes Software 4.0 as an autopoietic heterarchy of human intelligence, neural AI, and reflective symbolic substrate materialized in the Recognitive platform to enable native structural verification and evolution.