ML

LLVM loop unroll and jam pass and view-cfg

대학원 컴파일러 수업에서 ML을 이용하여 unroll and jam을 판별하는 모델을 학습을 하는 term project를 진행하였다. unroll and jam pass는 이름에서 알 수 있듯이 loop 최적화에 관련된 pass로 unroll 과 …

간단논문 정리 DARTS DIFFERENTIABLE ARCHITECTURE SEARCH (ICLR 2019)

제목DARTS: DIFFERENTIABLE ARCHITECTURE SEARCH 저자Hanxiao Liu,Karen Simonyan,Yiming Yang Motivation기존 NAS가 상당수의 시간 혹은 cost가 필요(2000 GPU days of …

간단논문 정리 End-to-End Deep Learning of Optimization Heuristics (PACT 17)

제목End-to-End Deep Learning of Optimization Heuristics 저자Chris Cummins ; Pavlos Petoumenos ; Zheng Wang ; Hugh Leather

간단논문 정리 Fast and Effective Orchestration of Compiler Optimizations(Zhelong Pan,Rudolf Eigenmann;Purdue University ;CGO’06)

제목Fast and Effective Orchestration of Compiler Optimizations 저자Zhelong Pan,Rudolf Eigenmann Motivationcompile-time optimizations 은 전반적으로 프로그 …

간단논문 정리 TVM An Automated End-to-End Optimizing Compiler for Deep Learning (OSDI 18)

논문 정리 Chameleon Adaptive Code Optimization for Expedited Deep Neural Network Compilation(ICLR 2020)

제목Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation

논문 정리 NeuroVectorizer End-to-End Vectorization with Deep Reinforcement Learning (CGO 20)

제목NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning