We had an amazing group of talk proposals submitted for the 2022 LLVM Developers’ Meeting. Thank you to all that submitted a talk proposal this year!Here is the 2022 LLVM Developers’ Meeting program:Keynotes:Paths towards unifying LLVM and MLIR - Nicolai HähnleImplementing Language Support for ABI-Stable Software Evolution in Swift and LLVM - Doug GregorTechnical Talks:Implementing the Unimplementable: Bringing HLSL’s Standard Library into Clang - Chris BienemanHeterogeneous Debug Metadata in LLVM - Scott LinderClang, Clang: Who’s there? WebAssembly!- Paulo MatosMC/DC: Enabling easy-to-use safety-critical code coverage analysis with LLVM - Alan PhippsWhat does it take to run LLVM Buildbots? - David Spickettllvm-gitbom: Building Software Artifact Dependency Graphs for Vulnerability Detection - Bharathi Seshadri, Yongkui HanCuPBoP: CUDA for Parallelized and Broad-range Processors - Ruobing HanUniformity Analysis for Irreducible CFGs - Sameer SahasrabuddheUsing Content-Addressable Storage in Clang for Caching Computations and Eliminating Redundancy - Steven Wu, Ben LangmuirDirect GPU Compilation and Execution for Host Applications with OpenMP Parallelism - Shilei Tian, Joseph HuberLinker Code Size Optimization for Native Mobile Applications - Gai LiuMinotaur: A SIMD Oriented Superoptimizer - Zhengyang LiuML-based Hardware Cost Model for High-Level MLIR - Dibyendu Das, Sandya MannarswamyVAST: MLIR for program analysis of C/C++ - Henrich LaukoMLIR for Functional Programming - Siddharth BhatSPIR-V Backend in LLVM: Upstream and Beyond - Michal Paszkowski, Alex BezzubikovIRDL: A Dialect for dialects - Mathieu Fehr, Théo DegioanniAutomated translation validation for an LLVM backend - Nader Boushehrinejad Moradillvm-dialects: bringing dialects to the LLVM IR substrate - Nicolai HähnleYARPGen: A Compiler Fuzzer for Loop Optimizations and Data-Parallel Languages - Vsevolod LivinskiiRISC-V Sign Extension Optimizations - Craig TopperExecution Domain Transition: Binary and LLVM IR can run in conjunction - Jaeyong KoTutorials:Using LLVM’s libc - Sivachandra Reddy, Michael Jones, Tue LyHow to implement a new JITLink backend in a week - Sunho KimPanels (some speakers still to be announced):Machine Learning Guided Optimizations (MLGO) in LLVMStatic Analysis in Clang - Gabor Horvath, Artem Dergachev, Bruno Cardoso LopesHigh-level IRs for a C/C++ Optimizing Compiler - Bruno Lopes, Ivan Baev, Johannes Doerfert, Mehdi AminiPanel discussion on “Best practices with toolchain release and maintenance” - Aditya KumarStudent Technical Talks:Merging Similar Control-Flow Regions in LLVM for Performance and Code Size Benefits - Charitha SaumyaAlive-mutate: a fuzzer that cooperates with Alive2 to find LLVM bugs - Yuyou FanEnabling Transformers to Understand Low-Level Programs - Zifan Guo, William S. MosesLAGrad: Leveraging the MLIR Ecosystem for Efficient Differentiable Programming - Mai Jacob PengScalable Loop Analysis - Vir NarulaQuick Talks:LLVM Education Initiativei - Chris Bieneman, Kit Barton, Mike EdwardsEnabling AArch64 Instrumentation Support In BOLT - Elvina YakubovaApproximating at Scale: How strtofloat in LLVM’s libc is faster - Michael JonesMIR support in llvm-reduce - Matthew ArsenaultInteractive Crashlogs in LLDB - Med Ismail Bennaniclang-extract-api: Clang support for API information generation in JSON - Zixu WangUsing modern CPU instructions to improve LLVM’s libc math library. - Tue LyChallenges Of Enabling Golang Binaries Optimization By BOLT - Vasily Leonenko, Vladislav KhmelevskyiInlining for Size - Kyungwoo Lee, Ellis Hoag, Nathan LanzaAutomatic indirect memory access instructions generation for pointer chasing patterns - Przemysław OssowskiLink-Time Attributes for LTO: Incorporating linker knowledge into the LTO recompile - Todd SniderExpecting the expected: Honoring user branch hints for code placement optimizations - Stan Kvasov, Vince Del VecchioCUDA-OMP — Or, Breaking the Vendor Lock - Johannes Doerfert, Joseph HuberThoughts on GPUs as First-Class Citizens - Johannes Doerfert, Shilei Tian, Joseph HuberBuilding an End-to-End Toolchain for Fully Homomorphic Encryption with MLIR - Alexander ViandLightning Talks:LLVM Office Hours: addressing LLVM engagement and contribution barriers - Kristof BeylsImproved Fuzzing of Backend Code Generation in LLVM - Yuyang RongInteractive Programming for LLVM TableGen - David SpickettEfficient JIT-based remote execution - Anubhab GhoshFFTc: An MLIR Dialect for Developing HPC Fast Fourier Transform Libraries - Yifei HeRecovering from Errors in Clang-Repl and Code Undo - Purva Chaudhari, Jun Zhang10 commits towards GlobalISel for PowerPC - Kai Nacke, Amy KwanNonstandard reductions with SPRAY - Jan Hueckelheim, Johannes DoerfertType Resugaring in Clang for Better Diagnostics and Beyond - Matheus IzvekovSwift Bindings for LLVM - Egor ZhdanMin-sized Function Coverage with IRPGO - Ellis Hoag, Kyungwoo LeeHigh-Performance GPU-to-CPU Transpilation and Optimization via High-Level Parallel Constructs in Polygeist/MLIR - William S. Moses, Ivan R. IvanovTools for checking and writing non-trivial DWARF programs - Chris JacksonAnalysis of RISC-V Vector Performance Using MCA Tools - Michael MaitlandOptimizing Clang with BOLT using CMake - Amir AyupovExploring OpenMP target offloading for the GraphCore architecture - Jose M Monsalve DaizPosters (more posters to be announced at a later date):Removal of Undef: Move Uninitialized Memory to Poison - John McIverOptimizing Julia’s ORC JIT - Prem ChintalapudiAn LLVM-Based Compiler for Quantum-Classical Applications - Xin-Chuan WuSpecializing Code to New Architectures via Dynamic Adaptive Recompilation - Quinn Pham, Dhanrajbir Singh HiraLLFPTrax: Tracking ill-conditioned floating-point inputs using relative error amplification in LLVM - Tanmay TirpankarLLVM continuous upstream integration and testing - Jay Azurin, Keerthana SubramaniAutomatic indirect memory access instructions generation for pointer chasing patterns - Adam PerdeuszThank you to the volunters on the Program Committee for all of their hard work and time spent reviewing proposals. A special thanks also goes out to this year’s chair - Anton Korobeynikov. Here is the complete 2022 LLVM Developers’ Meeting Program Committee:Kristof BeylsAndrey BokhankoChelsea CassanovaJohannes DoerfertFlorian HahnPetr HosekMin-Yih HsuAnton Korobeynikov (Chair)Aditya KumarHem NeemaDiego NovilloFangrui SongJ. Ryan StinnettCaroline TiceMircea TrofinRegistration closes on October 31st, so register today for the 2022 LLVM Developers’ Meeting.