BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143039Z
LOCATION:B310
DTSTART;TZID=America/New_York:20241118T090000
DTEND;TZID=America/New_York:20241118T173000
UID:submissions.supercomputing.org_SC24_sess754@linklings.com
SUMMARY:LLVM-HPC2024: The Tenth Workshop on the LLVM Compiler Infrastructu
 re in HPC
DESCRIPTION:LLVM, winner of the 2012 ACM Software System Award, has become
  an integral part of the software development ecosystem for optimizing com
 pilers, dynamic language execution engines, source code analysis and trans
 formation tools, debuggers, linking, and a whole host of programming langu
 age and toolchain-related components. The recent surge in AI development h
 as further proven the efficacy of the LLVM infrastructure as many predomin
 ant AI/ML compilation systems deployed in practice leverage the MLIR frame
 work to exploit high-level semantics provided by their frontends, while ma
 intaining a production grade and high-performance software stack. Research
  in, and implementation of, program analysis, compilation, optimization an
 d profiling have clearly benefited from the availability of a high-quality
 , freely available infrastructure on which to build. This workshop will fo
 cus on recent developments, from both academia and industry, that build on
  the LLVM ecosystem to advance the state-of-the-art in high-performance co
 mputing.\n\nLLVM — Lunch Break\n---------------------\nLLVM — Morning Brea
 k\n---------------------\nWelcome\n\nHal Finkel (DOE Office of Advanced Sc
 ientific Computing Research)\n---------------------\nParallel Runtime Inte
 rface for Fortran (PRIF): A Multi-Image Solution for LLVM Flang\n\nFortran
  compilers that provide support for Fortran's native parallel features oft
 en do so with a runtime library that depends on details of both the compil
 er implementation and the communication library, while others provide limi
 ted or no support at all. This paper introduces a new generalized inter...
 \n\n\nDan Bonachea and Katherine Rasmussen (Lawrence Berkeley National Lab
 oratory (LBNL)), Brad Richardson (NERSC at LBNL (Lawrence Berkeley Nationa
 l Laboratory)), and Damian Rouson (Lawrence Berkeley National Laboratory (
 LBNL))\n---------------------\nIntroducing ClangIR: An MLIR-Based High-Lev
 el IR for the C/C++ Family of Languages\n\nThe rapid pace of hardware inno
 vation and the quest for performance in HPC workloads demand that compiler
 s deliver their best. To support this effort, we introduce ClangIR (CIR), 
 a new intermediate representation (IR) for Clang that captures higher-leve
 l semantics for C, C++, and extensions. ClangIR...\n\n\nBruno Cardoso Lope
 s (Meta)\n---------------------\nThe Mojo Approach to Performance Programm
 ing\n\nAchieving performance generality for workloads across a wide variet
 y of hardware is not a solved problem. With Mojo, we have attempted and pr
 oven at least one viable approach that combines compiler and programming l
 anguage design to enable expert programmers to productively and consistent
 ly achieve ...\n\n\nJeff Niu (Modular)\n---------------------\nEvaluating 
 Tuning Opportunities of the LLVM/OpenMP Runtime\n\nTuning parallel applica
 tions on multi-core architectures is an arduous task. Several studies have
  utilized auto-tuning for OpenMP applications via standardized user-facing
  features, namely number of threads, thread placement and binding policy. 
 In this paper, we analyze OpenMP application runtime th...\n\n\nSmeet Chhe
 da, Gaurav Verma, Shilei Tian, and Barbara Chapman (Stony Brook University
 ) and Johannes Doerfert (Lawrence Livermore National Laboratory (LLNL))\n-
 --------------------\nFully integrating the Flang Fortran compiler with st
 andard MLIR\n\nFortran is the lingua franca of HPC code development and as
  such it is crucial that we as a community have open source Fortran compil
 ers capable of generating high performance executables. Flang is LLVM's Fo
 rtran compiler and leverages MLIR which is a reusable compiler infrastruct
 ure which, as part ...\n\n\nNick Brown (Edinburgh Parallel Computing Centr
 e (EPCC); University of Edinburgh, Scotland)\n---------------------\nThe P
 ath to IFX - Building a Fortran Compiler in LLVM\n\nRon Green (Intel Corpo
 ration)\n---------------------\nLLVM — Afternoon Break\n------------------
 ---\nPragma driven shared memory parallelism in Zig by supporting OpenMP l
 oop directives\n\nThe Zig programming language, which is designed to provi
 de performance and safety as first class concerns, has become popular in r
 ecent years. Given that Zig is built upon LLVM, and-so enjoys many of the 
 benefits provided by the ecosystem, including access to a rich set of back
 ends, Zig has signific...\n\n\nDavid Kacs (EPCC, The University of Edinbur
 gh); Nick Brown (Edinburgh Parallel Computing Centre (EPCC); University of
  Edinburgh, Scotland); and Joseph Lee and Justs Zarins (Edinburgh Parallel
  Computing Centre (EPCC))\n---------------------\nA Flang Plugin for Fortr
 an Feature Characterization\n\nAs new compute systems are developed, there
  is still a need to compile Fortran for execution on  leading edge systems
 .\nIn order to achieve this, compilers are continuously under development.
 \nThough the specification of Fortran is extensive, it is helpful to prior
 itize the development of key features...\n\n\nAnthony Cabrera (Oak Ridge N
 ational Laboratory (ORNL), Washington University in Saint Louis) and David
  Bernholdt (Oak Ridge National Laboratory (ORNL))\n---------------------\n
 Panel Discussion\n\nJohannes Doerfert (Lawrence Livermore National Laborat
 ory (LLNL)), Bruno Cardoso Lopes (Meta), William Moses (University of Illi
 nois Urbana-Champaign), and Jeff Hammond (NVIDIA Corporation)\n\nTag: Comp
 ilers, Parallel Programming Methods, Models, Languages and Environments, P
 erformance Optimization\n\nRegistration Category: Workshop Reg Pass\n\nSes
 sion Chairs: James Brodman (AMD); Johannes de Fine Licht (NextSilicon Inc,
  ETH Zürich); Ryan Kabrick (Tactical Computing Laboratories LLC, Universit
 y of Delaware); and Alexis Perry-Holby (Los Alamos National Laboratory (LA
 NL))
END:VEVENT
END:VCALENDAR