LLMpediaThe first transparent, open encyclopedia generated by LLMs

International Conference on Parallel Architectures and Compilation Techniques

Generated by GPT-5-mini
Note: This article was automatically generated by a large language model (LLM) from purely parametric knowledge (no retrieval). It may contain inaccuracies or hallucinations. This encyclopedia is part of a research project currently under review.
Article Genealogy
Parent: ACM SIGARCH Hop 4
Expansion Funnel Raw 87 → Dedup 0 → NER 0 → Enqueued 0
1. Extracted87
2. After dedup0 (None)
3. After NER0 ()
4. Enqueued0 ()
International Conference on Parallel Architectures and Compilation Techniques
NameInternational Conference on Parallel Architectures and Compilation Techniques
AcronymPACT
DisciplineComputer architecture; Compiler construction
Established1992
FrequencyAnnual
OrganizerACM Special Interest Group on Programming Languages; IEEE Computer Society

International Conference on Parallel Architectures and Compilation Techniques is an annual scholarly meeting focusing on research at the intersection of computer architecture, compiler design, and parallel computing systems. The conference brings together researchers from institutions such as Massachusetts Institute of Technology, Stanford University, Carnegie Mellon University, University of California, Berkeley, and University of Illinois Urbana–Champaign alongside industry participants from Intel Corporation, IBM, NVIDIA, Google, and Microsoft. PACT serves as a venue for presenting advances related to multiprocessors, heterogeneous systems, and optimizing compilers for high-performance computing platforms.

History

PACT traces roots to early 1990s initiatives that linked efforts at ACM SIGARCH, IEEE Computer Society, DARPA, and research centers including Los Alamos National Laboratory and Lawrence Livermore National Laboratory. Early conferences showcased work from researchers affiliated with Bell Labs, Digital Equipment Corporation, Sun Microsystems, and universities such as Princeton University and University of Cambridge. Over time PACT evolved alongside milestones like the emergence of multicore processors, the rise of GPU computing championed by NVIDIA and researchers from University of Toronto, and the consolidation of compiler frameworks exemplified by LLVM. Notable attendees and program chairs have included scholars affiliated with ETH Zurich, University of Illinois Chicago, Columbia University, and University of Washington.

Scope and Topics

PACT covers topics spanning instruction set architecture innovations, memory hierarchy design, thread-level parallelism, and dataflow architectures, as well as compiler optimizations, just-in-time compilation techniques practiced by teams at Oracle Corporation and Adobe Systems, and runtime systems developed by groups at Facebook and Amazon Web Services. The program frequently addresses research related to accelerators from AMD, ARM Holdings, and work on domain-specific architectures inspired by projects at Google DeepMind and IBM Research. Other recurring themes include performance modeling used by researchers at University of Texas at Austin, hardware/software co-design pursued at National University of Singapore, and energy-efficient computing efforts driven by labs at Seoul National University and Tsinghua University.

Conference Organization and Sponsorship

Organizational leadership typically involves committees drawing members from ACM SIGPLAN, ACM SIGARCH, and the IEEE Technical Committee on Computer Architecture, with program chairs from institutions like Cornell University and University of California, San Diego. Sponsorship has historically come from Intel Research, Google Research, Microsoft Research, and industry consortia including OpenMP Architecture Review Board and standards bodies such as IEEE Standards Association. Local arrangements often partner with host universities such as University of Edinburgh, University of Toronto, and Technical University of Munich, with funding or exhibition booths provided by companies like ARM Ltd. and Xilinx.

Proceedings and Publication Venues

PACT proceedings have been published in venues associated with ACM Digital Library and indexed by services used by researchers at Scopus, Web of Science, and university libraries like Harvard University Library and Bodleian Libraries. Selected papers have appeared subsequently in journals such as ACM Transactions on Computer Systems, IEEE Transactions on Computers, and special issues connected to symposia at International Symposium on Computer Architecture and International Symposium on Microarchitecture. Workshop outputs linked to PACT have been archived alongside proceedings from events like USENIX Annual Technical Conference and ISC High Performance.

Notable Papers and Contributions

PACT has hosted influential work including advances in out-of-order execution and branch prediction by authors associated with Intel Corporation and DEC, speculative execution analyses connected to security disclosures similar in impact to research that prompted responses from ARM and AMD, and compiler-driven loop transformations developed by teams at Rice University and University of Illinois Urbana–Champaign. The conference showcased early results on heterogeneous computing that paralleled developments at NVIDIA and algorithmic scheduling techniques later adopted in projects at Amazon Web Services and Google Cloud Platform. Contributions from faculty at Stanford University, UC Berkeley, Princeton University, and EPFL have influenced instruction set extensions, while doctoral research presented at PACT has been cited alongside work in venues such as SIGPLAN Conference on Programming Language Design and Implementation and NeurIPS when intersecting with machine-learning compilation.

Awards and Recognition

PACT recognizes outstanding papers and distinguished service with awards often aligned with accolades from organizations like ACM and IEEE. Best paper recipients have included researchers from Carnegie Mellon University, MIT, and University of Illinois Urbana–Champaign, and awardees have gone on to receive fellowships from ACM Fellows and honors such as the IEEE Fellow grade. Conference program committee members frequently serve on rosters for other major awards and prizes administered by ACM SIGARCH, ACM SIGPLAN, and national funding agencies including National Science Foundation and European Research Council.

Category:Computer architecture conferences