Compound Memory Models for Heterogeneous Processors
Offered By: ACM SIGPLAN via YouTube
Course Description
Overview
Explore a 16-minute video presentation from the PLDI 2023 conference that delves into Compound Memory Models. Learn how researchers address the challenge of defining memory consistency models for heterogeneous processors with shared memory interfaces. Discover the formalization of 'compound' memory models through a compositional operational approach, focusing on the x86TSO/PTX compound model. Understand the implications for compiler mappings from language-based memory models and the retention of existing proven mappings for individual devices. Gain insights into the complexities of memory consistency in modern heterogeneous computing environments, including CPUs, GPUs, and other accelerators. Access supplementary materials, including the full article, archive, and web page for further exploration of this cutting-edge research in computer architecture and programming languages.
Syllabus
[PLDI'23] Compound Memory Models
Taught by
ACM SIGPLAN
Related Courses
Future of Computing - IBM Power 9 and beyondopenHPI SIGCOMM 2020 - Reducto - On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
Association for Computing Machinery (ACM) via YouTube Offload Annotations - Bringing Heterogeneous Computing to Existing Libraries and Workloads
USENIX via YouTube Supercomputing Spotlights - Supercomputing Software for Moore and Beyond
Society for Industrial and Applied Mathematics via YouTube Liquid Metal - Taming Heterogeneity
GOTO Conferences via YouTube