Mon 19 Jun 2023 18:45 - 18:52 at Cypress 1 - SRC: Poster Session

The progress in high-performance interconnects has facilitated the feasibility of far-memory to support data-intensive workloads. However, such programs are usually developed in managed languages, which rely on the garbage collector to alleviate manual memory management efforts. The long-standing principle of the garbage collector design is object lifetime. Although it works well in a monolithic machine with the entire heap locally and cheaply accessible, it faces challenges in a far-memory setting where the heap spans multiple machines. The garbage collector, by lacking knowledge of the program semantics, can relocate frequently needed (hot) objects to far-memory, leading to excessive remote access. Our insight is that object hotness is also an important aspect in designing a garbage collector for a far-memory runtime. This extended abstract presents the ongoing work of Polar, an enhanced runtime that is hotness-aware and suitable for network-connected memory systems. In Polar, the garbage collector is designed to not only compact the local memory but also appropriately move objects to near and far memory pools based on data hotness.

Mon 19 Jun

Displayed time zone: Eastern Time (US & Canada) change

18:00 - 19:30
SRC: Poster SessionSRC at Cypress 1
18:00
7m
Poster
An Eager SMT Solver for Algebraic Data Type Queries
SRC
File Attached
18:07
7m
Poster
A Synchronization Mechanism for an Accelerator Design IR
SRC
Pai Li Cornell University, USA
Media Attached
18:15
7m
Poster
ConstraintFlow: A Declarative DSL for Certified Artificial Intelligence
SRC
Media Attached
18:22
7m
Poster
Distributions for Compositionally Differentiating Parametric Discontinuities
SRC
Jesse Michel Massachusetts Institute of Technology
Media Attached
18:30
7m
Poster
Formal Verification of a MIR-to-MIR optimisation
SRC
Media Attached
18:37
7m
Poster
Formal verification of approximate differential privacy via the characteristic function
SRC
Media Attached
18:45
7m
Poster
Leveraging Far Memory for Data-Intensive Processing: A Hotness-Segregated Heap Approach
SRC
Dat Nguyen Texas A & M University
File Attached
18:52
7m
Poster
On lightweight Hoare logic of probabilistic programs: a bound tighter than the union bound
SRC
Xingyu Xie Tsinghua University
Media Attached
19:00
7m
Poster
Prettybird: A DSL for Programmatic Font Compilation
SRC
Charles Averill University of Texas at Dallas
Media Attached
19:07
7m
Poster
Quantum Simulation using Context-Free-Language Ordered Binary Decision Diagrams
SRC
Media Attached
19:15
7m
Poster
Resource Sharing through Control-Flow Based Optimizations
SRC
Media Attached
19:22
7m
Poster
Scaling Decision-Theoretic Probabilistic Programs Through Factorization
SRC
Minsung Cho Northeastern University
Media Attached