Home · ASPLOS 2024 · Memory Systems & Caches
Challenges and Opportunities for Systems Using CXL Memory
Emmett Witchel
- Conference
- ASPLOS 2024
- Published
- 2024
- Pages
- 2
- Citations
- 3
The authors' abstract
This is the paper's own summary, in the paper's own words. It is dense on purpose — abstracts are written to compress.
We are at the start of the technology cycle for compute express link (CXL) memory, which is a significant opportunity and challenge for architecture, operating systems, and programming languages. The 3.0 CXL specification allows multiple, physically attached hosts to dynamically share memory. We call such a configuration a CXL pod. Pods provide an intermediate hardware configuration between a network of machines, each with their private memory, and a shared memory multiprocessor with a unified memory, accessible to all machines.
The plain-English explainer is not written yet
When it is, it will replace the abstract above and walk through six questions in order: what problem the paper attacks, what people did before, why that was not good enough, what the paper's idea is, why that idea works, and what the measurements actually showed. Terms get defined the first time they appear.
Related papers on Memory Systems & Caches
- Pond: CXL-Based Memory Pooling Systems for Cloud Platforms 2023
- TPP: Transparent Page Placement for CXL-Enabled Tiered-Memory 2023
- Clio: a hardware-software co-designed disaggregated memory system 2022
- TMO: transparent memory offloading in datacenters 2022
- Randomized row-swap: mitigating Row Hammer by breaking spatial correlation between aggressor and victim rows 2022