What is it about?
GPM enables GPUs to use persistent memory, offering both speed and reliability. It allows GPU programs to directly store and retrieve data safely, even after crashes, without relying on the CPU, benefiting applications like databases and large computations.
Featured Image
Photo by Andrey Matveev on Unsplash
Why is it important?
This is the first paper to combine GPU parallelism and NVM persistence using real hardware to benefit applications that rely on both.
Read the Original
This page is a summary of: GPM: leveraging persistent memory from a GPU, February 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3503222.3507758.
You can read the full text:
Contributors
The following have contributed to this page
