Abstract
PRISM is a distributed shared memory architecture that relies on a tightly integrated hardware and operating system design for scalable and reliable performance. PRISM's hardware provides mechanisms for flexible management and dynamic configuration of shared memory pages with different behaviors. Its operating system is structured as multiple independent kernels, where each kernel manages the resources on its local node. The system structure minimizes the amount of global coordination when managing shared memory. The structure also provides natural fault containment boundaries around each node because physical addresses do not address remote memory directly.
Original language | English (US) |
---|---|
Pages | 140-151 |
Number of pages | 12 |
State | Published - 1998 |
Externally published | Yes |
Event | Proceedings of the 1998 4th International Symposium on High-Performance Computer Architecture, HPCA - Las Vegas, NV, USA Duration: Jan 31 1998 → Feb 4 1998 |
Other
Other | Proceedings of the 1998 4th International Symposium on High-Performance Computer Architecture, HPCA |
---|---|
City | Las Vegas, NV, USA |
Period | 1/31/98 → 2/4/98 |
ASJC Scopus subject areas
- Hardware and Architecture