Journal ArticleThe BBN Butterfly? Parallel Processor is a commercially-available multiprocessor which uses a memory management strategy based on a segmentation of the available memory. Using all of the memory of the machine efficiently is difficult because of the need to change the memory mapping dynamically. This difficulty discourages the use of the Butterfly for applications requiring a large address space. This paper presents a scheme for using all of the Butterfly's memory with minimal impact through dynamic re-mapping of memory. Called SAR-smashing, it is appropriate for applications which require access to widely-scattered memory locations throughout a potentially large address space. The method was developed to support an OR-para...
The Kanerva Sparse Distributed Memory (SDM) is a mechanism for implementing a memory with...
Operating systems have historically had to manage only a single type of memory device. The imminent ...
New and emerging memory technologies combined with enormous growths in data collection and mining wi...
For three years, members of the Computer Science Department at the University of Rochester have used...
This work explores the tradeoffs of the memory system of a new massively parallel multiprocessor in ...
Journal ArticleThis report discusses the introductory work with implementing a parallel version of a...
Large-scale shared-memory multiprocessors such as the BBN Butterfly and IBM RP3 introduce a new leve...
The memory system is a major bottleneck in achieving high performance and energy efficiency for vari...
Conceptually, the BBN Butterfly Parallel Processor can support a model of computation based on eithe...
Large-scale shared-memory multiprocessors such as the BBN Butterfly and IBM RP3 introduce a new leve...
To design effective large-scale multiprocessors, designers need to understand the characteristics of...
Massively parallel computing holds the promise of extreme performance. The utility of these systems ...
Nonuniform memory access time (referred to as NUMA) is an important feature in the design of large s...
Multiprocessors with shared memory are considered more general and easier to program than message-pa...
File systems that allocate data contiguously often use bitmaps to represent and manage free space. I...
The Kanerva Sparse Distributed Memory (SDM) is a mechanism for implementing a memory with...
Operating systems have historically had to manage only a single type of memory device. The imminent ...
New and emerging memory technologies combined with enormous growths in data collection and mining wi...
For three years, members of the Computer Science Department at the University of Rochester have used...
This work explores the tradeoffs of the memory system of a new massively parallel multiprocessor in ...
Journal ArticleThis report discusses the introductory work with implementing a parallel version of a...
Large-scale shared-memory multiprocessors such as the BBN Butterfly and IBM RP3 introduce a new leve...
The memory system is a major bottleneck in achieving high performance and energy efficiency for vari...
Conceptually, the BBN Butterfly Parallel Processor can support a model of computation based on eithe...
Large-scale shared-memory multiprocessors such as the BBN Butterfly and IBM RP3 introduce a new leve...
To design effective large-scale multiprocessors, designers need to understand the characteristics of...
Massively parallel computing holds the promise of extreme performance. The utility of these systems ...
Nonuniform memory access time (referred to as NUMA) is an important feature in the design of large s...
Multiprocessors with shared memory are considered more general and easier to program than message-pa...
File systems that allocate data contiguously often use bitmaps to represent and manage free space. I...
The Kanerva Sparse Distributed Memory (SDM) is a mechanism for implementing a memory with...
Operating systems have historically had to manage only a single type of memory device. The imminent ...
New and emerging memory technologies combined with enormous growths in data collection and mining wi...