IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
Minimizing communications when mapping affine loop nests onto distributed memory parallel computers has already drawn a lot of attention. This paper focuses on the next step: as i...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
A concurrent partitioner for partitioning unstructured finite element meshes on distributed memory architectures is developed. The partitioner uses an element-based partitioning st...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
This paper presents the design and implementation of a Sliding Memory Plane (SliM) Array Processor, a mesh-connected SIMD architecture. To build the array processor, we developed ...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
- Partitionability allows the creation of many physically independent subsystems, each of which retains an identical functionality as its parent network and has no communication in...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
Brewer and Kuszmaul [BK94] demonstrated how barriers and traffic interleaving can alleviate the problem of bulk-transfer performance degradation on the Thinking Machines CM-5, by ...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
We introduce dag consistency, a relaxed consistency model for distributed shared memory which is suitable for multithreaded programming. We have implemented dag consistency in sof...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
In a shared-memory multiprocessor system, it is possible that certain synchronization operations are redundant -that is, their corresponding sequencing requirements are enforced c...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
Advances in multiprocessor interconnect technologyare leading to high performance networks. However, software overheadsassociated with message passing are limiting the processors ...
IPPS
1996
IEEE
14 years 9 months ago
1996
IEEE
This paper investigates methods to locate system resources, such as expensive hardware or software modules, to provide the most effective cost / performance tradeoffs in a torus p...