3321 search results - page 512 / 665 » Performance of parallel computations with dynamic processor ... |
119
Voted
IPPS
2000
IEEE
15 years 8 months ago
2000
IEEE
In this paper, we propose a novel hardware caching technique, called switch directory, to reduce the communication latency in CC-NUMA multiprocessors. The main idea is to implemen...
142
click to vote
HPCA
1998
IEEE
15 years 8 months ago
1998
IEEE
The goal of this paper is to gain insight into the relative performance of communication mechanisms as bisection bandwidth and network latency vary. We compare shared memory with ...
143
click to vote
ICS
2009
Tsinghua U.
15 years 1 months ago
2009
Tsinghua U.
Modern processors require highly accurate branch prediction for good performance. As such, a number of branch predictors have been proposed with varying size and complexity. This ...
123
click to vote
ICS
2004
Tsinghua U.
15 years 9 months ago
2004
Tsinghua U.
In contemporary out-of-order superscalar design, high IPC is mainly achieved by exposing high instruction level parallelism (ILP). Scaling issue window size can certainly provide ...
134
click to vote
PVM
1998
Springer
15 years 8 months ago
1998
Springer
Abstract. SKaMPI is a benchmark for MPI implementations. Its purpose is the detailed analysis of the runtime of individual MPI operations and comparison of these for di erent imple...