Extra high speed matrix multiplication on the Cray-2
SIAM Journal on Scientific and Statistical Computing
Exploiting fast matrix multiplication within the level 3 BLAS
ACM Transactions on Mathematical Software (TOMS)
Using Strassen's algorithm to accelerate the solution of linear systems
The Journal of Supercomputing
Performance results for two of the NAS parallel benchmarks
Proceedings of the 1991 ACM/IEEE conference on Supercomputing
LAPACK's user's guide
The performance realities of massively parallel processors: a case study
Proceedings of the 1992 ACM/IEEE conference on Supercomputing
Massively Parallel Computation of Conservation Laws
Proceedings of the Fourth SIAM Conference on Parallel Processing for Scientific Computing
Iterative Methods for Nonsymmetric Systems on MIMD Machines
Proceedings of the Fifth SIAM Conference on Parallel Processing for Scientific Computing
Misleading performance claims in parallel computations
Proceedings of the 46th Annual Design Automation Conference
Massively parallel processing: it's déjà vu all over again
Proceedings of the 46th Annual Design Automation Conference
Scalable arbitration of partitioned bus interconnection networks in 3D-IC systems
Proceedings of the 2nd International Workshop on Network on Chip Architectures
How to measure useful, sustained performance
State of the Practice Reports
Hi-index | 0.00 |
In a previous humorous note, I outlined 12 ways in which performance figures for scientific supercomputers can be distorted. In this paper, the problem of potentially misleading performance reporting is discussed in detail. Included are some examples that have appeared in recent published scientific papers. This paper also includes some proposed guidelines for reporting performance, the adoption of which would raise the level of professionalism and reduce the level of confusion in the field of supercomputing.