APPLU Class A (64x64x64) on SGi Origin 2000
APPLU Class B (102x102x102) on SGi Origin 2000
APPLU Class A (64x64x64) on Cray T3D
APPBT Class A (64x64x64) on SGi Origin 2000
APPBT Class A (64x64x64) on Cray T3D
APPSP Class A (64x64x64) on SGi Origin 2000
NAS LU, BT and SP Benchmarks
NAS LU Code
The NAS-LU code (sometimes referred to as APPLU or NPB-LU) is one of the NAS Parallel Benchmarks (NPB). The NAS-LU code is a lower-diagonal (LU) CFD application. However, it does not perform an LU factorization, but instead implements a symmetric successive over-relaxation (SSOR) numerical scheme to solve a regular-sparse, block lower and upper triangular system. The parallel code is generic and the parallel execution on a number of different platforms is achieved by transporting the code to the different platforms. Once transported, the code is compiled and linked with the appropriate version of CAPLib. The original serial code undergoes a relatively small number of changes to generate a parallel version of the code, this can be seen in the 1-D partition parallel code, the 1-D partition reduced memory parallel code , the 1-D partition overlapping communication parallel code and also for the 2-D partition parallel code.
The graphs to the
left show the
LU benchmark ran on an SGi Origin 2000 and
a Cray T3D.
On the Origin 2000, good scalabiltiy is acheived on 32 processors with more scalable 2D partitioned version showing performance comparible with that of the version created manually by the experts at NASA Ames.
On the Cray T3D,
good scalability on
256 processors is demonstrated with a
runtime 154 times faster than the
NPB2.3 LU code.
linked to the
NAS BT Code.