Composizione Unita' di Ricerca del Sottoprogetto NC
Responsabile UR:
Componenti UR Sottoprogetto NC:
Lavori
G. Conte, M. Mazzeo, A. Poggi, P. Rossi, M. Vignali: "Low Cost Database
for NOW," IPPS/SPDP 1999, 4th International Workshop on Embedded HPC Systems
and Applications (EHPC'99), San Juan,Puerto Rico, Aprile 1999. http://www.ce.unipr.it/research/parma2/pcnow99.ps.gz
M. Bertozzi, F. Boselli, G. Conte, M. Reggiani, "An MPI Implementation
on the Top of the Virtual Interface Architecture", Euro PVM/MPI '99, Barcelona,
Sept. 1999. Abstract: This paper describes an implementation of the LAM
MPI suite on the top of the Virtual Interface Architecture. The Virtual
Interface Architecture (VIA) is an emerging standard designed by Intel,
Microsoft, and Compaq aimed at the reduction of communication latency for
cluster of workstations or system area networks. Thanks to M-VIA, a Linux
software module that emulates VIA and provides programmers of VIA APIs,
it has been possible to develop an MPI implementation even in absence of
an hardware VIA interface. Nonetheless, the high optimization of the M-VIA
module as well as the VIA protocol simpleness permitted to reduce the latency
timewithrespect to the use of the TCP/IP protocol on Ethernet network interfaces.
A.Fava, E. Fava, M. Bertozzi "MPIPOV: a Parallel Implementation of POV-Ray
Based on MPI", Euro PVM/MPI '99, Barcelona, Sept. 1999. Abstract: The work
presents an MPI parallel implementation of Pov-Ray, a powerful public domain
ray tracing engine. The major problem in ray tracing is the large amount
of CPU time needed for theelaboration of the image. With this parallel
version it is possible to reduce the computation time or to render, with
the same elaboration time, more complex or detailed images. The program
was tested successfully on ParMa2, a low-cost cluster of personal computers
running Linux operating system. The results are compared with those obtained
with a commercial multiprocessor machine, a Silicon Graphics Onyx2 parallel
processing system based on an Origin CC-NUMA architecture.
G. Frugoli, A. Fava, E. Fava, and G. Conte, "Distributed Collision Handling
for Particle-Based Simulation", Euro PVM/MPI '99,Barcelona, Sept. 1999.
Abstract: The work is concerned with the parallel implementation of a simulator
of the dynamics of non-rigid materials. In particular, it has been realized
a distributed version of the algorithm that manages self-collisions and
collisions among different deformable objects, as this results one of the
most time-consuming parts of the original program.The implementation has
been done using the MPI message-passing library on a cluster of low-cost
personal computers running Linux as operating system. Some preliminary
tests porting the parallel code as-is on a Silicon Graphics Onyx2 shared-memory
system has been also carried out.
Schede tecniche
F. Boselli: "Analisi delle caratteristiche tecniche delle schede a doppio
processore PENTIUM II," Rapporto interno Dipartimento di Ingegneria dell'Informazione,Univ.Parma,
Settembre 1998.
D.Vignali: "ParMa2: Analisi delle prestazioni con MPI", Rapporto interno
Dipartimento di Ingegneria dell'Informazione,Univ.Parma, Settembre 1998.