Machine type: RISC-based distributed-memory multi-processor.
Models: SPP-1200.
Operating system: SPP-UX, based on OSF/1 AD microkernel.
Connection structure: Ring.
Compilers: Fortran, C.
System parameters:
| Model | SPP-1200 Clock cycle |
Performance:
 | 3.7 Gflop/s
 |
Note: The and values as given above stem from an 32
processor
system (4 hypernodes, see below).
The SPP-1200 is the successor of the SPP-1000 and structurally there are no differences with this machine. The system can be seen as a logical next step of integration after the Meta Series clusters of Convex. Where the latter is a cluster of workstations that still uses external interconnection channels like Ethernet or FDDI, the SPP-1200 has its communication structure integrated. As in the Meta Series the CPUs used are HP's PA-RISC processors. Up to 8 of those can be placed in what is called a hypernode by Convex. A maximal system consists of 16 nodes, i.e., 128
Within each hypernode up to 2GB of memory can be accommodated which can be reached by the local processors via a crossbar with an aggregate bandwidth of 16 GB/s. The hypernodes in turn are connected to each other by a crossbar with an aggregate bandwidth of 4 GB/s. So, the system concept is somewhat hybrid: within a hypernode the machine is effectively a shared-memory system, while between hypernodes it is a distributed memory system. Each node supports local I/O, while external global I/O can be done at an aggregate rate of 4 GB/s.
The Exemplar programming environment complements the SPP-1200 at the software side. This environment includes a message passing programming model (PVM) and a virtual shared memory model which allows the user to have shared-memory view of the system.