Symmetric Multi Processing [SMP]
Symmetric Multi-Processing [SMP] is a computer
architecture that provides fast performance by using multiple CPUs
to run individual processes simultaneously (multiprocessing).
Unlike asymmetrical processing [in which separate specialized processors
are used for specific tasks], any idle processor can be assigned
any task. Additional CPUs can be easily added to improve performance
and handle increased loads. SMP is utilized by both:
- OS- Both UNIX and Windows NT operating systems
support SMP.
- Applications - Specific applications can benefit
from SMP if the code allows multithreading.
SMP uses a single operating system and shares common memory and
disk input/output resources. This is distinct from more advanced
'Shared Nothing' architectures, where each processing node runs
totally independently.
SMP is similar to Massively
Parallel Processing [MPP], the main difference being that in
SMP systems all the CPUs share the same memory, whereas in MPP systems,
each CPU has its own memory.
MPP systems are more difficult to program because the application
must be divided in such a way that all the executing segments can
communicate with each other.
However, MPP does not suffer from the bottleneck problems inherent
in SMP systems, which occurs when all the CPUs attempt to access
the same memory at once.
Next: Massively
Parallel Processing
Back To Top
For
The World's Leading Guide To BI Strategy, Program & Technology
Database Index | Relational
Model | Object Model | Other
Models | DBMS | Contextual
Types | Microsoft SQL | Oracle
OODBMS | Data Warehouse | Teradata
ADW | Data Mart | MS
vs Teradata | Development Platforms
| ODBC | JDBC | SMP
| MPP | SN
| Glossary
|