Measuring Operating System Overhead on CMT Processors

Numerous studies have shown that operating system (OS)noise is one of the reasons for significant performance degradation in clustered architectures. Although many studies examine the OS noise for high performance computing (HPC),especially in multi-processor/core systems, most of them focus on 2- o...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2008 20th International Symposium on Computer Architecture and High Performance Computing s. 133 - 140
Hlavní autoři: Radojkovic, P., Cakarevic, V., Verdu, J., Pajuelo, A., Gioiosa, R., Cazorla, F.J., Nemirovsky, M., Valero, M.
Médium: Konferenční příspěvek Publikace
Jazyk:angličtina
Vydáno: IEEE 01.10.2008
IEEE Computer Society Publications
Témata:
Application software
CMT processor
Compiladors (Programes d'ordinador)
Compilers (Computer programs)
Computer architecture
Degradation
Hardware
High performance computing
Informàtica
Linux
Multiprocessadors
Multithreading
Netra DPS
Operating System overhead
Operating systems
Simultaneous multithreading processors
Sistemes operatius
Sistemes operatius (Ordinadors)
Sun
Working environment noise
Àrees temàtiques de la UPC
ISBN:9780769534237, 0769534236
ISSN:1550-6533
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Numerous studies have shown that operating system (OS)noise is one of the reasons for significant performance degradation in clustered architectures. Although many studies examine the OS noise for high performance computing (HPC),especially in multi-processor/core systems, most of them focus on 2- or 4-core systems. In this paper, we analyze the major sources of OS noise on a massive multithreading processor, the Sun UltraSPARC T1,running Linux and Solaris. Since a real system is too complex to analyze, we compare those results with a low-overhead runtime environment: the Netra Data Plane Software Suite (Netra DPS). Our results show that the overhead introduced by the OStimer interrupt in Linux and Solaris depends on the particular core and hardware context in which the application is running. This overhead is up to 30% when the application is executed on the same hardware context of the timer interrupt handler and up to 10% when the application and the timer interrupt handler run on different contexts but on the same core.We detect no overhead when the benchmark and the timer interrupt handler run on different cores of the processor.
ISBN:9780769534237
0769534236
ISSN:1550-6533
DOI:10.1109/SBAC-PAD.2008.19