Gillespie’s Stochastic Simulation Algorithm on MIC coprocessors

To investigate the behavior of biochemical systems, many runs of Gillespie’s Stochastic Simulation Algorithm (SSA) are generally needed, causing excessive computational costs on Central Processing Units (CPUs). Since all SSA runs are independent, the Intel Xeon Phi coprocessors based on the Many Int...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Journal of supercomputing Ročník 73; číslo 2; s. 676 - 686
Hlavní autoři: Tangherloni, Andrea, Nobile, Marco S., Cazzaniga, Paolo, Besozzi, Daniela, Mauri, Giancarlo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.02.2017
Springer Nature B.V
Témata:
Central processing units
Compilers
Computer Science
Computer simulation
Coprocessors
CPUs
Graphics processing units
Interpreters
Processor Architectures
Programming Languages
Redesign
Stochastic Simulation Algorithm
High-Performance Computing
Parallel computing
Stochastic modeling
GPU
MIC
ISSN:0920-8542, 1573-0484
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To investigate the behavior of biochemical systems, many runs of Gillespie’s Stochastic Simulation Algorithm (SSA) are generally needed, causing excessive computational costs on Central Processing Units (CPUs). Since all SSA runs are independent, the Intel Xeon Phi coprocessors based on the Many Integrated Core (MIC) architecture can be exploited to distribute the workload. We considered two execution modalities on MIC: one consisted in running exactly the same CPU code of SSA, while the other exploited MIC’s vector instructions to reuse the CPU code with only few modifications. MIC performance was compared with Graphics Processing Units (GPUs), specifically implemented in CUDA to optimize the use of memory hierarchy. Our results show that GPU largely outperforms MIC and CPU, but required a complete redesign of SSA. MIC allows a relevant speedup, especially when vector instructions are used, with the additional advantage of requiring minimal modifications to CPU code.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-016-1778-8