Parallel Implementation of Relational Database Management Systems Operations on a Multi-Core Network-Optimized System on a Chip
نویسندگان
چکیده
In a commercial Relational Database Management System (RDBMS), sort and join are the most demanding operations and it is quite beneficial to improve the performance of external sort and external join algorithms that handle large input data sizes. This paper proposes parallel implementations of multi-threaded external sort and external hash join algorithms to accelerate IBM DB2, one of leading RDBMSs, in sort and join operations using an IBM Power Edge of Network (IBM PowerEN TM ) Peripheral Component Interconnect Express (PCIe) card. The PowerEN PCIe card is used as an accelerator, and is based on PowerEN chip that runs at 2.3 GHz. The PowerEN chip consists of sixteen embedded 64-bit PowerPC cores, and each of sixteen cores supports four hardware threads. The main advantage of using features of PowerEN TM such as multithreaded multi-core, 10 GE Ethernet interface and hardware compression and decompression coprocessor is to execute the algorithms in parallel and reduce the size of data stored externally, and hence reduces the execution time as well as the size of external storage and bandwidth
منابع مشابه
Parallel Implementation of External Sort and Join Operations on a Multi-core Network-Optimized System on a Chip
In a commercial Relational Database Management System (RDBMS), sort and join are the most demanding operations, and it is quite beneficial to improve the performance of external sort and external join algorithms that handle large input data sizes. This paper proposes parallel implementations of multithreaded external sort and external hash join algorithms to accelerate IBM DB2, one of leading R...
متن کاملPerformance evaluation of hash joins on chip multiprocessors
The join operation is computationally the most expensive operation the relational model supports. It has therefore received significant research attention and various algorithms have been proposed. Joining via hashing was introduced over two decades ago and has been shown to possess interesting properties which allow it to parallelize efficiently in parallel database systems. With the advent of...
متن کاملReliability and Performance Evaluation of Fault-aware Routing Methods for Network-on-Chip Architectures (RESEARCH NOTE)
Nowadays, faults and failures are increasing especially in complex systems such as Network-on-Chip (NoC) based Systems-on-a-Chip due to the increasing susceptibility and decreasing feature sizes. On the other hand, fault-tolerant routing algorithms have an evident effect on tolerating permanent faults and improving the reliability of a Network-on-Chip based system. This paper presents reliabili...
متن کاملOptimization Strategy of Parallel Query Processing Based on Multi-core Architecture
Chip Multi-Processor (CMP) could support more than two threads to execute simultaneously, and some executing units are owned by each core. Because threads share various resources of CMP, such as L2-Cache, among many threads, CMP system is inherently different from multiprocessors system and, CMP is also different from simultaneously multithreading (SMT). In this paper a novel and complete appro...
متن کاملNext Generation Data Warehouse Design with OLTP and OLAP Systems Sharing same Database
Online Transaction Processing (OLTP) systems have been using the traditional relational Database management system for many years. Online Analytical Processing (OLAP) system for analytical reporting is optimized to aggregate many records which involve more read operations. Hence to enhance the performance in OLAP systems various modeling options like star schema, extended star schema was implem...
متن کامل