PM: An Operating System Coordinated High Performance Communication Library
نویسندگان
چکیده
We have developed a new communication library, called PM, for the Myrinet gigabit LAN card, that has a dedicated processor and on-board memory to handle a communication protocol. In order to obtain high performance communication and support a multi-user environment, we have co-desgined PM, an operating system realized by a daemon process, and the run-time routine for a programming language. Several unique features, e.g., network context switching and modi ed ACK/NACK ow control algorithm have been developed for PM. The PM library has been implemented on two types of clusters: Sun Sparc station model 20/71 workstations and Intel Pentium based PCs. PM for the Suns has a speed of 20 seconds round trip for a user-level 8 bytes message and 38.6 Mbytes/second bandwidth for an 8 Kbytes message. The result of a NAS parallel benchmark shows that a Sparc 20 workstation cluster achieves almost the same performance as Cray T3D.
منابع مشابه
Overhead Analysis of Preemptive
A preemptive gang scheduler is developed and evaluated. The gang scheduler, called SCoreD , is implemented on top of a UNIX operating system and runs on workstation and PC clusters connected by Myrinet, a giga-bit class, high-performance network. To have high-performance communication at the user-level and a multiuser environment simultaneously, we propose network preemption to save and restore...
متن کاملHigh Performance Communication using a Gigabit Ethernet
A high performance communication facility, called the GigaE PM, has been designed and implemented for parallel applications on clusters of computers using a Gigabit Ethernet. The GigaE PM provides not only a reliable high bandwidth and low latency communication function, but also supports existing network protocols such as TCP/IP. In the design of the GigaE PM, it is assumed that a Gigabit Ethe...
متن کاملRobust Coordinated Design of UPFC Damping Controller and PSS Using Chaotic Optimization Algorithm
A Chaotic Optimization Algorithm (COA) based approach for the robust coordinated design of the UPFC power oscillation damping controller and the conventional power system stabilizer has been investigated in this paper. Chaotic Optimization Algorithms, which have the features of easy implementation, short execution time and robust mechanisms of escaping from local optimum, is a promising tool fo...
متن کاملOverhead Analysis of Preemptive Gang Scheduling
A preemptive gang scheduler is developed and evaluated. The gang scheduler, called SCoreD , is implemented on top of a UNIX operating system and runs on workstation and PC clusters connected by Myrinet, a giga-bit class, high-performance network. To have high-performance communication at the user-level and a multiuser environment simultaneously, we propose network preemption to save and restore...
متن کاملSensor-less Vector Control of a Novel Axial Field Flux-Switching Permanent-Magnet Motor with High-Performance Current Controller
Axial field flux switching motor with sandwiched permanent magnet (AFFSSPM) is a novel of flux switching motor. Based on the vector control method, the mathematical model of the AFFSSPM is derived and the operating performance of the AFFSSPM in the overall operating region is investigated.A novel control method for the AFFSSPM drive system, including the id =0, maximum torque per ampere, consta...
متن کامل