P. Bozeman and B. Saphir. A Modular High Performance Implementation of the Virtual Interface Architecture. In Proceedings of the 2nd Extreme Linux Workshop, Monterey, CA, June 1999.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....If an error occurs, it is reported. Reliable reception is just like reliable delivery, except that a transfer is only successfully completed when the data have been delivered to the target memory location. VIA has several successful implementations, e.g. Myrinet VI [10] Giganet VIA [18] M VIA [8], ServerNet VIA [32] FirmVIA [4] Our experiments are made with Giganet VIA. This implementation supports VIA in hardware using its proprietary cLAN network interfaces connected through 2.5 Gbits s full duplex links. Giganet VIA does not support remote memory reads (only remote writes are ....

....large (96node) clusters. 2.3 Related Work The main contribution of this paper is to quantify the performance impact of user level communication and several messaging characteristics on cluster based servers. Previous studies of user level communication were performed either for microbenchmarks [6, 35, 27, 36, 15, 10, 8, 32] or in the context of scientific applications [28, 23, 33] This paper extends those studies to real, non scientific applications, in particular to the now very popular cluster based servers. As far as we are aware, in only one other paper [22] has the performance of a server been evaluated as a ....

[Article contains additional citation context not shown here]

P. Bozeman and B. Saphir. A Modular High Performance Implementation of the Virtual Interface Architecture. In Proceedings of the 2nd Extreme Linux Workshop, Monterey, CA, June 1999.

....DNS scheme. After a request is received by one of the nodes, the distribution algorithm described in figure 17 is executed with T = 20 connections, t = 10 connections, and K = 20 seconds. We simulate a cluster communication infrastructure comprised of a software implementation of VIA, M VIA [8], for a Gigabit Ethernet network. With this setup, each broadcast of locality or load information is implemented by multiple point to point M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, ....

....M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, including the CPU and network interface overheads. More specifically, sendinga 4 byte messageacross the network takes 19 microseconds [8]. Out of this one way latency, 8 microseconds are spent by the CPUs (4 microseconds a piece) and 10 microseconds are spent by the network interfaces (5 microsecondsa piece) involved. The network itself peaks at 1 Gbit s bandwidth and exhibits a 1 microsecond switch latency [29] All types of ....

P. Bozemana and B. Saphir. A Modular High Performance Implementation of the Virtual Interface Architecture. In Proceedings of the 2nd Extreme Linux Workshop, June 1999.

....are assigned to nodes using a round robin DNS scheme. After a request is received by one of the nodes, the L2S distribution algorithm is executed with T = 20 connections and t = 10 connections. We simulate a cluster communication infrastructure comprised of a software implementation of VIA, M VIA [6], for a Gigabit Ethernet network. With this setup, each broadcast of locality or load information is implemented by multiple point to point M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, ....

....M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, including the CPU and network interface overheads. More specifically, sendinga 4 byte messageacrossthe network takes 19 microseconds [6]. Out of this one way latency, 6 microseconds are spent by the CPUs (3 microseconds a piece) and 12 microseconds are spent by the network interfaces (6 microseconds a piece) involved. The network itself peaks at 1 Gbit s bandwidth and exhibits a 1 microsecond switch latency [21] All types of ....

P. Bozemana and B. Saphir. A Modular High Performance Implementation of the Virtual Interface Architecture. In Proceedings of the 2nd Extreme Linux Workshop, June 1999.

....DNS scheme. After a request is received by one of the nodes, the distribution algorithm described in figure 17 is executed with T = 20 connections, t = 10 connections, and K = 20 seconds. We simulate a cluster communication infrastructure comprised of a software implementation of VIA, M VIA [8], for a Gigabit Ethernet network. With this setup, each broadcast of locality or load information is implemented by multiple point to point M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, ....

....M VIA messages. Forwarding of requests is also implemented with M VIA for both L2S and the LARD server. All communication latencies are simulated faithfully, including the CPU and network interface overheads. More specifically, sendinga 4 byte messageacross the network takes 19 microseconds [8]. Out of this one way latency, 6 microseconds are spent by the CPUs (3 microseconds a piece) and 12 microseconds are spent by the network interfaces (6 microsecondsa piece) involved. The network itself peaks at 1 Gbit s bandwidth and exhibits a 1 microsecond switch latency [28] All types of ....

P. Bozemana and B. Saphir. A Modular High Performance Implementation of the Virtual Interface Architecture. In Proceedings of the 2nd Extreme Linux Workshop, June 1999.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC