The broadcast function MPI_Bcast() from the MPI-1.1 standard is one of the most heavily used collective operations for the message passing programming paradigm. This diploma thesis makes use of a feature called "Multicast", which is supported by several network technologies (like Ethernet or InfiniBand), to create an efficient MPI_Bcast() implementation, especially for large communicators and small-sized messages. A preceding analysis of existing real-world applications leads to an algorithm which does not only perform well for synthetical benchmarks but also even better for a wide class of parallel applications. The finally derived broadcast has been implemented for the open source MPI library "Open MPI" using IP multicast. The achieved ...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
workshop drnoc2012The delay of instructions broadcast has a significant impact on the performance of...
Abstract. We present a new, simple algorithmic idea for exploiting the potential for bidirectional c...
The broadcast function MPI_Bcast() from the MPI-1.1 standard is one of the most heavily used collect...
Many common implementations of Message Passing Inter- face (MPI) implement collective operations ove...
Many common implementations of Message Passing Inter- face (MPI) implement collective operations ove...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Broadcast Communication is among the most primitive collective capabilities of any message passing n...
The performance of collective communication operations is one of the deciding factors in the overa...
The performance of collective communication operations is one of the deciding factors in the overa...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
Multicast communication is a frequently invoked communication pattern in many parallel algorithms. A...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
workshop drnoc2012The delay of instructions broadcast has a significant impact on the performance of...
Abstract. We present a new, simple algorithmic idea for exploiting the potential for bidirectional c...
The broadcast function MPI_Bcast() from the MPI-1.1 standard is one of the most heavily used collect...
Many common implementations of Message Passing Inter- face (MPI) implement collective operations ove...
Many common implementations of Message Passing Inter- face (MPI) implement collective operations ove...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Due to the importance of collective communications in scientific parallel applications, many strateg...
Broadcast Communication is among the most primitive collective capabilities of any message passing n...
The performance of collective communication operations is one of the deciding factors in the overa...
The performance of collective communication operations is one of the deciding factors in the overa...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
Multicast communication is a frequently invoked communication pattern in many parallel algorithms. A...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
Parallel computing on clusters of workstations and personal computers has very high potential, sinc...
workshop drnoc2012The delay of instructions broadcast has a significant impact on the performance of...
Abstract. We present a new, simple algorithmic idea for exploiting the potential for bidirectional c...