Finepoints: Partitioned multithreaded MPI communication
RE Grant, MGF Dosanjh, MJ Levenhagen… - … Conference, ISC High …, 2019 - Springer
The MPI multithreading model has been historically difficult to optimize; the interface that it
provides for threads was designed as a process-level interface. This model has led to …
provides for threads was designed as a process-level interface. This model has led to …
Implementation and evaluation of MPI 4.0 partitioned communication libraries
MGF Dosanjh, A Worley, D Schafer, P Soundararajan… - Parallel Computing, 2021 - Elsevier
Partitioned point-to-point communication primitives provide a performance-oriented
mechanism to support a hybrid parallel programming model and have been included in the …
mechanism to support a hybrid parallel programming model and have been included in the …
Give MPI threading a fair chance: A study of multithreaded MPI designs
T Patinyasakdikul, D Eberius… - … Conference on Cluster …, 2019 - ieeexplore.ieee.org
The Message Passing Interface (MPI) has been one of the most prominent programming
paradigms in high-performance computing (HPC) for the past decade. Lately, with changes …
paradigms in high-performance computing (HPC) for the past decade. Lately, with changes …
Partitioned collective communication
Partitioned point-to-point communication and persistent collective communication were both
recently standardized in MPI-4.0. Each offers performance and scalability advantages over …
recently standardized in MPI-4.0. Each offers performance and scalability advantages over …
Callback-based completion notification using MPI Continuations
J Schuchart, P Samfass, C Niethammer, J Gracia… - Parallel Computing, 2021 - Elsevier
Asynchronous programming models (APM) are gaining more and more traction, allowing
applications to expose the available concurrency to a runtime system tasked with …
applications to expose the available concurrency to a runtime system tasked with …
A Dynamic Network-Native MPI Partitioned Aggregation Over InfiniBand Verbs
Modern HPC systems require efficient hybrid programming model to utilize their hardware
resources effectively. The Message Passing Interface (MPI) has accommodated next …
resources effectively. The Message Passing Interface (MPI) has accommodated next …
Fargraph+: Excavating the parallelism of graph processing workload on RDMA-based far memory system
Disaggregated architecture brings new opportunities to memory-consuming applications like
graph processing. It allows one to outspread memory access pressure from local to far …
graph processing. It allows one to outspread memory access pressure from local to far …
MPI sessions: Evaluation of an implementation in open MPI
N Hjelm, H Pritchard, SK Gutiérrez… - 2019 IEEE …, 2019 - ieeexplore.ieee.org
The recently proposed MPI Sessions extensions to the MPI standard present a new
paradigm for applications to use with MPI. MPI Sessions has the potential to address several …
paradigm for applications to use with MPI. MPI Sessions has the potential to address several …
Taking the MPI standard and the open MPI library to exascale
DE Bernholdt, G Bosilca, A Bouteiller… - … Journal of High …, 2024 - journals.sagepub.com
The Open MPI for Exascale (OMPI-X) project was one of two in the Exascale Computing
Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with …
Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with …
RaDD runtimes: Radical and different distributed runtimes with smartnics
As network speeds increase, the overhead of processing incoming messages is becoming
onerous enough that many manufacturers now provide network interface cards (NICs) with …
onerous enough that many manufacturers now provide network interface cards (NICs) with …