TaskTorrent: a Lightweight Distributed Task-Based Runtime System in C++

09/22/2020
by   Léopold Cambier, et al.
0

We present TaskTorrent, a lightweight distributed task-based runtime in C++. TaskTorrent uses a parametrized task graph to express the task DAG, and one-sided active messages to trigger remote tasks asynchronously. As a result the task DAG is completely distributed and discovered in parallel. It is a C++14 library and only depends on MPI. We explain the API and the implementation. We perform a series of benchmarks against StarPU and ScaLAPACK. Micro benchmarks show it has a minimal overhead compared to other solutions. We then apply it to two large linear algebra problems. TaskTorrent scales very well to thousands of cores, exhibiting good weak and strong scalings.

READ FULL TEXT
research
07/21/2022

Quantifying Overheads in Charm++ and HPX using Task Bench

Asynchronous Many-Task (AMT) runtime systems take advantage of multi-cor...
research
12/12/2022

Collective Vector Clocks: Low-Overhead Transparent Checkpointing for MPI

MPI is the de facto standard for parallel computation on a cluster of co...
research
01/10/2019

Integrating Blocking and Non-Blocking MPI Primitives with Task-Based Programming Models

In this paper we present the Task-Aware MPI library (TAMPI) that integra...
research
07/27/2016

System-level Scalable Checkpoint-Restart for Petascale Computing

Fault tolerance for the upcoming exascale generation has long been an ar...
research
09/07/2020

Asynchronous Runtime with Distributed Manager for Task-based Programming Models

Parallel task-based programming models, like OpenMP, allow application d...
research
06/24/2019

Heterogeneous Active Messages (HAM) – Implementing Lightweight Remote Procedure Calls in C++

We present HAM (Heterogeneous Active Messages), a C++-only active messag...
research
10/21/2020

Runtime vs Scheduler: Analyzing Dask's Overheads

Dask is a distributed task framework which is commonly used by data scie...

Please sign up or login with your details

Forgot password? Click here to reset