GPU Triggered Networking for Intra-Kernel Communications
SessionGPUs and Communication
Authors
Event Type
Paper
TimeWednesday, November 15th10:30am -
11am
Location402-403-404
DescriptionGPUs are widespread across clusters of compute nodes
due to their attractive performance for data parallel
codes. However, communicating between GPUs across the
cluster is cumbersome when compared to CPU networking
implementations. A number of recent works have enabled
GPUs to more naturally access the network, but suffer
from performance problems, require hidden CPU helper
threads, or restrict communications to kernel
boundaries.
In this paper, we propose GPU Triggered Networking, a novel, GPU-centric networking approach which leverages the best of CPUs and GPUs. In this model, CPUs create and stage network messages and GPUs trigger the network interface when data is ready to send. GPU Triggered Networking decouples these two operations, thereby removing the CPU from the critical path. We illustrate how this approach can provide up to 25% speedup compared to standard GPU networking across microbenchmarks, a Jacobi stencil, an important MPI collective operation, and machine-learning workloads.
In this paper, we propose GPU Triggered Networking, a novel, GPU-centric networking approach which leverages the best of CPUs and GPUs. In this model, CPUs create and stage network messages and GPUs trigger the network interface when data is ready to send. GPU Triggered Networking decouples these two operations, thereby removing the CPU from the critical path. We illustrate how this approach can provide up to 25% speedup compared to standard GPU networking across microbenchmarks, a Jacobi stencil, an important MPI collective operation, and machine-learning workloads.
Download PDF:
here
