6 papers
Implementing True MPI Sessions and Evaluating MPI Initialization Scalability
Hui Zhou, Kenneth Raffenetti, Yanfei Guo +2
Sessions is one of the major features introduced in the MPI-4 standard. It offers an alternative to the traditional world communicator model by allowing applications to construct c…
FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access
Aditya Tanikanti, Benoit Côté, Yanfei Guo +9
We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FI…
ZCCL: Significantly Improving Collective Communication With Error-Bounded Lossy Compression
Jiajun Huang, Sheng Di, Xiaodong Yu +12
With the ever-increasing computing power of supercomputers and the growing scale of scientific applications, the efficiency of MPI collective communication turns out to be a critic…
LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators
Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale +6
Large Language Models (LLMs) have propelled groundbreaking advancements across several domains and are commonly used for text generation applications. However, the computational de…
MPI Progress For All
Hui Zhou, Robert Latham, Ken Raffenetti +2
The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective com…
gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters
Jiajun Huang, Sheng Di, Xiaodong Yu +11
GPU-aware collective communication has become a major bottleneck for modern computing platforms as GPU computing power rapidly rises. A traditional approach is to directly integrat…