MGSim + MGMark: A Framework for Multi-GPU System Research

by   Yifan Sun, et al.

The rapidly growing popularity and scale of data-parallel workloads demand a corresponding increase in raw computational power of GPUs (Graphics Processing Units). As single-GPU systems struggle to satisfy the performance demands, multi-GPU systems have begun to dominate the high-performance computing world. The advent of such systems raises a number of design challenges, including the GPU microarchitecture, multi-GPU interconnect fabrics, runtime libraries and associated programming models. The research community currently lacks a publically available and comprehensive multi-GPU simulation framework and benchmark suite to evaluate multi-GPU system design solutions. In this work, we present MGSim, a cycle-accurate, extensively validated, multi-GPU simulator, based on AMD's Graphics Core Next 3 (GCN3) instruction set architecture. We complement MGSim with MGMark, a suite of multi-GPU workloads that explores multi-GPU collaborative execution patterns. Our simulator is scalable and comes with in-built support for multi-threaded execution to enable fast and efficient simulations. In terms of performance accuracy, MGSim differs 5.5% on average when compared against actual GPU hardware. We also achieve a 3.5× and a 2.5× average speedup in function emulation and architectural simulation with 4 CPU cores, while delivering the same accuracy as the serial simulation. We illustrate the novel simulation capabilities provided by our simulator through a case study exploring programming models based on a unified multi-GPU system (U-MGPU) and a discrete multi-GPU system (D-MGPU) that both utilize unified memory space and cross-GPU memory access. We evaluate the design implications from our case study, suggesting that D-MGPU is an attractive programming model for future multi-GPU systems.


Modeling Deep Learning Accelerator Enabled GPUs

The efficacy of deep learning has resulted in its use in a growing numbe...

Descend: A Safe GPU Systems Programming Language

Graphics Processing Units (GPU) offer tremendous computational power by ...

Exploring Modern GPU Memory System Design Challenges through Accurate Modeling

This paper explores the impact of simulator accuracy on architecture des...

Daisen: A Framework for Visualizing Detailed GPU Execution

Graphics Processing Units (GPUs) have been widely used to accelerate art...

ScaleSimulator: A Fast and Cycle-Accurate Parallel Simulator for Architectural Exploration

Design of next generation computer systems should be supported by simula...

SimNet: Computer Architecture Simulation using Machine Learning

While cycle-accurate simulators are essential tools for architecture res...

CUDAMPF++: A Proactive Resource Exhaustion Scheme for Accelerating Homologous Sequence Search on CUDA-enabled GPU

Genomic sequence alignment is an important research topic in bioinformat...

Please sign up or login with your details

Forgot password? Click here to reset