SST-GPU: An Execution -Driven CUDA Kernel Scheduler and Streaming-Multiprocessor Compute Model

Technical Report · Fri Feb 22 04:00:00 EST 2019

DOI:https://doi.org/10.2172/1497416· OSTI ID:1497416

Khairy, Mahmoud ^[1]; Zhang, Mengchi ^[1]; Green, Roland ^[1]; Hammond, Simon David ^[2]; Hoekstra, Robert J. ^[2]; Rogers, Timothy ^[1]; Hughes, Clayton ^[2]

---

1. Purdue Univ., West Lafayette, IN (United States)
2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of massive amounts of data have created a space for massively parallel acceleration where the context for thousands of concurrent threads are resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. The design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. To address the need for a scalable, decentralized GPU model that can model large GPUs, chiplet-based GPUs and multi-node GPUs, this report details the first steps in integrating the open-source, execution driven GPGPU-Sim into the SST framework. The first stage of this project, creates two elements: a kernel scheduler SST element accepts work from SST CPU models and schedules it to an SM-collection element that performs cycle-by-cycle timing using SSTs Mem Hierarchy to model a flexible memory system.

• Research Organization: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• DOE Contract Number: AC04-94AL85000; NA0003525
• OSTI ID: 1497416
• Report Number(s): SAND--2019-1967; 672807
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING