PPT-GPU: Scalable GPU Performance Modeling

Journal Article · Tue Jan 01 04:00:00 EST 2019 · IEEE Computer Architecture Letters

DOI:https://doi.org/10.1109/LCA.2019.2904497· OSTI ID:1504654

Arafa, Yehia ^[1]; Badawy, Abdel Hameed A. ^[1]; Chennupati, Gopinath ^[2]; Santhi, Nandakishore ^[2]; Eidenbenz, Stephan Johannes ^[2]

---

1. New Mexico State Univ., Las Cruces, NM (United States)
2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Performance modeling is a challenging problem due to the complexities of hardware architectures. In this paper, we present PPT-GPU, a scalable and accurate simulation framework that enables GPU code developers and architects to predict the performance of applications in a fast, and accurate manner on different GPU architectures. PPT-GPU is part of the open source project, Performance Prediction Toolkit (PPT) developed at the Los Alamos National Laboratory. We extend the old GPU model in PPT that predict the runtimes of computational physics codes to offer better prediction accuracy, for which, we add models for different memory hierarchies found in GPUs and latencies for different instructions. To further show the utility of PPT-GPU, we compare our model against real GPU device(s) and the widely used cycle-accurate simulator, GPGPU-Sim using different workloads from RODINIA and Parboil benchmarks. The results indicate that the predicted performance of PPT-GPU is within a 10% error compared to the real device(s). In addition, PPT-GPU is highly scalable, where it is up to 450x faster than GPGPU-Sim with more accurate results.

• Research Organization: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: 89233218CNA000001; AC52-06NA25396
• OSTI ID: 1504654
• Report Number(s): LA-UR--18-30853
• Journal Information: IEEE Computer Architecture Letters, Journal Name: IEEE Computer Architecture Letters Journal Issue: 1 Vol. 18; ISSN 1556-6056
• Publisher: IEEE
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Computer Hardware
Computer Science