Analyzing Machine Learning Workloads Using a Detailed GPU Simulator
By Jonathan Lew, Deval Shah, Suchita Pati, Shaylin Cattell, Mengchi Zhang, Amruth Sandhupatla, Christopher Ng, Negar Goli, Matthew D. Sinclair, Timothy G. Rogers and 1 more. 2018
83 citations recorded by the source corpus.
Machine learning (ML) has recently emerged as an important application driving future architecture design. Traditionally, architecture research has used detailed simulators to model and measure the impact of proposed changes. However, current open-source, publicly available simulators lack support for running a full ML stack like PyTorch. High-confidence, cycle-accurate simulations are crucial for architecture research and without them, it is difficult to rapidly prototype new ideas. In this paper, we describe changes we made to GPGPU-Sim, a popular, widely used GPU simulator, to run ML applications that use cuDNN and PyTorch, two widely used frameworks for running Deep Neural Networks (DNNs). This work has the potential to enable significant microarchitectural research into GPUs for DNNs. Our results show that the modified simulator, which has been made publicly available with this paper 1Source code available at https://github.com/gpgpu-sim/gpgpu-sim_distribution (dev branch), provides execution time results within 18% of real hardware. We further use it to study other ML workloads and demonstrate how the simulator identifies opportunities for architectural optimization that prior tools are unable to provide.
Subfields: Electrical and Electronic Engineering, Hardware and Architecture
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Electrical and Electronic Engineering
In Hardware and Architecture
- Timothy G. Rogers
- Mahmoud Khairy
- G. Em Karniadakis
- Tor M. Aamodt
- Dongkun Zhang
- Zhen Li
- Xuhui Meng
- Zhesheng Shen
Citations in the corpus
- PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs (2019, background): “…cost for training DNN has been mitigated by a number of advances, including high-performance computers [3], graphics processing units (GPUs) [4], tensor processing units (TPUs) [5], and fast large-scale optimization schemes [6], i.e., adaptive moment estimation (Adam) [7] and adaptive…”
- Network intrusion detection system: A systematic study of machine learning and deep learning approaches (2020, background): “8 Both ML and DL are powerful tools in learning useful features from the network traffic and predicting the normal and abnormal activities based on the learned patterns.”
- Accel-Sim: An Extensible Simulation Framework for Validated GPU Modeling (2018, methodology): “Although recent work has augmented GPGPU-Sim [31] to enable virtual ISA execution of these libraries, the functionality only works in pre-Volta GPUs.”