Software

MacSim

MacSim is a cycle-level, heterogeneous architecture simulator for x86, ARM, NVIDIA PTX, and Intel GPU instructions. The simulator project has been supported by Intel, NSF, and Sandia National Lab

Recent News

Intel GPU simulator is publicly available! Check out the simulator HERE. Please refer to the following paper Performance Characterisation and Simulation of Intel’s Integrated GPU Architecture (ISPASS’18) for more detailed information.

Stay tuned! We are preparing to release Intel GPU traces of various workloads from Intel OpenCL samples and Rodinia benchmark suites.

Resources

Tutorials at HPCA’12 and ISCA’12

We’ve developed a power model for GPU architecture using McPAT. Please refer to the following paper for more detailed information. Power Modeling for GPU Architecture using McPAT (TODAES’14)

We’ve characterised the performance of Intel’s integrated GPUs using MacSim. Please refer to the following paper for more detailed information. Performance Characterisation and Simulation of Intel’s Integrated GPU Architecture (ISPASS’18)

If you are interested in the MacSim simulator, send an email to macsim-dev@googlegroups.com


GraphBig

GraphBIG is a comprehensive graph benchmark suite. By supporting a wide selection of workloads from both CPU and GPU sides, GraphBIG covers the broad spectrum of graph computing.

Resources

Publication at SC’15:

GraphBIG: Understanding Graph Computing in the Context of Industrial Solutions


Vortex

Vortex is an open source Hardware and Software project to support GPGPU based on RISC-V ISA extensions. Currently, Vortex supports OpenCL and it runs on FPGA. The vortex platform is highly customizable and scalable with a complete open source compiler, driver and runtime software stack to enable research in GPU architectures.

Resources

Publication at MICRO’21:

Vortex: Extending the RISC-V ISA for GPGPU and 3D-Graphics Research

Vortex Homepage


CuPBoP

CuPBoP is a framework which support executing unmodified CUDA source code on non-NVIDIA devices. Currently, CuPBoP support serveral CPU backends, including x86, AArch64, and RISC-V. Supporting Vortex (a RISC-V GPU) is working in progress.

Resources

Publication at PPoPP’23:

CuPBoP: A Framework to Make CUDA Portable