Velociraptor: a compiler toolkit for array-based languages targeting CPUs and GPUs

Garg, Rahul; Jagdale, Sameer; Hendren, Laurie

doi:10.1145/2774959.2774967

Cited by 8 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For JVM-based languages, many approaches (Leung et al 2009, Dubach et al 2012, Hayashi et al 2013 provide high-level abstractions of GPU programming. Velociraptor (Garg & Hendren 2014) compiles MATLAB and Python to GPUs.…”

Section: Compiling High-level/directive-based Languages To Gpusmentioning

confidence: 99%

Performance evaluation of OpenMP's target construct on GPUs - exploring compiler optimisations

Hayashi

Shirako

Tiotto

et al. 2019

IJHPCN

View full text Add to dashboard Cite

OpenMP is a directive-based shared memory parallel programming model and has been widely used for many years. From OpenMP 4.0 onwards, GPU platforms are supported by extending OpenMP's high-level parallel abstractions with accelerator programming. This extension allows programmers to write GPU programs in standard C/C++ or Fortran languages, without exposing too many details of GPU architectures. However, such high-level programming models generally impose additional program optimizations on compilers and runtime systems. Otherwise, OpenMP programs could be slower than fully hand-tuned and even naive implementations with low-level programming models like CUDA. To study potential performance improvements by compiling and optimizing high-level programs for GPU execution, in this paper, we 1) evaluate a set of OpenMP benchmarks on two NVIDIA Tesla GPUs (K80 and P100) and 2) conduct a comparable performance analysis among handwritten CUDA and automatically-generated GPU programs by the IBM XL and clang/LLVM compilers.

show abstract

Section: Compiling High-level/directive-based Languages To Gpusmentioning

confidence: 99%

Performance evaluation of OpenMP's target construct on GPUs - exploring compiler optimisations

Hayashi

Shirako

Tiotto

et al. 2019

IJHPCN

View full text Add to dashboard Cite

show abstract

“…Our second contribution is that we have implemented our shape inference infrastructure in the Velociraptor toolkit [6]. Velociraptor is a reusable toolkit that can be used for implementing compilers for array-based languages targeting both CPUs and GPUs.…”

Section: Reusable Implementation Demonstrated For Two Languagesmentioning

confidence: 99%

“…Instead, it is a toolkit that can be embedded in different compiler infrastructures . More details about the the Velociraptor toolkit can be found in a technical report [6].…”

Section: Velociraptor Overviewmentioning

confidence: 99%

Just-in-time shape inference for array-based languages

Garg

Hendren

2014

Proceedings of ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming

Self Cite

View full text Add to dashboard Cite

In dynamic array-based languages, the most computationally intensive parts of the program often involve either explicit loops or vector operations. These loops and vector operations can be better optimized if the compiler has accurate information about array shapes and loop-bounds. However, accurate shape information about loops and arrays may not be known until runtime. We present a method of performing shape inference in a just-in-time compiler by using information obtained at runtime. We have implemented our method in a compiler toolkit for array-based languages that is integrated into two different compilers: a prototype compiler for Python, and McVM, a virtual machine for MATLAB. We present results obtained from these two compiler integrations on a variety of benchmarks to evaluate the accuracy of shape inference of our method and the runtime overhead of our implementation.

show abstract

“…High-performance compilation for GPUs, by now, is hardly a new topic, and many different approaches have been used, including ones using OpenMP-style directives [14,17], ones that are fully automatic [27], ones based on functional languages [23], and ones based on the polyhedral model [26]. Other ones define an automatic, array computation middleware [11] designed as a back-end for multiple languages, including Python. Automatic, GPU-targeted compilers for languages embedded in Python also abound [4,6,20], most of which transform a Python AST at runPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.…”

Section: Introductionmentioning

confidence: 99%

Loo.py: from fortran to performance via transformation and substitution rules

Klöckner

2015

Proceedings of the 2nd ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming

View full text Add to dashboard Cite

A large amount of numerically-oriented code is written and is being written in legacy languages. Much of this code could, in principle, make good use of data-parallel throughput-oriented computer architectures. Loo.py, a transformation-based programming system targeted at GPUs and general data-parallel architectures, provides a mechanism for user-controlled transformation of array programs. This transformation capability is designed to not just apply to programs written specifically for Loo.py, but also those imported from other languages such as Fortran. It eases the trade-off between achieving high performance, portability, and programmability by allowing the user to apply a large and growing family of transformations to an input program. These transformations are expressed in and used from Python and may be applied from a variety of settings, including a pragma-like manner from other languages.

show abstract

Velociraptor: a compiler toolkit for array-based languages targeting CPUs and GPUs

Cited by 8 publications

References 9 publications

Performance evaluation of OpenMP's target construct on GPUs - exploring compiler optimisations

Performance evaluation of OpenMP's target construct on GPUs - exploring compiler optimisations

Just-in-time shape inference for array-based languages

Loo.py: from fortran to performance via transformation and substitution rules

Contact Info

Product

Resources

About