• Home
  • Search
  • Designing a Tunable Nested Data-Parallel Programming System
  • Cite Icon2
  • https://doi.org/10.1145/3012011Copy DOI Icon

Designing a Tunable Nested Data-Parallel Programming System

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This article describes Surge, a nested data-parallel programming system designed to simplify the porting and tuning of parallel applications to multiple target architectures. Surge decouples high-level specification of computations, expressed using a C++ programming interface, from low-level implementation details using two first-class constructs: schedules and policies. Schedules describe the valid ways in which data-parallel operators may be implemented, while policies encapsulate a set of parameters that govern platform-specific code generation. These two mechanisms are used to implement a code generation system that analyzes computations and automatically generates a search space of valid platform-specific implementations. An input and architecture-adaptive autotuning system then explores this search space to find optimized implementations. We express in Surge five real-world benchmarks from domains such as machine learning and sparse linear algebra and from the high-level specifications, Surge automatically generates CPU and GPU implementations that perform on par with or better than manually optimized versions.

Similar Papers
  • PDF
  • Research Article
  • Citations4

Formalizing and testing the consistency of DSL transformations

  • Mar 15, 2016
  • Formal Aspects of Computing
  • Sarmen Keshishzadeh +1
  • Conference Article
  • Citations28

Evaluating Machine LearningWorkloads on Memory-Centric Computing Systems

  • Apr 01, 2023
  • Juan Gómez-Luna +7
  • Research Article
  • Citations2

AI-ASSISTED CODE GENERATION AND OPTIMIZATION: LEVERAGING MACHINE LEARNING TO ENHANCE SOFTWARE DEVELOPMENT PROCESSES

  • Sep 30, 2020
  • International Journal of Innovations in Engineering Research and Technology
  • Swamy Prasadarao Velaga
  • Research Article
  • Citations20

DPU: DAG Processing Unit for Irregular Graphs With Precision-Scalable Posit Arithmetic in 28 nm

  • Aug 01, 2022
  • IEEE Journal of Solid-State Circuits
  • Nimish Shah +4
  • Book Chapter
  • Citations2

Formalizing DSL Semantics for Reasoning and Conformance Testing

  • Jan 01, 2014
  • Sarmen Keshishzadeh +1
  • Research Article
  • Citations4

An Analysis of Deductive-Query Processing Approaches for Logic Macroprograms in Wireless Sensor Networks

  • Jul 05, 2012
  • Engineering Journal
  • Supasate Choochaisri +1
  • Book Chapter

Basics of Machine Learning in Architecture

  • Jan 01, 2021
  • Synthesis lectures on computer architecture
  • Lizhong Chen +2
  • Research Article

Efficient Online Processing for Advanced Analytics

  • Jan 01, 2017
  • Infoscience (Ecole Polytechnique Fédérale de Lausanne)
  • El Seidy +1
  • Research Article

Dynamic Operator Optimization for Efficient Multi-Tenant LoRA Model Serving

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Changhai Zhou +4
  • Research Article
  • Citations57

A Model-Driven Development Approach to Mapping UML State Diagrams to Synthesizable VHDL

  • Oct 01, 2008
  • IEEE Transactions on Computers
  • Steve K Wood +4
  • Research Article

Parallel Implementation of K-Best Quadrature Amplitude Modulation Detection for Massive Multiple Input Multiple Output Systems

  • Jul 15, 2024
  • Electronics
  • Bhargav Gokalgandhi +4
  • Conference Article
  • Citations3

Jigsaw: A Slice-and-Dice Approach to Non-uniform FFT Acceleration for MRI Image Reconstruction

  • May 01, 2021
  • Brendan L West +2
  • PDF
  • Research Article
  • Citations13

Code Generation by Example Using Symbolic Machine Learning

  • Jan 17, 2023
  • SN Computer Science
  • Kevin Lano +1
  • Conference Article
  • Citations32

Accelerating compressive sensing reconstruction OMP algorithm with CPU, GPU, FPGA and domain specific many-core

  • May 01, 2015
  • Amey Kulkarni +1
  • Conference Article
  • Citations18

Abstractions for Practical Virtual Machine Replay

  • Mar 25, 2016
  • Anton Burtsev +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.