A Framework for Automated and Controlled Floating-Point Accuracy Reduction in Graphics Applications on GPUs

No abstract is available for this paper.

• Publication year

  2017

• Venue

  ACM Transactions on Architecture and Code Optimization (TACO)

• Publication date

  2017-12-05

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1145/3151032
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Assessment of elevated high-sensitivity troponin T to predict different mortality risks in patients with COVID-19

  2022cited by this paper
• Pilot Register File: Energy Efficient Partitioned Register File for GPUs

  2017cited by this paper
• Concise loads and stores: The case for an asymmetric compute-memory architecture for approximation

  2016cited by this paper
• An eDRAM-Based Approximate Register File for GPUs

  2016cited by this paper
• GPU register file visualization

  2015cited by this paper
• Warped-Compression: Enabling power efficient GPUs through register compression

  2015influential reference
• FlexJava: language support for safe and modular approximate programming

  2015cited by this paper
• Chisel

  2014cited by this paper
• SAGE: Self-tuning approximation for graphics engines

  2013cited by this paper
• Quality programmable vector processors for approximate computing

  2013cited by this paper
• Abstract: Automatically Adapting Programs for Mixed-Precision Floating-Point Computation

  2013cited by this paper
• Precimonious: Tuning assistant for floating-point precision

  2013cited by this paper
• Lossless and lossy memory I/O link compression for improving performance of GPGPU workloads

  2012cited by this paper
• Power-efficient computing for compute-intensive GPGPU applications

  2012cited by this paper
• EnerJ: approximate data types for safe and general low-power computation

  2011cited by this paper
• Precision selection for energy-efficient pixel shaders

  2011cited by this paper
• Image-space horizon-based ambient occlusion

  2008cited by this paper
• Asymmetrically Banked Value-Aware Register Files

  2007cited by this paper
• Word-length optimization for differentiable nonlinear systems

  2006cited by this paper
• A small, fast and low-power register file by bit-partitioning

  2005cited by this paper
• Register Packing: Exploiting Narrow-Width Operands for Reducing Register File Pressure

  2004cited by this paper
• LLVM: a compilation framework for lifelong program analysis & transformation

  2004cited by this paper
• Image quality assessment: from error visibility to structural similarity

  2004cited by this paper
• Reducing power by optimizing the necessary precision/range of floating-point arithmetic

  2000cited by this paper
• Theory for off-specular reflection from roughened surfaces

  1967cited by this paper

• X-SA: An Efficient Configurable Systolic Array Computing Architecture for GPGPU

  2025cites this paper
• Synergistic Memory Optimisations: Precision Tuning in Heterogeneous Memory Hierarchies

  2025cites this paper
• Kernel Float: Unlocking Mixed-Precision GPU Programming

  2025cites this paper
• SeTHet - Sending Tuned numbers over DMA onto Heterogeneous clusters: an automated precision tuning story

  2024cites this paper
• The Impact of Profiling Versus Static Analysis in Precision Tuning

  2024cites this paper
• FBTuner: A Feedback-Directed Approach for Safe Mixed-Precision Tuning

  2024cites this paper
• Constrained Precision Tuning

  2022cites this paper
• L2C: Combining Lossy and Lossless Compression on Memory and I/O

  2022cites this paper
• MemSZ

  2020cites this paper
• A GPU Register File using Static Data Compression

  2020influential citation
• Tools for Reduced Precision Computation

  2020influential citation
• AVR: Reducing Memory Traffic with Approximate Value Reconstruction

  2019cites this paper
• Energy-Efficient Iterative Refinement Using Dynamic Precision

  2018influential citation