Extended precision

hgpu.org » Extended precision

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Shaobo Ma, Chao Fang, Haikuo Shao, Zhongfeng Wang

View

Tags: Computer science, CUDA, Data recovery, Extended precision, LLM, Matrix multiplication, nVidia, nVidia GeForce RTX 3090, Security

October 6, 2024 by hgpu

Double-Precision Floating-Point Data Visualizations Using Vulkan API

Nezihe Sözen

View

Download (PDF)

Source codes

Tags: Computer science, Extended precision, GLSL, nVidia, nVidia GeForce RTX 3090, Package, Rendering, Visualization, Vulkan

August 25, 2024 by hgpu

Accelerating 128-bit Floating-Point Matrix Multiplication on FPGAs

Fumiya Kono, Naohito Nakasato, Maho Nakata

View

Download (PDF)

Tags: Benchmarking, Computer science, Extended precision, FPGA, Matrix multiplication, OpenCL

June 11, 2023 by hgpu

Solver for Systems of Linear Equations with Infinite Precision on a GPU Cluster

Jiri Khun

View

Download (PDF)

Tags: AMD Radeon HD 8750 M, ATI, Computer science, Extended precision, GPU cluster, Linear Algebra, Modular arithmetic, MPI, OpenCL

June 2, 2016 by hgpu

Arbitrary-Precision Arithmetics on the GPU

Bernhard Langer

View

Download (PDF)

Tags: Computer science, CUDA, Extended precision, nVidia, nVidia Quadro K 2100 M

April 17, 2015 by hgpu

Accelerating Polynomial Homotopy Continuation on a Graphics Processing Unit with Double Double and Quad Double Arithmetic

Jan Verschelde, Xiangcheng Yu

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Extended precision, Linear Algebra, Mathematical Software, Numerical Analysis, nVidia, Package, Tesla K20

January 28, 2015 by hgpu

Towards fast and certified multiple-precision libraries

Valentina Popescu

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Extended precision, nVidia, Tesla C2075, Thesis

July 26, 2014 by hgpu

GPU vs FPGA: A Comparative Analysis for Non-standard Precision

Umar Ibrahim Minhas, Samuel Bayliss, George A. Constantinides

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Extended precision, FPGA, nVidia, Tesla C1060

May 25, 2014 by hgpu

Searching for sinks of Henon map using a multiple-precision GPU arithmetic library

Mioara Joldes, Valentina Popescu, Warwick Tucker

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Extended precision, nVidia, Tesla C2050

March 15, 2014 by hgpu

Full-Speed Deterministic Bit-Accurate Parallel Floating-Point Summation on Multi- and Many-Core Architectures

Sylvain Collange, David Defour, Stef Graillat, Roman Iakymchuk

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 7970, Computer science, Extended precision, Intel Xeon Phi, nVidia, OpenCL, Tesla K20

February 26, 2014 by hgpu

Increasing precision of uniform pseudorandom number generators

Vadim Demchik, Alexey Gulov

View

Download (PDF)

Tags: Algorithms, Computer science, Extended precision, Mathematical Software, Pseudo-random number generators, Security

February 12, 2014 by hgpu

GPU acceleration of Newton’s method for large systems of polynomial equations in double double and quad double arithmetic

Jan Verschelde, Xiangcheng Yu

View

Download (PDF)

Tags: Algorithms, CUDA, Extended precision, Linear Algebra, Mathematics, nVidia, Tesla C2050, Tesla K20

January 26, 2014 by hgpu

CFAL-bench

Comparing Parallel Functional Array Languages: Programming and Performance

Efficient Graph Embedding at Scale: Optimizing CPU-GPU-SSD Integration

Can Large Language Models Predict Parallel Code Performance?

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores

Double-Precision Floating-Point Data Visualizations Using Vulkan API

Accelerating 128-bit Floating-Point Matrix Multiplication on FPGAs

Solver for Systems of Linear Equations with Infinite Precision on a GPU Cluster

Arbitrary-Precision Arithmetics on the GPU

Accelerating Polynomial Homotopy Continuation on a Graphics Processing Unit with Double Double and Quad Double Arithmetic

Towards fast and certified multiple-precision libraries

GPU vs FPGA: A Comparative Analysis for Non-standard Precision

Searching for sinks of Henon map using a multiple-precision GPU arithmetic library

Full-Speed Deterministic Bit-Accurate Parallel Floating-Point Summation on Multi- and Many-Core Architectures

Increasing precision of uniform pseudorandom number generators

GPU acceleration of Newton’s method for large systems of polynomial equations in double double and quad double arithmetic

Recent source codes

CFAL-bench

Efficient Graph Embedding at Scale: Optimizing CPU-GPU-SSD Integration

Can Large Language Models Predict Parallel Code Performance?

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

Most viewed papers (last 30 days)