high performance computing on graphics processing units: hgpu.org

hgpu.org » Data recovery

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

LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory

Tyler Sorensen, Heidy Khlaaf

View

Download (PDF)

Source codes

Tags: Computer science, Data recovery, nVidia, nVidia GeForce RTX 4070, OpenCL, Package, Security, Vulkan

February 4, 2024 by hgpu

Data Remanence and Digital Forensic Investigation for CUDA Graphics Processing Units

X. J. A. Bellekens, G. Paul, J. M. Irvine, C. Tachtatzis, R. C. Atkinson, C. Renfrew, T. Kirkham

View

Download (PDF)

Tags: Computer science, data leak, Data recovery, forensic, GPU, Memory, remanence, vulnerable

May 28, 2016 by xhgpu

GPUstore: Harnessing GPU Computing for Storage Systems in the OS Kernel

Weibin Sun, Robert Ricci, Matthew L. Curry

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Data recovery, nVidia, nVidia GeForce GTX 480, Package, Security, Storage system

March 26, 2012 by hgpu

Using Graphics Processors for Parallelizing Hash-based Data Carving

Sylvain Collange, Yoginder Dandass, Marc Daumas, David Defour

View

Download (PDF)

Tags: Computer science, Data recovery, Hashing, nVidia, nVidia GeForce 8500 GT, nVidia GeForce 8600 M GT

November 13, 2010 by hgpu

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

Profile Util library: A quick and easy way to get MPI, OpenMP and GPU runtime information

MaC: Mamba CPU performance predictor

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Mixed-precision finite element kernels

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

SHMT: The Simultaneous and Heterogenous Multithreading project

General-Purpose Computing on Tensor Processors

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

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

LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory

Data Remanence and Digital Forensic Investigation for CUDA Graphics Processing Units

GPUstore: Harnessing GPU Computing for Storage Systems in the OS Kernel

Using Graphics Processors for Parallelizing Hash-based Data Carving

Recent source codes

Kokkidio: Kokkos+Eigen - write fast, readable multi-platform code

LLaMA-Inference-Bench

MATAR

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

MaC: Mamba CPU performance predictor

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Most viewed papers (last 30 days)