Thesis: High-Performance Computing: from Optimization to Automation #CUDA #HIP #HPC hgpu.org?p=30292

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR #MLIR #OpenCL #Testing #Package hgpu.org?p=30291

ConCuR: Conciseness Makes State-of-the-Art Kernel Generation #CUDA #CodeGeneration #LLM #DeepLearning #DL #Package hgpu.org?p=30290

Accelerating cosmological simulations on GPUs: a portable approach using OpenMP #OpenMP #HPC #Astrophysics #Package hgpu.org?p=30289

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models #CUDA #LLM #AI #DeepLearning #DL #PyTorch hgpu.org?p=30288

VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs #CUDA #OpenMP #OpenACC #HPC #LLM #CodeGeneration #Package hgpu.org?p=30280

Opal: A Modular Framework for Optimizing Performance using Analytics and LLMs #CUDA #ROCm #Performance #LLM #AI hgpu.org?p=30279

Performance and Numerical Aspects of Decompositional Factorizations with FP64 Floating-Point Emulation in INT8 #NVIDIA #Int8 #FP64 #Factorization hgpu.org?p=30278

exa-AMD: An Exascale-Ready Framework for Accelerating the Discovery and Design of Functional Materials #Physics #Chemistry #CondensedMatter #MaterialsScience #Package hgpu.org?p=30277

Compile-Time Resource Safety for GPU APIs: A Low-Overhead Typestate Framework #CUDA #Rust #Performance #Security #Package hgpu.org?p=30276

Towards GPU Parallelism Abstractions in Rust: A Case Study with Linear Pipelines #CUDA #OpenCL #Rust #CodeGeneration hgpu.org?p=30267

TRUST: the HPC open-source CFD platform – from CPU to GPU #HIP #CUDA #OpenMP #CFD #HPC #MPI #Package hgpu.org?p=30266

Robust LLM Training Infrastructure at ByteDance #CUDA #LLM #AI hgpu.org?p=30265

Cost-Performance Analysis: A Comparative Study of CPU-Based Serverless and GPU-Based Training Architectures #Cost #MachineLearning #ML hgpu.org?p=30264

Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem #CUDA #HIP #ROCm #Compilers #Package hgpu.org?p=30263

AI Factories: It’s time to rethink the Cloud-HPC divide #AI #HPC #Cloud #HPC hgpu.org?p=30223

Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models #CUDA #RiscV #LLM hgpu.org?p=30222

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization #CUDA #Benchmarking #LLM #Package hgpu.org?p=30221

Dato: A Task-Based Programming Model for Dataflow Accelerators #FPGA #ProgrammingLanguages #Package hgpu.org?p=30220

High Performance GPU Implementation of KNN Algorithm: A Review #kNN #MachineLearning #ML hgpu.org?p=30219

An HPC Benchmark Survey and Taxonomy for Characterization #CUDA #OpenCL #ROCm #HIP #MPI #HIP #OpenMP #HPC #Benchmarking #Package hgpu.org?p=30191

Thesis: Towards Calculating HPC CUDA Kernel Performance on Nvidia GPUs #CUDA #PTX #HPC hgpu.org?p=30190

Combining Performance and Productivity: Accelerating the Network Sensing Graph Challenge with GPUs and Commodity Data Science Software #CUDA #HPC #Performance hgpu.org?p=30189

High Performance Matrix Multiplication #CUDA #OpenMP #BLAS #Performance #Package hgpu.org?p=30188

Home-made Diffusion Model from Scratch to Hatch #ImageGeneration #PyTorch #Package hgpu.org?p=30187

CrossTL: A Universal Programming Language Translator with Unified Intermediate Representation #CUDA #Vulkan #HLSL #GLSL #HIP #DirectX #OpenGL #Compilers #Package hgpu.org?p=30171

Managing Multi Instance GPUs for High Throughput and Energy Savings #CUDA #EnergyEfficiency #LLM #PyTorch hgpu.org?p=30170

GPU-acceleration of the Discontinuous Galerkin Shallow Water Equations Solver (DG-SWEM) using CUDA and OpenACC #CUDA #OpenACC #CFD #FluidDynamics #Package hgpu.org?p=30169

Harnessing Batched BLAS/LAPACK Kernels on GPUs for Parallel Solutions of Block Tridiagonal Systems #ROCm #CUDA #BLAS #Factorization #Package hgpu.org?p=30168

AnnotationGym: A Generic Framework for Automatic Source Code Annotation #HLS #FPGA #OpenMP #OpenACC hgpu.org?p=30167

BePilot: An AI Programming Assistant for Compiler Backend Development #LLM #AI #CodeGeneration #Compilers hgpu.org?p=30159

Scaling GPU-Accelerated Databases beyond GPU Memory Size #GPU #Memory #Databases hgpu.org?p=30158

Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs #HIP #AMD #GPU #Memory #Performance #Package hgpu.org?p=30157

Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture #LLM #HPC #SLURM hgpu.org?p=30156

Accelerating a Linear Programming Algorithm on AMD GPUs #HIP #AMD #GPU #Package hgpu.org?p=30155

Bandicoot: A Templated C++ Library for GPU Linear Algebra #OpenCL #CUDA #LinearAlgebra #Package hgpu.org?p=30143

Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: a Deep Dive #HIP #MPI #HPC #AMD #Performance hgpu.org?p=30145

Fuzz4cuda: Fuzzing Your Nvidia Gpu Libraries Through Debug Interface #CUDA #PTX #Security hgpu.org?p=30144

Towards Efficient and Practical GPU Multitasking in the Era of LLM #CUDA #Performance #LLM #PyTorch #Package hgpu.org?p=30142

Profiling Concurrent Vision Inference Workloads on NVIDIA Jetson – Extended #CUDA #Jetson #Performance hgpu.org?p=30141

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries #CUDA #Performance #Package hgpu.org?p=30098

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference #ARM #DeepLearning #DL #Package hgpu.org?p=30097

Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision #OpenCL #SYCL #HIP #Kokkos #Julia hgpu.org?p=30096

Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling #CUDA #LLM #TaskScheduling #Package hgpu.org?p=30095

GPUHammer: Rowhammer Attacks on GPU Memories are Practical #CUDA #Security #Package hgpu.org?p=30094

SIGMo: High-Throughput Batched Subgraph Isomorphism on GPUs for Molecular Matching #CUDA #oneAPI #MPI #Chemistry #Biology #Package hgpu.org?p=30085

AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization #EnergyEfficiency #LLM hgpu.org?p=30082

Understanding the Landscape of Ampere GPU Memory Errors #HPC #NVidia #Ampere #Memory hgpu.org?p=30083

ConTraPh: Contrastive Learning for Parallelization and Performance Optimization #OpenCL #OpenACC #OpenMP #HPC #LLM #CodeGeneration hgpu.org?p=30084

DGEMM without FP64 Arithmetic – using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme #CUDA #Performance #DGEMM #FP64 #Package hgpu.org?p=30081