HGPU group
LightNews LightNews
banner
hgpu.bsky.social
HGPU group
@hgpu.bsky.social
86 followers 10 following 230 posts
High performance computing on graphics processing units (GPU): AMD, Nvidia, Intel, CUDA, OpenCL, OpenGL, HPC
Posts Replies Media Videos
hgpu.bsky.social
CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

#CUDA #CodeGeneration #Performance #Package

hgpu.org?p=30343
CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
Developing efficient CUDA kernels is increasingly critical for AI applications such as large-scale LLM training. However, manual kernel design is both costly and time-consuming, motivating automati…
hgpu.org
November 9, 2025 at 4:29 PM
hgpu.bsky.social
Characterizing the Performance of Parallel Data-Compression Algorithms across Compilers and GPUs

#CUDA #HIP #Compression #Package

hgpu.org?p=30342
Characterizing the Performance of Parallel Data-Compression Algorithms across Compilers and GPUs
Different compilers can generate code with notably different performance characteristics – even on the same system. Today, GPU developers have three popular options for compiling CUDA or HIP …
hgpu.org
November 9, 2025 at 4:28 PM
hgpu.bsky.social
FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error

#FP8 #Precision

hgpu.org?p=30341
FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error
Training large Mixture-of-Experts (MoE) models remains computationally prohibitive due to their extreme compute and memory demands. Although low-precision training promises to accelerate computatio…
hgpu.org
November 9, 2025 at 4:28 PM
hgpu.bsky.social
AMD MI300X GPU Performance Analysis

#AMD #HIP #Benchmarking #Performance

hgpu.org?p=30340
AMD MI300X GPU Performance Analysis
The rapid growth of large language models (LLMs) has driven the need for high-performance, scalable GPU hardware capable of efficiently serving models with hundreds of billions of parameters. While…
hgpu.org
November 9, 2025 at 4:27 PM
hgpu.bsky.social
RDMA Point-to-Point Communication for LLM Systems

#CUDA #RDMA #LLM #Package

hgpu.org?p=30339
RDMA Point-to-Point Communication for LLM Systems
Emerging Large Language Model (LLM) system patterns, such as disaggregated inference, Mixture-of-Experts (MoE) routing, and asynchronous reinforcement fine-tuning, require flexible point-to-point c…
hgpu.org
November 9, 2025 at 4:26 PM
hgpu.bsky.social
A Study of Floating-Point Precision Tuning in Deep Learning Operators Implementations

#CUDA #DeepLearning #DL #Package

hgpu.org?p=30330
A Study of Floating-Point Precision Tuning in Deep Learning Operators Implementations
Deep learning (DL) has already played a significant role in numerous fields, making it crucial to ensure the stability of both training and inference in DL systems. The computation of DL models can…
hgpu.org
November 2, 2025 at 4:05 PM
hgpu.bsky.social
Enhancing Transformer Performance and Portability through Auto-tuning Frameworks

#CUDA #LLM #AutoTuning #PerformancePortability #Package

hgpu.org?p=30329
Enhancing Transformer Performance and Portability through Auto-tuning Frameworks
Abstract Transformer-based models such as BERT and GPT2 have become the foundation of many modern applications, yet their execution requires substantial computational and memory resources. To addre…
hgpu.org
November 2, 2025 at 4:04 PM
hgpu.bsky.social
Serve Programs, Not Prompts

#LLM #NLP

hgpu.org?p=30328
Serve Programs, Not Prompts
Current large language model (LLM) serving systems, primarily designed for text completion, are neither efficient nor adaptable for increasingly complex LLM applications due to their inflexible des…
hgpu.org
November 2, 2025 at 4:03 PM
hgpu.bsky.social
Scalable GPU-Based Integrity Verification for Large Machine Learning Models

#SYCL #oneAPI #Rust #Security #Package

hgpu.org?p=30327
Scalable GPU-Based Integrity Verification for Large Machine Learning Models
We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms and significantly reducing verification overheads. …
hgpu.org
November 2, 2025 at 4:02 PM
hgpu.bsky.social
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

#CUDA #MachineLearning #ML #Package

hgpu.org?p=30326
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Modern AI hardware, such as Nvidia’s Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Large Language …
hgpu.org
November 2, 2025 at 4:02 PM
hgpu.bsky.social
Architecting Tensor Core-Based Reductions for Irregular Molecular Docking Kernels

#CUDA #Chemistry #MolecularDocking #Package

hgpu.org?p=30318
Architecting Tensor Core-Based Reductions for Irregular Molecular Docking Kernels
Tensor Cores (TCs) are specialized hardware units designed for efficient matrix multiplication and are widely utilized in deep learning workloads. However, their adoption in more irregular high-per…
hgpu.org
October 26, 2025 at 8:04 PM
hgpu.bsky.social
STARK: Strategic Team of Agents for Refining Kernels

#CodeGeneration #LLM

hgpu.org?p=30317
STARK: Strategic Team of Agents for Refining Kernels
The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, threa…
hgpu.org
October 26, 2025 at 8:04 PM
hgpu.bsky.social
A Compute Graph Simulation and Implementation Framework Targeting AMD Versal AI Engines

#AMD #FPGA #CodeGeneration #AI

hgpu.org?p=30316
A Compute Graph Simulation and Implementation Framework Targeting AMD Versal AI Engines
We present a framework for developing compute graph-based applications targeting the AI Engine (AIE) array of AMD Versal SoCs. This framework enables users to embed AIE-based dataflow graph prototy…
hgpu.org
October 26, 2025 at 8:03 PM
hgpu.bsky.social
Collective Communication for 100k+ GPUs

#CUDA #GPUcluster #LLM #Performance #Package

hgpu.org?p=30315
Collective Communication for 100k+ GPUs
The increasing scale of large language models (LLMs) necessitates highly efficient collective communication frameworks, particularly as training workloads extend to hundreds of thousands of GPUs. T…
hgpu.org
October 26, 2025 at 8:03 PM
hgpu.bsky.social
Tutoring LLM into a Better CUDA Optimizer

#CUDA #LLM #CodeGeneration #Package

hgpu.org?p=30314
Tutoring LLM into a Better CUDA Optimizer
Recent leaps in large language models (LLMs) caused a revolution in programming tools (like GitHub Copilot) that can help with code generation, debugging, and even performance optimization. In this…
hgpu.org
October 26, 2025 at 8:03 PM
hgpu.bsky.social
Thesis: Compiler and Runtime Systems for Generative AI Models

#CUDA #LLM #DeepLearnig #DL #Package

hgpu.org?p=30305
Compiler and Runtime Systems for Generative AI Models
Generative AI (GenAI) workloads have rapidly become the predominant data center GPU workload. However, designing efficient GPU kernels for GenAI presents significant challenges due to two central f…
hgpu.org
October 19, 2025 at 8:41 PM
hgpu.bsky.social
Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

#SYCL #HIP #CUDA #Performance #Package

hgpu.org?p=30304
Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation
Specializing kernels by including runtime information during just-in-time (JIT) -compilation can improve performance at the expense of potentially generating more kernels. In this work, we contribu…
hgpu.org
October 19, 2025 at 8:40 PM
hgpu.bsky.social
Anonymized Network Sensing using C++26 std::execution on GPUs

#CUDA #CXX

hgpu.org?p=30303
Anonymized Network Sensing using C++26 std::execution on GPUs
Large-scale network sensing plays a vital role in network traffic analysis and characterization. As network packet data grows increasingly large, parallel methods have become mainstream for network…
hgpu.org
October 19, 2025 at 8:40 PM
hgpu.bsky.social
A Performance Portable Matrix Free Dense MTTKRP in GenTen

#Kokkos #CUDA #OpenMP #Package

hgpu.org?p=30302
A Performance Portable Matrix Free Dense MTTKRP in GenTen
We extend the GenTen tensor decomposition package by introducing an accelerated dense matricized tensor times Khatri-Rao product (MTTKRP), the workhorse kernel for canonical polyadic (CP) tensor de…
hgpu.org
October 19, 2025 at 8:40 PM
hgpu.bsky.social
Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

#CUDA #ROCm #Performance #DeepLearning #DL #Package

hgpu.org?p=30301
Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs
Operator fusion has become a key optimization for deep learning, which combines multiple deep learning operators to improve data reuse and reduce global memory transfers. However, existing tensor c…
hgpu.org
October 19, 2025 at 8:35 PM
hgpu.bsky.social
Thesis: High-Performance Computing: from Optimization to Automation

#CUDA #HIP #HPC

hgpu.org?p=30292
High-Performance Computing: from Optimization to Automation
The digital revolution of our society is driven by major technological advancements, enabled not only by the growing capabilities of computers but also by the evolution of their uses. These develop…
hgpu.org
October 12, 2025 at 2:49 PM
hgpu.bsky.social
Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

#MLIR #OpenCL #Testing #Package

hgpu.org?p=30291
Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However, ensuring the corr…
hgpu.org
October 12, 2025 at 2:48 PM
hgpu.bsky.social
ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

#CUDA #CodeGeneration #LLM #DeepLearning #DL #Package

hgpu.org?p=30290
ConCuR: Conciseness Makes State-of-the-Art Kernel Generation
GPU kernel generation by LLMs has recently experienced rapid development, leveraging test-time scaling and reinforcement learning techniques. However, a key challenge for kernel generation is the s…
hgpu.org
October 12, 2025 at 2:48 PM
hgpu.bsky.social
Accelerating cosmological simulations on GPUs: a portable approach using OpenMP

#OpenMP #HPC #Astrophysics #Package

hgpu.org?p=30289
Accelerating cosmological simulations on GPUs: a portable approach using OpenMP
In this work we present the porting to Graphics Processing Units (GPUs, using OpenMP target directives) and optimization of a key module within the cosmological {pinocchio} code, a Lagrangian Pertu…
hgpu.org
October 12, 2025 at 2:47 PM
hgpu.bsky.social
EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

#CUDA #LLM #AI #DeepLearning #DL #PyTorch

hgpu.org?p=30288
EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
CUDA kernel optimization has become a critical bottleneck for AI performance, as deep learning training and inference efficiency directly depends on highly optimized GPU kernels. Despite the promis…
hgpu.org
October 12, 2025 at 2:47 PM