HGPU group

handle.invalid

Followers · Following

High performance computing on graphics processing units (GPU): AMD, Nvidia, Intel, CUDA, OpenCL, OpenGL, HPC

Joined November 2024

Posts Replies Media Original posts Likes

HGPU group handle.invalid · Feb 1
Generating Literature-Driven Scientific Theories at Scale #LLM #Package hgpu.org?p=30521
Generating Literature-Driven Scientific Theories at Scale

Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Feb 1
Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs #CUDA #LLM #Package hgpu.org?p=30520
Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs

SMEs increasingly seek alternatives to cloud LLM APIs, which raise data privacy concerns. Dedicated cloud GPU instances offer improved privacy but with limited guarantees and ongoing costs, while p…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Feb 1
BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics #Bioinformatics #AI #LLM #Package hgpu.org?p=30519
BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics

This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark co…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Feb 1
ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler #OpenCL #LLM hgpu.org?p=30518
ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler

As large language models (LLMs) move from research to production, understanding how inference engines behave in real time has become both essential and elusive. Unlike general-purpose engines such …

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Feb 1
Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool) #CUDA #Triton #Profiling #Package hgpu.org?p=30517
Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool)

The proliferation of Python DSLs for developing kernels has democratized GPU programming. While kernel development is now Python-native, performance analysis and optimization still rely on external…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 25
Towards Automated Kernel Generation in the Era of LLMs #CUDA #Triton #ROCm #LLM hgpu.org?p=30511
Towards Automated Kernel Generation in the Era of LLMs

The performance of modern AI systems is fundamentally constrained by the quality of their underlying kernels, which translate high-level algorithmic semantics into low-level hardware operations. Ac…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 25
A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization #CUDA #LLM hgpu.org?p=30510
A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization

GPU code optimization is a key performance bottleneck for HPC workloads as well as large-model training and inference. Although compiler optimizations and hand-written kernels can partially allevia…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 25
SynPerf: A Hybrid Analytical-ML Framework for GPU Performance Prediction #Triton #CUDA #Performance #ML hgpu.org?p=30509
SynPerf: A Hybrid Analytical-ML Framework for GPU Performance Prediction

The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely gen…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 25
Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10 #CUDA #Performance hgpu.org?p=30508
Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10

High-performance attention kernels are essential for Large Language Models. This paper presents analysis of CuTile-based Flash Attention memory behavior and a technique to improve its cache perform…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 25
PhysProver: Advancing Automatic Theorem Proving for Physics #Physics #LLM #Package hgpu.org?p=30507
PhysProver: Advancing Automatic Theorem Proving for Physics

The combination of verifiable languages and LLMs has significantly influenced both the mathematical and computer science communities because it provides a rigorous foundation for theorem proving. R…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 11
The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers #Compilers #LLM hgpu.org?p=30502
The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers

This survey has provided a systematic overview of the emerging field of LLM-enabled compilation by addressing several key research questions. We first answered how LLMs are being integrated by prop…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 11
DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation #CodeGeneration #LLM hgpu.org?p=30501
DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation

Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 11
Equivalence Checking of ML GPU Kernels #CUDA #PTX #LLM hgpu.org?p=30500
Equivalence Checking of ML GPU Kernels

With the rapid progress of deep learning and large language models (LLMs), companies now spend enormous sums executing GPU kernels. These kernels have, therefore, become prime targets for aggressiv…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 11
AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis #Triton #CUDA #CodeGeneration #DSL #LLM hgpu.org?p=30499
AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis

Modern AI models demand high-performance computation kernels. The growing complexity of LLMs, multimodal architectures, and recommendation systems, combined with techniques like sparsity and quanti…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 11
ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation #CUDA #OpenMP #CodeGeneration #LLM #Package hgpu.org?p=30498
ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

Parallel programming is central to HPC and AI, but producing code that is correct and fast remains challenging, especially for OpenMP GPU offload, where data movement and tuning dominate. Autonomou…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 4
SeedFold: Scaling Biomolecular Structure Prediction #Biology #Biomolecules hgpu.org?p=30497
SeedFold: Scaling Biomolecular Structure Prediction

Highly accurate biomolecular structure prediction is a key component of developing biomolecular foundation models, and one of the most critical aspects of building foundation models is identifying …

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 4
Hardware Acceleration for Neural Networks: A Comprehensive Survey #FPGA #TPU #NeuralNetworks #NN #Survey hgpu.org?p=30496
Hardware Acceleration for Neural Networks: A Comprehensive Survey

Neural networks have become a dominant computational workload across cloud and edge platforms, but rapid growth in model size and deployment diversity has exposed hardware bottlenecks increasingly …

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 4
Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission #Compression #Video #AI hgpu.org?p=30495
Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission

Whether a video can be compressed at an extreme compression rate as low as 0.01%? To this end, we achieve the compression rate as 0.02% at some cases by introducing Generative Video Compression (GV…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 4
GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs #CUDA #HIP #HPC #LLM #Performance hgpu.org?p=30494
GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs

In high-performance computing, hotspot GPU kernels are primary bottlenecks, and expert manual tuning is costly and hard to port. Large language model methods often assume kernels can be compiled an…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Jan 4
KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta #CUDA #Triton #PTX #AI #Meta #LLM hgpu.org?p=30493
KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges – model architecture diversity, ker…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 29, 2025
Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation #CUDA #PTX #Triton #ProgrammingLanguages #Package hgpu.org?p=30481
Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation

Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 29, 2025
Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs #CUDA #AI #Memory #Package hgpu.org?p=30480
Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

Recent advances in transformer-based foundation models have made them the default choice for many tasks, but their rapidly growing size makes fitting a full model on a single GPU increasingly diffi…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 29, 2025
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization #LLM #AI #Performance hgpu.org?p=30479
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI accelerators, eliminating the need for expert-provided hardware-s…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 29, 2025
Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs #CUDA #ProgrammingLanguages hgpu.org?p=30478
Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs

GPU architectures have continued to grow in complexity, with recent incarnations introducing increasingly powerful fixed-function units for matrix multiplication and data movement to accompany high…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 29, 2025
PEAK: A Performance Engineering AI-Assistant for GPU Kernels Powered by Natural Language Transformations #CUDA #HIP #HLSL #AI #LLM #NLP hgpu.org?p=30477
PEAK: A Performance Engineering AI-Assistant for GPU Kernels Powered by Natural Language Transformations

Advancements in large language models (LLMs) are showing promising impact in software development and programming assistance. However, these models struggle when operating on low-level backend code…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning #CUDA #CUBLAS #MatrixMultiplication #Package hgpu.org?p=30469
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA …

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
BoltzGen:Toward Universal Binder Design #Biology #Bioinformatics #Biomolecules #Package hgpu.org?p=30468
BoltzGen:Toward Universal Binder Design

We introduce BoltzGen, an all-atom generative model for designing proteins and peptides across all modalities to bind a wide range of biomolecular targets. BoltzGen builds strong structural reasoni…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation #CUDA #CodeGeneration #LLM hgpu.org?p=30467
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks l…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage #CUDA #PyTorch #Databases hgpu.org?p=30466
PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage

The AI hardware boom has led modern data centers to adopt HPC-style architectures centered on distributed, GPU-centric computation. Large GPU clusters interconnected by fast RDMA networks and backe…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
ML Inference Scheduling with Predictable Latency #ML #MachineLearning #TaskScheduling hgpu.org?p=30465
ML Inference Scheduling with Predictable Latency

Machine learning (ML) inference serving systems can schedule requests to improve GPU utilization and to meet service level objectives (SLOs) or deadlines. However, improving GPU utilization may com…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 21, 2025
cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution #CUDA #LLM #AI #Package hgpu.org?p=30464
cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While re…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 14, 2025
Accurate Models of NVIDIA Tensor Cores #CUDA #Performance #Package hgpu.org?p=30454
Accurate Models of NVIDIA Tensor Cores

Matrix multiplication is a fundamental operation in for both training of neural networks and inference. To accelerate matrix multiplication, Graphical Processing Units (GPUs) provide it implemented…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 14, 2025
Accelerating Molecular Simulations with Triton: Fused GPU Kernels for TensorNet Neural Potentials #Triton #CUDA #MolecularDynamics #MD #MolecularSimulations #PyTorch #Chemistry #Biology hgpu.org?p=30453
Accelerating Molecular Simulations with Triton: Fused GPU Kernels for TensorNet Neural Potentials

Molecular dynamics (MD) simulations are essential for understanding molecular behavior in biology and chemistry, but remain computationally expensive at the scales required for drug discovery and m…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 14, 2025
Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency #ROCm #LLM hgpu.org?p=30452
Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency

Training large language models (LLMs) efficiently requires a deep understanding of how modern GPU systems behave under real-world distributed training workloads. While prior work has focused primar…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 14, 2025
Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters #GPUcluster #TaskScheduling #Package hgpu.org?p=30451
Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Modern cloud platforms increasingly host large-scale deep learning (DL) workloads, demanding high-throughput, low-latency GPU scheduling. However, the growing heterogeneity of GPU clusters and limi…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 14, 2025
TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization #Triton #CUDA #PyTorch #Package hgpu.org?p=30450
TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

High-performance GPU kernel optimization remains a critical yet labor-intensive task in modern machine learning workloads. Although Triton, a domain-specific language for GPU programming, enables d…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 7, 2025
tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection #Triton #BLAS #GEMM #AMD #ROCm #HPC #Performance #Package hgpu.org?p=30441
tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

We present tritonBLAS, a fast and deterministic analytical model that uses architectural parameters like the cache hierarchy, and relative code and data placement to generate performant GPU GEMM ke…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 7, 2025
Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles #LLVM #Compilers hgpu.org?p=30440
Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles

Ensuring the correctness of compiler optimizations is critical, but existing fuzzers struggle to test optimizations effectively. First, most fuzzers use optimization pipelines (heuristics-based, fi…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 7, 2025
Decoupled Triton: A Block-Level Decoupled Language for Writing and Exploring Efficient Machine-Learning Kernels #Triton #Compilers #MachineLearning #ML #Thesis hgpu.org?p=30439
Decoupled Triton: A Block-Level Decoupled Language for Writing and Exploring Efficient Machine-Learning Kernels

Machine-learning (ML) applications frequently utilize high-performance ML kernels to execute tensor operations like matrix product and softmax. An ML kernel can be decomposed into two components: t…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 7, 2025
hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware #FPGA #HLS #MachineLearning #ML #DeepLearning #DL #Package hgpu.org?p=30438
hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Dec 7, 2025
Microbenchmarking NVIDIA’s Blackwell Architecture: An in-depth Architectural Analysis #PTX #CUDA #Benchmarking #Blackwell #HPC hgpu.org?p=30437
Microbenchmarking NVIDIA’s Blackwell Architecture: An in-depth Architectural Analysis

As GPU architectures rapidly evolve to meet the overcoming demands of exascale computing and machine learning, the performance implications of architectural innovations remain poorly understood acr…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 30, 2025
QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation #Triton #CUDA #AI #CodeGeneration #LLM hgpu.org?p=30413
QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs offer promise fo…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 30, 2025
KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit #Triton #CUDA #LLM #CodeGeneration hgpu.org?p=30412
KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit

High quality kernels are critical for reducing training and inference costs of Large Language Models (LLMs), yet they traditionally require significant expertise in hardware architecture and softwa…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 30, 2025
GPU-Initiated Networking for NCCL #CUDA #NCCL hgpu.org?p=30411
GPU-Initiated Networking for NCCL

Modern AI workloads, especially Mixture-of-Experts (MoE) architectures, increasingly demand low-latency, fine-grained GPU-to-GPU communication with device-side control. Traditional GPU communicatio…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 30, 2025
NVIDIA Nemotron Parse 1.1 #Nvidia #OCR #Package hgpu.org?p=30410
NVIDIA Nemotron Parse 1.1

We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabi…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 30, 2025
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels #CUDA #AI #Package hgpu.org?p=30409
ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

Inter-GPU communication has become a major bottleneck for modern AI workloads as models scale and improvements in hardware compute throughput outpace improvements in interconnect bandwidth. Existin…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 23, 2025
Iris: First-Class Multi-GPU Programming Experience in Triton #Triton #HIP #CUDA #Package hgpu.org?p=30375
Iris: First-Class Multi-GPU Programming Experience in Triton

Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on low-level HIP/CUDA…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 23, 2025
ProofWright: Towards Agentic Formal Verification of CUDA #CUDA #LLM #CodeGeneration hgpu.org?p=30374
ProofWright: Towards Agentic Formal Verification of CUDA

Large Language Models (LLMs) are increasingly used to automatically generate optimized CUDA kernels, substantially improving developer productivity. However, despite rapid generation, these kernels…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 23, 2025
AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs #ROCm #CUDA #LLM hgpu.org?p=30373
AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs

The rise of Large Language Models (LLM) has increased the need for scalable, high-performance inference systems, yet most existing frameworks assume homogeneous, resource-rich hardware, often unrea…

hgpu.org

View on Bluesky Show all post labels

HGPU group handle.invalid · Nov 23, 2025
Inside VOLT: Designing an Open-Source GPU Compiler #OpenCL #CUDA #Compilers hgpu.org?p=30372
Inside VOLT: Designing an Open-Source GPU Compiler

Recent efforts in open-source GPU research are opening new avenues in a domain that has long been tightly coupled with a few commercial vendors. Emerging open GPU architectures define SIMT function…

hgpu.org

View on Bluesky Show all post labels

HGPU group

Generating Literature-Driven Scientific Theories at Scale

Private LLM Inference on Consumer Blackwell GPUs: A Practical Guide for Cost-Effective Local Deployment in SMEs

BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics

ProfInfer: An eBPF-based Fine-Grained LLM Inference Profiler

Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool)

Towards Automated Kernel Generation in the Era of LLMs

A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization

SynPerf: A Hybrid Analytical-ML Framework for GPU Performance Prediction

Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10

PhysProver: Advancing Automatic Theorem Proving for Physics

The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers

DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation

Equivalence Checking of ML GPU Kernels

AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis

ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

SeedFold: Scaling Biomolecular Structure Prediction

Hardware Acceleration for Neural Networks: A Comprehensive Survey

Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission

GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation

Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs

AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs

PEAK: A Performance Engineering AI-Assistant for GPU Kernels Powered by Natural Language Transformations

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

BoltzGen:Toward Universal Binder Design

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage

ML Inference Scheduling with Predictable Latency

cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

Accurate Models of NVIDIA Tensor Cores

Accelerating Molecular Simulations with Triton: Fused GPU Kernels for TensorNet Neural Potentials

Chopper: A Multi-Level GPU Characterization Tool & Derived Insights Into LLM Training Inefficiency

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles

Decoupled Triton: A Block-Level Decoupled Language for Writing and Exploring Efficient Machine-Learning Kernels

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

Microbenchmarking NVIDIA’s Blackwell Architecture: An in-depth Architectural Analysis

QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit

GPU-Initiated Networking for NCCL

NVIDIA Nemotron Parse 1.1

ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

Iris: First-Class Multi-GPU Programming Experience in Triton

ProofWright: Towards Agentic Formal Verification of CUDA

AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs

Inside VOLT: Designing an Open-Source GPU Compiler