high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia GB10

Reverse Engineering the CUDA Software Stack: A Clean-Room GPU Machine-Code Toolchain for the NVIDIA GB10

M. Drake Stapleton

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, nVidia, nVidia DGX Spark, nVidia GB10, Package, PTX

October 28, 2026 by hgpu

Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks

Nathan Graddon, Aaron Jarmusch, Sunita Chandrasekaran

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Memory, nVidia, nVidia GB10, nVidia GB200, nVidia GH200, Prefetch

October 19, 2026 by hgpu

AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines

Li Chen

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, LLM, nVidia, nVidia GB10, Package, Performance

September 20, 2026 by hgpu

Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10

Yifan Zhu, Yekai Pan, Chen Ding

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GB10, Programming techniques

January 25, 2026 by hgpu

Qwen3-235B @ 1M tokens on AMD MI355X

CHUNDER: Enabling Million-Token Qwen3 Serving on AMD ROCm

CUDA++ for the NVIDIA DGX Spark

Reverse Engineering the CUDA Software Stack: A Clean-Room GPU Machine-Code Toolchain for the NVIDIA GB10

ATTUNE: Agentic Throughput Tuning for LLM Training

HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills

Brian2 Atlas

A Unified Intermediate Representation and Execution Architecture for Heterogeneous and Distributed Neural Simulation

AgentGarten: Code Worlds for Evolving Agents

KernelLens: Automated Triton-to-C++ Compiler for Enterprise Inference Runtimes

KernelLens: Deploying Triton Kernels to C++ Inference Engines

KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation

Introduction to Computer Vision

ACT: Accelerator Compiler Toolkit

Automatically Generating ML Compiler Backends from Tensor Accelerator ISA Descriptions

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Reverse Engineering the CUDA Software Stack: A Clean-Room GPU Machine-Code Toolchain for the NVIDIA GB10

Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks

AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines

Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10

Recent source codes

Qwen3-235B @ 1M tokens on AMD MI355X

CUDA++ for the NVIDIA DGX Spark

ATTUNE: Agentic Throughput Tuning for LLM Training

HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills

Brian2 Atlas

AgentGarten: Code Worlds for Evolving Agents

KernelLens: Automated Triton-to-C++ Compiler for Enterprise Inference Runtimes

KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation

Introduction to Computer Vision

ACT: Accelerator Compiler Toolkit

Most viewed papers (last 30 days)