Stories by matt_d

An Empirical Study: AI Agent Rules Need Context and Layered Enforcement

SPIR-V on ROCm: A Portable IR for AMD GPUs

GEMM Performance Measurement Methodology Guidelines

Faster Algorithms for Structured Matrix Multiplication via Flip Graph Search

AI for Systems is "AGI-Complete"

Controlling Reasoning Effort in LLMs

Making TLA+ and x86 Kiss via Z3Py

Irreducible Loops

Fleet: Hierarchical Task-Based Abstraction for Megakernels on Multi-Die GPUs

Accelerating Block Low-Rank Foundation Model Inference on MemoryConstrained GPUs

Locality-Aware Automatic Differentiation on the GPU for Mesh-Based Computations

Triton Plugin Extensions: Enabling TLX and Custom Compiler Passes Out of the Box

What If the Harness Comes Before Pretraining? A Data Flywheel Perspective

Mimesys: Turn Resource Usage Traces into Executable Workloads

System call instrumentation on Linux/x86-64 using memory-indirect calls

Bidirectional Elaborators à la Carte

CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems

AI Model Co-Design: Hardware-Friendly LLM Design

Towards Free Normalization: Fusing Normalization into GEMM and Attention Kernels

Negotiating AI in Open Source Software Communities: A Case Study of LLVM Project

1 2 3 4 5 6 7 8 9 10