Stories by matt_d

Does Linux Provide Performance Isolation for NVMe SSDs? Configuring cgroups [pdf]

International Conference on Managed Programming Languages & Runtimes (MPLR) 2025

Collective Matrix Multiplication – JAX Pallas:Mosaic GPU

StreamTensor: Make Tensors Stream in Dataflow Accelerators for LLMs

Can AI Co-Design Distributed Systems? Scaling from 1 GPU to 1k

Hybrid Architectures for Language Models: Systematic Analysis & Design Insights

LLMc: Beating All Compression with LLMs

Muon Outperforms Adam in Tail-End Associative Memory Learning [video]

Barbara Liskov Oral History [video]

CMOS 2.0 – Redefining the Future of Scaling

Fuss-Free Universe Hierarchies

Pretraining Large Language Models with NVFP4

The Next Computing Revolution: Bringing Processing Inside Memory

llvm-mos: Modern C/C++ on the Venerable 6502 | VCFMW 20 (2025) (2025) [video]

Mercury: Unlocking Multi-GPU Optimization for LLMs via Remote Memory Scheduling [pdf]

Optimizing a 6502 image decoder – part II: assembly

Arm A-Profile Architecture developments 2025: Armv9.7-A

TypeDis: A Type System for Disentanglement [pdf]

From CPU Transparency to GPU Complexity – The Performance Engineering Frontier

1
2
3
4
5
6
7
8
9
10