matt_d 的提交内容

The Art of Deconstraining: A guide to convex optimization in PyTorch

Data Race Freedom à la Mode [pdf]

Modern CPUs Assign Registers to Speed Up Your Code - Matt Godbolt [video]

Hello SME! Generating Fast Matrix Multiplication Kernels Using the SME

RISC-V Vector Extension overview

Hitchhiker's Guide to Programming and Optimizing CXL-Based Heterogeneous Systems

ACM ByteCast Episode 57: Xavier Leroy

PyTorch 2 Faster ML Dynamic Python Bytecode Transformation and Graph Compilation [video]

Safe and efficient C++ interoperability via non-escapable types and lifetimes

MLIR Project Charter and Restructuring Survey

Big Specification: Specification, Proof, and Testing at Scale 2024

Automated reasoning often makes systems more efficient and easier to maintain

Function Effect Analysis – Clang 20.0.0

A Dogged Pursuit for Satisfaction–Ryan Williams (MIT CSAIL) [video]

Static Basic Block Versioning

[RFC] MLIR Project Charter and Restructuring

Scalable self-improvement for compiler optimization

Revisiting Reliability in Large-Scale Machine Learning Research Clusters

Scheduling Languages: A Past, Present, and Future Taxonomy

Sorting for Rendering

Refinement Type Refutations

Accelerate RISC-V Instruction Set Simulation by Tiered JIT Compilation

Unboxing Virgil ADTs for Fun and Profit

Taking a Closer Look:An Outlier-Driven Approach to Compilation-Time Optimization

Efficient GEMM Kernel Designs with Pipelining

Memory Safety without Lifetime Parameters

efency: An efficient electric-fence malloc debugger for the 21st century

Tensor programming for databases, with first class dimensions

A Case for First-Class Environments

Can logic programming be liberated from predicates and backtracking? [pdf]