back
user profile

matt_d

21,168karma·3,275submissions·April 21, 2014
recent activity (3,275 total)
1 pts
Native DSLs Ops in PyTorch(ianbarber.blog)
5mo ago·discuss
185 pts
Flash-KMeans: Fast and Memory-Efficient Exact K-Means(arxiv.org)
5mo ago·14 comments
22 pts
Gluon: Explicit Performance(lei.chat)
5mo ago·discuss
2 pts
Block Number Formats are (Still!) Direction Preservers(constantinides.net)
5mo ago·discuss
4 pts
cuTile Rust: a safe, tile-based kernel programming DSL for Rust(github.com)
5mo ago·discuss
1 pts
KernelBlaster: A framework for in context learning for code optimization(github.com)
5mo ago·discuss
1 pts
Demystifying and Improving Lazy Promotion in Cache Eviction [pdf](vldb.org)
5mo ago·discuss
2 pts
Journeying through Optimization with Heuristics [video](youtube.com)
5mo ago·discuss
2 pts
To Sparsify or to Quantize: A Hardware Architecture View(sigarch.org)
5mo ago·1 comments
64 pts
Efficient sparse computations using linear algebra aware compilers (2025)(osti.gov)
5mo ago·7 comments
2 pts
A Field Guide to Reward Hacking in AI Kernel Generation(wafer.ai)
5mo ago·1 comments
2 pts
AI and the Mixed-Consistency Future(jhellerstein.github.io)
5mo ago·discuss
3 pts
FIDES: End-to-end Compartments for Mixed-language Systems [pdf](kcsrk.info)
5mo ago·discuss
1 pts
Practical Type Inference: High‑Throughput Recovery of Real‑World Types(arxiv.org)
5mo ago·discuss
2 pts
Idempotent Slices with Applications to Code-Size Reduction(arxiv.org)
5mo ago·discuss
1 pts
Designing AI Chip Hardware and Software(docs.google.com)
5mo ago·discuss
11 pts
Refinement Modeling and Verification of RISC-V Assembly Using Knuckledragger(philipzucker.com)
5mo ago·discuss
2 pts
Breaking Control Flow Integrity by Abusing Modern C++ (Coroutines) – BH USA 2025 [video](youtube.com)
5mo ago·discuss
2 pts
Programming the Loop(ianbarber.blog)
5mo ago·discuss
2 pts
Scalable Training of Mixture-of-Experts Models with Megatron Core(arxiv.org)
5mo ago·discuss
3 pts
PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks(arxiv.org)
5mo ago·discuss
3 pts
Formalizing Data Structures and Algorithms with Agents(risemsr.github.io)
5mo ago·discuss
20 pts
Thinnings: Sublist Witnesses and de Bruijn Index Shift Clumping(philipzucker.com)
5mo ago·2 comments
2 pts
Advent of Computing: Dan Temkin – Forty-Four Esolangs(adventofcomputing.libsyn.com)
5mo ago·discuss
1 pts
Checking Write Bandwidth on GPUs(clamtech.org)
5mo ago·discuss
5 pts
Challenges in Decompilation and Reverse Engineering of CUDA-Based Kernels [pdf](nicolo.dev)
5mo ago·discuss
8 pts
Block Number Formats Are Direction Preservers(constantinides.net)
5mo ago·discuss
2 pts
Cutie Fly: CuTe Layout Representation and Algebra, CuTeDSL, FlyDSL(ianbarber.blog)
5mo ago·discuss
21 pts
Converting Binary Floating-Point Numbers to Shortest Decimal Strings(onlinelibrary.wiley.com)
5mo ago·5 comments
3 pts
Controlling Floating-Point Determinism in NVIDIA CCCL(developer.nvidia.com)
5mo ago·discuss