back
user profile

matt_d

21,167karma·3,275submissions·April 21, 2014
recent activity (3,275 total)
12 pts
Fast GPU Linear Algebra via Compile Time Expression Fusion(arxiv.org)
3mo ago·discuss
3 pts
The AI Compute Extensions (ACE) for x86 [pdf](x86ecosystem.org)
3mo ago·discuss
2 pts
Finding and Understanding Bugs in FPGA Place-and-Route Engines [video](youtube.com)
3mo ago·discuss
1 pts
AutoSP: Long-Context LLM Training via Compiler-Based Sequence Parallelism(pytorch.org)
3mo ago·discuss
2 pts
Partial UDF Inlining(doi.org)
3mo ago·discuss
11 pts
From Convergence to Confidence: Push-Button Verification for RDTs(kcsrk.info)
3mo ago·discuss
71 pts
Low-Compilation-Cost Register Allocation in LLVM-Based Binary Translation(dl.acm.org)
3mo ago·4 comments
2 pts
AdaExplore: Search for Efficient Kernel Generation(stiglidu.github.io)
3mo ago·discuss
1 pts
vLLM-Compile: Bringing Compiler Optimizations to LLM Inference(docs.google.com)
3mo ago·discuss
2 pts
Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs(arxiv.org)
3mo ago·discuss
2 pts
Compiler Testing – Part 1: Coverage-Guided Fuzzing with Grammars and LLMs(nowarp.io)
3mo ago·discuss
1 pts
Disaggregated Serving for Hybrid SSM Models in vLLM(vllm-website-lx4pji0mz-inferact-inc.vercel.app)
3mo ago·discuss
2 pts
Great Paper: The Calculated Typer – Iowa Type Theory Commute Podcast S7 E6(pocketcasts.com)
3mo ago·discuss
3 pts
Barbara Liskov, Turing Award'08: Data Abstraction, Dijkstra, Distributed Systems(developing.dev)
3mo ago·discuss
4 pts
Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell(arxiv.org)
3mo ago·1 comments
3 pts
Reimagining Kernel Generation at the PTX Layer(standardkernel.com)
3mo ago·discuss
1 pts
A Deductive System for (Hardware-Software) Contract Satisfaction Proofs(arxiv.org)
3mo ago·discuss
2 pts
Tile Kernels: An optimized GPU kernels library written in TileLang(github.com)
3mo ago·discuss
1 pts
AMD's Zen: Coming Back from the Dead(clamtech.org)
3mo ago·1 comments
1 pts
Learning to Repair Lean Proofs from Compiler Feedback(arxiv.org)
3mo ago·discuss
2 pts
RLix: A scheduling layer for concurrent LLM RL(github.com)
3mo ago·discuss
2 pts
Primus Projection: Estimate Memory and Performance Before You Train(rocm.blogs.amd.com)
3mo ago·discuss
2 pts
PRowhammer: Propagating Bit-flips from CPU to GPU [pdf](cse.iitb.ac.in)
3mo ago·discuss
3 pts
The Quantization Robustness of Diffusion Language Models in Coding Benchmarks(arxiv.org)
3mo ago·discuss
2 pts
Different Perspectives of Memory System Simulation(arxiv.org)
3mo ago·discuss
4 pts
Adding Compilation Metadata to Binaries to Make Disassembly Decidable(arxiv.org)
3mo ago·discuss
1 pts
ICLR 2026 Outstanding Papers(blog.iclr.cc)
3mo ago·discuss
3 pts
Decoupled DiLoCo for Resilient Distributed Pre-Training(arxiv.org)
3mo ago·discuss
comment
Pretty nifty work; more details (full type system specification, including type inference rules, collective signatures, and forward-backward pairs): https://github.com/meta-pytorch…
3mo ago·view thread
2 pts
spmd_types: A type system for distributed (SPMD) tensor computations in PyTorch(github.com)
3mo ago·1 comments