back
user profile

matt_d

21,168karma·3,275submissions·April 21, 2014
recent activity (3,275 total)
1 pts
Tessera: Unlocking Heterogeneous GPUs Through Kernel-Granularity Disaggregation(arxiv.org)
4mo ago·discuss
2 pts
From SIMT to Systolic: A Foundation for GPU and TPU Architecture(twitter.com)
4mo ago·discuss
2 pts
Packrat Parsing at the Speed of Wasm [video](youtube.com)
4mo ago·discuss
3 pts
Sparser, Faster, Lighter Transformer Language Models(arxiv.org)
4mo ago·discuss
1 pts
When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Telemetry(arxiv.org)
4mo ago·discuss
3 pts
Stupid RCU Tricks: Corner-Case RCU Implementations(people.kernel.org)
4mo ago·discuss
1 pts
How Many Compilers Is Too Many? V8's History, Tradeoffs, and Architecture [video](youtube.com)
4mo ago·discuss
1 pts
Fully-Automatic Type Inference for Borrows with Lifetimes(al.radbox.org)
4mo ago·discuss
119 pts
The GNU libc atanh is correctly rounded(inria.hal.science)
4mo ago·29 comments
1 pts
MMU Handbook: Memory Management Units and TLBs(kalairajah-personal.github.io)
4mo ago·discuss
2 pts
PEP 831 – Frame Pointers Everywhere: Enabling System-Level Observability(peps.python.org)
4mo ago·discuss
13 pts
UpDown: Efficient Manycore based on Many Threading & Scalable Memory Parallelism(people.cs.uchicago.edu)
4mo ago·1 comments
146 pts
Reflections on 30 years of HPC programming(chapel-lang.org)
4mo ago·123 comments
1 pts
Recent lld/ELF performance improvements(maskray.me)
4mo ago·discuss
45 pts
Circuit Transformations, Loop Fusion, and Inductive Proof(natetyoung.github.io)
4mo ago·3 comments
2 pts
AI for Systems: Using LLMs to Optimize Database Query Execution(together.ai)
4mo ago·discuss
3 pts
Optimization of 32-bit Unsigned Division by Constants on 64-bit Targets(arxiv.org)
4mo ago·discuss
4 pts
GCC Translation Validation Part 6: Uninitialized Memory(kristerw.github.io)
4mo ago·discuss
2 pts
Agentic Code Optimization via Compiler-LLM Cooperation(arxiv.org)
4mo ago·discuss
1 pts
Bespoke OLAP: Using AI to Synthesize Workload-Specific DBMS Engines from Scratch(ucbskyadrs.github.io)
4mo ago·discuss
2 pts
Understanding Agents: Code Coverage for Coding Agents(blog.asymmetric.re)
4mo ago·discuss
1 pts
Cyclotron: The Streaming Multiprocessor Abstraction Is Broken [pdf](capra.cs.cornell.edu)
4mo ago·discuss
2 pts
UCCL-EP: Portable Expert-Parallel Communication – Full Results(uccl-project.github.io)
4mo ago·discuss
4 pts
vLLM IR: A Functional Intermediate Representation for vLLM(github.com)
4mo ago·discuss
1 pts
Test-Time Scaling Makes Overtraining Compute-Optimal(arxiv.org)
4mo ago·discuss
1 pts
Analyzing Reverse Address Translation Overheads in Multi-GPU Scale-Up Pods(arxiv.org)
4mo ago·discuss
3 pts
Tracing a Full MoE Training Step Through the XLA Compiler(patricktoulme.substack.com)
4mo ago·discuss
2 pts
Breaking Down the Cerebras Wafer Scale Engine(wafer.substack.com)
4mo ago·discuss
2 pts
The need for better compiler frontend benchmarks: Carbon's benchmarking approach(discourse.llvm.org)
4mo ago·discuss
3 pts
DAXFS: A Lock-Free Shared Filesystem for CXL Disaggregated Memory(arxiv.org)
4mo ago·discuss