Skip to content
#

microbenchmark

Here are 63 public repositories matching this topic...

Low-level command-line tool for measuring CPU and Metal GPU memory bandwidth, synthetic LLM decode and prefill memory traffic, cache and main-memory latency, access-pattern performance, TLB behavior, and two-thread cache-line handoff protocol latency on Apple Silicon Macs.

  • Updated Sep 6, 2026
  • C++

Add this topic to your repo

To associate your repository with the microbenchmark topic, visit your repo's landing page and select "manage topics."

Learn more