Keynote: Simple goal. Hard to accomplish
summary
Goal: make Ruby three times faster, but keep compatibility, low memory, maintainability and avoid heavy third‑party deps. Team builds a register-based VM and a JIT that emits C, compiles with GCC to shared objects, and loads them at runtime. Real benchmarks (Rails-based and Optcarrot) show ~2.8–3x speedups; microbenchmarks hit ~6x but memory rises (examples: 1.16x to 18x to 200x in different engines). JIT is promising, not default, and must be enabled explicitly.
AI-written summary · about
chapters (12)
- 0:00Setting goals for software
- 1:06The importance of stability
- 4:10Lessons from breaking changes
- 8:01The Ruby 3x3 initiative
- 10:37Constraints and regulations
- 17:56Measuring performance
- 20:26Standardizing benchmarks
- 24:31Introducing JIT technology
- 30:27Register-based architecture
- 35:54The MJIT implementation
- 41:30Future and conclusion
- 44:42Q&A session
