A Survey of E31 RISC-V Core Floor-Plan and Its Impact on Power, Performance and Area (PPA)
summary
Survey shows a practical floor‑planning method that breaks the E31 core into hierarchical subblocks, runs synthesis with Yosys, placement with TimberWolf/Qflow, routing with Qrouter, and timing with Vesta (OpenTimer coming). A flat full-chip run yields ~74 MHz, while hierarchical isolation raises the slowest block to about 240 MHz (and picoRV32 moves from ~275 MHz to ~400 MHz, ~1.5x). Team also demonstrates a flat tape‑out on X‑FAB 180 nm using the open-source EDA flow.
AI-written summary · about
chapters (9)
- 0:00Introduction and VSD mission
- 2:34Floor planning fundamentals
- 6:30Advanced timing analysis
- 9:01Hierarchical design of E31
- 14:20Results and performance
- 18:35Scaling to PicoRV32
- 22:19Open source EDA roadmap
- 27:01Q&A and EDA ecosystem
- 31:14Community outreach and VSD
related talks
12mPicoSoC: How We Created A RISC V Based ASIC Processor Using A Full Open Source Foundry Targeted...
18mRISC-V Performance Delivered
43mRISC-V CPU Project in Western Digital
11mThe PULP Cores: A Set Of Open Source Ultra Low Power RISC V Cores For Internet Of Things...
22mBOOM v2: An Open Source Out Of Order RISC V Core
41mRISC-V and Open Source Hardware BoF
17mRISC-V Meets 22FDX: an Open Source Ultra-low Power Microcontroller Platform
37mKeynote: RISC-V Launchpad Showcase
