Master Thesis: Advanced IP Netlist Power Regression and AI-Ready Analytics Framework
Teknik, data och digitalt · Mjukvaru- och webbutveckling · Mjukvaruutveckling · Datavetenskap · Inbyggda system
I korthet
Master Thesis opportunity to develop an automated, AI-ready post-processing and interpretation framework for IP-level netlist power analysis and optimization. The role involves building a drop-triggered power regression system, generating GLS collateral, and implementing an in-house analytics and AI-ready interpretation layer with an HTML dashboard.
Ansvarsområden
- Build a drop-triggered power regression that selects the method per IP (GLS-based or vectorless).
- For key IPs, generate and validate GLS collateral (replay testbenches, sanity checks).
- Deliver an in-house analytics layer ingesting FusionCompiler and PTPX/PrimePower prelayout results.
- Implement an AI-ready interpretation layer over the structured dataset (PTPX reports → normalized schema / Parquet artifacts).
- Develop an HTML dashboard presenting analysis results for shared access.
Krav
- Master´s student in Electrical/Computer Engineering, Computer Science or similar.
- Background in Computer architecture.
- Background in ASIC design.
- Background in RTL HDL coding.
- Background in testbench design using SystemVerilog.
- Working knowledge of UVM.
- Scripting (Tcl/Python) for EDA tools is preferred.
Önskade kvalifikationer
- AI-ready interpretation layer with two capability tiers: Tier 1 (core) for deterministic queries and Tier 2 (assistive) for correlation and hypothesis generation.
- HTML dashboard rendering hierarchical treemaps, pie charts, and trend lines.
Förmåner
- Outstanding opportunity to use your skills and imagination to push boundaries.
- Chance to build solutions never seen before.
- Join a team of diverse innovators.
- Be part of crafting what comes next.
#ASIC backend#netlist generation#power analysis#regression#AI#analytics#framework#frontend#GLS#RTL power tools#SpyGlass-Power#synthesis#FusionCompiler#PTPX#PrimePower#prelayout#treemaps#switching activity#clock-gating#dCGE#QoR#Parquet#natural-language#queries#columnar dataset#retrieval#filtering#ranking#threshold reports#optimization#datapath#glitch hotspots#operating point#idle#active windows#HTML dashboard#pie charts#trend lines#Electrical Engineering#Computer Engineering#Computer Science#Computer architecture#scripting