온디맨드 웨비나

STMicroelectronics: A Common C++ and UVM Verification Flow of High-Level IP

예상 소요 시간: 22분

공유

STMicroelectronics presents a unified way to integrate the definition of RTL and C functional coverage and assertion (reducing the coding effort) as well as a method to add constraints to the random values generated in UVMF.

High-Level Synthesis has the great advantage of keeping the design at an algorithmic level, simplifying the translation into RTL. High-Level Verification at C++ level can help to catch several bugs in the earliest stage of the design. The usage of the UVMF (UVM Framework), generated by Catapult, is a good starting point to complete the verification at RTL Level. STMicroelectronics presents a unified way to integrate the definition of RTL and C functional coverage and assertion (reducing the coding effort) as well as a method to add constraints to the random values generated in UVMF.

발표자 소개

Politecnico di Torino

Stefano Moncalvo

MSc Electronic Engineering student

MSc Electronic Engineering student at Politecnico di Torino, specializing in embedded systems. Currently working on the master’s thesis, developing a verification flow for High-Level Synthesis IPs in collaboration with STMicroelectronics.

STMicroelectronics

Martino Zerbini

Digital Design Engineer

Martino Zerbini joined STMicroelectronics in 2006 as Digital Design Engineer. He started using CatapultC in 2010 and introduced its usage inside the Audio Division design team. The main activity was the development of DSP part of Class-D amplifiers. Later he moved inside the MEMS Actuator Division developing laser and micro-mirror drivers. Since 2019, Martino focused his interests on Digital Verification, he is responsible for developing and executing an integrated strategy for the chip verification. From 2021 this includes IPs developed with CatapultC.

관련 자료

블루닷: Catapult-HLS를 이용한 NN기반의 DeepField-PQO 설계 가속화
White Paper

블루닷: Catapult-HLS를 이용한 NN기반의 DeepField-PQO 설계 가속화

고화질 영상에 대한 시장의 수요 증가로 인해 높은 인코딩 비용에 대한 비디오 서비스 제공 업체의 부담이 커지고 있습니다. 이 문제를 해결하기 위해 블루닷은 비디오 인코딩 효율을 향상시키는 AI 기반의 CODEC용 전처리 DeepField-PQO 필터를 개발하였습니다. 블루닷은 필터를 FPGA용 IP로 빠르게 구현하기 위해 HLS를 활용하고, ASIC용으로는 Catapult HLS를 활용하였습니다.

Xperi®: A Designer’s Life with HLS
Webinar

Xperi®: A Designer’s Life with HLS

This webinar will discuss two aspects of their experience going from RTL to HLS. The first topic is using HLS for algorithms such as Face Detection th