白皮书

LG Electronics: Video Encoder IP Design Optimization and Verification Using the Catapult Platform

Picture of LG Electronic's Alpha 11 AI Processor Chip

As the algorithmic complexity of intellectual property (IP) designed for semiconductors increases, the time and effort required for IP development and verification escalates. This shift is contributing to longer development cycles in the semiconductor industry, becoming a major factor delaying time-to-market (TTM). Additionally, optimizing power, performance, and area (PPA) to meet the requirements of various product lines is crucial for competitiveness in the IP landscape. This necessitates efficient development and verification of complex IP blocks, as well as enhancing productivity through IP reuse, which is challenging due to the need for managing various hardware versions of complex base logic, making maintenance difficult. To address this, LG Electronics’ SoC Center has adopted CatapultTM HLS (High-Level Synthesis) and used it to design a highly complex video encoder. Through this new design approach, LG Electronics’ SoC Center concluded that adopting Catapult in IP development significantly increases efficiency in terms of time and cost, and there are plans to increase the use of Catapult in their future IP development projects.

分享

相关资源

LG Electronics: Video Encoder IP Design Optimization and Verification Using Catapult
Webinar

LG Electronics: Video Encoder IP Design Optimization and Verification Using Catapult

In this session, LGE describes a new design approach which concluded that adopting Catapult in IP development increases efficiency in time and cost, and they plan to increase usage in future IP projects.

谷歌利用 High-Level Synthesis 开发 WebM 视频解压缩硬件 IP
White Paper

谷歌利用 High-Level Synthesis 开发 WebM 视频解压缩硬件 IP

本文还会介绍 WebM 团队在成功实现 G2 VP9 的过程中如何实际使用 Catapult HLS,并分享一些结果和感想。

Chips&Media:深度学习对象检测 IP 的设计和验证
White Paper

Chips&Media:深度学习对象检测 IP 的设计和验证

Chips&Media 决定采用新的 High-Level Synthesis (HLS) 流程来实现深度学习算法。这使他们可以专注于算法和架构设计,并减少痛苦的调试以及使用昂贵计算资源。