DL Compiler for Efficiently Utilizing Inter-Core Connected AI Chips (UIUC, Microsoft)
By Technical Paper Link - 28 Aug, 2024 - Comments: 0

A new technical paper titled "Scaling Deep Learning Computation over the Inter-Core Connected Intelligence Processor" was published by researchers at UIUC and Microsoft Research. Abstract "As AI chips incorporate numerous parallelized cores to scale deep learning (DL) computing, inter-core communication is enabled recently by employing high-bandwidth and low-latency interconnect links on th... » read more

Real-Time Safety Monitoring
By Ed Sperling - 28 Aug, 2024 - Comments: 0

Various types of semiconductor test will determine whether a chip is free of defects and meets the specification, but understanding how it's behaving in the field under real workloads and harsh ambient conditions may be very different in automotive applications, where vibration, heat, cold can disrupt the normal functioning of a chip over time and reduce its lifespan. Alex Burlak, vice presiden... » read more

Chiplets and the Early Adopter’s Dilemma
By Eliyan - 28 Aug, 2024 - Comments: 0

Early adopters of a new technology often face a serious dilemma. On one hand, moving early means exploiting the most aggressive new technology available. But on the other hand, making early technology decisions can lock a product line into a path that will later become uncompetitive—either a single-vendor solution that can’t guarantee continuity of supply, or a roadmap that can’t shift an... » read more

Developing Workflows To Streamline System-Level Design
By Ann Mutschler - 28 Aug, 2024 - Comments: 0

Experts At The Table: One of the big challenges facing EDA companies is explaining to customers what's possible, how to streamline their designs, and what can be accomplished at what level of risk. Semiconductor Engineering sat down to talk about how relationships are fundamentally changing between EDA companies and their customers Michal Siwinski, chief marketing officer at Arteris; Chris Muet... » read more

Enabling Efficient Multi-Die Design Implementation and IP Integration
By Synopsys - 28 Aug, 2024 - Comments: 0

Many industry trends are driving chip developers to consider multi-die designs using advanced 2.5D and 3D technologies. Such designs enable incorporating heterogeneous and homogeneous dies in a single package, increasing density while reducing signal propagation times. However, multi-die designs introduce new challenges that must be addressed by all relevant electronic design automation (EDA) a... » read more

Blog Review: Aug. 28
By Jesse Allen - 28 Aug, 2024 - Comments: 0

Synopsys' Jon Ames checks out how the Ultra Ethernet Consortium aims to revolutionize networking by optimizing Ethernet for the rapidly evolving AI and HPC workloads by addressing critical issues like tail latency that are encountered by machine learning algorithms in large compute clusters. Cadence's Kos Gitchev introduces the DDR5 Multiplexed Rank DIMM (MRDIMM), a memory module technology ... » read more

Wire Bond Electrical Structural Test Methodologies
By Keysight - 28 Aug, 2024 - Comments: 0

Wire bonding, a foundational process in microelectronics, is essential to establishing a robust and low-resistance electrical connection between semiconductor chips and their respective packages or, in the case of multi-chip modules, between different chips. This intricate process ensures the device's functionality, reliability, and overall performance. Wire bonding faces several challenges ... » read more

Making Cache Coherent SoC Design Easier with Ncore
By Arteris - 28 Aug, 2024 - Comments: 0

As the number and variety of computing elements in SoCs grow, specific application areas require the tight connection of key processing elements through coherency. Ncore Interconnect IP from Arteris makes cache coherent SoC designs easier, saving 100’s of person-years effort per project vs DIY solutions. This white paper discusses the challenges and solutions in designing cache-coherent Sy... » read more

Intel and Cadence Collaboration on UCIe: Demonstration of Simulation Interoperability
By Cadence - 28 Aug, 2024 - Comments: 0

The Universal Chiplet Interconnect Express (UCIe) 1.0 specification was announced in early 2022. A new updated UCIe 1.1 specification was released on August 8, 2023. The standardized open chiplet standard allows for heterogeneous integration of die-to-die link interconnects within the same package. The UCIe standard allows for advanced package and standard package options to tradeoff cost, band... » read more

GPU Microarchitecture Integrating Dedicated Matrix Units At The Cluster Level (UC Berkeley)
By Technical Paper Link - 27 Aug, 2024 - Comments: 0

A new technical paper titled "Virgo: Cluster-level Matrix Unit Integration in GPUs for Scalability and Energy Efficiency" was published by UC Berkeley. Abstract "Modern GPUs incorporate specialized matrix units such as Tensor Cores to accelerate GEMM operations central to deep learning workloads. However, existing matrix unit designs are tightly coupled to the SIMT core, limiting the size a... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2026 SMG   |  Terms of Service  |  Privacy Policy