Yield Tracking In RDL


Yield is a much bigger issue when it comes to panel-level packages, which may contain up to 24 RDL layers. Just finding the defects is a massive challenge, let alone understanding how they will impact the entire device. Many of these advanced packages are being used in data centers for generative AI, and killer defects caused by bridges and opens can cause serious problems. What happens, for in... » read more

Why There Are Still No Commercial 3D-ICs


Building chips in three dimensions is drawing increased attention and investment, but so far there have been no announcements about commercial 3D-IC chips. There are some fundamental problems that must be overcome and new tools that need to be developed. In contrast, the semiconductor industry is becoming fairly comfortable with 2.5D integration, where individual dies are assembled on some k... » read more

Can Data Centers Afford To Turn Up The Heat?


Typically, when we discuss digital twin software for data centers, we highlight how engineers can use data center software to model complex thermals using physics-based simulation and find effective ways to cool IT equipment. However, there are compelling efficiency and cost-saving reasons for data center operators to actively seek to run their data centers hotter. But how can this be done wit... » read more

Reducing Power In Data Centers


The rollout of generative AI, coupled with more data in general, is requiring data centers to run servers harder and longer. That, in turn, is generating more heat and accelerating aging, and to ensure these systems continue working over their projected lifetimes, chipmakers are building extra margin into chips. That increases the amount of energy required to run and cool them, and it can short... » read more

The Future Of Memory


Experts at the Table: Semiconductor Engineering sat down to talk about the impact of off-chip memory on power and heat, and what can be done to optimize performance, with Frank Ferro, group director, product management at Cadence; Steven Woo, fellow and distinguished inventor at Rambus; Jongsin Yun, memory technologist at Siemens EDA; Randy White, memory solutions program manager at Keysight; a... » read more

Very Short Reach SerDes In Data Centers


Speed is critical inside of data centers, and the distance that signals have to travel can have a big impact on time to results. But there are a number of variables that need to be considered, including what is an acceptable loss, how much power can be dissipated in a server rack, and what are the various connection options being used. Keivan Javadi Khasraghi, staff technical product manager at... » read more

Reduce Data Center Over-Provisioning And Stranded Capacity For Sustainability


In the ever-evolving landscape of data centers, the issue of stranded capacity has become a significant concern for operators. Stranded capacity refers to the underutilization of resources. It is best referred to as the elephant in the data center due to the enormity of its impact. The losses are even more significant for the enterprise data center categories at above 40%. This outcome n... » read more

Die-To-Die Security


Security concerns are growing as more chiplets or die are added into a package. There are more possible attack points, and data is becoming increasingly valuable, which makes a successful attack much more lucrative than in the past. Mike Borza, Synopsys scientist, talks about the impact of heterogeneous integration on security, what the risks are for multi-tenant data centers, and what happens ... » read more

Developing Energy-Efficient AI Accelerators For Intelligent Edge Computing And Data Centers


Artificial intelligence (AI) accelerators are deployed in data centers and at the edge to overcome conventional von Neumann bottlenecks by rapidly processing petabytes of information. Even as Moore’s law slows, AI accelerators continue to efficiently enable key applications that many of us increasingly rely on, from ChatGPT and advanced driver assistance systems (ADAS) to smart edge device... » read more

Improved Arm Server Price-Performance For HPC


The availability of Amazon EC2 Hpc7g instances with the AWS Graviton3E and Elastic Fabric Adapter (EFA) is opening new opportunities in key areas: Manufacturing Aerospace Automotive engineering Weather prediction The new AWS EC2 instance types have AWS Graviton3E’s 64 Arm Neoverse V1 cores and 8 channels of DDR5 memory. This is alongside the AWS Nitro v5 card with EFA deliver... » read more

← Older posts