Blog Review: Aug. 14

By Jesse Allen - 14 Aug, 2024 - Comments: 0

Cadence's Dimitry Pavlovsky highlights two new features in the AMBA CHI protocol Issue G update that enhance security of the Arm architecture: Memory Encryption Contexts, which allows data in each Realm in the memory to be encrypted with a different encryption key, and Device Assignment, which introduces hardware provisions to support fully coherent caches in partially trusted remote coherent d... » read more

Reusable Power Models

By Brian Bailey - 14 Aug, 2024 - Comments: 0

Power is not a new concern, and proprietary models are available for some tasks, but the industry lacks standardization. The Silicon Integration Initiative (Si2) is hoping to help resolve that with an upcoming release of IEEE 2416, based on its Unified Power Model (UPM) work. The creation of any model is not to be taken lightly. There is a cost to its creation, verification and maintenance. ... » read more

CPU Performance Bottlenecks Limit Parallel Processing Speedups

By Bryon Moyer - 12 Aug, 2024 - Comments: 0

Multi-core processors theoretically can run many threads of code in parallel, but some categories of operation currently bog down attempts to raise overall performance by parallelizing computing. Is it time to have accelerators for running highly parallel code? Standard processors have many CPUs, so it follows that cache coherency and synchronization can involve thousands of cycles of low-le... » read more

Chip Industry Week In Review

By The SE Staff - 09 Aug, 2024 - Comments: 0

Three Fraunhofer Institutes (IIS/EAS, IZM, and ENAS) launched the Chiplet Center of Excellence, a research initiative to support the commercial introduction of chiplet technology. The center initially will focus on automotive electronics, developing workflows and methods for electronics design, demonstrator construction, and the evaluation of reliability. The UCIe Consortium published the Un... » read more

HBM3E: All About Bandwidth

By Frank Ferro - 08 Aug, 2024 - Comments: 0

The rapid rise in size and sophistication of AI/ML training models requires increasingly powerful hardware deployed in the data center and at the network edge. This growth in complexity and data stresses the existing infrastructure, driving the need for new and innovative processor architectures and associated memory subsystems. For example, even GPT-3 at 175 billion parameters is stressing the... » read more

Power Delivery Challenged By Data Center Architectures

By Ann Mutschler - 08 Aug, 2024 - Comments: 0

Processor and data center architectures are changing in response to the higher voltage needs of servers running AI and large language models (LLMs). At one time, servers drew a few hundred watts for operation. But over the past few decades that has changed drastically due to a massive increase in the amount of data that needs to be processed and user demands to do it more quickly. NVIDIA's G... » read more

Voltage Drop Now Requires Dynamic Analysis

By Karen Heyman - 08 Aug, 2024 - Comments: 0

At one time a relatively infrequent occurrence, voltage drop is now a major impediment to reliability at advanced nodes. Decades ago, voltage drop was only an issue for very large and high-speed designs, where there was concern about supply lines delivering full voltage to transistors. As design margins have tightened in modern advanced designs, controlling voltage drop has become a requiremen... » read more

Blog Review: Aug. 7

By Jesse Allen - 07 Aug, 2024 - Comments: 1

Synopsys' Jyotika Athavale and Randy Fish investigate the problem of silent data corruption caused by difficult-to-detect hardware defects that cause unnoticed errors in the data being processed and is becoming an increasingly pressing problem as computing scales massively at a rapid pace with the demands of AI. Siemens' Keith Felton suggests adopting physical design reuse circuits to provid... » read more

Chip Industry Week in Review

By The SE Staff - 02 Aug, 2024 - Comments: 0

Okinawa Institute of Science and Technology proposed a new EUV litho technology using only four reflective mirrors and a new method of illumination optics that it claims will use 1/10 the power and cost half as much as existing EUV technology from ASML. Applied Materials may not receive expected U.S. funding to build a $4 billion research facility in Sunnyvale, CA, due to internal government... » read more

Chip Security Now Depends On Widening Supply Chain

By Ann Mutschler - 01 Aug, 2024 - Comments: 0

Securing chips is becoming more challenging as SoCs are disaggregated into chiplets, creating new vulnerabilities that involve hardware and software, as well as multiple entities, and extending threats across a much broader supply chain. In the past, much of the cyber threat model was confined to either hardware or software, and where multiple vendors were involved, various chips were separa... » read more

← Older posts Newer posts →

Knowledge Centers
Entities, people and technologies explored

Shift Left Is The Tip Of The Iceberg

A transformative change is underway for semiconductor design and EDA. New languages, models, and abstractions will need to be created.

by Brian Bailey

Partitioning In The Chiplet Era

Understanding how chiplets interact under different workloads is critical to ensuring signal integrity and optimal performance in heterogeneous designs.

by Ann Mutschler

3.5D: The Great Compromise

Pros and cons of a middle-ground chiplet assembly that combines 2.5D and 3D-IC.

by Ed Sperling

AI’s Role In Chip Design Widens, Drawing In New Startups

Focus is on letting engineers do much more with the same or fewer resources — and less drudgery.

by Karen Heyman

What Comes After HBM For Chiplets

The standard for high-bandwidth memory limits design freedom at many levels, but that is required for interoperability. What freedoms can be taken from other functions to make chiplets possible?

by Brian Bailey

Memory Fundamentals For Engineers

eBook: Nearly everything you need to know about memory, including detailed explanations of the different types of memory; how and where these are used today; what's changing, which memories are successful and which ones might be in the future; and the limitations of each memory type.

by The SE Staff

Why Small Fab And Assembly Houses Are Thriving

Megafabs churning out the most advanced processors are not the only game in town.

by Bryon Moyer

New AI Processors Architectures Balance Speed With Efficiency

Hot Chips 24: Large language models ratchet up pressure for sustainable computing and heterogeneous integration; data management becomes key differentiator.