What To Do About Electrostatic Discharge


Electrostatic discharge is a well-understood phenomenon, but it’s becoming more difficult to plan for as single chips are replaced by multiple chips or chiplets in a package, and as the density of components continues to increase with each new node. In both cases, the probability for failure increases unless these sudden shocks are addressed in the design. Dermott Lynch, director of product m... » read more

Total Overlay With Multiple RDLs


As Advanced IC Substrates (AICS) add more RDL layers, requiring additional via connections between the RDL layers, the potential for cumulative overlay shift increases. This overlay shift can lead to longer RDL traces, which increases interconnect resistance, resulting in lower yield. Keith Best, director of product marketing, for lithography at Onto Innovation, talks about total overlay — th... » read more

Designing Chips For Outer Space


If designing chips in cars sounds difficult, try designing them for space. There are huge temperature swings, and more radioactive particles than on Earth, which can cause single-event upsets, transients, functional interrupts, and latch-ups. A destructive latch-up can ruin a device, and in space that could transform an expensive piece of hardware into space junk. Ian Land, senior director for ... » read more

Coding And Debugging RISC-V


As monolithic device scaling continues to wind down and evolve toward increasingly heterogeneous designs, it has created an inflection point for chip architects to create customized cores that are much more energy efficient and faster than off-the-shelf processors. Zdeněk Přikryl, CTO of Codasip, talks about where RISC-V fits into this picture, using a modular ISA and custom instruction layer... » read more

DSP Techniques For High-Speed SerDes


Sensors everywhere, more connected devices, and the rollout of smart everything has created a flood of data. The question now is how to best handle all of that data, where to process it, and how to move it locally and to the outside network. Madhumita Sanyal, technical product manager at Synopsys, talks about the need for continuous performance improvements in SerDes, PCIe, NRZ, and PAM4, and w... » read more

Memory And High-Speed Digital Design


As DRAM gets faster, timing constraints, jitter, and signal integrity become harder to control. The real challenge is to understand what can go wrong early in the design process, and that becomes more complex with each new version of memory and higher signal speeds. Stephen Slater, product manager for EDA products at Keysight, talks about how simulation can be applied to these issues, what to t... » read more

Verifying A RISC-V Processor


Verifying an SoC is very different than verifying a processor due to the huge state space in the processor. In addition to the tools needed for an SoC, additional tools are required for a step and compare environment. Larry Lapides, vice president at Imperas, talks about the need to verify asynchronous events like interrupts, how to compare a reference model to RTL, and the need for both hardwa... » read more

Issues In Calculating Glitch Power


The amount of power consumed by redundant non-functional toggles, or glitch power, can be as high as 35% of total power consumption in a design. What can be done about that? Godwin Maben, low-power architect and scientist at Synopsys, takes a deep dive into the causes of glitch, how it is affected by new process nodes and heterogeneous integration, and the impact of different workloads, higher ... » 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

Application-Optimized Processors


Executing a neural network on top of an NPU requires an understanding of application requirements, such as latency and throughput, as well as the potential partitioning challenges. Sharad Chole, chief scientist and co-founder of Expedera, talks about fine-grained dependencies, why processing packets out of order can help optimize performance and power, and when to use voltage and frequency scal... » read more

← Older posts Newer posts →