Holistic Die-to-Die Interface Design Methodology For 2.5-D Multi-Chip-Module Systems


More than Moore technologies can be supported by system level diversification enabled by chiplet based integrated systems within multi-chip-modules (MCM) and silicon interposer based 2.5D systems. The division of large system-on-chip dies into smaller chiplets with different technology nodes specific to the chiplet application requirement enables the performance enhancement at system level whil... » read more

The Computational Electromagnetics Simulation Challenge Of 3D-IC


By Kelly Damalou and Matt Commens Innovation in semiconductor design today is energized primarily by AI/ML, data centers, autonomous and electric vehicles, 5G/6G, and IoT. Recently developed 2.5 and 3D-IC silicon-based packaging technologies have advanced the state of the art beyond SoC technologies which first united digital, analog, and memory functions on a single chip in the '90s. These ... » read more

Dissolving The Barriers In Multi-Substrate 3D-IC Assembly Design


Advanced packaging continues to promise improved form factor, cost, performance, and functionality compared to the traditional transistor scaling on SoCs. This is done by integrating multiple dies on top of a substrate (organic or silicon). Besides multiple dies, multiple substrates can typically exist in a 3D-IC assembly. In this case, the benefits of advanced packaging are taken to a whole ne... » read more

Heterogeneous Integration Using Organic Interposer Technology


As the costs of advanced node silicon have risen sharply with the 7 and 5-nanometer nodes, advanced packaging is coming to a crossroad where it is no longer fiscally prudent to pack all desired functionality into a single die. While single-die packages will still be around, the high-end market is shifting towards multiple-die packages to reduce overall costs and improve functionality. This shif... » read more

Chipmakers Getting Serious About Integrated Photonics


Integrating photonics into semiconductors is gaining traction, particularly in heterogeneous multi-die packages, as chipmakers search for new ways to overcome power limitations and deal with increasing volumes of data. Power has been a growing concern since the end of Dennard scaling, which happened somewhere around the 90nm node. There are more transistors per mm², and the wires are thinne... » read more

HBM2E Raises The Bar For AI/ML Training


The largest AI/ML neural network training models now exceed an enormous 100 billion parameters. With the rate of growth over the last decade on a 10X annual pace, we’re headed to trillion parameter models in the not-too-distant future. Given the tremendous value that can be derived from AI/ML (it is mission critical to five of six of the top market cap companies in the world), there has been ... » read more

Nvidia’s Top Technologists Discuss The Future Of GPUs


Semiconductor Engineering sat down to discuss the role of the GPU in artificial intelligence, autonomous and assisted driving, advanced packaging and heterogeneous architectures with Bill Dally, Nvidia’s chief scientist, and Jonah Alben, senior vice president of Nvidia’s GPU engineering, at IEEE’s Hot Chips 2019 conference. What follows are excerpts of that conversation. SE: There are ... » read more

Silicon Photonics Begins To Make Inroads


Integrating photons and electrons on the same die is still a long way off, but advances in packaging and improvements in silicon photonics are making it possible to use optical communication for a variety of new applications. Utilizing light-based communication between chips, or in self-contained modules, ultimately could have a big impact on chip design. Photons moving through waveguides ar... » read more

Chiplet Momentum Builds, Despite Tradeoffs


Chip design is a series of tradeoffs. Some are technical, others are related to cost, competitive features or legal restrictions. But with the nascent 'chiplet' market, many of the established balance points are significantly altered, depending on market segments and ecosystem readiness. Chiplets provide an alternative mechanism for integrating intellectual property (IP) blocks into a semico... » read more

GDDR6 – HBM2 Tradeoffs


Steven Woo, Rambus fellow and distinguished inventor, talks about why designers choose one memory type over another. Applications for each were clearly delineated in the past, but the lines are starting to blur. Nevertheless, tradeoffs remain around complexity, cost, performance, and power efficiency.   Related Video Latency Under Load: HBM2 vs. GDDR6 Why data traffic and bandw... » read more

← Older posts