How To Build Resilience Into Chips


Disaggregating chips into specialized processors, memories, and architectures is becoming necessary for continued improvements in performance and power, but it's also contributing to unusual and often unpredictable errors in hardware that are extremely difficult to find. The sources of those errors can include anything from timing errors in a particular sequence, to gaps in bonds between chi... » read more

Dealing With Performance Bottlenecks In SoCs


A surge in the amount of data that SoCs need to process is bogging down performance, and while the processors themselves can handle that influx, memory and communication bandwidth are straining. The question now is what can be done about it. The gap between memory and CPU bandwidth — the so-called memory wall — is well documented and definitely not a new problem. But it has not gone away... » read more

Process Innovations Enabling Next-Gen SoCs and Memories


Achieving improvements in performance in advanced SoCs and packages — those used in mobile applications, data centers, and AI — will require complex and potentially costly changes in architectures, materials, and core manufacturing processes. Among the options under consideration are new compute architectures, different materials, including thinner barrier layers and those with higher th... » read more

Devices And Transistors For The Next 75 Years


The 75th anniversary of the invention of the transistor sparked a lively panel discussion at IEDM, spurring debate about the future of CMOS, the role of III-V and 2D materials in future transistors, and what will be the next great memory architecture.[1] Industry veterans from the memory, logic, and research communities see high-NA EUV production, NAND flash with 1,000 layers, and hybrid bon... » read more

Choosing The Correct High-Bandwidth Memory


The number of options for how to build high-performance chips is growing, but the choices for attached memory have barely budged. To achieve maximum performance in automotive, consumer, and hyperscale computing, the choices come down to one or more flavors of DRAM, and the biggest tradeoff is cost versus speed. DRAM remains an essential component in any of these architectures, despite years ... » read more

Choosing The Right Memory At The Edge


As the amount of data produced by sensors in cars and phones continues to grow, more of that data needs to be processed locally. It takes too much time and power to send it all to the cloud. But choosing the right memory for a particular application requires a series of tradeoffs involving cost, bandwidth, power, which can vary greatly by device, application, and even the data itself. Frank Fer... » read more

Boosting Data Center Memory Performance In The Zettabyte Era With HBM3


We are living in the Zettabyte era, a term first coined by Cisco. Most of the world’s data has been created over the past few years and it is not set to slow down any time soon. Data has become not just big, but enormous! In fact, according to the IDC Global Datasphere 2022-2026 Forecast, the amount of data generated over the next 5 years will be at least 2x the amount of data generated over ... » read more

Research Bits: Nov. 29


Earth-bound, more accurate GPS A new idea for terrestrial-based global navigation satellite systems (GNSS) that uses very accurate national atomic clocks on the ground may help self-driving cars in urban environments get where they are going. Researchers from Delft University of Technology (TU Delft), Vrije Universiteit Amsterdam, and VSL have prototyped a hybrid optical–wireless mobile netw... » read more

Ensuring Memory Reliability Throughout the Silicon Lifecycle


By Anand Thiruvengadam and Guy Cortez Memories are everywhere in modern electronics. Discrete memory chips account for much of the space on printed circuit boards (PCBs). Embedded memories consume much of the floorplan in system-on-chip (SoC) devices. Many multi-die chip configurations, including 2.5D/3DIC devices, are driven by the need for faster memory access. Designing and verifying memo... » read more

GDDR6 Memory Enables High-Performance AI/ML Inference


A rapid rise in the size and sophistication of inference models has necessitated increasingly powerful hardware deployed at the network edge and in endpoint devices. To keep these inference processors and accelerators fed with data requires a state-of-the-art memory that delivers extremely high bandwidth. This blog will explore how GDDR6 supports the memory and performance requirements of artif... » read more

← Older posts Newer posts →