Power/Performance Bits: Nov. 16


Light-emitting memory Researchers from Kyushu University and National Taiwan Normal University propose a 'light-emitting memory' based on a perovskite that can simultaneously store and visually transmit data. The team used the idea in conjunction with resistive RAM (RRAM), in which states of high and low resistance represent ones and zeros. "The electrical measurements needed to check the r... » read more

A graph placement methodology for fast chip design


Abstract "Chip floorplanning is the engineering task of designing the physical layout of a computer chip. Despite five decades of research1, chip floorplanning has defied automation, requiring months of intense effort by physical design engineers to produce manufacturable layouts. Here we present a deep reinforcement learning approach to chip floorplanning. In under six hours, our method autom... » read more

Week In Review: Manufacturing, Test


Markets Worldwide semiconductor industry revenue is expected to grow 17.3% in 2021, compared with 10.8% in 2020, according to a new IDC report. Segment breakdown is as follows: [table id=5 /] “Semiconductor wafer prices increased in 1H21 and IDC expects increases to continue for the rest of 2021 due to material costs and opportunity cost in mature process technologies. Overall, IDC pre... » read more

Power/Performance Bits: Sept. 21


Catching switches in action Researchers from SLAC National Accelerator Laboratory, Stanford University, Hewlett Packard Labs, Penn State University, and Purdue University observed atoms moving inside an electronic switch as it turns on and off, revealing a state they suspect could lead to faster, more energy-efficient devices. "This research is a breakthrough in ultrafast technology and sci... » read more

Power/Performance Bits: Aug. 24


Low power AI Engineers at the Swiss Center for Electronics and Microtechnology (CSEM) designed an SoC for edge AI applications that can run on solar power or a small battery. The SoC consists of an ASIC chip with RISC-V processor developed at CSEM along with two tightly coupled machine-learning accelerators: one for face detection, for example, and one for classification. The first is a bin... » read more

New Power, Performance Options At The Edge


Increasing compute intelligence at the edge is forcing chip architects to rethink how computing gets partitioned and prioritized, and what kinds of processing elements and memory configurations work best for a particular application. Sending raw data to the cloud for processing is both time- and resource-intensive, and it's often unnecessary because most of the data collected by a growing nu... » read more

One-On-One: Lip-Bu Tan


Lip-Bu Tan, CEO of Cadence, sat down with Semiconductor Engineering to talk about the impact of massive increases in data across a variety of industries, the growing need for computational software, and the potential implications of U.S.-China relations. What follows are excerpts of that discussion. SE: What do you see as the biggest change for the chip industry? Tan: We're in our fifth g... » read more

Power/Performance Bits: May 25


5G energy harvesting Researchers at Georgia Institute of Technology propose a way to harvest power for IoT devices using 5G networks. The team's device uses a flexible Rotman lens-based rectifying antenna (rectenna) system capable of millimeter-wave harvesting in the 28-GHz band. “With this innovation, we can have a large antenna, which works at higher frequencies and can receive power fr... » read more

Manufacturing Bits: March 23


Measuring acceleration The National Institute of Standards and Technology (NIST) has developed a new and better way to measure acceleration. NIST has developed an optomechanical accelerometer, a technology that has more resolution and bandwidth than conventional accelerometers. Optomechanical accelerometers uses laser light of a known frequency to measure acceleration. With the technology, ... » read more

Power/Performance Bits: Feb. 8


Transparent sensor Researchers at Osaka University created a thin, flexible, transparent sensor using silver nanowire networks. High-resolution printing was used to fabricate the centimeter-scale cross-aligned silver nanowire arrays, with reproducible feature sizes from 20 to 250 micrometers. As a proof-of-concept for functionality, they used their arrays to detect electrophysiological signals... » read more

← Older posts Newer posts →