Goto

Collaborating Authors

This Chip for AI Works Using Light, Not Electrons

WIRED

As demand for artificial intelligence grows, so does hunger for the computer power needed to keep AI running. Lightmatter, a startup born at MIT, is betting that AI's voracious hunger will spawn demand for a fundamentally different kind of computer chip--one that uses light to perform key calculations. "Either we invent new kinds of computers to continue," says Lightmatter CEO Nick Harris, "or AI slows down." Conventional computer chips work by using transistors to control the flow of electrons through a semiconductor. By reducing information to a series of 1s and 0s, these chips can perform a wide array of logical operations, and power complex software.


This Chip for AI Works Using Light, Not Electrons

#artificialintelligence

As demand for artificial intelligence grows, so does hunger for the computer power needed to keep AI running. Lightmatter, a startup born at MIT, is betting that AI's voracious hunger will spawn demand for a fundamentally different kind of computer chip--one that uses light to perform key calculations. "Either we invent new kinds of computers to continue," says Lightmatter CEO Nick Harris, "or AI slows down." Conventional computer chips work by using transistors to control the flow of electrons through a semiconductor. By reducing information to a series of 1s and 0s, these chips can perform a wide array of logical operations, and power complex software.


Samsung expands ARTIK IoT module line-up, upgrades cloud

ZDNet

Samsung Electronics has introduced two new modules in its ARTIK IoT platform and updated cloud capabilities. The new ARTIK 0 family is low-power, lightweight and cost-optimized, while the higher-spec ARTIK 7 is intended for high-end gateways and multimedia applications. ARTIK 0 is for end-devices such as HVAC, lighting, industrial sensors, and personal health monitoring. It has a power-efficient ARM Cortex-M microcontrollers and supports lower power wireless standards: ZigBee, Thread, or Bluetooth Smart. It comes with networking stacks, RF, and precertification for regulatory approval.


Apple reportedly bringing artificial intelligence to chips

#artificialintelligence

Apple got an early start in artificial intelligence software with the 2011 introduction of Siri, a tool that lets users operate their smartphones with voice commands. Now the electronics giant is bringing artificial intelligence to chips. Apple is working on a processor devoted specifically to AI-related tasks, according to a person familiar with the matter. The chip, known internally as the Apple Neural Engine, would improve the way the company's devices handle tasks that would otherwise require human intelligence -- such as facial recognition and speech recognition, said the person, who requested anonymity discussing a product that hasn't been made public. Engineers at Apple are racing to catch their peers at Amazon.com and Alphabet in the booming field of artificial intelligence.


Samsung develops first CXL interface based DRAM

ZDNet

Samsung Electronics has developed a new DRAM module based on the Compute Express Link (CXL) interface, something that the company has touted as an industry first. The CXL-based DDR5 memory module comes in the EDSFF form factor and will enable server systems to scale their memory capacity and bandwidth significantly, the South Korean tech giant claimed. The new module can scale memory capacity to terabyte levels, reduce system latency caused by memory caching, as well as allow server systems to accelerate their AI, machine learning, and high-performance computing workloads, Samsung added. The CXL interface was designed to enable high speed and low latency communication between a host processor and other devices such as accelerators, memory buffers and smart I/O, while expanding memory capacity and bandwidth. The interface itself was created by the CXL Consortium, which was formed in 2019 to address the memory capacity and bandwidth need of systems that use more processors to process massive volumes of data for applications such as AI. Its members include Intel, Google, Samsung and other global server and chip companies.