Explore

Trendline Trendline
Relativity Networks Secures $22 Million to Advance Faster Fiber Technology for Data Centers

Relativity Networks Secures $22 Million to Advance Faster Fiber Technology for Data Centers

Relativity Networks Secures $22 Million to Advance Faster Fiber Technology for Data Centers
Rapid Read Rapid Read
IBM Unveils Modular Cryogenic System to Advance Quantum Computing Towards Fault Tolerance

IBM Unveils Modular Cryogenic System to Advance Quantum Computing Towards Fault Tolerance

IBM has introduced a new modular, ultracold cryogenic system designed to interconnect hundreds of quantum computer chips. This innovation aims to address significant infrastructure challenges in quantum computing and pave the way for the development of a powerful, fault-tolerant quantum system by 2029. The system consists of individual units, each measuring 8 feet tall by 8 feet wide, with an internal capacity of approximately 9 cubic feet. These 'quantum fridges' can achieve temperatures as low as 10 millikelvins, which is nearly absolute zero and significantly colder than deep space. Such extreme cold is crucial for the proper operation of IBM's superconducting quantum processing units (QPUs). The modular design allows for the expansion of system capabilities by networking individual modules together using 'L-couplers,' which are superconducting cables approximately 3.3 feet long. This interconnectivity between separate cryogenic modules has been demonstrated, marking a significant step in scaling quantu...
Trendline Trendline
OCI Tokuyama Semiconductor Materials Advances Ultralow-K Dielectrics for Future Electronic Devices

OCI Tokuyama Semiconductor Materials Advances Ultralow-K Dielectrics for Future Electronic Devices

OCI Tokuyama Semiconductor Materials Advances Ultralow-K Dielectrics for Future Electronic Devices
Trendline Trendline
Semiconductor Industry Prepares for Complementary Field Effect Transistors (CFETs) to Boost Chip Performance

Semiconductor Industry Prepares for Complementary Field Effect Transistors (CFETs) to Boost Chip Performance

Semiconductor Industry Prepares for Complementary Field Effect Transistors (CFETs) to Boost Chip Performance
Rapid Read Rapid Read
SK hynix and Global Researchers Publish Co-Packaged Optics Roadmap in Nature Electronics for AI Infrastructure

SK hynix and Global Researchers Publish Co-Packaged Optics Roadmap in Nature Electronics for AI Infrastructure

SK hynix, in collaboration with researchers from the University of Virginia (UVA), University of Illinois Urbana-Champaign (UIUC), Nanyang Technological University (NTU), Massachusetts Institute of Technology (MIT), and Yonsei University, has published a technology roadmap for co-packaged optics (CPO) in 'Nature Electronics.' This research addresses the growing 'bandwidth wall' bottleneck in hyperscale AI clusters, where data movement between thousands of GPUs and High Bandwidth Memory (HBM) stacks is becoming a limiting factor. The paper proposes an optics-centric co-design architecture that connects memory and processors through optical links, aiming to improve the scalability of large-scale AI systems. CPO integrates optical transceivers into the same package as the processor, allowing chips to exchange data using light instead of traditional copper-based electrical interconnects, which suffer from signal loss and high power consumption over longer distances.
Trendline Trendline
IBM Achieves Milestone in Quantum Computing with Modular Cryogenic System Connection

IBM Achieves Milestone in Quantum Computing with Modular Cryogenic System Connection

IBM Achieves Milestone in Quantum Computing with Modular Cryogenic System Connection
Trendline Trendline
Cerebras Unveils Faster WSE-3 Turbo Processor and Rack-Scale CS-4 System for AI Acceleration

Cerebras Unveils Faster WSE-3 Turbo Processor and Rack-Scale CS-4 System for AI Acceleration

Cerebras Unveils Faster WSE-3 Turbo Processor and Rack-Scale CS-4 System for AI Acceleration
Trendline Trendline
Claude Code Sessions Optimize Token Usage for AI Development Efficiency

Claude Code Sessions Optimize Token Usage for AI Development Efficiency

Claude Code Sessions Optimize Token Usage for AI Development Efficiency
Trendline Trendline
Cerebras Systems Overclocks WSE-3 Engine for New CS-4 "Nexus" Systems, Enhancing AI Inference Capabilities

Cerebras Systems Overclocks WSE-3 Engine for New CS-4 "Nexus" Systems, Enhancing AI Inference Capabilities

Cerebras Systems Overclocks WSE-3 Engine for New CS-4 "Nexus" Systems, Enhancing AI Inference Capabilities
Rapid Read Rapid Read
MatrAIx AI Project Releases Persona 1M Dataset on Hugging Face for AI System Evaluation

MatrAIx AI Project Releases Persona 1M Dataset on Hugging Face for AI System Evaluation

The MatrAIx project has released its Persona 1M dataset on Hugging Face, providing a population-scale, persona-driven infrastructure for evaluating AI systems and interactive products. This initiative aims to simulate heterogeneous users to test AI systems, moving beyond generic user testing. The core of MatrAIx is a shared schema of 1,290 categorical dimensions covering background, psychology, capability, and behavior. These personas are generated synthetically but are grounded in human evidence, with a quality-filtered coreset of one million personas available for research. The system allows for reproducible tasks across four environments: Survey, AI Chatbot, Web, and App (native desktop and mobile). This release is intended to foster collaboration and contribution within the MatrAIx research community.
Rapid Read Rapid Read
AI Algorithm Designs Microchip Components 500 Times Smaller Than Human Capabilities

AI Algorithm Designs Microchip Components 500 Times Smaller Than Human Capabilities

Scientists have successfully utilized an artificial intelligence (AI) algorithm to design and fabricate components for photonic microchips that are up to 500 times smaller than what human engineers could previously achieve. This breakthrough, published on May 28 in the journal Nature Communications, involves shrinking three essential components: wavelength splitters, spatial mode sorters, and mirrors. Photonic microchips, which use light particles (photons) instead of electrons to transmit and process information, offer significantly faster data processing, higher bandwidth, and reduced energy loss compared to conventional microchips. The AI algorithm was given specific functional requirements for the components and manufacturing constraints, then iteratively refined designs to create nanostructures that were beyond human intuition. This method allows for a substantial increase in available on-chip space, potentially enabling new functionalities by integrating more components.