CiM Integration For ML Inference Acceleration


A technical paper titled “WWW: What, When, Where to Compute-in-Memory” was published by researchers at Purdue University. Abstract: "Compute-in-memory (CiM) has emerged as a compelling solution to alleviate high data movement costs in von Neumann machines. CiM can perform massively parallel general matrix multiplication (GEMM) operations in memory, the dominant computation in Machine Lear... » read more

System For Composing Hardware Generators (Cornell Univ.)


A technical paper titled “Correct and Compositional Hardware Generators” was published by researchers at Cornell University. Abstract: "Hardware generators help designers explore families of concrete designs and their efficiency trade-offs. Both parameterized hardware description languages (HDLs) and higher-level programming models, however, can obstruct composability. Different concrete ... » read more

Training Large LLM Models With Billions To Trillion Parameters On ORNL’s Frontier Supercomputer


A technical paper titled “Optimizing Distributed Training on Frontier for Large Language Models” was published by researchers at Oak Ridge National Laboratory (ORNL) and Universite Paris-Saclay. Abstract: "Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Recent studies on loss scaling ... » read more

Reducing Power In Data Centers


The rollout of generative AI, coupled with more data in general, is requiring data centers to run servers harder and longer. That, in turn, is generating more heat and accelerating aging, and to ensure these systems continue working over their projected lifetimes, chipmakers are building extra margin into chips. That increases the amount of energy required to run and cool them, and it can short... » read more

Research Bits: Jan. 16


3D stacking of 2D materials Researchers from Penn State University demonstrated monolithic 3D integration with 2D transistors made from 2D semiconductors called transition metal dichalcogenides. The 2D materials have unique electronic and optical properties, including sensitivity to light, making them ideal for use as sensors. “One challenge is the process temperature ceiling of 450 degre... » read more

Chip Industry Technical Paper Roundup: Jan. 16


New technical papers added to Semiconductor Engineering’s library this week. [table id=188 /] More ReadingTechnical Paper Library home » read more

Properties Of The State-Of-The-Art Commercially Available SiC and GaN Power Transistors


A technical paper titled “Review and Outlook on GaN and SiC Power Devices: Industrial State-of-the-Art, Applications, and Perspectives” was published by researchers at University of Padova. Abstract: "We present a comprehensive review and outlook of silicon carbide (SiC) and gallium nitride (GaN) transistors available on the market for current and next-generation power electronics. Materi... » read more

Novel Neuromorphic Artificial Neural Network Circuit Architecture


A technical paper titled “Mosaic: in-memory computing and routing for small-world spike-based neuromorphic systems” was published by researchers at CEA-LETI Université Grenoble Alpes, University of Zurich and ETH Zurich. Abstract: "The brain’s connectivity is locally dense and globally sparse, forming a small-world graph—a principle prevalent in the evolution of various species, sugg... » read more

Suitability of FeFET-Based CAM Cells For Storage-Class Memory, Under Junction Temperature Variations


A technical paper titled “Ferroelectric Field Effect Transistors–Based Content-Addressable Storage-Class Memory: A Study on the Impact of Device Variation and High-Temperature Compatibility” was published by researchers at Fraunhofer Institute for Photonic Microsystems (IPMS) and Indian Institute of Technology Madras (IIT Madras). Abstract: "Hafnium oxide (HfO2)-based ferroelectric fiel... » read more

An Engineering Algorithm For Chemical Accuracy With Shallow Quantum Circuits


A technical paper titled “Towards chemical accuracy with shallow quantum circuits: A Clifford-based Hamiltonian engineering approach” was published by researchers at California Institute of Technology (Caltech), Microsoft Research AI4Science Lab, and Tencent Quantum Lab. Abstract: "Achieving chemical accuracy with shallow quantum circuits is a significant challenge in quantum computationa... » read more

← Older posts Newer posts →