Taking aim at creating a future supercomputer, NVIDIA has created a new H100 Tensor Core graphics processing unit (GPU) leveraging its latest architecture, Hopper.
Taking aim at creating a future supercomputer, NVIDIA has created a new H100 Tensor Core graphics processing unit (GPU) leveraging its latest architecture, Hopper.
Continuing to unpack NVIDIA's GTC Conference releases, one stand out was the Hopper architecture targeting…
Continuing to unpack NVIDIA's GTC Conference releases, one stand out was the Hopper architecture targeting high-performance computing (HPC) and AI/machine learning.
At this year's GTC Conference, NVIDIA released a variety of impressive new computing technology. One stand out was its…
At this year's GTC Conference, NVIDIA released a variety of impressive new computing technology. One stand out was its Grace "Superchip" CPU (central processing unit).
Altium Education guides college students from the basics of PCB design through developing their first printed circuit board.
Altium Education guides college students from the basics of PCB design through developing their first printed circuit board.
New super-junction metal–oxide–semiconductor field-effect transistors (MOSFETs) from Alpha and Omega are eyeing high…
New super-junction metal–oxide–semiconductor field-effect transistors (MOSFETs) from Alpha and Omega are eyeing high efficiency, small form factor data center design.
How do you design hardware for an idea as big, ambitious, and mysterious as the Metaverse? Qualcomm’s VP & GM of XR,…
How do you design hardware for an idea as big, ambitious, and mysterious as the Metaverse? Qualcomm’s VP & GM of XR, Hugo Swart, takes us behind the scenes to discuss the Extended Reality (XR) technology that one day may immerse us in a virtual universe and change the way we work, live, and play.
Citing a necessary industry shift from system-on-chip (SoC) to system-on-package (SoP) technology, Intel joins the launch…
Citing a necessary industry shift from system-on-chip (SoC) to system-on-package (SoP) technology, Intel joins the launch of the Universal Chiplet Interconnect Express (UCIe) Consortium.
Power management ICs (PMICs) are continually scaling down. Here's how a few companies are packing functionality in these…
Power management ICs (PMICs) are continually scaling down. Here's how a few companies are packing functionality in these devices in the face of miniaturization.
What happens when you apply the merits of analog compute to ML? According to Aspinity, a chip that reduces system power…
What happens when you apply the merits of analog compute to ML? According to Aspinity, a chip that reduces system power by up to 95%.
Packing thousands of NVIDIA GPUS, Meta researchers unveil AI Research SuperCluster (RSC) supercomputer that could train…
Packing thousands of NVIDIA GPUS, Meta researchers unveil AI Research SuperCluster (RSC) supercomputer that could train large AI models needed for new AI-based applications.
Researchers from the National Institute of Science and Technology (NIST) have brought an old charge pumping technique…
Researchers from the National Institute of Science and Technology (NIST) have brought an old charge pumping technique back to life to ensure transistor quality, revitalizing it as "Frequency Modulated Charge Pumping."
Aiming to kick non-volatile memory to the next level, Weebit Nano demonstrated its first crossbar resistive random-access…
Aiming to kick non-volatile memory to the next level, Weebit Nano demonstrated its first crossbar resistive random-access memory (ReRAM or RRAM) arrays.
Announced at AltiumLive, the new Altimade application brings designers, supply chain experts, and manufacturers all on…
Announced at AltiumLive, the new Altimade application brings designers, supply chain experts, and manufacturers all on the same continuous digital thread.
Arm recently announced a new prototype architecture that has spun out of its Morello program, which may pave the road for…
Arm recently announced a new prototype architecture that has spun out of its Morello program, which may pave the road for next-generation data security systems.
At CES this year, Intel's executives are demonstrating new chips from its mobile computing platform and hardware from one…
At CES this year, Intel's executives are demonstrating new chips from its mobile computing platform and hardware from one of its automotive subsidiaries, Mobileye.
Processing-in-memory is no longer confined to the research realm. Even companies like Samsung and IBM are spearheading…
Processing-in-memory is no longer confined to the research realm. Even companies like Samsung and IBM are spearheading the movement toward in-memory computing.
A huge amount of the internet—up to a third of it, in fact—is run by Amazon Web Services. But the cloud, as Wayne…
A huge amount of the internet—up to a third of it, in fact—is run by Amazon Web Services. But the cloud, as Wayne Duso puts it, is not magic pixie dust. It works because of the blood, sweat, and tears of engineers. Hear all about it in this Season 3 finale of Moore's Lobby.
Hoping to take on real-time processing in more niche areas of research, a team from MIT along with A3D3 Institute, are…
Hoping to take on real-time processing in more niche areas of research, a team from MIT along with A3D3 Institute, are using deep learning models to make digesting large data sets easier.
Three recent announcements reflect what's happening in the memory space—and how it correlates with advances in…
Three recent announcements reflect what's happening in the memory space—and how it correlates with advances in high-performance computing.
How close are we to reverse-engineering the human brain's plasticity? New research in computational neuroscience and…
How close are we to reverse-engineering the human brain's plasticity? New research in computational neuroscience and nanotechnologies indicates that neuromorphic chips can read synaptic connectivity with greater sensitivity.
Facebook
Google
GitHub
Linkedin