GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing semiengineering.com — high-bandwidth memory Archives
tag: high-bandwidth memory3D Integration Reduces Embodied-Emissions Impact Of GPU Scaling (imec, VUB)
By Technical Paper Link - 02 Nov, 2026 - Comments: 0
Researchers at imec and Vrije Universiteit Brussels published “Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI.”
Abstract
"GPU compute resources are scaling to support growing AI workloads, leading to further rises in the climate change impact of hyperscale data centers that rely on high-performance GPUs. To model how packaging decisions impact the carbon... » read more
Vertical DRAM Stacking Expands Thermal Design Space Beyond HBM-on-GPU (imec)
By Technical Paper Link - 26 Oct, 2026 - Comments: 0
Researchers at imec published “Beyond HBM-on-GPU: Thermal Design Envelope for 3D Volumetric DRAM-on-GPU Integration.”
Summary:
Researchers evaluated a 3D memory architecture that rotates DRAM dies vertically above a GPU and places cooling cavities between them as an alternative to conventional 2.5D HBM and direct-stacked HBM-on-GPU. Package-level thermal simulations examined stack heigh... » read more
Characterization of HBM Power Consumption (ETH Zurich, NYU)
By Technical Paper Link - 14 Oct, 2026 - Comments: 0
Researchers at ETH Zürich and New York University published a technical paper titled “Understanding the Power Consumption of Modern High Bandwidth Memory: Experimental Analysis and Modeling Using Real HBM2 DRAM Chips."
Abstract Excerpt:
“We perform the first comprehensive experimental characterization of power consumed by real HBM2 DRAM chips. Our extensive characterization yields 1)... » read more
HBF for High-Throughput LLM Serving (UC Berkeley, FuriosaAI)
By Technical Paper Link - 02 Oct, 2026 - Comments: 0
Researchers at the UC Berkeley and FuriosaAI published a technical paper titled “Characterizing High Bandwidth Flash for LLM Serving.”
Abstract
“Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth increasingly become bottlenecks for serving performance... » read more
Concurrent HBM And Host Memory Access Improves LLM Inference Throughput (Georgia Tech, Nvidia, Stanford)
By Technical Paper Link - 21 Sep, 2026 - Comments: 0
Researchers at Georgia Tech, Nvidia Research, and Stanford University published a technical paper titled “BOOST: Concurrent Access to Host Memory and HBM to Accelerate LLM Inference.”
Abstract Excerpt:
“This paper presents BOOST, the first runtime system that provides concurrent and proportional access to both GPU memory tiers, extracting the combined bandwidth of host m... » read more
Reducing HBM ECC Controller Overhead For AI Inference (RPI, IBM)
By Technical Paper Link - 11 Sep, 2026 - Comments: 0
Researchers at Rensselaer Polytechnic Institute and IBM T.J. Watson Research Center published a technical paper titled “REACH: Controller-Managed Long-Span ECC for HBM AI Inference.”
Abstract Excerpt: “High-Bandwidth Memory (HBM) cost motivates stronger controller protection that can support a wider range of device error rates.High-Bandwidth Memory (HBM) cost motivates stro... » read more
Workload-Driven HBF Substrate For Capacity-Scalable LLM Inference (Huawei, ETH Zurich, HUST)
By Technical Paper Link - 31 Aug, 2026 - Comments: 0
Researchers at Huawei, ETH Zürich, and HUST published a technical paper titled “FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration.”
Abstract:
“LLM inference is increasingly constrained by accelerator memory capacity rather than compute throughput. This constraint is especially acute in single-accelerator and small-node i... » read more
Hybrid HBM-HBF Architecture in LLM Inference (University of Oxford)
By Technical Paper Link - 30 Aug, 2026 - Comments: 0
Researchers at the University of Oxford published a technical paper titled “Hardware-Managed Heterogeneous High-Bandwidth Memory and Flash in LLM Inference Systems.”
Abstract Excerpt: “ High-Bandwidth Flash (HBF) offers a denser alternative, providing 16x more capacity per stack at comparable bandwidth. In this work, we show that while replacing HBM with HBF can address the capac... » read more
Issues Stack Up With More HBM Layers
By Ed Sperling - 27 Aug, 2026 - Comments: 0
Key Takeaways:
HBM scaling is running into physical limitations.
More bandwidth translates into higher area and capacity costs.
AI demand is intensifying the DRAM shortage.
DRAM is under stress, and the fallout is affecting the entire chip industry.
Pressed by large systems companies to move data in and out of memory faster, the big three DRAM vendors — Micron, Samsung,... » read more
Near-memory Dequantization Architecture In Custom HBM for LLM inference (SK hynix)
By Technical Paper Link - 13 Jul, 2026 - Comments: 0
Researchers from SK hynix published a technical paper titled “StreamDQ: Near-Memory Weight DeQuantization in Custom HBM for Scalable AI Inference Acceleration.”
The paper proposes StreamDQ for “a lightweight architectural enhancement that enables on-the-fly dequantization in the memory subsystem for high-throughput, large-batch LLM inference,” and reports “up to 7.08× speedup and ... » read more
Trending ArticlesChip Industry Week In Review
Fab expansion accelerates; China advances memory and EUV; Teradyne's test deal; SEMICON West and OCP highlights; 3D SiP; TSMC and ASML signals; 300mm fab spending; optical and 3D-compute startups raise fresh funding; quantum HW advances.
by The SE Staff
Why Physical AI Is So Hard To Engineer
Integrating sensors, compute, and actuators into autonomous systems adds new challenges for chip design.
by Brian Bailey
Chip Industry Week In Review
CHIPS Act $389M to power chips, vertical GaN, materials; Micron's memory roadmap; Nvidia expands supply chain capacity; Tenstorrent raises $1.5B; China NAND fabs; 800V power for AI data centers; Intel advances Arizona fab; China orders +$35B in Nvidia GPUs.
by The SE Staff
Chip Industry Week In Review
Marvell to buy Lumentum; HBM shortages threaten AI expansion; TSMC weighs price hikes; advanced packaging ramps; domain-specialized AI models; Infineon and UMC boost fab investments; Intel's quantum move; Lam and imec advance 3D integration; Google expands TPUs; AI-driven earnings; CPU benchmarking methodology for agentic AI.
by The SE Staff
How Close Are We To Fully Autonomous Chip Design?
Synopsys CEO Sassine Ghazi talks about AI agents, the limits of autonomous engineering, digital twins, and the challenges facing 3D-ICs.
by Ed Sperling
Related ArticlesAI Agent Orchestration For ASIC Autonomy
How to achieve a 10X productivity improvement using AI agents.
by Ed Sperling
Self-Driving Cars Have An Aging Problem
AI workloads are pushing automotive sensors harder, forcing engineers to rethink how long safety-critical systems can be trusted.
Chip Industry Week In Review
DAC's big buzz; CHIPS Act $; China's immersion DUV; UMC expands; SIA's state of the industry; DRAM shortages; earnings; PCB design credential program; IBM's quantum advantage; AI security alliance; foreign robotics ban.
by The SE Staff
Chip Industry Week In Review
2D Tunnel FET; in-memory photonic computing; India's $13.4B Semicon 2.0; SEMICON Taiwan; PCIe 6/7 test; MediaTek deal; 300mm Si photonics; InP expansion; $75M to recycle rare earths; GF PDKs; Gain-Cell RAM; edge AI developer tools; heterogeneous HBM; safe AI in SDVs.
by The SE Staff
Chip Industry Week In Review
Lam Research and ASE expansions; data center shifts; CPO system architecture initiative; 2D-transistor interface solution; USENIX HW security; patent suits; image sensors; programmable AI memtransistor; Nvidia's new plan; earnings; Tier IV's L4 auto chip.
by The SE Staff
Copper’s Grip On AI Scaling Is Starting To Slip
As AI clusters push beyond rack-scale limits, optical interconnects and circuit switching are reshaping how data centers scale.
by Bryon Moyer
Chip Industry Week In Review
New Micron lab; chip/AI price jump; multi-die monitoring; cryo links for quantum chips; interconnect RC bottleneck; 18A win; CPO roadmap; 2 new CEOs; humanoid readiness gap; Hot Interconnects.
by The SE Staff
Semiconductor Earnings Roundup: Revenue, Growth and Takeaways
Company-by-company breakdown: Earnings across +80 semiconductor companies show AI-driven demand extending well beyond the usual suspects.
Popular Tags2.5D
5G
advanced packaging
AI
AMD
ANSYS
Apple
Applied Materials
ARM
Arteris
automotive
business
Cadence
chiplets
DRAM
EDA
EUV
GlobalFoundries
Google
IBM
imec
Infineon
Intel
IoT
IP
Keysight
Lam Research
machine learning
memory
Mentor
Mentor Graphics
MIT
Nvidia
NXP
Qualcomm
Rambus
Samsung
security
SEMI
Siemens
Siemens EDA
Synopsys
test
TSMC
verification
Recent Comments
NavigationCopyright ©2013-2026 SMG | Terms of Service | Privacy Policy
|
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |