D-Matrix co-founder and CTO Sudeep Bhoja told Let's Data Science that Raptor's early 3D-DRAM silicon uses 0.37 picojoules per bit moved, roughly five to eight times better than the 2 to 3 picojoules p…
Global Unichip Corp. (GUC) announced on September 22, 2026 that its HBM4E PHY and Controller IP is design-ready and has been adopted in customer AI ASICs, reaching data transfer speeds up to 16 Gbps o…
Nvidia's next-generation Rubin Ultra accelerator will ship with 192GB of HBM per GPU, down from 288GB in standard Rubin and B300, according to SemiAnalysis, which first reported the change. SemiAnalys…
High bandwidth memory (HBM) is hitting scaling limits driven primarily by thermal gradients across the stack, according to a technical deep dive that cites JEDEC standards and Samsung's HBM4 architect…
NVIDIA has revived its Rubin CPX GPU for production in the first quarter of 2027, according to supply-chain analyst Ming-Chi Kuo of TF International Securities, switching from 128 GB of GDDR7 to 168 G…
NVIDIA has revived its 'Rubin CPX' AI accelerator, now featuring 168 GB of HBM4 memory instead of the previously planned 128 GB of GDDR7, according to supply chain analyst Ming Chi Kuo. The GPU, dedic…
OpenAI and Broadcom's Jalapeño inference chip, unveiled Tuesday at the Hot Chips conference, delivers 1.5 to 1.9 times more work per watt and 1.7 to 3.6 times lower latency on tested models, according…
Micron Technology (NASDAQ:MU) trades at $910.43, up 674.9% over the past year, with 24/7 Wall St. setting a 12-month price target of $954.59 (4.85% upside) and a HOLD recommendation at 90% confidence …
SK hynix is collaborating with TSMC and Intel Foundry to integrate its HBM4 memory into advanced packaging technologies, including Intel's EMIB, as disclosed at Hot Chips 2026. The collaboration aims …
D-Matrix unveiled Raptor, a datacenter inference accelerator that bonds 3D DRAM directly to the logic die, eliminating the memory PHY, at Hot Chips 2026. The card delivers 32GB of capacity at over 100…
SK hynix detailed its advanced packaging roadmap for High-Bandwidth Memory (HBM) at Hot Chips 2026, focusing on HBM4 and beyond, with plans to double TSV counts, increase I/O speeds, and integrate log…
Micron Technology at Hot Chips 2026 detailed how high-bandwidth memory (HBM) and advanced packaging are central to AI system design, citing a widening gap where AI accelerator TFLOPS grow 3x every two…
Micron CEO Sanjay Mehrotra said artificial intelligence has changed the memory industry's traditional boom-and-bust cycle by creating sustained demand for high-bandwidth memory and other data-center p…
Micron Technology (NASDAQ:MU) trades at $937.11 with a 24/7 Wall St. 12-month price target of $966.70, implying 3.16% upside and a HOLD rating with 90% confidence. The stock has surged 228.54% year to…
NVIDIA reported Q1 FY27 revenue of $82 billion, up 85% year-over-year, with data center revenue at $75 billion, and guided Q2 revenue to $91 billion, while Micron Technology reported fiscal Q3 revenue…
Sandisk taped out its first High Bandwidth Flash (HBF) memory die, a milestone announced at its 2026 Investor Day on August 13, with first HBF inference product samples targeted for 2027. The first-ge…
SK hynix reported record quarterly revenue and operating profit in the second quarter, surpassing KRW 100 trillion in cumulative first-half revenue for the first time, driven by AI memory demand. Ryu …
SanDisk's High Bandwidth Flash technology delivered 12.8 TB/s of memory bandwidth with 4 TB of capacity per GPU in simulation, closing to within 2.2% of HBM bandwidth for inference workloads. The stac…
AMD's Instinct MI455X accelerator, unveiled at the 2026 Advancing AI event, introduces the CDNA 5 architecture, delivering 4x peak FP4/FP8 matrix performance and 2x other compute versus the MI355X, bu…
A new paper from Google DeepMind, co-authored by Turing Award winner David Patterson and Xiaoyu Ma, argues that the biggest obstacle to scaling large language model inference is memory, not raw comput…