Install
Packaging & Memory
Chiplets, 3D IC, HBM stacks, DDR5/PCIe lanes, and bandwidth tradeoffs.
- 25 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in Packaging & Memory
Microsoft Maia 300 Puts 288GB of HBM4 at 18TB/s on an N2P Chiplet and 96 Accelerators in a 167kW Rack
52+ min ago (178+ words) Home » News » Microsoft Maia 300 Puts 288GB of HBM4 at 18TB/s on an N2P Chiplet and 96 Accelerators in a 167kW Rack Microsoft’s rack diagram shows jobs sharded across racks over the scale-up fabric with expert-parallel traffic between shards, which is the traffic pattern that large…...
ADDING and REPLACING Marvell Unveils Second-generation Structera X, Industry-first Six-channel CXL 3.2 Memory Expanders for AI Inference
4+ hour, 11+ min ago (921+ words) In the " Industry Ecosystem Support " section, please note the addition of a new fourth paragraph, a quote from Yashar Bayani, director, Hardware Engineering at Meta. The updated release reads: AI and ML workloads are rewriting the rules of data center…...
Nvidia's RTX 5080 Super 24GB slips toward CES 2027 as AI eats the memory
2+ hour, 57+ min ago (287+ words) Board partners like MSI already have RTX 5080 Super hardware with 24GB of GDDR7 ready to ship, but Nvidia has pushed the launch three times, most recently toward a CES 2027 reveal in Las Vegas. Nvidia's long-rumored 24GB RTX 5080 refresh is now tracking toward early…...
KIOXIA CM9-DLC Brings Direct Liquid Cooling to Dual-Port E3.S SSDs up to 30.72TB
2+ hour, 16+ min ago (220+ words) Home » News » KIOXIA CM9-DLC Brings Direct Liquid Cooling to Dual-Port E3.S SSDs up to 30.72TB KIOXIA ties the launch to rising rack power in AI servers, where cold-plate loops that already cool the CPUs and GPUs typically remove heat more efficiently…...
NVIDIA and Cisco USFP Optics Target 400Gb/s per Lane, With MGX 1.2 and DSX OS Updates at OCP 2026
2+ hour, 6+ min ago (168+ words) Home » News » NVIDIA and Cisco USFP Optics Target 400Gb/s per Lane, With MGX 1.2 and DSX OS Updates at OCP 2026 “Building the world’s largest AI factories starts with rethinking the smallest of connections,” said Gilad Shainer, senior vice president at NVIDIA....
Marvell Structera X 3406 and 3506 CXL 3.2 Memory Expanders
4+ hour, 38+ min ago (326+ words) CXL has seen a massive surge recently, and Marvell announced its second-generation Structera X CXL memory expanders, adding CXL 3.2 support, PCIe Gen6 connectivity, and increasing memory channels from four to six. For hyperscalers running DDR4 and lower-speed DDR5 reclamation projects, that means the…...
Gigabyte Confirms New Intel Chips Are Coming to Older DDR4 LGA1700 Boards
5+ hour, 11+ min ago (585+ words) Intel’s LGA1700 socket looked like it had reached the end of the road. It arrived in 2021, has been home to three generations of Core processors and seemed set for retirement. Now it appears to be getting one more lease on life....
KIOXIA Exceria G3 4TB NVME PCIe 5.0 SSD
7+ hour, 28+ min ago (29+ words) The KIOXIA Exceria G3 4TB NVMe PCIe 5.0 SSD is an entry-level storage solution from KIOXIA designed to bring next-generation PCIe 5.0 performance to mainstream client desktops and laptops....
Microsoft's New AI Chip Nearly Triples Rack-Level HBM, Boosting Korean Memory Demand
6+ hour, 56+ min ago (422+ words) Microsoft unveiled its Maia 300 AI accelerator with eight HBM4 units, raising rack-level HBM content by about 2.7 times and lifting demand for Samsung and SK hynix memory....
Marvell Unveils Second-generation Structera X, Industry-first Six-channel CXL 3.2 Memory Expanders for AI Inference
8+ hour, 31+ min ago (195+ words) The Joplin Globe - Download the Globe app to my phone or tablet Marvell Six-channel CXL 3.2 Memory Expander for AI Inference SANTA CLARA, Calif.--(BUSINESS WIRE)--Oct 12, 2026-- Marvell Technology, Inc. (NASDAQ: MRVL), a leader in data infrastructure semiconductor solutions, today announced…...