Samsung Electronics said on Friday it is in "close discussion" to supply its next-generation high-bandwidth memory (HBM) chips, or HBM4, to Nvidia , as the South Korean chipmaker scrambles to catch up with rivals in the AI chip race.

New concerns and challenges for memory in AI data centers.

Podobnie jak reszta największych korporacji na świecie, także Samsung pokazał światu wyniki za trzeci kwartał roku finansowego 2025. Nie mogło jednak zabraknąć też dużych ogłoszeń. A bez wątpienia takim jest zakup 50 tys. kart GPU od firmy NVIDIA. Wyjaśnijmy zatem dlaczego Koreańczycy zdecydowali się na takie wydatki. Samsung też chce mieć swoją megafabrykę AI Wspomniane […]

Micron now shipping 11Gbps HBM4 to first customers, future 40 Gbps GDDR7 mentioned Micron has confirmed that its 12-Hi HBM4 DRAM stacks are now shipping to customers, delivering over 11 Gb/s per-pin speeds...

SK hynix completes HBM4 development, preps mass production SK hynix has confirmed it has finished developing HBM4 and prepared its mass-production system. The company claims doubled bandwidth versus the...

Top AI chipmakers count on faster, denser, more efficient memory to boost training AMD and Nvidia have already announced their next-gen datacenter GPUs will make the leap to HBM4, and if SK Hynix has its way, it’ll be the one supplying the bulk of it.…

Die finalen Verträge stehen vor der Unterzeichnung: SK Hynix wird Nvidias Rubin-Beschleuniger mit dem notwendigen HBM4 bestücken.

韓國晶片製造商SK海力士（SK Hynix）今天表示，已完成下一代高頻寬記憶體4（HBM4）晶片的內部認證流程，並已為客戶建立了生產系統。

Micron advances memory tech by shipping 11 Gbps HBM4 and confirming ultra-fast 40 Gbps GDDR7 development. Explore how these innovations shape AI, HPC, and graphics systems.

Micron has started shipping its fastest HBM4 memory at 11Gbps, aiming to outpace competitors. Partnership with TSMC for HBM4E is planned. ⚙️📦

Com a adoção da tecnologia, a empresa espera voltar ao topo do mercado e brigar melhor contra a SK Hynix e a Micron.

SK hynix is changing wafer cutting for thinner HBM4 and 400-layer NAND, using femto-second lasers to reduce defects but challenges remain. ⚙️🔬

Micron recently announced that it has begun shipping out its HBM4 memory modules to many of its key customers.

SEOUL : Nvidia CEO Jensen Huang asked memory chip maker SK Hynix to bring forward the supply of its next-generation high-bandwidth memory chips (HBM) called HBM4 by six months, SK Group chairman Chey Tae-won said on Monday.SK Hynix previously said it aimed to ship its HBM4 chips to customers in the second

Next up in AI-GPUs: HBM4 in 2025, HBM4e in 2027 The data-center GPU market is now moving away from HBM3 memory in favor of faster HBM3e technology. It will enable higher density per layer and larger capacity...

Vận May Của Samsung Được Thiết Lập Để Chuyển Khi Năng Suất HBM4 Đạt 40% #Samsung #HBM4 #BộNhớBăngThôngCao #SKHynix #NVIDIA #ChipBộNhớ #CôngNghệBánDẫn Samsung, gã khổng lồ công nghệ Hàn Quốc, đang chuẩn bị bước vào một giai đoạn quan trọng trong cuộc đua sản xuất bộ nhớ băng thông cao (HBM). Với việc năng suất thử nghiệm HBM4 đạt mức ấn tượng 40%, Samsung đang hy vọng sẽ lật ngược tình thế sau những thất bại trước đó trong cuộc cạnh tranh với SK Hynix và Micron.

Тестовият образец на процесора Intel Jaguar Shores, заедно с платката, се появи на снимка. Той е предназначен за монтаж в сървърна стойка, има HBM4 памет и е произведен по 18A технологичен процес. Чували ли сте нещо за AI-чиповете на Intel напоследък? Уебсайтът Wccftech ни напомня, че през януари тази година компанията отмени очакваната AI-платформа Falcon Shores. След това Intel обяви намерението си да разработи следващата технология, Jaguar Shores. Инженерният образец на чипа беше заснет това лято. Редакторът на Hardwareluxx Андреас Шилинг сподели в X снимка на тестовия комплект Jaguar Shores, който според него в момента се използва от екипа по топлотехника.

: Top AI chipmakers count on faster, denser, more efficient memory to boost training

Samsung has started sample production of HBM4 memory for NVIDIA testing, aiming to catch up with SK hynix in the competitive memory market. ⚙️🔍

NVIDIA's Rubin AI GPU might arrive 6 months early, boosting AI tech with TSMC's 3nm process and HBM4 memory. Exciting times ahead! 🚀🔧