Hackernews posts about HBM3E
- AMD crafts custom EPYC CPU with HBM3 for Azure: 88 Zen 4 cores and 450GB of HBM3 (www.tomshardware.com)
- Azure HBv5: 352 AMD Genoa Cores with over 400 GB of HBM3 (techcommunity.microsoft.com)
- Micron Kicks Off Production of HBM3E Memory (www.anandtech.com)
- AMD Instinct MI325X in Q4 2024, 288GB of HBM3E (ir.amd.com)
- Samsung announces 'Shinebolt' HBM3E memory (www.anandtech.com)
- Nvidia Unveils Updated GH200 Grace Hopper with HBM3e Memory, Shipping in Q2'2024 (www.anandtech.com)
- Nvidia Unveils GH200 'Grace Hopper' GPU with HBM3e Memory (www.anandtech.com)
- Nvidia at SC23: H200 Accelerator with HBM3e and Jupiter Supercomputer for 2024 (www.anandtech.com)
- Nvidia H200 Launched with 141GB of HBM3e at SC23 (www.servethehome.com)
- Nvidia's Plans – B100, "X100", H200, 224G SerDes, OCS, CPO, PCIe 7.0, HBM3E (www.semianalysis.com)
- Micron to Ship HBM3E Memory to Nvidia in Early 2024 (www.anandtech.com)
- Nvidia Announces a H100 144GB HBM3e Model and Anticipated Business Model Shift (www.servethehome.com)
- New 36GB SK Hynix HBM3E 12-High in Volume Production – ServeTheHome (www.servethehome.com)
- Samsung Launches 12-Hi 36GB HBM3E Memory Stacks with 10 GT/S Speed (www.anandtech.com)
- Nvidia at SC23: H200 Accelerator with HBM3e and Jupiter Supercomputer (2023) (www.anandtech.com)
- SK Hynix HBM3e CXL Computational Memory Mcrdimm and More OCP Summit 2023 (www.servethehome.com)
- Micron Kicks Off Production of HBM3E Memory (www.anandtech.com)
- Nvidia at SC23: H200 Accelerator with HBM3e and Jupiter Supercomputer for 2024 (www.anandtech.com)
- Micron to Ship HBM3E Memory to Nvidia in Early 2024 (www.anandtech.com)
- Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild (www.servethehome.com)
- Intel Xeon Max 9480 Deep-Dive 64GB HBM2e Onboard Like a GPU or AI Accelerator (www.servethehome.com)
- Photonics to Make Celestial HBM3 Memory Fabric (www.nextplatform.com)
- SK Hynix Now Sampling 24GB HBM3 Stacks, Preparing for Mass Production (www.anandtech.com)
- Improving Performance and Power with HBM3 (semiengineering.com)
- Faulty Nvidia H100 GPUs and HBM3 memory caused failures during Llama 3 training (www.tomshardware.com)
- Intel Xeon Max 9480 Deep-Dive 64GB HBM2e Onboard Like a GPU or AI Accelerator (www.servethehome.com)
- Micron Publishes Updated DRAM Roadmap: 32 GB DDR5 DRAMs, GDDR7, HBMNext (www.anandtech.com)
- Micron's New HBM3 Gen2 Is Fastest at 1.2 TB/S, Teases Next-Gen at 2 TB/S+ (www.tomshardware.com)