Home Blog Page 29
Google Ironwood TPU Rack
At Hot Chips 2025, Google went into its Ironwood TPU packages and deployment in an awesome glimpse of the company's AI hardware prowess
AMD MI350 Accelerator
The second big machine learning accelerator talk of the afternoon belongs to AMD. The company's chip architects are at this year's show to tell...
NVIDIA GB10 SoC
We got more architectural details around the NVIDIA GB10 at Hot Chips 2025 including how the Arm CPU and Blackwell GPU are combined
Huawei UB-mesh
The third and final machine learning presentation before the afternoon break comes from Huawei. Unlike many of the other ML vendors who are here...
Card Level Scaleup: 16 Chiplet Hierarchical All-to-All
d-Matrix Corsair is an in-memory computing platform for AI Inference and the company went into its future plans at Hot Chips 2025
Why Is Memory Important
Marvell showed its massively dense SRAM, its custom HBM solution, and how it is adding Arm cores to CXL memory controllers at Hot Chips 2025
Fabric8Labs ECAM Enabled Thermal Solutions _Page_11
Fabric8Labs ECAM uses the electrical current from an OLED display to manufacture copper liquid cooling 3D coldplates with pixel precision
NVIDIA Co Packaged Optics With Silicon Photonics At Hot Chips 2025 _Page_14
At Hot Chips 2025, NVIDIA showed its co-packaged optics solutions and its next-generation Spectrum-XGS for scale-across long-distance AI clusters
Lightmatter Passage M1000 At Hot Chips 2025 Passage M1000 Components
The Lightmatter Passage M1000 is an optical interposer that will allow for massive chips with 114Tbps of bandwidth
Ayar Labs UCIe Optical IO Retimer Hot Chips 2025 _Page_06
Ayar Labs has a UCIe optical I/O retimer that it is showing off at Hot Chips 2025. The basic idea is to make a...