Subcategory of memory components (including HBM) used in accelerators and compute systems.
A subcategory covering memory components — including high-bandwidth memory (HBM) — critical to the performance of AI accelerators and compute systems.
NVIDIA's custom high-bandwidth memory (HBM) architecture, part of the NVLink Fusion ecosystem; increases bandwidth, reduces HBM power and saves area on the XPU compute die.
