数据库分类 · 12 记录
内存
High-bandwidth memory is the scarcest commodity in AI hardware. The generations, the suppliers and where each is used.
现场笔记
如果你在整个网站只学一条硬件课，就选这条：AI性能通常由内存决定，而非算力。能提供关键内存的只有三家公司，产品已经断货多年，本站所有GPU路线图都在围绕它弯曲。
从这三个开始
HB
High-Bandwidth Memory (HBM)
先读这篇。堆叠内存是现代AI芯片得以运转的根本原因。
HB
HBM4
2026年一代——更宽、更快，已被预订一空。
SK hynix
整场AI热潮中悄然胜出的赢家。
SK hynix
整场AI热潮中悄然胜出的赢家。
Memory technologies
9
HB
High-Bandwidth Memory (HBM)
Stacked DRAM wired straight to the GPU — the scarcest commodity in AI.
HB
HBM3E
The 2024–26 workhorse: up to 36 GB per stack in 12-high form.
HB
HBM4
2026's generation: a 2,048-bit interface and logic-die base from the foundries.
CX
CXL
Compute Express Link: pooled and expanded memory over PCIe wiring.
D&
DDR5 & LPDDR5X
The system memory feeding CPUs — and, via Grace, the GPUs too.
GD
GDDR7
Graphics memory conscripted for cost-efficient inference.
HB
HBM2
The 2016–2020 generation that powered V100 and A100-40GB.
HB
HBM2E
The refined HBM2 behind A100-80GB, Gaudi and Maia.
HB
HBM3
The H100/MI300X generation: ~0.8 TB/s per stack.
