Unverified85% confidenceFactTime unknown
Blackwell单颗GPU晶体管数量是前代Hopper架构H100的约两倍
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBlackwell采用双芯片互联设计，两颗GPU裸片通过10TB/s的芯片间互联（NV-HBI）连接，在操作系统层面呈现为单一逻辑GPU74% similarUnverifiedNVIDIA's GB300 Blackwell Ultra GPU integrates two GPU chips and one Grace CPU, interconnected via NVLink-C2C, with memory bandwidth exceeding 8 TB/s and inference performance 4 to 5 times higher than the H100.73% similarUnverified现代GPU如NVIDIA H100、H800原生支持FP8计算，理论上可实现约2倍吞吐量提升70% similarUnverifiedBlackwell (B100/B200 series) was released in 2024, manufactured using TSMC's 4NP process, with a single GPU integrating 208 billion transistors69% similarUnverifiedBlackwell introduces FP4 for inference and, in the form of the GB200 NVL72 rack, unifies 72 GPUs into a single compute pool with unified addressing.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4495API
curl https://kongchang.com/api/v1/knowledge/claims/4495MCP
get_claim(id=4495)