[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’

▲ LPO retains the pluggable optical module architecture while eliminating the DSP inside the module, whereas NPO places optical engines close to the switch chip but outside its package.

Related

Silicon[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’ SK hynix Newsroom

Silicon[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’ SK hynix Newsroom

Silicon[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’ SK hynix Newsroom

Silicon[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’ SK hynix Newsroom

Silicon[Tech Note] Why does AI still have to wait with tens of thousands of GPUs? How silicon photonics and CPO are building the ‘highways of light’ SK hynix Newsroom

JapanNVIDIA、音声の文字起こし・翻訳を行うAIモデル「Nemotron 3.5 Transcribe」を公開 gihyo.jp

More from SK hynix Newsroom on Accept All.