https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Tue, 16 Jun 2026 00:00:00 GMT https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging.en https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging.en A single giant die can no longer push performance higher on its own. This post walks through how chiplets, CoWoS, 3D stacking, and the UCIe standard turned advanced packaging into the variable that decides accelerator performance. From the limits of the monolithic die to the TSMC supply bottleneck, thermal and power challenges, and the optical-integration future. Tue, 16 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) gpu-cudachipletadvanced-packagingcowosuciehbmhardware https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging.ja https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging.ja 一つの巨大なダイだけでは、もはや性能を引き上げられない時代です。本稿では、チップレット、CoWoS、3D積層、UCIe標準を通じて、先端パッケージングがどのようにAIアクセラレータの性能を分ける核心的な変数になったのかを見ていきます。モノリシックダイの限界から、TSMCの供給ボトルネック、熱と電力の課題、そして光集積の未来までを整理します。 Tue, 16 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) gpu-cudachipletadvanced-packagingcowosuciehbmhardware https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging https://www.youngju.dev/blog/gpu-cuda/2026-06-16-chiplet-cowos-advanced-packaging 하나의 거대한 다이로는 더 이상 성능을 끌어올릴 수 없는 시대입니다. 이 글에서는 칩렛, CoWoS, 3D 적층, UCIe 표준을 통해 첨단 패키징이 어떻게 AI 가속기의 성능을 가르는 핵심 변수가 되었는지 살펴봅니다. 모놀리식 다이의 한계부터 TSMC 공급망 병목, 열·전력 과제, 그리고 광 통합의 미래까지 정리합니다. Tue, 16 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) gpu-cudachipletadvanced-packagingcowosuciehbmhardware