뉴스, 기술 자료

반도체 뉴스, HBM 기술 - Hot Chips 2025, AI, Datacenter, IBM, Intel, AMD, Nvidia, Interposer, Photonic, GPU, NPU, Memory, DRAM, SOC, Chiplet

HappyThinker 2026. 1. 12. 07:05

2026-01-12 : 뉴스 9건, 기술자료 PDF 파일 55개입니다. 아래 링크 참고하시기 바랍니다.  다른 자료는 Search에서 키워드 입력하여 검색 가능합니다. 
※ 기술자료는 " Perplexity AI"를 이용하여 3줄로 " 내용 요약 " 정리 하였습니다. 

 

  ♥ 반도체 뉴스 (9건)    
         
NO 키워드 제목 등록일 출처
N1 뉴스 모음 한국 반도체 산업협회 - 데일리 뉴스 모음 2026-01-12 6:30 KSIA
https://www.ksia.or.kr/infomationKSIA.php?data_tab=1
N2 뉴스 모음 [제20260108-TT-01호] 2026년 1월 8일 반도체 기술 관련 주요 뉴스 요약 2026-01-09 9:00 SPTA
Times
https://www.sptatimeskorea.com/post/제20260108-tt-01호-2026년-1월-8일-반도체-기술-관련-주요-뉴스-요약
N3 뉴스 모음 [제20260108-TM-01호] 2026년 1월 8일 반도체 제조 관련 주요 뉴스 요약 2026-01-09 9:00 SPTA
Times
https://www.sptatimeskorea.com/post/제20260108-tm-01호-2026년-1월-8일-반도체-제조-관련-주요-뉴스-요약
N4 뉴스 모음 [제20260108-TI-01호] 2026년 1월 8일 글로벌 반도체 산업 관련 주요 뉴스 요약 2026-01-09 9:00 SPTA
Times
https://www.sptatimeskorea.com/post/제20260108-ti-01호-2026년-1월-8일-글로벌-반도체-산업-관련-주요-뉴스-요약
N5 뉴스 모음 [제20260109-TT-01호] 2026년 1월 9일 반도체 기술 관련 주요 뉴스 요약 2026-01-09 17:00 SPTA
Times
https://www.sptatimeskorea.com/post/제20260109-tt-01호-2026년-1월-9일-반도체-기술-관련-주요-뉴스-요약
N6 뉴스 모음 [제20260109-TI-01호] 2026년 1월 9일 글로벌 반도체 산업 관련 주요 뉴스 요약 2026-01-09 17:00 SPTA
Times
https://www.sptatimeskorea.com/post/제20260109-ti-01호-2026년-1월-9일-글로벌-반도체-산업-관련-주요-뉴스-요약
N7 뉴스 모음 [제 20260111-AI-01호] 2026년 1월 2주차 글로벌 반도체산업 관련 기사 분석 2026-01-11 2:00 SPTA
Times
https://www.sptatimeskorea.com/post/제-20260111-ai-01호-2026년-1월-2주차-글로벌-반도체산업-관련-기사-분석
N8 뉴스 모음 Chip Industry Week in Review (영문)
> hip sales record; chiplet ecosystem accelerator; CES blitz; SDV deals; global fabs; DRAM, NAND price spike; auto L4 delay; data center connectivity buy; GPU-driven swings in power demand; Intel’s 18A AI PC chip; glass substrate deal.
2026-01-09 Semiconductor
Engineering
https://semiengineering.com/chip-industry-week-in-review-120/
N9 뉴스 모음 최신 동향 - AI·ICT Brief > [AI·ICT Brief 2026-01호] "
> CES 2026, AI·ICT 10대 이슈 전망, 중국 인간형 AI 규제
Ⅰ 주요 이슈
   1. CES 2026, 생성형 AI 붐을 지나 실질적 AI 도입 단계로
   2. 2026년을 관통할 AI·ICT 10대 이슈 전망
Ⅱ 주요국 동향
   1. 중국, 인간형 AI 규제 초안 발표
Ⅲ ICT 부문별 모니터링
Ⅳ 주요 ICT 행사 일정
2026-01-09 ITFIND
https://www.itfind.or.kr/streamdocs/view/sd;streamdocsId=8TocIQMYInSrVhgLncE2nUMW6F4n7N070I00xV7usJ4

 

  ♥ 반도체 기술 자료 (PDF 파일 55개)    
  ※ Hot Chips 2025는 2025년8월24일~26일 미국 캘리포니아에서 개최된 세계적인 반도체 기술 컨퍼런스이다.
> 엔비디아, 인텔, AMD, 구글, 애플, 삼성 등 글로벌 빅테크 기업들이 자사의 **최신 고성능 칩 (CPU, GPU, AI 가속기 등)**에 대한 세부 아키텍처를 처음으로 심도 있게 공개하는 자리이다.
NO 키워드 제목 등록일 출처
T1 AI,
Datacenter
Hot Chips 2025 > Tutorials: Sunday, August 24, 2025, Permalink : 7개
Time (PDT)    Title     Presenters
8:30AM-10:30AM    Tutorial 1: Datacenter Racks   
    . How AI workloads shape rack system architecture,     Frank Helms, AMD
    . Scaling fabric technologies,     Darrin Vallis, AMD
    . Liquid cooling with Google Characteristics,     Jorge Padilla, Google
    . Rearchitected power systems,  Harsha Bojja, Microsoft
10:55AM-12:25PM     Tutorial 1: Datacenter Racks (cont)
    . Case study: Nvidia GB200NVL72,  John Norton, NVIDIA
    . Case study: Meta’s Catalina (NVL72),  William Arnold and Matt Bowman, Meta
    . Case study: Google TPU Rack,  Pankaj Makhija, Google
2025-08-24 Hot Chips
https://hc2025.hotchips.org/
T2 AI,
GPU,
TPU
Hot Chips 2025 > Tutorials: Sunday, August 24, 2025, Permalink :  5개
Time (PDT)    Title    Presenters
1:30PM-3:30PM     Tutorial 2: AI Kernel Programming
    . Introduction,  Fredrik Kjolstad, Stanford
    . Decoupling Performance from Correctness with User-Schedulable Kernel Languages,  Andrew Adams, Adobe Research
    . Pallas: Using JAX to write custom kernels for GPUs and TPUs, Sharad Vikram, Google
4:00PM-5:30PM     Tutorial 2: Kernel Programming (cont)
    . Domain specific languages for GPU kernels and automatic kernel authoring with LLMs,  Tri Dao, Princeton, Together AI
    . Programming techniques for implementing ML models on GPUs, Zihao Jia, CMU
2025-08-24 Hot Chips
https://hc2025.hotchips.org/
T3 CPU,
IBM, AI
Hot Chips 2025 > Conference Day 1: Monday, August 25, 2025, Permalink :  5개
Time (PDT)     Title    Presenters
9:15AM-9:30AM     Welcome
     . General Chair Welcome,  Jan-Willem van de Waerdt & Larry Yang, General Chair
     . Program Co-Chairs Welcome,  Ian Bratt & Nhon Quach, PC Co-Chairs
9:30AM-11:00AM     CPU 1a, Chair: Gabriel Southern
     . Cuzco: A High-Performance RISC-V RVA23 Compatible CPU IP,  Ty Garibay & Shashank Nemawarkar, Condor Computing
     . PEZY-SC4s: The Fourth Generation MIMD Many-core Processor with High Energy Efficiency and Fleibility for HPC and AI Applications,  Naoya Hatta, PEZY Computing
     . IBM’s Next Generation Power Microprocessor,  William Starke, IBM
2025-08-25 Hot Chips
https://hc2025.hotchips.org/
T4 CPU,
Intel
Hot Chips 2025 > Conference Day 1: Monday, August 25, 2025, Permalink :  3개
Time (PDT)     Title    Presenters
11:30AM-12:00PM     CPU 1b, Chair: Gabriel Southern
     . Introducing the Next Generation Intel® Xeon® Processor with Efficiency Cores,  Don Soltis, Intel
12:00PM-1:00PM     Security, Chair: Greg Papadopoulos
     . Presto: A RISC-V-Compatible SoC for Unified Multi-Scheme FHE Acceleration over Module Lattice,  Luchang Lei & Hongyang Jia, Tsinghua University
     . Azure Secure Hardware Architecture: Establishing a Robust Security Foundation for Cloud Workloads,  Bryan Kelly, Microsoft
2025-08-25 Hot Chips
https://hc2025.hotchips.org/
T5 AI,
AMD,
SOC
Hot Chips 2025 > Conference Day 1: Monday, August 25, 2025, Permalink : 4개
Time (PDT)     Title     Presenters
2:15PM-3:15PM     Keynote #1, Chair: Cliff Young
     . Predictions for the Next Phase of AI,  Noam Shazeer, GDM VP, Engineering, Google
3:15PM-4:45PM     Graphics, Chair: Lavanya Subramanian
     . AMD RDNA 4 and Radeon RX 9000 Series GPU,  Andy Pomianowski & Laks Pappu, AMD
     . RTX 5090: Designed for the Age of Neural Rendering,  Marc Blackstein, NVIDIA
     . Specialized SoC enabling low-power ‘World Lock Rendering’ in Augmented and Mixed Reality Devices,  Ohad Meitav & Jay Tsao, Meta
2025-08-25 Hot Chips
https://hc2025.hotchips.org/
T6 AMD,
NVIDIA,
AI
Hot Chips 2025 > Conference Day 1: Monday, August 25, 2025, Permalink : 4개
Time (PDT)     Title     Presenters
5:15PM-7:15PM     Networking, Chair: Sherry Xu
     . Intel Mount Morgan Infrastructure Processing Unit (IPU),  Patrick Fleming, Intel
     . AMD Pensando™ Pollara 400 AI NIC Architecture and Application,  Kevin Chu, AMD
     . NVIDIA ConnectX-8 SuperNIC: A Programmable RoCE Architecture for AI Data Centers,  Idan Burstein, NVIDIA
     . Tomahawk Ultra - Ultra Low Latency, High Bandwidth Ethernet Switch chip for HPC and AI/ML applications,  Mohan Kalkunte & Asad Khamisy, Broadcom
2025-08-25 Hot Chips
https://hc2025.hotchips.org/
T7 Photonic,
Interposer
Hot Chips 2025 > Conference Day 2: Tuesday, August 26, 2025, Permalink : 4개
Time (PDT)     Title     Presenters
8:30AM-10:30AM   Optical,  Chair: Borivoje Nikolic
    . Celestial AI Photonic Fabric Module (PF Module) - The world’s first SoC with in-die Optical IO,     Phil Winterbottom, Celestial AI
    . A UCIe Optical I/O Retimer Chiplet for AI Scale-up Fabrics,     Vladimir Stojanovic, Ayar Labs
    . Passage M1000: 3D photonic interposer for AI,     Darius Bunandar, Lightmatter
    . Co-Packaged Silicon Photonics Switches for Gigawatt AI Factories,     Gilad Shainer, NVIDIA
2025-08-26 Hot Chips
https://hc2025.hotchips.org/
T8 AI,
SOC
Hot Chips 2025 > Conference Day 2: Tuesday, August 26, 2025, Permalink : 4개
Time (PDT)     Title     Presenters
11:00AM-12:30PM     Power / Methodology, Chair: Jae W. Lee
    . ECAM Enabled Advanced Thermal Management Solutions for the AI Data Center,     Michael Matthews, Fabric8Labs
    . Everactive Self-Powered SoC with Energy Harvesting, Wakeup Receiver, and Energy-Aware Subsystem,     Ben Calhoun, Everactive
    . Taping Out Three Class Chips per Semester in Intel 16 Technology,     Lucy Revina, UC Berkeley
1:40PM-1:45PM     Awards
    . TCMM Awards Presentation,     Gabriel Southern, TCMM Chair
2025-08-26 Hot Chips
https://hc2025.hotchips.org/
T9 Rapidus,
AI,
Memory,
Chiplet
Hot Chips 2025 > Conference Day 2: Tuesday, August 26, 2025, Permalink : 4개
Time (PDT)      Title     Presenters
1:45PM-2:45PM     Keynote #2,  Chair: Yasuo Ishii
    . Up and Running with Rapidus: How Japan and Cutting-Edge Technologies are Transforming Semiconductor Manufacturing,     Dr. Atsuyoshi Koike, Rapidus
2:45PM-4:15PM     Machine Learning 1,  Chair: Ronny Krashinsky
    . Memory: (Almost) the Only Thing That Matters,     Mark Kuemerle, Marvell
    . Corsair - An In-memory Computing Chiplet Architecture for Inference-time Compute Acceleration,     Sudeep Bhoja, d-Matrix
    . UB-Mesh: Huawei’s Next-Gen AI SuperComputer with A Unified-Bus Interconnect and nD-FullMesh Architecture,     Liao Heng, Huawei
2025-08-26 Hot Chips
https://hc2025.hotchips.org/
T10 NVIDIA,
AMD
Hot Chips 2025 > Conference Day 2: Tuesday, August 26, 2025, Permalink : 4개
Time (PDT)     Title     Presenters
4:45PM-6:15PM     Machine Learning 2,  Chair: Pradeep Dubey
    . NVIDIA’s GB10 SoC: AI Supercomputer On Your Desk,     Andi Skende, NVIDIA
    . 4th Gen AMD CDNA™ Generative AI Architecture Powering AMD Instinct™ MI350 Series GPUs and Platforms,     Michael Floyd & Michael Steffen, AMD
    . Ironwood: Delivering best in class perf, perf/TCO and perf/Watt for reasoning model training and serving,     Norm Jouppi & Sridhar Lakshmanamurthy, Google
6:15PM-6:30PM     Closing Remarks
    . Closing Remarks,     Larry Yang, Vice Chair
2025-08-26 Hot Chips
https://hc2025.hotchips.org/
T11 AI,
SOC,
DRAM
Posters : 5개
> HyperAccel Adelia: A 4nm LLM Processor for Efficient Generative AI Inference Seungjae Moon; Hyper Accel
> Basilisk: A 34 mm² End-to-End Open-Source 64-bit Linux-Capable RISC-V SoC in 130nm BiCMOS Philippe Sauter; ETH Zurich
> Bit-Separable Transformer Accelerator Leveraging Output Activation Sparsity for Efficient DRAM Access Seunghyun Park; Kyungpook National University
> Multi-modal Few-step Diffusion Model Accelerator with Mixed-Precision and Reordered Group-Quantization for On-device Generative AI Sangjin Kim; KAIST
> An Energy-Efficient Spatial Computing SoC for Real-time Interactable-Rendering and Modeling with Surface-aware 3D Gaussian Splatting Seokchan Song; KAIST
2025-08-24 Hot Chips
https://hc2025.hotchips.org/
T12 AI,
NPU
Posters : 6개
> BROCA: A Low-power and Low-latency Conversational Agent RISC-V System-on-Chip for Voice-interactive Mobile Devices Wooyoung Jo; KAIST
> MEGA.mini: A NPU with Novel Heterogeneous AI Processing Architecture Balancing Efficiency, Performance, and Intelligence for the Era of Generative AI Donghyeon Han; Chung-Ang University
> High Density Si-IPD Technologies as enabler for High-Performance and Low-Power consumption Processor Chips Mohamed Mehdi Jatlaoui; Murata
> Clo-HDnn: Continual On-Device Learning Accelerator with Hyperdimensional Computing via Progressive Search Chang Eun Song; UC San Diego
> A 4.69mW LLM Processor with Binary/Ternary Weights for Billion-Parameter Llama Model Sangyeob Kim; Yonsei University
> KLIMA: Low-latency mixed-signal In-Memory Computing accelerator for solving arbitrary-order Boolean Satisfiability Tinish Bhattacharya; UC Santa Barbara
2025-08-24 Hot Chips
https://hc2025.hotchips.org/