惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 【当耐特】
小众软件
小众软件
S
SegmentFault 最新的问题
GbyAI
GbyAI
量子位
爱范儿
爱范儿
L
LangChain Blog
Vercel News
Vercel News
A
About on SuperTechFans
腾讯CDC
博客园_首页
酷 壳 – CoolShell
酷 壳 – CoolShell
月光博客
月光博客
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
H
Help Net Security
U
Unit 42
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
V
V2EX
V
Visual Studio Blog
美团技术团队
D
DataBreaches.Net
The GitHub Blog
The GitHub Blog
N
Netflix TechBlog - Medium

Latest from Tom's Hardware in Semiconductors

Post-silicon era gets closer as industry giants crack the 2D transistor scaling bottleneck with breakthrough tech — imec, ASML, and TSMC fab complementary 2D-material transistors at 50nm pitch on a 300mm wafer Intel Intel’s performance-enhanced 18A-P process enters risk production — drop-in 18A upgrade promises 9% performance improvement at iso-power, cuts thermal resistance by 40% Chinese fab SMIC TSMC says panel packaging won Analyzing TSMC's fab expansion roadmap — multi-fab N2 ramp, CoWoS, SoIC, and uncorking bottlenecks Chinese startup claims photonic chip production without DUV lithography, says nanoimprint process cuts costs by 90%… ASML becomes Europe's most valuable company ever as analysts bet on higher EUV output — its market cap hit… TSMC CEO C.C. Wei says, ‘It will be a long time before we can meet customer demand’ — tells shareholders that he will keep prices stable, refrain from implementing price hikes Seven hospitalized after toxic gas fire at SK hynix advanced memory plant — Cheongju 4th campus incident today led… TikTok owner ByteDance is reportedly developing its own custom AI CPUs — company looks to ease China's… Trailing-edge foundry roadmaps for GlobalFoundries, UMC, and SMIC — mature node chipmakers each pursue differing… Chinese university builds 3D chip design tool tailored to Huawei's ‘LogicFolding’ architecture — 3D design delivers increased performance and better thermal management China adds homegrown AI chips to 'secure and reliable' procurement list for the first time — nine options added as move away from Nvidia continues SK hynix unveils 'iHBM' thermal architecture that cools AI memory at the source — integrated cooling elements inside HBM interface cut thermal resistance by 30%, target next-gen HBM5 accelerators and dense AI data centers Imec builds world's first High-NA EUV-fabricated quantum dot qubit device — breakthrough could pull quantum computing onto the same manufacturing roadmap as next-gen AI processors, compressing timelines Huawei claims sanctions-busting breakthrough with 1.4nm-class chips by 2031, claims 55% higher transistor density — firm claims new LogicFolding chip architecture can bypass EUV restrictions, introduces 'Tau Scaling Law' to replace Moore's Law Samsung's $400,000 payout for memory workers sparks revolt as other divisions get only $4,000, fueling intentional production slowdowns — internal resentment disrupts packaging operations, major AI chip project decisions to a complete halt The custom AI ASIC state of play (May 2026) — Broadcom deals, Google TPUs, Meta MTIA & beyond AMD begins production ramp of 256-core EPYC Venice — first 2nm HPC chip claims 70% performance leap Intel kicks off development on next-decade 10A and 7A process technologies — 14A node remains on track for… SMIC founder and AMEC CEO urge Chinese fabs to test domestic chipmaking tools on active production lines — equipment makers post record revenue but falling margins Russia’s Mikron is selling framed test wafers with up to 120,000 processors as souvenirs — 12 designs, priced around $170 each, sold alongside $2 vials of cleanroom air Trump calls $14 billion Taiwan arms deal a 'negotiating chip' with China after Xi said Taiwan issue could lead to 'clashes and even conflicts' — Trump says 'Taiwan would be very smart to cool it a little bit' Leading-edge foundry roadmaps for TSMC, Intel and Samsung — outlining the path to 1.4nm nodes and beyond TSMC allocates $20 billion to Arizona expansion — project faces water and labor shortages, complicated by visa… NASA partners with Microchip to build next-generation spaceflight chips with 100x the power of current offerings — chip designed to withstand radiation for extended missions on the Moon and Mars Intel, SK hynix shares surge following reports of chip packaging partnership — SK is said to be testing… Apple reportedly strikes deal for Intel to make some of its chips — two tech giants reached a preliminary… Global semiconductor sales hit nearly $300 billion in Q1 2026 — chips are on track to top $1 trillion for this…
Samsung shows first HBM5 mockup with Heat Path Block cool...
Luke James · 2026-06-03 · via Latest from Tom's Hardware in Semiconductors
Samsung HBM5 with HPB
(Image credit: Future)

Samsung displayed its first physical mockup of HBM5 memory at Computex 2026 in Taipei. Tom's Hardware dropped by to see its pairing of the eighth-generation AI memory with a new in-package cooling structure it calls Heat Path Block, or HPB. Just last week, rival SK hynix unveiled its own iHBM thermal design, meaning both companies are now focusing on the same heat bottleneck in the die-to-die interface that connects memory to the processor. Samsung also confirmed that it’ll fab HBM5’s base die on its in-house 2nm process, down from the 4nm node used for HBM4 and HBM4E.

Tom's Hardware Premium Roadmaps

Rather than letting heat escape outward through the core dies, HPB builds a separate set of thermal pillars that pull heat from inside the stack and carry it to a spreader sitting above or beside the package, according to Samsung at Computex.

Samsung HBM5 with HPB

(Image credit: Future)

The design concentrates on the D2D PHY layer, the high-speed link between the HBM base die and the GPU, where power density and temperatures increase exponentially as stacks grow taller and run quicker. Samsung said it has already implemented and verified HPB on HBM4E, the generation whose first 12-layer samples it began shipping last month at 14 Gbps, scaling to 16 Gbps, with 3.6 TB/s of bandwidth per stack.

Samsung runs both a memory business and a logic foundry, letting it build the HBM5 stack and the 2nm die beneath it in-house. "AI systems are becoming more powerful and densely integrated, making heat management, data-processing efficiency, and packaging stability just as important as memory performance itself," Song Jai-hyuk, president and CTO of Samsung's Device Solutions division, told reporters at Computex, according to the Korea Herald. Song said the company would keep building its competitiveness in next-generation memory through cooperation with partners, including Nvidia.

Last year, a roadmap from KAIST projected HBM5 reaching a 4,096-bit interface, roughly 4 TB/s per stack, and about 100 watts of per-stack power, a thermal load that goes a long way in explaining why both Korean memory giants are reworking their packaging now rather than at launch.

Image 1 of 2

Samsung HBM5 with HPB
(Image credit: Future)

SK hynix faced the same problem via a different route. Its iHBM design embeds cooling elements made of electrically non-conductive, thermally conductive silicon into the D2D PHY layer, which the company said cuts thermal resistance by more than 30% against current products.

SK hynix has opted to place a cooling element directly at the hotspot, while Samsung has built a route to evacuate heat away from it. Both methods are slated to debut with HBM5, but it’ll be a little while before we see either in action, as neither company expects it to reach mass production before 2028.

Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.

Google Preferred Source

Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

Luke James is a freelance writer and journalist.  Although his background is in legal, he has a personal interest in all things tech, especially hardware and microelectronics, and anything regulatory.