Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

The first Qualcomm High Bandwidth Compute silicon is here, and it’s validated on real hardware. We’re bringing compute closer to memory to take on the memory wall and lay the foundation for Qualcomm Dragonfly AI250. Learn more:

Qualcomm

444,624 subscribers

15,793 просмотров • 5 дней назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 4

Фото профиля anurag

anurag4 дней назад

Qualcomm for 1T $

Фото профиля Lunaris

Lunaris4 дней назад

Getting that first HBC silicon validated on real hardware is a big milestone, I like seeing it move out of the lab.

Фото профиля 蓝眼泪（互关）

蓝眼泪（互关）3 дней назад

计算靠近内存这条路线，本质是在挑战GPU的内存带宽瓶颈。高通从手机芯片切入AI PC，走通了就是第二战场。

Фото профиля Raúl Nogales 🇪🇸🇺🇸

Raúl Nogales 🇪🇸🇺🇸5 дней назад

The memory wall is the least glamorous problem in AI and probably the most expensive one. Models do not stall because they cannot think, they stall waiting for data to arrive, and moving compute closer to memory attacks exactly that wait.

Похожие видео

AI inference is memory-bound more often than compute-bound. High Bandwidth Compute (HBC) flips the traditional model by moving compute to the data, helping unlock dramatic gains in memory bandwidth and efficiency. Learn more:

AI inference is memory-bound more often than compute-bound. High Bandwidth Compute (HBC) flips the traditional model by moving compute to the data, helping unlock dramatic gains in memory bandwidth and efficiency. Learn more:

Qualcomm

11,901 просмотров • 2 месяцев назад

The compute continuum is complete. Introducing Qualcomm Dragonfly. More soon at #QCOMInvestorDay.

The compute continuum is complete. Introducing Qualcomm Dragonfly. More soon at #QCOMInvestorDay.

Qualcomm

32,806 просмотров • 5 месяцев назад

Qualcomm is bringing our CPU to the data center. Qualcomm Chief Financial Officer and Chief Operating Officer Akash Palkhiwala explains. Listen in full at #JPMTMC with moderator Samik Chatterjee:

Qualcomm is bringing our CPU to the data center. Qualcomm Chief Financial Officer and Chief Operating Officer Akash Palkhiwala explains. Listen in full at #JPMTMC with moderator Samik Chatterjee:

Qualcomm

16,344 просмотров • 1 год назад

The year of agents is in full swing. From the stage at #COMPUTEX2026, Qualcomm CEO Cristiano R. Amon on AI becoming more personal, shifting from tools we use to systems that can take action on their own:

The year of agents is in full swing. From the stage at #COMPUTEX2026, Qualcomm CEO Cristiano R. Amon on AI becoming more personal, shifting from tools we use to systems that can take action on their own:

Qualcomm

12,179 просмотров • 5 месяцев назад

Speaking of spot on. Gavin Gavin Baker was asked in early Jan'25 his prediction for best performing asset class of the year (as @jason references in latest The All-In Podcast): "I think the companies that make high bandwidth memory. Going back to "we're going to run out of compute," it's actually a pretty shocking stat: high bandwidth memory is a bigger part of NVIDIA's COGS on GPUs than Taiwan Semi is. And today there's two companies that can make it, SK Hynix and Micron. We'll see if Samsung gets their act together. But HBM, it's in NVIDIA GPUs, AMD GPUs, Amazon Trainiums. And particularly in a world of test-time compute and inference being so important, high bandwidth memory is arguably more important than it ever was. And it's been sold out for the last two years. So high bandwidth memory would be my pick."

Speaking of spot on. Gavin Gavin Baker was asked in early Jan'25 his prediction for best performing asset class of the year (as @jason references in latest The All-In Podcast): "I think the companies that make high bandwidth memory. Going back to "we're going to run out of compute," it's actually a pretty shocking stat: high bandwidth memory is a bigger part of NVIDIA's COGS on GPUs than Taiwan Semi is. And today there's two companies that can make it, SK Hynix and Micron. We'll see if Samsung gets their act together. But HBM, it's in NVIDIA GPUs, AMD GPUs, Amazon Trainiums. And particularly in a world of test-time compute and inference being so important, high bandwidth memory is arguably more important than it ever was. And it's been sold out for the last two years. So high bandwidth memory would be my pick."

Fireside Alpha

66,227 просмотров • 4 месяцев назад

We're announcing a multi-generation collaboration with Amazon Web Services to build next-generation AI data center infrastructure, working together on customized silicon and AI inference at scale. Read the announcement: Read the 8-K:

We're announcing a multi-generation collaboration with Amazon Web Services to build next-generation AI data center infrastructure, working together on customized silicon and AI inference at scale. Read the announcement: Read the 8-K:

Qualcomm

72,951 просмотров • 2 месяцев назад

Qualcomm and Xiaomi extend their 15-year collaboration with a new multi-year deal, continuing to drive innovation together in mobile and beyond. Xiaomi will keep using premium Snapdragon 8-series and be among the first to adopt the next-gen chip later this year.

Qualcomm and Xiaomi extend their 15-year collaboration with a new multi-year deal, continuing to drive innovation together in mobile and beyond. Xiaomi will keep using premium Snapdragon 8-series and be among the first to adopt the next-gen chip later this year.

Qualcomm

25,834 просмотров • 1 год назад

🎙️ NEW EPISODE: Qualcomm's HBC vs HBM, Dragonfly AI 250, and Winning on TCO Austin sits down with Qualcomm's Durga Malladi live in Maui to talk HBC (High Bandwidth Compute). HBC is Qualcomm's differentiated bet to win data center inference workloads. HBM shuttles data across wide buses to a separate accelerator. HBC puts compute directly on the stacked DRAM's logic die. - HBM is fast but power-hungry; HBC drops latency AND power per bit - 18x effective bandwidth on the AI 250 at the SAME 768 GB and SAME 160 kW - A trillion-parameter FP4 model on a single card - Foundry + memory-vendor relationships de-risk multi-megawatt supply at scale Chapters: 0:00 Introduction 2:49 The Memory Wall Problem 8:05 HBC Physical Architecture 9:33 HBC vs. Custom HBM 11:50 Silicon Proof Points Coming 12:08 Managing Thermals 13:34 Dragonfly AI 250 14:48 Trillion-Parameter Model on One Card 16:56 Tokenomics and TCO 18:26 Why TCO is Key 19:26 Manufacturing at Scale Get more of Austin and Vik daily, free! Sign up: Connect with Vik and Austin: Vik's Paid Substack: Austin's Paid Substack: Austin Lyons Vikram Sekar ✈️ Japan Qualcomm Snapdragon

🎙️ NEW EPISODE: Qualcomm's HBC vs HBM, Dragonfly AI 250, and Winning on TCO Austin sits down with Qualcomm's Durga Malladi live in Maui to talk HBC (High Bandwidth Compute). HBC is Qualcomm's differentiated bet to win data center inference workloads. HBM shuttles data across wide buses to a separate accelerator. HBC puts compute directly on the stacked DRAM's logic die. - HBM is fast but power-hungry; HBC drops latency AND power per bit - 18x effective bandwidth on the AI 250 at the SAME 768 GB and SAME 160 kW - A trillion-parameter FP4 model on a single card - Foundry + memory-vendor relationships de-risk multi-megawatt supply at scale Chapters: 0:00 Introduction 2:49 The Memory Wall Problem 8:05 HBC Physical Architecture 9:33 HBC vs. Custom HBM 11:50 Silicon Proof Points Coming 12:08 Managing Thermals 13:34 Dragonfly AI 250 14:48 Trillion-Parameter Model on One Card 16:56 Tokenomics and TCO 18:26 Why TCO is Key 19:26 Manufacturing at Scale Get more of Austin and Vik daily, free! Sign up: Connect with Vik and Austin: Vik's Paid Substack: Austin's Paid Substack: Austin Lyons Vikram Sekar ✈️ Japan Qualcomm Snapdragon

Semi Doped

22,380 просмотров • 1 месяц назад

To understand what’s next for AI, you first have to understand how computing architecture is evolving. In the agentic era, intelligence is becoming distributed across devices, the edge, and the data center, allowing every layer of the stack to do what it does best:

To understand what’s next for AI, you first have to understand how computing architecture is evolving. In the agentic era, intelligence is becoming distributed across devices, the edge, and the data center, allowing every layer of the stack to do what it does best:

Qualcomm

10,398 просмотров • 3 месяцев назад

$MU $SKHY $DRAM Holy Shit $AMD's Lisa Su just spent two full minutes at the 2026 AI keynote raving about HBM4 capacity as the thing that separates Helios from the competition. Not compute. Memory. "When you compare Helios to the competition, we're delivering 15% more compute, 50% more HBM4 memory capacity and memory bandwidth, and 50% more scale-out bandwidth." Notice which number is bigger. "What that means is that every Helios can deliver more performance for the largest models, more capacity for longer context, and the bandwidth to scale across thousands of racks.... More than 18,000 CDNA five GPU compute units, over 4,600 Zen 6 CPU cores, and 31 terabytes of HBM4 memory, all in a single rack." "That's what it takes to run agentic AI at scale. Today, I'm excited to announce that Helios is in full production. We have shipments on track to start at the end of the third quarter and ramping into the fourth quarter in the second half of the year. I can tell you, customer demand for Helios is extremely strong, we're extremely proud of the work that we have done across the leading AI labs to adopt Helios."

$MU $SKHY $DRAM Holy Shit $AMD's Lisa Su just spent two full minutes at the 2026 AI keynote raving about HBM4 capacity as the thing that separates Helios from the competition. Not compute. Memory. "When you compare Helios to the competition, we're delivering 15% more compute, 50% more HBM4 memory capacity and memory bandwidth, and 50% more scale-out bandwidth." Notice which number is bigger. "What that means is that every Helios can deliver more performance for the largest models, more capacity for longer context, and the bandwidth to scale across thousands of racks.... More than 18,000 CDNA five GPU compute units, over 4,600 Zen 6 CPU cores, and 31 terabytes of HBM4 memory, all in a single rack." "That's what it takes to run agentic AI at scale. Today, I'm excited to announce that Helios is in full production. We have shipments on track to start at the end of the third quarter and ramping into the fourth quarter in the second half of the year. I can tell you, customer demand for Helios is extremely strong, we're extremely proud of the work that we have done across the leading AI labs to adopt Helios."

Trade Whisperer

180,543 просмотров • 3 месяцев назад

Micron’s new DRAM-based Compute Express Links (CXLs) are high-speed devices that help interconnect processors, accelerators, memory, storage and IO while simultaneously increasing compute efficiency and scalability. Learn More → Mouser Electronics

Micron’s new DRAM-based Compute Express Links (CXLs) are high-speed devices that help interconnect processors, accelerators, memory, storage and IO while simultaneously increasing compute efficiency and scalability. Learn More → Mouser Electronics

Supplyframe

139,526 просмотров • 1 год назад

Android XR is officially here! 🚀 Our new OS for next-gen headsets & glasses debuts on Samsung’s Galaxy XR. It’s the first platform built for the Gemini era, integrating a helpful AI assistant from the ground up to change how you get things done. Huge congrats to the teams at Android, Samsung Mobile and Qualcomm on this launch! Learn more here:

Android XR is officially here! 🚀 Our new OS for next-gen headsets & glasses debuts on Samsung’s Galaxy XR. It’s the first platform built for the Gemini era, integrating a helpful AI assistant from the ground up to change how you get things done. Huge congrats to the teams at Android, Samsung Mobile and Qualcomm on this launch! Learn more here:

Sameer Samat

132,268 просмотров • 1 год назад

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

SK Hynix's Hoshik Kim admits high bandwidth memory "is not the answer" to the memory-wall problem, and SK is working on different solutions to solve the bottleneck. "No, actually, I kind of agree with Pat. So HBM is not the answer." [SK Hynix is admitting that HBM is a bad memory?] "Nothing is a bad memory. It's a good memory, but it's not the final answer. So actually, HBM will not solve the memory-wall problem. Memory-wall problem is an inherent AI problem, which you cannot avoid." "So we try our best to provide higher bandwidth with this memory, with HBM technology even though it has some limitation, as Pat already mentioned, with thermal, IOs, cost, a lot of stuff. "But that's the only thing we got right now to help ease this memory-wall problem, memory-bottleneck problem. But at the same time, we are working in different directions to solve this memory-wall problem with different solutions."

Fireside Alpha

161,722 просмотров • 3 месяцев назад

We’re hiring! Join the team at BTQ Technologies and work on the cutting-edge QCIM (Quantum Compute-in-Memory) platform, a next-gen quantum-secure hardware architecture that’s redefining security for payments, AI, IoT, and more. If you’re passionate about crypto-agile silicon hardware and software, post-quantum cryptography, and being part of something transformational, we want to hear from you! Apply today and help build the future of secure systems. Roles available in New York, USA, Portland,USA, and Sydney, Australia:

We’re hiring! Join the team at BTQ Technologies and work on the cutting-edge QCIM (Quantum Compute-in-Memory) platform, a next-gen quantum-secure hardware architecture that’s redefining security for payments, AI, IoT, and more. If you’re passionate about crypto-agile silicon hardware and software, post-quantum cryptography, and being part of something transformational, we want to hear from you! Apply today and help build the future of secure systems. Roles available in New York, USA, Portland,USA, and Sydney, Australia:

BTQ Technologies

20,836 просмотров • 11 месяцев назад

Rebuilding the internet’s base layer for high-performance blockchains is the next frontier. Austin Federa | 🇺🇸 explains why bandwidth, not compute, is the real bottleneck + how Shelby and DoubleZero pair decentralized hot storage with global high-throughput on Aptos.

Rebuilding the internet’s base layer for high-performance blockchains is the next frontier. Austin Federa | 🇺🇸 explains why bandwidth, not compute, is the real bottleneck + how Shelby and DoubleZero pair decentralized hot storage with global high-throughput on Aptos.

Aptos Labs

56,533 просмотров • 11 месяцев назад

📣 Call for proposals! Our first funded programme is now live — Scaling Compute: AI at 1/1000th the cost. Hear more from PD Suraj Bramhavar on how we aim to radically reduce the cost + energy consumption of compute hardware, and open new avenues to reap the benefits of AI 👇

📣 Call for proposals! Our first funded programme is now live — Scaling Compute: AI at 1/1000th the cost. Hear more from PD Suraj Bramhavar on how we aim to radically reduce the cost + energy consumption of compute hardware, and open new avenues to reap the benefits of AI 👇

ARIA

61,149 просмотров • 2 лет назад

Behind every AI agent that can reason, plan, and act is an orchestration layer that keeps everything in sync. Learn why the CPU plays a critical role in powering agentic AI experiences:

Behind every AI agent that can reason, plan, and act is an orchestration layer that keeps everything in sync. Learn why the CPU plays a critical role in powering agentic AI experiences:

Qualcomm

22,812 просмотров • 2 месяцев назад

Elon Musk on Tesla’s AI5 chip: At Tesla, there are two chip programs: • Dojo → training • AI4 / AI5 → inference in vehicles AI4 is what’s shipping in cars today AI5 is being finalized and it’s a massive leap By some metrics, AI5 is ~40× better than AI4 (Not 40%. 40 times.) Why the jump is so big: "This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip" • Tesla fixes actual bottlenecks, not just adds compute • Example: SoftMax – AI4: ~40 emulation steps – AI5: a few steps natively in silicon Raw improvements: • ~8× compute • ~9× memory • ~5× memory bandwidth • Native mixed-precision handling But the real gain comes from eliminating core AI4 limitations at the silicon level, turning those raw gains into a ~40× real-world improvement This isn’t just a faster chip, it’s a fundamentally smarter one

Elon Musk on Tesla’s AI5 chip: At Tesla, there are two chip programs: • Dojo → training • AI4 / AI5 → inference in vehicles AI4 is what’s shipping in cars today AI5 is being finalized and it’s a massive leap By some metrics, AI5 is ~40× better than AI4 (Not 40%. 40 times.) Why the jump is so big: "This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip" • Tesla fixes actual bottlenecks, not just adds compute • Example: SoftMax – AI4: ~40 emulation steps – AI5: a few steps natively in silicon Raw improvements: • ~8× compute • ~9× memory • ~5× memory bandwidth • Native mixed-precision handling But the real gain comes from eliminating core AI4 limitations at the silicon level, turning those raw gains into a ~40× real-world improvement This isn’t just a faster chip, it’s a fundamentally smarter one

X Freeze

73,645 просмотров • 9 месяцев назад

Qualcomm just announced Snapdragon Reality Elite, its new flagship XR chipset, and it will debut in the compute puck of Xreal's Aura Android XR device this fall. Details here:

Qualcomm just announced Snapdragon Reality Elite, its new flagship XR chipset, and it will debut in the compute puck of Xreal's Aura Android XR device this fall. Details here:

UploadVR

14,291 просмотров • 4 месяцев назад