Latest news with #CDNA4
Yahoo
a day ago
- Business
- Yahoo
AMD (AMD) Unveils 1,400W MI355X AI GPU to Challenge Nvidia's Blackwell
AMD (AMD, Financials) officially launched its Instinct MI355X GPU accelerator Wednesday, showcasing a massive leap in compute power and energy demands as it competes with Nvidia's Blackwell Ultra B300. Warning! GuruFocus has detected 3 Warning Signs with AMD. The MI355X is part of AMD's new CDNA 4 architecture and is optimized for AI inference. With support for FP4, FP6, FP8, and FP16 precision, the MI355X delivers up to 20.1 PFLOPS in FP4/FP6 workloads and 10.1 PFLOPS in FP8, slightly ahead of Nvidia's B300 at 15 FP4 PFLOPS. To support this performance, the MI355X consumes 1,400W peak, nearly doubling the 750W required by its predecessor, the MI300X. AMD expects some users may still air-cool the chip, but liquid cooling is the standard. The GPU includes 288 GB of HBM3E memory with bandwidth reaching 8 TB/s. A scaled 8-way configuration brings system-level performance to 161 PFLOPS (FP4) and 80.5 PFLOPS. While raw compute marks a win on paper, AMD still trails Nvidia in deployment scale and software ecosystem. Pegatron is reportedly preparing a 128-way MI350X system, but Nvidia remains dominant in large-scale AI training clusters. AMD's Chief Technology Officer Mark Papermaster said zettascale supercomputing by 2035 will require processors consuming up to 2,000W each. He projected that future AI systems may need nuclear-scale powerup to 500 MW per machine. This article first appeared on GuruFocus. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Forbes
2 days ago
- Business
- Forbes
AMD Accelerates AI Data Centers With Instinct And Helios
Today, AMD held its Advancing AI event in San Jose, California. This year's event centered around the launch of the new Instinct MI350 series GPU accelerators for servers, advances to the company's ROCm (Radeon Open Compute) software development platform for the Instinct accelerators, and AMD's data center system roadmap. Disclosure: My company, Tirias Research, has consulted for AMD and other companies mentioned in this article. The Instinct MI350 & MI355X GPU accelerator specs AMD First up is the latest in the Instinct product line, the MI350 and MI355X. Like its main competitor in the AI segment, AMD has committed to an annual cadence for new server AI accelerators. The MI350 and MI355X are the latest and are based on the new CDNA 4 architecture. The MI350 is a passively cooled solution that utilizes heat sinks and fans, whereas the MI355X is a liquid-cooled solution that employs direct-to-chip cooling. The liquid cooling system provides two significant benefits: the first is an increase in Total Board Power (TBP) from 1000W to 1400W, and the second is an increase in rack density from 64 GPUs per rack to up to 128 GPUs per rack. According to AMD, the MI350 series of GPU accelerators provides approximately a 3x improvement in both AI training and inference over the previous MI300 generation, with competitive performance equal to or better than the competition on select AI models and workloads. (Tirias Research does not provide competitive benchmark information unless it can verify it). Structurally, the MI350 series is similar to the previous MI300 generation, utilizing 3D hybrid bonding to stack an Infinity Fabric die, two I/O dies, and eight compute dies on top of a silicon interposer. The most significant changes are the shift to the CDNA 4 compute architecture, the use of the latest HBM3E high-speed memory, and architectural enhancements to the I/O, which resulted in two dies rather than four. The various dies are manufactured on TSMC's N3 and N6 process nodes. The result is an increase in performance efficiency throughout the chip while maintaining a small footprint. New ROCm 7 features AMD The Second significant announcement, or group of announcements, is around ROCm, AMD's open-source software development platform for GPUs. The release of ROCm 7 demonstrates just how far the software platform has come. One of the most significant changes is the ability to run PyTorch natively on Windows on an AMD-enabled PC, a huge plus for developers, and making ROCm truly portable across all AMD platforms. ROCm now supports all major AI frameworks and models, including 1.8 million models on Hugging Face. ROCm 7 also provides an average of 3 times better training performance than ROCm 6 on leading industry models and 3.5 times higher inference performance. In addition the enhancements to ROCm, AMD is doing more outreach to developers, including a developer track at the Advancing AI event, and the availability of the new AMD Developer Cloud accessed through GitHub. Helios AI Rack AMD The third major announcement was the forthcoming rack architecture, scheduled for 2026, called Helios. Like the rest of the industry, AMD is shifting its system focus to the rack as the platform, rather than just the server tray. The Helios will be a new rack architecture based on the latest AMD technology for processing, AI, and networking. Helios will feature the Zen 6 Epyc processor, the Instinct MI400 GPU accelerator based on the CDNA Next architecture, and the Pensando Vulcano AI NIC for scale-out networking. For scale-up networking between GPU accelerators within a rack, Helios will leverage UALink. The UALink 1.0 specification was released in April. Marvell and Synopsys have both announced the availability of UALink IP, and switch chips are anticipated from several vendors, including UALink partners like Astera Labs and Cisco. Additionally, an A-list of partners and customers joined AMD at Advancing AI, including Astera Labs, Cohere, Humain, Meta, Marvell, Microsoft, OpenAI, Oracle, Red Hat, and xAI. Humain was the most interesting because of its joint venture with AMD and other silicon vendors to build an AI infrastructure in Saudi Arabia. Humain has already begun the construction of eleven data centers with plans to add 50MW modules every quarter. Key to Humain's strategy is leveraging the abundant power and young labor force in Saudi Arabia. There is much more detail behind these and the extensive list of partnership announcements, but these three underscore AMD's dedication to remaining competitive in data center AI solutions, demonstrate its consistent execution, and reinforce its position as a viable alternative provider of data center GPU accelerators and AI platforms. As the tech industry struggles to meet the demand for AI, AMD continues to enhance its server platforms to meet the needs of AI developers and workloads. While this does not leapfrog the competition, it does narrow the gap in many respects, making AMD the most competitive alternative to Nvidia.
Yahoo
01-05-2025
- Business
- Yahoo
Better Semiconductor Stock: AMD vs. Nvidia
The negative stock market sentiment has weighed on shares of AMD and Nvidia this year. However, both companies have been delivering healthy growth thanks to catalysts such as AI. It won't be surprising to see these chip stocks regain their mojo on account of recent tariff-related developments. The PHLX Semiconductor Sector index has been under duress this year and lost over 14% of its value thanks to the tariff-fueled economic uncertainty that has raised the potential of a global recession, which explains why some of the major names in this sector have performed poorly on the stock market in 2025. Shares of both Advanced Micro Devices (NASDAQ: AMD) and Nvidia (NASDAQ: NVDA) are down close to 20% so far this year. However, the recent tariff-related developments suggest that these semiconductor stocks could see a solid comeback, especially considering their impressive results in recent quarters. From pausing reciprocal tariffs for 90 days to exempting duties on imports of semiconductors and other equipment from China to starting trade talks, there are signs of the trade war easing. Where to invest $1,000 right now? Our analyst team just revealed what they believe are the 10 best stocks to buy right now. Continue » China has reportedly rolled back retaliatory tariffs on certain semiconductor components made in the U.S. So, there is a good chance that the cloud of uncertainty hovering over companies such as Nvidia and AMD that have been caught in the trade war could clear and help these semiconductor stocks regain their mojo. But if you have to buy one of these two chip stocks for your portfolio, which one should it be? Let's find out. AMD manufactures chips that go into applications such as data centers, personal computers (PCs), and gaming consoles, among others. The demand for AMD's chips that go into data centers and PCs has been picking up in recent quarters thanks to artificial intelligence (AI). Specifically, AMD's revenue from data center chip sales shot up 69% year over year in the fourth quarter of 2024 to $3.9 billion. The company credited this impressive growth to a ramp-up in sales of its data center graphics cards and server processors. While Nvidia is the dominant player in the AI GPU market, AMD has been gradually gaining ground over here. On its February earnings conference call, CEO Lisa Su remarked that the deployment of its MI300X AI accelerators "expanded with our largest cloud partners." The likes of Meta Platforms, Microsoft, IBM, and DigitalOcean are powering their AI models with AMD's chips, which is why the company has decided to accelerate the launch of its upcoming MI350 AI chips based on the CDNA 4 architecture. AMD points out that the CDNA 4 architecture delivers a 35x jump in AI compute performance as compared to the previous generation CDNA 3. The company has received positive customer feedback and believes that the MI350 family of AI chips could drive "deeper and broader customer engagements with both existing and net new hyperscale customers." AMD will begin shipments of the MI350 chips in the middle of 2025. So, there is a good chance that its data center revenue will continue to grow at a healthy pace thanks to AI. However, this is not the only AI-focused opportunity that the company is sitting on. The adoption of AI PCs is giving AMD's client processor business a nice boost. Its revenue from this segment rose 58% year over year in the fourth quarter of 2024, thanks to the strong demand for its Ryzen processors. AMD reported record sell-through of its desktop processors in the fourth quarter of 2024 and exceeded 70% share at several major retailers. The company is also pushing the envelope in the laptop space with the launch of 22 new mobile processors equipped with AI capabilities. AMD believes that its solid portfolio of laptop and desktop CPUs should help it grab a bigger share of the PC market in 2025. It is worth noting that AMD's overall CPU market share increased in the fourth quarter of 2024 to almost 25%, according to Mercury Research, and the points discussed above suggest that it can make a bigger dent in this market. So, the robust demand for chips used in servers and computers should remain a tailwind for AMD in 2025 and beyond, driving healthy growth in the company's top and bottom lines. Nvidia's dominant position in the market for AI chips helped the company deliver impressive growth in recent quarters. Nvidia ended fiscal 2025 with $130.5 billion in revenue, up by 114% from the previous year. Its revenue guidance of $43 billion for the current quarter points toward a potential jump of 65% in its top line, suggesting that its healthy pace of growth is here to stay. That's not surprising, as Nvidia reportedly controls a whopping 90% of the data center GPU market. This is also the reason why its data center revenue growth of 93% in the last reported quarter was higher than AMD's, even though Nvidia has a much larger revenue base. Looking ahead, Nvidia's technological advantage over AMD could help it remain the leading player in AI chips, and that puts the company in a terrific position to keep growing at a solid pace. After all, the market for AI chips is expected to jump by 2.5x by 2029, generating an annual revenue of $311 billion. Nvidia's data center revenue of $115 billion in the previous quarter indicates that it still has a lot of room for growth in this space, and it may be able to corner a significant chunk of the end-market opportunity thanks to its massive share of this space. Nvidia also has additional catalysts coming into play, such as the automotive market, where it is expecting its revenue to nearly triple this year following a 55% increase in the previous fiscal year. So, it is easy to see why analysts are forecasting Nvidia's earnings to increase by 48% in the current fiscal year, though don't be surprised to see the company doing better than that, as its margin profile should start improving once the production of its Blackwell AI processors ramps up. So, just like AMD, even Nvidia is thriving on solid semiconductor demand. But is it a better buy than its peer? Let's find out. We have seen that Nvidia is on track to clock healthy earnings growth this year. A similar scenario is expected to unfold at AMD, with an estimated earnings jump of 33% in 2025. Importantly, AMD's bottom-line growth is expected to grow to 36% in 2026. However, Nvidia expects a slowdown as its bottom line is projected to grow 28% in the next fiscal year. AMD's stronger growth forecast next year can be attributed to the company's diversified business, while the potential slowdown in Nvidia's earnings growth could be a result of intensifying competition in AI chips. What's more, AMD's price/earnings-to-growth ratio (PEG ratio) of just 0.44 indicates that it is undervalued after accounting for its annual projected earnings growth for the next five years, according to Yahoo! Finance. Nvidia seems overvalued right now, with a PEG ratio of 1.57, which can be attributed to a potential drop in its pace of earnings growth. So, AMD seems like the better semiconductor growth stock to buy right now, considering the points discussed above, though investors cannot go wrong by choosing Nvidia either, as the latter's massive addressable opportunity could ensure years of solid growth and stock upside. Before you buy stock in Advanced Micro Devices, consider this: The Motley Fool Stock Advisor analyst team just identified what they believe are the for investors to buy now… and Advanced Micro Devices wasn't one of them. The 10 stocks that made the cut could produce monster returns in the coming years. Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $598,818!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $666,416!* Now, it's worth noting Stock Advisor's total average return is 872% — a market-crushing outperformance compared to 160% for the S&P 500. Don't miss out on the latest top 10 list, available when you join . See the 10 stocks » *Stock Advisor returns as of April 28, 2025 Randi Zuckerberg, a former director of market development and spokeswoman for Facebook and sister to Meta Platforms CEO Mark Zuckerberg, is a member of The Motley Fool's board of directors. Harsh Chauhan has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Advanced Micro Devices, DigitalOcean, International Business Machines, Meta Platforms, Microsoft, and Nvidia. The Motley Fool recommends the following options: long January 2026 $395 calls on Microsoft and short January 2026 $405 calls on Microsoft. The Motley Fool has a disclosure policy. Better Semiconductor Stock: AMD vs. Nvidia was originally published by The Motley Fool Sign in to access your portfolio
