Tag: chip

Categories
Featured

AMD has plans to support a little known chip for at least another 16 years — and no, it is neither a Ryzen, nor a Threadripper or an Epyc CPU

[ad_1]

Spartan UltraScale+ is the latest addition to AMD‘s extensive portfolio of cost-optimized Field Programmable Gate Arrays (FPGAs) and adaptive SoCs. It has been introduced to replace the Xilinx Spartan 6 and Spartan 7 lines.

The new Spartan UltraScale+ devices are designed for a wide range of I/O-intensive applications at the edge. AMD says its latest FPGAs can deliver up to 30 percent lower total power consumption compared to the previous generation – energy efficiency is a hot topic right now – while boasting the most robust set of security features in the AMD’s cost-optimized portfolio.

[ad_2]

Source Article Link

Categories
Featured

Firm headed by legendary chip architect behind AMD Zen finally releases first hardware — days after being selected to build the future of AI in Japan, Tenstorrent unveils Grayskull, its RISC-V answer to GPUs

[ad_1]

Tenstorrent, the firm led by legendary chip architect Jim Keller, the mastermind behind AMD‘s Zen architecture and Tesla’s original self-driving chip, has launched its first hardware. Grayskull is a RISC-V alternative to GPUs that is designed to be easier to program and scale, and reportedly excels at handling run-time sparsity and conditional computation.

Off the back of this, Tenstorrent has also unveiled its Grayskull-powered DevKits – the standard Grayskull e75 and the more powerful Grayskull e150. Both are inference-only hardware designed for AI development, and come with TT-Buda and TT-Metalium software. The former is for running models right away, while the latter is for users who want to customize their models or write new ones.

[ad_2]

Source Article Link

Categories
Bisnis Industri

13-inch and 15-inch MacBook Air with M3 chip now available in stores

[ad_1]

2024 MacBook Air
You can now get the M3 MacBook Air from your nearest Apple store.
Photo: Apple

Apple’s new M3 MacBook Airs, announced earlier this week, are now on sale. The 13-inch and 15-inch models feature upgraded internals and faster Wi-Fi.

Pre-orders for the new Airs went live right after Apple’s announcement on March 4.

2024 MacBook Air is all about the M3 chip

From the outside, the M3 MacBook Air(s) look the same as their predecessors. But internally, they pack two key changes. The first is the switch to a faster and more efficient M3 chip. Apple claims a performance boost of up to 60 percent than the M1 chip and “up to 13x faster than the fastest Intel-based MacBook Air.”

The M3 SoC debuted on the M3 MacBook Pro last fall. It also features a revamped GPU with mesh shading and ray tracing for better performance and higher-quality graphics. While there are no new AI features on the M3 MacBook Airs, Apple claims they are “the world’s best consumer laptop for AI,” thanks to the faster 16-core Neural Engine.

Besides the faster performance, the new M3 Airs support dual external displays — a first in the lineup. But there’s a catch: you can only use the second monitor with the laptop’s lid closed.

Lastly, Apple’s 2024 MacBook Air lineup has Wi-Fi 6E support, allowing for faster wireless transfer speeds. You can read our M2 vs. M3 MacBook Air comparison to learn more about their differences.

Despite the big performance boost, Apple claims the new M3 Air can last up to 18 hours on a charge.

Same starting price as their M2 predecessors

The new 13-inch MacBook Air and 15-inch Air with M3 chip have the same starting price as their predecessors: $1,099 and $1,299, respectively. Education customers can get an additional $100 off this price.

If you pre-ordered the laptop, you should receive it today. If not, you can buy one from the Apple store nearest to you.

Buy from: Apple



[ad_2]

Source Article Link

Categories
Business Industry

Galaxy Book 4 Edge ARM chip confirmed by online benchmark

[ad_1]

Last updated: March 8th, 2024 at 12:51 UTC+01:00

Yesterday, we brought to light a trademark application pertaining to a new Samsung device called the Book 4 Edge. We thought about it for a bit and guessed that the Book 4 Edge might be Samsung’s first Windows 11 on ARM laptop. Now, an online benchmark is lending weight to our prediction.

The Galaxy Book 4 Edge by Samsung popped up in the online benchmark Geekbench earlier today (via Windows Latest). The laptop runs Windows 11 Home (64-bit) and is powered by the Snapdragon X Elite CPU and 16GB of RAM.

Qualcomm previously said it is looking for partners for its new Snapdragon X Elite chip, and this benchmark, if legitimate, confirms that Samsung is on the list.

Conversely, this benchmark also seems to indicate that Samsung is not yet ready to create its own Exynos ARM-based chip for laptops. And that’s probably a good thing at the moment, seeing how the company is busy proving that it sorted out Exynos for mobile phones.

Plenty of power for Windows on ARM devices

Synthetic benchmark scores for the Galaxy Book 4 Edge laptop powered by the Snapdragon X Elite chip look promising. The laptop scored 2,706 points in single-core and 12,646 points in multi-core tests in Geekbench 6.2.2.

Comparing these scores to Apple’s M1, M2, and M3 chips, it looks like the Snapdragon X Elite beats the first two but is outperformed by the M3. Apple M Pro chips excluded.

Of course, in practice, the M and Snapdragon X Elite chips run in very different environments, i.e., MacOS and Windows 11 on ARM, which means these benchmark figures might not necessarily say which chip performs better in the real world. Apple has optimized its M chips for MacOS very well, and it remains to be seen if we can say the same about the Snapdragon X Elite and Windows 11 on ARM.

Interestingly, recent rumors say Qualcomm’s new chip will also power the upcoming Microsoft Surface Laptop 6 and Surface Pro 10 tablet PC. Samsung’s Galaxy Book 4 Edge will inevitably compete with Microsoft’s Surface line, but whether this Book 4 Edge is a regular notebook, a 2-in-1 with a 360-degree hinge, or a tablet PC with a detachable keyboard is to be determined.

[ad_2]

Source Article Link

Categories
News

EdgeCortix flagship SAKURA-I Chip for Edge AI applications

EdgeCortix flagship SAKURA-I Chip showcased

At the prestigious Singapore Airshow 2024, EdgeCortix, a leading Japanese semiconductor company, is set to unveil a new chip that is expected to transform the way artificial intelligence (AI) is processed in the defense and aerospace sectors. The SAKURA-I chip, a specialized co-processor, is designed to handle AI tasks right at the edge of the network, where data is generated and collected. This innovation is particularly important for applications that require immediate decision-making, such as those found in aviation and military operations.

The airshow, scheduled for February 20-25, will serve as the platform for EdgeCortix to introduce this new technology to the world. Visitors to the event will be able to see the SAKURA-I chip in action at the booth of the Acquisitions, Technology and Logistics Agency (ATLA), which represents Japan’s commitment to advancing its air and defense technologies.

EdgeCortix SAKURA-I

The SAKURA-I chip stands out for its ability to process complex AI tasks with high efficiency and low latency. This is crucial in environments where quick responses are essential and power resources are often limited. The chip’s debut is timely, as there is a growing need for technologies that can operate effectively under these constraints.

“EdgeCortix’s SAKURA-I chip, with its small form factor and high efficiency, is proving a crucial tool in edge computing in defense and aerospace sectors, which EdgeCortix predicts will increasingly rely on software-driven hardware solutions to achieve their tasks going forward,” says Sakyasingha Dasgupta, CEO and Founder of EdgeCortix. “We are honored to be featured in ATLA’s booth representing Japanese innovation at the Singapore Airshow and are proud to stand shoulder-to-shoulder with such elite companies at the show.”

AI is becoming increasingly important in enhancing safety and efficiency across various industries, including transportation and defense. The SAKURA-I chip is designed to meet the demanding needs of these sectors, providing performance improvements that can help prevent accidents, optimize logistics, and ensure secure operations in sensitive areas.

Edge computing, which involves processing data close to where it is generated, is changing the landscape of defense and aerospace. Innovations like the SAKURA-I chip are at the forefront of this shift, enabling faster and more reliable decision-making in situations where time is of the essence.

The Singapore Airshow 2024 is more than just an exhibition; it is a demonstration of Japan’s technological advancements in defense equipment and technology. The partnership between ATLA and EdgeCortix highlights the role of collaboration between the public and private sectors in achieving technological breakthroughs. The SAKURA-I chip exemplifies such progress and is expected to establish new standards in the industry.

EdgeCortix’s participation in the Singapore Airshow 2024 emphasizes the company’s position as a leader in semiconductor technology and its significant contributions to the evolution of AI processing. The SAKURA-I chip marks a step towards more energy-efficient, software-driven hardware solutions in the fields of defense and aerospace. Attendees are encouraged to witness this state-of-the-art technology at the ATLA booth, where Japan’s expertise in air and defense technology will be on full display.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

60% of all PCs sales in 2027 will be equipped with an AI chip forecasts IDC

Microsoft Copilot artificial intelligent equipped PCs

Imagine a world where your computer not only understands your commands but also anticipates your needs, learns from your habits, and protects your privacy more fiercely than ever before. This is not a distant dream but a reality that’s unfolding at a rapid pace. By 2027, the personal computing arena is set to be dominated by artificial intelligence (AI)-enhanced machines, with nearly 60% of all PCs shipped worldwide expected to boast this smart technology.

The International Data Corporation (IDC) has forecasted a surge in the shipment of these AI-powered personal computers, from 50 million units in 2024 to an impressive 167 million in just three years later. This growth signifies a monumental shift in how we interact with technology on a daily basis. The PCs of the future will not only be equipped with traditional central processing units (CPUs) and graphics processing units (GPUs), but they will also include neural processing units (NPUs) within their system-on-a-chip (SoC) designs. These NPUs are tailor-made to handle AI tasks, offering a level of efficiency and performance that was previously unattainable.

AI PCs

The IDC report categorizes AI PCs into three types, with the most advanced, next-generation AI PCs expected to surpass the others in shipments by 2027. These machines will be a boon to both businesses and individual consumers, providing a level of convenience and customization that will redefine the user experience. Here are some other articles you may find of interest on the subject of Microsoft Copilot.

One of the most significant advantages of these AI-enhanced PCs is the ability to process AI tasks directly on the device. This local processing means that your data doesn’t have to be sent to the cloud, which not only speeds up the task at hand but also provides a much-needed boost to privacy and security. Moreover, it reduces the reliance on cloud computing resources, which can be expensive and not always efficient.

The IDC’s comprehensive analysis delves into various aspects of the AI PC market, including NPU performance, processor architecture, and the range of products across desktop and notebook PCs. It also differentiates between the needs of commercial users and individual consumers, ensuring a thorough understanding of how these AI advancements will impact different user groups.

It’s important to note that PCs with high-performance GPUs capable of handling AI workloads are not included in the AI PC category for this report. This distinction is made to accurately capture the growth of the dedicated AI PC market, which is distinct from the broader PC market that includes traditional, non-AI-specific machines.

As we look to the future, the integration of AI into personal computing promises to bring about a new class of PCs. These machines will not only be smarter and more efficient but will also be designed to cater to the specific needs of their users, whether for work or play. The evolution of AI is set to transform the traditional PC into a more intuitive, responsive, and secure companion in our digital lives. Keep an eye on this space, as the next few years are poised to usher in an era where AI and personal computing become inextricably linked.

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

High-Speed computing with SOT-MRAM array chip from ITRI & TSMC research

High-Speed computing with SOT-MRAM array chip

The semiconductor industry is on the brink of a significant advancement with the latest collaboration between the Industrial Technology Research Institute (ITRI) and Taiwan Semiconductor Manufacturing Company (TSMC). These two powerhouses have joined forces to create a new type of memory chip that promises to make high-speed computing even faster and more efficient. The spin-orbit-torque magnetic random-access memory (SOT-MRAM) array chip they’ve developed is a marvel of modern engineering, designed to use a fraction of the power of current memory chips while delivering lightning-fast performance.

Imagine a memory chip that operates with just 1% of the power required by the chips we use today. That’s exactly what ITRI and TSMC have achieved with their SOT-MRAM chip. Despite this dramatic reduction in power usage, the chip’s speed is not compromised. It boasts access speeds of up to 10 nanoseconds, which is incredibly fast and exactly what’s needed for the demanding applications of today’s high-performance computing, artificial intelligence, and automotive industries.

The unveiling of the SOT-MRAM array chip at the IEEE International Electron Devices Meeting (IEDM 2023) was a moment of pride for the developers. This event is where the brightest minds in the industry gather to discuss and explore the latest technological innovations. The SOT-MRAM chip stood out as a highlight, drawing attention to its potential to become a key component in future memory solutions.

High-Speed Computing with SOT-MRAM

The implications of this technology are vast. In high-performance computing, where speed and efficiency are paramount, SOT-MRAM could be a game-changer. Artificial intelligence systems, which require rapid data processing and energy efficiency, stand to benefit greatly from this technology. The automotive industry, too, with its increasing reliance on advanced electronics, could see a significant boost in performance and reliability from automotive chips that incorporate SOT-MRAM technology.

As we move into an era where artificial intelligence, 5G, and the Artificial Intelligence of Things (AIoT) are becoming more prevalent, the demand for advanced memory solutions is growing. These technologies need to handle large volumes of data while keeping energy consumption to a minimum. The SOT-MRAM chip is a promising solution to this challenge, offering powerful performance without the high energy costs.

This technological breakthrough also reinforces Taiwan’s status as a leader in the semiconductor industry. The country is already recognized as a global hub for semiconductor manufacturing, and the successful partnership between ITRI and TSMC is a testament to Taiwan’s commitment to pushing the boundaries of innovation and maintaining its competitive edge.

The SOT-MRAM array chip is a testament to the power of collaboration and innovation in the field of memory technology. It’s set to make a significant impact on high-speed computing across various sectors. With its advanced architecture, reduced power consumption, and rapid operation, the chip is a shining example of what can be achieved when industry leaders come together to tackle the challenges of modern computing. As the world continues to demand faster and more efficient technology, the SOT-MRAM chip is poised to play a crucial role in meeting those needs.

 

Filed Under: Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

DEEPX DX-M1 chip designed for AI of Things applications

DEEPX DX-M1 chip designed for new AI of Things applications

Anyone in the process of or interested in building AI of Things applications might be interested to know that DEEPX has unveiled its latest creation, the DX-M1 chip. This new piece of technology is making waves in the realm of artificial intelligence (AI), promising to deliver top-notch performance while keeping energy use to a minimum. The chip’s launch has caught the eye of customers, including some of the biggest names in both global and Korean markets. This surge of interest suggests that the DX-M1 could significantly alter the way AI technology is applied across various sectors.

DEEPX has designed the DX-M1 chip to meet the growing demand for energy-efficient and powerful AI computing. This innovation is expected to have a profound effect on industries such as robotics, smart mobility, AI video security systems, and AI servers. The chip’s advanced capabilities could lead to major advancements in these fields, enhancing their efficiency and effectiveness.

AI of Things

To ensure that the DX-M1 meets the specific needs of different industries, DEEPX has initiated the Early Engagement Customer Program (EECP). This program allows clients to get their hands on the hardware and software of the DX-M1 early on. By doing so, they can conduct pre-production testing and provide feedback, which DEEPX can use to fine-tune the chip for mass production. This collaborative process is key to making sure the DX-M1 is ready to hit the market with a bang.

DEEPX DX-M1 chip CES 2024 Awards

Here are some other articles you may find of interest on the subject of hardware for artificial intelligence :

One of the standout features of the DX-M1 chip is its optimization for the physical security market. It offers real-time AI processing and is compatible with a wide range of AI models. The chip’s cutting-edge design is built on a 5 nm process, which reduces the need for large cache memory without compromising on computational power or accuracy. This gives the DX-M1 a competitive edge in the AI semiconductor field.

For companies looking to upgrade their systems with more efficient AI solutions, the DX-M1 is also available as an M.2 module. This modular approach makes it easy to integrate the chip into existing systems, which could help speed up its adoption in the market. The potential of the DX-M1 chip has not gone unnoticed in the industry. It has been recognized at the CES Innovation Awards 2024, where it received accolades in both the Embedded Technology and Robotics categories. This recognition underscores the chip’s potential to shape the future of AI technology.

There’s a growing sense of anticipation for DEEPX’s showcase of the DX-M1 chip at the upcoming CES 2024 in Las Vegas. The event is expected to attract industry experts and potential clients, offering a glimpse into the future of AI semiconductor technology.

DEEPX’s DX-M1 chip represents a significant step forward in AI semiconductor technology, striking a balance between efficiency, high performance, and cost-effectiveness. As DEEPX continues to collaborate with customers to refine its product, the DX-M1 is poised to become an essential element in AI solutions across a variety of industries.

Filed Under: Hardware, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.

Categories
News

Synopsys unveils innovative RISC-V ARC-V processor IP for next-gen chip design

Synopsys unveils innovative RISC-V ARC-V processor IP for next-gen chip design

If you’re closely following the semiconductor space, you will be pleased to know that Synopsys, Inc. has made a significant announcement this week. With the introduction of the new RISC-V ARC-V Processor IP, a move set to empower customers with a gamut of processor choices tailored for optimal power-performance efficiency across various applications.

For the uninitiated, RISC-V is an open standard for processors that’s been gaining traction in the tech world, thanks to its flexibility and community-driven development. Synopsys’ foray into this area isn’t a simple step but a giant leap, building upon its decades-long prowess in processor IP and software toolkit development. The ARC-V Processor IP is the company’s existing ARC Processors’ latest incarnation, only supercharged with the perks of the RISC-V’s burgeoning software ecosystem.

RISC-V ARC-V processor IP

Other articles you may find of interest on the subject of RISC-V :

Here’s what sets the ARC-V Processor IP apart:

  • High-performance, mid-range, and ultra-low power options: Tailor your chip’s energy consumption and processing power to your application’s demands.
  • Functional safety versions: These are designed to meet the rigorous demands of applications requiring a high level of reliability, such as automotive systems.
  • Synopsys MetaWare Development Toolkit: This toolkit stands out for producing highly efficient code, crucial for getting the most out of the processors.
  • Synopsys.ai: Integrated with the EDA suite, this offering is co-optimized with ARC-V Processor IP to streamline development and verification, enhancing productivity and results.

Industry experts and market leaders have already voiced their support for this innovation. Thomas Boehm from Infineon highlighted the importance of resilience in the automotive chip market and welcomed the addition of safety-certified RISC-V based processor IP. Similarly, Calista Redmond of RISC-V International lauded the move, noting Synopsys’ contribution to the flexibility and choice in the semiconductor ecosystem.

“The increasing numbers of chips in automotive systems demand resilience in the semiconductor ecosystem, and to that end the industry is pushing for the adoption of open standards like RISC-V,” said Thomas Boehm, senior vice president, Automotive Microcontroller at Infineon. “By developing safety-certified RISC-V based processor IP, Synopsys is supporting us to expand the architecture choices with an open standard to build high-performance automotive systems with the highest levels of functional safety, and we look forward to continuing to partner with them in our future products.”

Synopsys isn’t just about processor IP; its portfolio is a testimony to its ability to deliver power-efficient, scalable processors, already a staple in countless automotive, storage, and IoT systems. The ARC-V IP capitalizes on this legacy, offering ultra-configurable, extensible processors that allow developers to fine-tune their SoCs for the optimal balance of power, performance, and area (PPA).

The company’s commitment to RISC-V doesn’t end with product development. They’re actively participating in shaping the future of computing as part of the RISC-V International Board of Directors and Technical Steering Committee.

As for the nitty-gritty details, the ARC-V Processor IP lineup is quite robust:

  • Functional Safety (FS) Processor IP: Comes with integrated hardware safety features, supporting ASIL B and D safety levels, and facilitating automotive safety and cybersecurity qualifications.
  • ISO 9001-certified Quality Management System (QMS): Assures that the development standards meet the stringent ASIL D criteria.

If you are wondering how Synopsys supports the design and verification of SoCs using this new IP, look no further. Their portfolio includes Synopsys.ai, Fusion QuickStart Implementation Kits, and a suite of verification solutions that provide a comprehensive environment for system-level analysis, power and performance optimization, and accelerated software development.

The grand unveiling of the Synopsys ARC-V Processor IP portfolio has stirred the industry, with general availability kicking off in 2024. The lineup includes the 32-bit Synopsys ARC-V RMX, the 32-bit ARC-V RHX, and the 64-bit ARC-V RPX, catering to embedded, real-time, and host processing needs, respectively.

As we wrap up this exploration into Synopsys’ latest offering, it’s clear that the company is positioning itself as a key player in the RISC-V landscape. With these developments, Synopsys not only promises to deliver robust processor solutions but also signals its commitment to the open-source ecosystem, paving the way for innovation and choice in chip design.

Source: Synopsys

Filed Under: Hardware, Technology News, Top News





Latest timeswonderful Deals

Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, timeswonderful may earn an affiliate commission. Learn about our Disclosure Policy.