The RTX 50-series fever continues to rage on, with independent reviews for the RTX 5080 and RTX 5090 dropping towards the end of this month. That does not stop benchmarks from leaking out, unsurprisingly, and a recent lineup of Geekbench listings have revealed the raw performance uplifts that can be expected from NVIDIA's next generation GeForce flagship. A sizeable chunk of the tech community was certainly rather disappointed with NVIDIA's reliance on AI-powered frame generation for much of the claimed improvements in gaming. Now, it appears we can finally figure out how much raw improvement NVIDIA was able to squeeze out with consumer Blackwell, and the numbers, for the most part, appear decent enough.

Starting off with the OpenCL tests, the highest score that we have seen so far from the RTX 5090 puts it around 367,000 points, which marks an acceptable jump from the RTX 4090, which manages around 317,000 points according to Geekbench's official average data. Of course, there are a plethora of cards that may easily exceed the average scores, which must be kept in mind. That said, we are not aware of the details of the RTX 5090 that was tested, so pitting it against average scores does seem fair. Moving to Vulkan, the performance uplift is much more satisfying, with the RTX 5090 managing a minimum of 331,000 points and a maximum of around 360,000 points, compared to the RTX 4090's 262,000 - a sizeable 37% improvement at the highest end. Once again, we are comparing the best results posted so far against last year's averages, so expect slightly more modest gains in the real world. Once more reviews start appearing after the embargo lifts, the improvement figures should become much more reliable.

At yesterday's J.P. Morgan Healthcare Conference NVIDIA announced new partnerships to transform the $10 trillion healthcare and life sciences industry by accelerating drug discovery, enhancing genomic research and pioneering advanced healthcare services with agentic and generative AI. The convergence of AI, accelerated computing and biological data is turning healthcare into the largest technology industry. Healthcare leaders IQVIA, Illumina and Mayo Clinic, as well as Arc Institute, are using the latest NVIDIA technologies to develop solutions that will help advance human health.

These solutions include AI agents that can speed clinical trials by reducing administrative burden, AI models that learn from biology instruments to advance drug discovery and digital pathology, and physical AI robots for surgery, patient monitoring and operations. AI agents, AI instruments and AI robots will help address the $3 trillion of operations dedicated to supporting industry growth and create an AI factory opportunity in the hundreds of billions of dollars.

Morse Micro, the world's leading provider of Wi-Fi HaLow chips based on the IEEE 802.11ah specification, has announced the launch of its highly anticipated second-generation MM8108 System-on-Chip (SoC). Building on the success of the first-generation MM6108 SoC, the MM8108 offers even better performance in all key areas of range, throughput, and power efficiency while also reducing the cost, effort, and time to bring the next generation of Wi-Fi HaLow enabled products to market.

The MM8108 delivers class-leading data rates of up to 43.33 Mbps using world-first sub-GHz 256-QAM modulation at an 8 MHz bandwidth, making it ideal for a range of applications in agricultural, mining, industrial, home, and city environments. Its integrated 26dBm power amplifier (PA) with exceptional power efficiency, and low-noise amplifier (LNA) ensure exceptional performance and enable global regulatory certification without the need for external Surface Acoustic Wave (SAW) filters. The exceptional power efficiency significantly extends battery life and enables the uptake of solar-powered Wi-Fi HaLow connected cameras and IoT devices.

VeriSilicon today announced the launch of its latest Vitality architecture Graphics Processing Unit (GPU) IP series, designed to deliver high-performance computing across a wide range of applications, including cloud gaming, AI PC, and both discrete and integrated graphics cards.

VeriSilicon's new generation Vitality GPU architecture delivers exceptional advancements in computational performance with scalability. It incorporates advanced features such as a configurable Tensor Core AI accelerator and a 32 MB to 64 MB Level 3 (L3) cache, offering both powerful processing power and superior energy efficiency. Additionally, the Vitality architecture supports up to 128 channels of cloud gaming per core, addressing the needs of high concurrency and high image quality cloud-based entertainment, while enabling large-scale desktop gaming and applications on Windows systems. With robust support for Microsoft DirectX 12 APIs and AI acceleration libraries, this architecture is ideally suited for a wide range of performance-intensive applications and complex computing workloads.

We started Android over a decade ago with a simple idea: transform computing for everyone. Android powers more than just phones—it's on tablets, watches, TVs, cars and more.

Now, we're taking the next step into the future. Advancements in AI are making interacting with computers more natural and conversational. This inflection point enables new extended reality (XR) devices, like headsets and glasses, to understand your intent and the world around you, helping you get things done in entirely new ways.

At AWS re:Invent, Amazon Web Services, Inc. (AWS), an Amazon.com, Inc. company, today announced the general availability of AWS Trainium2-powered Amazon Elastic Compute Cloud (Amazon EC2) instances, introduced new Trn2 UltraServers, enabling customers to train and deploy today's latest AI models as well as future large language models (LLM) and foundation models (FM) with exceptional levels of performance and cost efficiency, and unveiled next-generation Trainium3 chips.

"Trainium2 is purpose built to support the largest, most cutting-edge generative AI workloads, for both training and inference, and to deliver the best price performance on AWS," said David Brown, vice president of Compute and Networking at AWS. "With models approaching trillions of parameters, we understand customers also need a novel approach to train and run these massive workloads. New Trn2 UltraServers offer the fastest training and inference performance on AWS and help organizations of all sizes to train and deploy the world's largest models faster and at a lower cost."

Smartkem, positioned to power the next generation of displays using its disruptive organic thin-film transistors (OTFTs), has partnered with AUO, the largest display manufacturer in Taiwan, to jointly develop the world's first advanced rollable, transparent microLED display using Smartkem's technology.

"We believe that collaborating with global display industry leader AUO to develop a novel microLED display puts Smartkem's technology on the frontier of microLED display commercialization. Our unique transistor technology is expected to enable display manufacturers to efficiently produce microLED displays, making mass production commercially viable. Smartkem's technology has the potential to take today's microLED TVs from high end market prices of $100,000 down to mass market prices," stated Ian Jenks, Smartkem Chairman and CEO.

TSMC, the world leader in semiconductor manufacturing, is moving to production with NVIDIA's computational lithography platform, called cuLitho, to accelerate manufacturing and push the limits of physics for the next generation of advanced semiconductor chips. A critical step in the manufacture of computer chips, computational lithography is involved in the transfer of circuitry onto silicon. It requires complex computation - involving electromagnetic physics, photochemistry, computational geometry, iterative optimization and distributed computing. A typical foundry dedicates massive data centers for this computation, and yet this step has traditionally been a bottleneck in bringing new technology nodes and computer architectures to market.

Computational lithography is also the most compute-intensive workload in the entire semiconductor design and manufacturing process. It consumes tens of billions of hours per year on CPUs in the leading-edge foundries. A typical mask set for a chip can take 30 million or more hours of CPU compute time, necessitating large data centers within semiconductor foundries. With accelerated computing, 350 NVIDIA H100 Tensor Core GPU-based systems can now replace 40,000 CPU systems, accelerating production time, while reducing costs, space and power.

LG Electronics (LG) is excited to announce that its newest LG gram laptop featuring the Intel Core Ultra processor (Series 2) will be showcased at the Intel Core Ultra Global Launch Event from September 3-8. Renowned for its powerful performance and ultra-lightweight design, the LG gram series now integrates advanced AI capabilities powered by the latest Intel Core Ultra processor. The LG gram 16 Pro, the first model to feature these new Intel processors, will be unveiled before its release at the end of 2024.

As the first on-device AI laptop from the LG gram series, it offers up to an impressive 48 neural processing unit (NPU) tera operations per second (TOPS), setting a new standard for AI PCs and providing the exceptional performance required for Copilot experiences. Powered by the latest Intel Core Ultra processor, the LG gram 16 Pro is now more efficient thanks to advanced AI functionalities such as productivity assistants, text and image creation and collaboration tools. What's more, its extended battery life helps users handle tasks without worry.

Intel's 13th and 14th generation processors, codenamed "Raptor Lake" and "Raptor Lake Refresh," have been notoriously riddled with stability issues over the past few months, up until Intel shipped the 0x129 microcode update on August 10 to fix these issues. However, the upcoming Intel Core Ultra 200 "Arrow Lake" and 200V series "Lunar Lake" processors will not have these issues as the company confirmed that an all-new design is used, even for the segment of power regulation. The official company note states: "Intel confirms that its next generation of processors, codenamed Arrow Lake and Lunar Lake, are not affected by the Vmin Shift Instability issue due to the new architectures powering both product families. Intel will ensure future product families are protected against the Vmin Shift Instability issue as well."

Originally, Intel's analysis for 13th—and 14th-generation processors indicated that stability issues stemmed from excessive voltage during processor operation. These voltage increases led to degradation, raising the minimum voltage necessary for stable performance, which Intel refers to as "Vmin shift." Given that the design phase of new architectures lasts for years, Intel has surely anticipated that the old power delivery could yield problems, and the upcoming CPU generations are now exempt from these issues, bringing stability once again to Intel's platforms. When these new products launch, all eyes will be on the platform's performance, but with a massive interest in stability testing from enthusiasts.

EK, the leading premium liquid cooling gear manufacturer, is releasing the next generation of its versatile flat-style combo units. EK-Quantum Kinetic³ FLT D5 series pump-reservoir units are equipped with genuine D5 pumps made in Europe, capable of delivering flow rates of 1000 liters per hour with a maximum head pressure of up to 5.2 meters! These new FLT series combo units are available in six different sizes 92 mm, 120 mm, 240 mm, 140 mm, 280 mm, and 360 mm.

The main upgrades of the Kinetic³ combo units include:

• Additional G1/4" connection ports
• Front-mounted pump for added versatility
• Side and back mounting holes for flexibility during installation
• A custom-made inner O-ring that prevents coolant from seeping between the channels and improves flow
• Dense LED strip implementation
• User-friendly LED cover for LED strip service

Intel today announced that its lead products on Intel 18A, Panther Lake (AI PC client processor) and Clearwater Forest (server processor), are out of the fab and have powered-on and booted operating systems. These milestones were achieved less than two quarters after tape-out, with both products on track to start production in 2025. The company also announced that the first external customer is expected to tape out on Intel 18A in the first half of next year.

"We are pioneering multiple systems foundry technologies for the AI era and delivering a full stack of innovation that's essential to the next generation of products for Intel and our foundry customers. We are encouraged by our progress and are working closely with customers to bring Intel 18A to market in 2025." -Kevin O'Buckley, Intel senior vice president and general manager of Foundry Services

NEO Semiconductor, a leading developer of innovative technologies for 3D NAND flash memory and 3D DRAM, announced today the development of its 3D X-AI chip technology, targeted to replace the current DRAM chips inside high bandwidth memory (HBM) to solve data bus bottlenecks by enabling AI processing in 3D DRAM. 3D X-AI can reduce the huge amount of data transferred between HBM and GPUs during AI workloads. NEO's innovation is set to revolutionize the performance, power consumption, and cost of AI Chips for AI applications like generative AI.

AI Chips with NEO's 3D X-AI technology can achieve:

• 100X Performance Acceleration: contains 8,000 neuron circuits to perform AI processing in 3D memory.
• 99% Power Reduction: minimizes the requirement of transferring data to the GPU for calculation, reducing power consumption and heat generation by the data bus.
• 8X Memory Density: contains 300 memory layers, allowing HBM to store larger AI models.

Marvell Technology, Inc., a leader in data infrastructure semiconductor solutions, today launched the Marvell Structera product line of Compute Express Link (CXL) devices that enable cloud data center operators to overcome memory performance and scaling challenges in general-purpose servers.

To address memory-intensive applications, data center operators add extra servers to get higher memory bandwidth and higher memory capacity. The compute capabilities from the added processors are typically not utilized for these applications, making the servers inefficient from cost and power perspectives. The CXL industry standard addresses this challenge by enabling new architectures that can efficiently add memory to general-purpose servers.

Cornelis Networks, a leading independent provider of intelligent, high-performance networking solutions, today announced the appointment of Lisa Spelman as its new chief executive officer (CEO), effective August 15. Spelman joins Cornelis from Intel Corporation, where she held executive leadership roles for more than two decades, including leading the company's core data center business. Spelman will succeed Philip Murphy, who will assume the role of president and chief operating officer (COO).

"Cornelis is unique in having the products, roadmap, and talent to help customers address this issue. I look forward to joining the team to bring their innovations to even more organizations around the globe."

Tenstorrent is launching their next generation Wormhole chip featuring PCIe cards and workstations designed for developers who are interested in scalability for multi-chip development using Tenstorrent's powerful open-source software stacks.

These Wormhole-based cards and systems are now available for immediate order on tenstorrent.com:

• Wormhole n150, powered by a single processor
• Wormhole n300, powered by two processors
• TT-LoudBox, a developer workstation powered by four Wormhole n300s (eight processors)

Intel is preparing to launch its next generation of mobile CPUs with Core Ultra 200 series "Lunar Lake" leading the charge. However, as these processors are about to hit the market, leakers reveal Intel's plans for the next-generation Core Ultra 300 series "Panther Lake". According to rumors, Panther Lake will double the core count of Lunar Lake, which capped out at eight cores. There are several configurations of Panther Lake in the making based on the different combinations of performance (P) "Cougar Cove," efficiency (E) "Skymont," and low power (LP) cores. First is the PTL-U with 4P+0E+4LP cores with four Xe3 "Celestial" GPU cores. This configuration is delivered within a 15 W envelope. Next, we have the PTL-H variant with 4P+8E+4LP cores for a total of 16 cores, with four Xe3 GPU cores, inside a 25 W package. Last but not least, Intel will also make PTL-P SKUs with 4P+8E+4LP cores, with 12 Xe3 cores, to create a potentially decent gaming chip with 25 W of power.

Intel's Panther Lake CPU architecture uses an innovative design approach, utilizing a multi-tile configuration. The processor incorporates five distinct tiles, with three playing active roles in its functionality. The central compute operations are handled by one "Die 4" tile with CPU and NPU, while "Die 1" is dedicated to platform control (PCD). Graphics processing is managed by "Die 5", leveraging Intel's Xe3 technology. Interestingly, two of the five tiles serve a primarily structural purpose. These passive elements are strategically placed to achieve a balanced, rectangular form factor for the chip. This design philosophy echoes a similar strategy employed in Intel's Lunar Lake processors. Panther Lake is poised to offer greater versatility compared to its Lunar Lake counterpart. It's expected to cater to a wider range of market segments and use cases. One notable advancement is the potential for increased memory capacity compared to Lunar Lake, which capped out at 32 GB of LPDDR5X memory running at 8533 MT/s. We can expect to hear more potentially at Intel's upcoming Innovation event in September, while general availability of Panther Lake is expected in late 2025 or early 2026.

HYTE, a leading manufacturer of cutting-edge PC components and peripherals, today announced the next generation of its viral Y70 Touch case, Y70 Touch Infinite, alongside the Y70 Touch Infinite Display Upgrade, as promised to its users. After the unfortunate discontinuation of Y70 Touch in February 2024, HYTE was diligent in its development and pursuit of an infinite touchscreen solution for one of its leading cases.

Y70 Touch Infinite
Introducing Y70 Touch Infinite with a larger 14.5" integrated touchscreen, 688 x 2560 resolution, and 183 PPI for improved compatibility and resource usage. Y70 Touch Infinite boasts a 33% closer dot pitch for a sharper-looking image alongside a 17% brighter LCD panel and a 25% higher contrast ratio. The 60Hz refresh rate with 50% faster pixel response time enables a smoother and more fluid visual experience than its predecessor.

AMD on Monday said that its 2024 Computex Keynote address slated for June 3, will see a slew of next-generation product announcements. "Join us as Dr. Lisa Su delivers the Computex 2024 opening keynote and shares the latest on how AMD and our partners are pushing the envelope with our next generation of high-performance PC, data center and AI solutions," the brief release said.

AMD is widely expected to unveil its next-generation Ryzen 9000 "Strix Point" mobile processors for AI PCs capable of powering the recently announced Microsoft Copilot+, its next-generation Ryzen 9000 "Granite Ridge" desktop processors, its 5th Generation EPYC "Turin" server processors, and possibly even its next-generation Radeon RX RDNA 4 generation. At the heart of all its processor announcements is the new "Zen 5" CPU microarchitecture that's expected to introduce an over 10% IPC improvement with significant improvements in AVX512 performance over "Zen 4," which should benefit certain kinds of AI workloads.

AMD's next generation RDNA 4 graphics architecture is expected to feature a completely new ray tracing engine, Kepler L2, a reliable source with GPU leaks, claims. Currently, AMD uses a component called Ray Accelerator, which performs the most compute-intensive portion of the ray intersection and testing pipeline, while AMD's approach to ray tracing on a hardware level still relies greatly on the shader engines. The company had debuted the ray accelerator with RDNA 2, its first architecture to meet DirectX 12 Ultimate specs, and improved the component with RDNA 3, by optimizing certain aspects of its ray testing, to bring about a 50% improvement in ray intersection performance over RDNA 2.

The way Kepler L2 puts it, RDNA 4 will feature a fundamentally transformed ray tracing hardware solution from the ones on RDNA 2 and RDNA 3. This could probably delegate more of the ray tracing workflow onto fixed-function hardware, unburdening the shader engines further. AMD is expected to debut RDNA 4 with its next line of discrete Radeon RX GPUs in the second half of 2024. Given the chatter about a power-packed event by AMD at Computex, with the company expected to unveil "Zen 5" CPU microarchitecture on both server and client processors; we might expect some talk on RDNA 4, too.

TSMC today unveiled its newest semiconductor process, advanced packaging, and 3D IC technologies for powering the next generation of AI innovations with silicon leadership at the Company's 2024 North America Technology Symposium. TSMC debuted the TSMC A16 technology, featuring leading nanosheet transistors with innovative backside power rail solution for production in 2026, bringing greatly improved logic density and performance. TSMC also introduced its System-on-Wafer (TSMC-SoW) technology, an innovative solution to bring revolutionary performance to the wafer level in addressing the future AI requirements for hyperscaler datacenters.

This year marks the 30th anniversary of TSMC's North America Technology Symposium, and more than 2,000 attended the event, growing from less than 100 attendees 30 years ago. The North America Technology Symposium in Santa Clara, California kicks off TSMC Technology Symposiums around the world in the coming months. The symposium also features an "Innovation Zone," designed to highlight the technology achievements of our emerging start-up customers.

Meta has announced the next generation of its Meta Training and Inference Accelerator (MTIA) chip, which is designed to train and infer AI models at scale. The newest MTIA chip is a second-generation design of Meta's custom silicon for AI, and it is being built on TSMC's 5 nm technology. Running at the frequency of 1.35 GHz, the new chip is getting a boost to 90 Watts of TDP per package compared to just 25 Watts for the first-generation design. Basic Linear Algebra Subprograms (BLAS) processing is where the chip shines, and it includes matrix multiplication and vector/SIMD processing. At GEMM matrix processing, each chip can process 708 TeraFLOPS at INT8 (presumably meant FP8 in the spec) with sparsity, 354 TeraFLOPS without, 354 TeraFLOPS at FP16/BF16 with sparsity, and 177 TeraFLOPS without.

Classical vector and processing is a bit slower at 11.06 TeraFLOPS at INT8 (FP8), 5.53 TeraFLOPS at FP16/BF16, and 2.76 TFLOPS single-precision FP32. The MTIA chip is specifically designed to run AI training and inference on Meta's PyTorch AI framework, with an open-source Triton backend that produces compiler code for optimal performance. Meta uses this for all its Llama models, and with Llama3 just around the corner, it could be trained on these chips. To package it into a system, Meta puts two of these chips onto a board and pairs them with 128 GB of LPDDR5 memory. The board is connected via PCIe Gen 5 to a system where 12 boards are stacked densely. This process is repeated six times in a single rack for 72 boards and 144 chips in a single rack for a total of 101.95 PetaFLOPS, assuming linear scaling at INT8 (FP8) precision. Of course, linear scaling is not quite possible in scale-out systems, which could bring it down to under 100 PetaFLOPS per rack.Below, you can see images of the chip floorplan, specifications compared to the prior version, as well as the system.

NVIDIA has been offering its GPU IP for more than a decade now ever since the introduction of Kepler uArch, and its IP has had relatively low traction in other SoCs. However, that trend seems to be reaching an inflection point as NVIDIA has given MediaTek a license to use its GPU IP to produce the next generation of processors for the auto industry. The newest MediaTek Dimensity Auto Cockpit family consists of CX-1, CY-1, CM-1, and CV-1, where the CX-1 targets premium vehicles, CM targets medium range, and CV targets lower-end vehicles, probably divided by their compute capabilities. The Dimensity Auto Cockpit family is brimming with the latest technology, as the processor core of choice is an Armv9-based design paired with "next-generation" NVIDIA GPU IP, possibly referring to Blackwell, capable of doing ray tracing and DLSS 3, powered by RTX and DLA.

The SoC is supposed to integrate a lot of technology to lower BOM costs of auto manufacturing, and it includes silicon for controlling displays, cameras (advanced HDR ISP), audio streams (multiple audio DSPs), and connectivity (WiFi networking). Interestingly, the SKUs can play movies with AI-enhanced video and support AAA gaming. MediaTek touts the Dimensity Auto Cockpit family with fully local AI processing capabilities, without requiring assistance from outside servers via WiFi, and 3D spatial sensing with driver and occupant monitoring, gaze-aware UI, and natural controls. All of that fits into an SoC fabricated at TSMC's fab on a 3 nm process and runs on the industry-established NVIDIA DRIVE OS.

Silicon Box, a cutting-edge, advanced panel-level packaging foundry announced its intention to collaborate with the Italian government to invest up to $3.6 billion (€3.2 billion) in Northern Italy, as the site of a new, state-of-the-art semiconductor assembly and test facility. This facility will help meet critical demand for advanced packaging capacity to enable next generation technologies that Silicon Box anticipates by 2028. The multi-year investment will replicate Silicon Box's flagship foundry in Singapore which has proven capability and capacity for the world's most advanced semiconductor packaging solutions, then expand further into 3D integration and testing. When completed, the new facility will support approximately 1,600 Silicon Box employees in Italy. The construction of the facility is also expected to create several thousand more jobs, including eventual hiring by suppliers. Design and planning for the facility will begin immediately, with construction to commence pending European Commission approval of planned financial support by the Italian State.

As well as bringing the most advanced chiplet integration, packaging, and testing to Italy, Silicon Box's manufacturing process is based on panel-level-production; a world leading, first-of-its-kind combination that is already shipping product to customers from its Singapore foundry. Through the investment, Silicon Box has plans for greater innovation and expansion in Europe, and globally. The new integrated production facility is expected to serve as a catalyst for broader ecosystem investments and innovation in Italy, as well as the rest of the European Union.

Microsoft has just announced that their new DirectSR Super Resolution API for DirectX will provide a unified interface for developers to implement super resolution in their games. This means that game studios no longer have to choose between DLSS, FSR, XeSS, or spend additional resources to implement, bug-test and support multiple upscalers. For gamers this is huge news, too, because they will be able to run upscaling in all DirectSR games—no matter the hardware they own. While AMD FSR and Intel XeSS run on all GPUs from all vendors, NVIDIA DLSS is exclusive to Team Green's hardware. With their post, Microsoft also confirms that DirectSR will not replace FSR/DLSS/XeSS with a new upscaler by Microsoft, rather that it builds on existing technologies that are already available, unifying access to them.

While we have to wait until March 21 for more details to be revealed at GDC 2024, Microsoft's Joshua Tucker stated in a blog post: "We're thrilled to announce DirectSR, our new API designed in partnership with GPU hardware vendors to enable seamless integration of Super Resolution (SR) into the next generation of games. Super Resolution is a cutting-edge technique that increases the resolution and visual quality in games. DirectSR is the missing link developers have been waiting for when approaching SR integration, providing a smoother, more efficient experience that scales across hardware. This API enables multi-vendor SR through a common set of inputs and outputs, allowing a single code path to activate a variety of solutions including NVIDIA DLSS Super Resolution, AMD FidelityFX Super Resolution, and Intel XeSS. DirectSR will be available soon in the Agility SDK as a public preview, which will enable developers to test it out and provide feedback. Don't miss our DirectX State of the Union at GDC to catch a sneak peek at how DirectSR can be used with your games!"