A few weeks ago, we spotted an Intel Core Ultra 7 1003H Meteor Lake-P processor in the wild, running a PugetBench set of benchmarks. Today, we are in luck as there is another Meteor Lake-P processor running in the wild, spotted by @InstLatX64 on Twitter. Called Intel Core Ultra 7 1002H, the CPU represents a similar SKU to the previously discovered 1003. Also, having 16 cores in total, they are split into two categories: 6 Performance cores, and ten Efficient cores, two of which are on the SoC die, divided from the remaining eight on the compute die. Interestingly, only P-cores feature 2-way hyperthreaded, so 12 threads from P-cores and ten threads from E-cores combine into 22 threads.

What we don't know is the frequency of this chip and the position it plays in the Meteor Lake-P family of processors. The screenshot states a potential base clock of 3000 MHz; however, it could be an early engineering sample chip, so we have to wait for the final design. With 1003H having exactly the same core/thread number, we expect that the newly discovered 1002H has potentially lower clocks and TDP to match.

Apple today announced M2 Ultra, a new system on a chip (SoC) that delivers huge performance increases to the Mac and completes the M2 family. M2 Ultra is the largest and most capable chip Apple has ever created, and it makes the new Mac Studio and Mac Pro the most powerful Mac desktops ever made. M2 Ultra is built using a second-generation 5-nanometer process and uses Apple's groundbreaking UltraFusion technology to connect the die of two M2 Max chips, doubling the performance. M2 Ultra consists of 134 billion transistors—20 billion more than M1 Ultra. Its unified memory architecture supports up to a breakthrough 192 GB of memory capacity, which is 50 percent more than M1 Ultra, and features 800 GB/s of memory bandwidth—twice that of M2 Max. M2 Ultra features a more powerful CPU that's 20 percent faster than M1 Ultra, a larger GPU that's up to 30 percent faster, and a Neural Engine that's up to 40 percent faster. It also features a media engine with twice the capabilities of M2 Max for blazing ProRes acceleration. With all these advancements, M2 Ultra takes Mac performance to a whole new level yet again.

"M2 Ultra delivers astonishing performance and capabilities for our pro users' most demanding workflows, while maintaining Apple silicon's industry-leading power efficiency," said Johny Srouji, Apple's senior vice president of Hardware Technologies. "With huge performance gains in the CPU, GPU, and Neural Engine, combined with massive memory bandwidth in a single SoC, M2 Ultra is the world's most powerful chip ever created for a personal computer."

Considering all the buzz around WiFi 7, there weren't many live demos at Computex, but Realtek had a demo running in its suite at the show. Realtek will offer both client and router/AP solutions, with their client product which goes under the RTL8922AE model name, coming in M.2 2230 and 1620 formats, where the latter is a solder down module. To simulate a real world scenario, Realtek was running a second radio to cause some additional interference, but the RTL8922AE test setup was still capable of delivering between 1,750 and 1,950 Mbps, which is almost twice as fast as WiFi 6, using a similar 2x2 antenna setup. This was obviously over a fairly short distance, so the question is how well WiFi 7 will work over longer distances.

The RTL8922AE has a claimed maximum sync speed of 2800 Mbps when connected to the 5 GHz and 6 GHz bands simultaneously and combining the bandwidth of both bands. However, it is limited to a 160 MHz channel bandwidth, whereas WiFi 7 can go up to a 320 MHz wide channel, but it's unclear if competing first gen clients will support this. The RTL8922AE also incorporates support for Bluetooth 5.4 and is as far as we're aware one of the first WiFi chips to support the upcoming standard that mostly focuses on improving BLE Audio and Auracast support. The RTL8922AE should launch sometime in the fourth quarter this year to Realtek's customers, so it might not appear on the market until early 2024.

Shenzhen based Milk-V has been busy announcing some very high performance RISC-V based platforms, and has now added another to a rapidly growing list. The Milk-V Mars is a new hobbiest grade RISC-V SBC that intentionally mimics the footprint and layout of the Raspberry Pi 3 Model B, so much so that existing cases and accessories will fit. The credit-card sized Mars packs a very competent array of features, starting with the StarFive JH7110 SoC. The JH7110 contains four 64-bit SiFive U74 RISC-V cores clocked as high as 1.5 GHz as well as an integrated Imagination Technologies IMG BXE-2-32 graphics engine with support for Vulkan 1.3, OpenGL ES 3.x, OpenCL 3.0, and Android NN HAL. This SoC should be the perfect choice for an SBC in this form factor, as it has proven to be on the similarly sized PINE64 Star64 as well as StarFive's VisionFive 2. Surrounding the SoC is a single LPDDR4 module, configurable at purchase up to 8 GB, the traditional 40-pin GPIO header row, a M.2 E-Key for WiFi/BT expansion, a MIPI display serial interface with 4K30 output and H.264/H.265 4K60 decoding, MIPI camera serial interface, HDMI, a USB-C for 5 V power input, a 3.5 mm audio jack, and finally the rear I/O block which consists of three USB 3.0 Type-A, a single USB 2.0 Type-A, and the RJ-45 for Gigabit Ethernet as well as PoE. Storage is expandable with both eMMC and microSD cards. The last tiny header is for powering a fan, which many R Pi cases opt to include, but is not included with the Mars. Availability of the Milk-V Mars is listed as "Coming Soon" and prices have not yet been announced. However to compete with the other options on the market we hope, and expect, that it does not exceed $75 USD. Unlike the Milk-V Pioneer there hasn't been any word on whether the Mars will be as open-source friendly, but it would behoove them to consider the option for this type of hobbyist oriented device.

MediaTek, a leading innovator in connectivity and multimedia, is teaming with NVIDIA to bring drivers and passengers new experiences inside the car. The partnership was announced today at a COMPUTEX press conference with MediaTek CEO Rick Tsai and NVIDIA founder and CEO Jensen Huang.

"NVIDIA is a world-renowned pioneer and industry leader in AI and computing. With this partnership, our collaborative vision is to provide a global one-stop shop for the automotive industry, designing the next generation of intelligent, always-connected vehicles," said Tsai. "Through this special collaboration with NVIDIA, we will together be able to offer a truly unique platform for the compute-intensive, software-defined vehicle of the future."

"AI and accelerated computing are fueling the transformation of the entire auto industry," said Huang. "The combination of MediaTek's industry-leading system-on-chip plus NVIDIA's GPU and AI software technologies will enable new user experiences, enhanced safety and new connected services for all vehicle segments, from luxury to entry-level."

Mobile devices touch every aspect of our digital lives. In the palm of your hand is the ability to both create and consume increasingly immersive, AI-accelerated experiences that continue to drive the need for more compute. Arm is at the heart of many of these, bringing unlimited delight, productivity and success to more people than ever. Every year we build foundational platforms designed to meet these increasing compute demands, with a relentless focus on high performance and efficiency. Working closely with our broader ecosystem, we're delivering the performance, efficiency and intelligence needed on every generation of consumer device to expand our digital lifestyles.

Today we are announcing Arm Total Compute Solutions 2023 (TCS23), which will be the platform for mobile computing, offering our best ever premium solution for smartphones. TCS23 delivers a complete package of the latest IP designed and optimized for specific workloads to work seamlessly together as a complete system. This includes a new world-class Arm Immortalis GPU based on our brand-new 5th Generation GPU architecture for ultimate visual experiences, a new cluster of Armv9 CPUs that continue our performance leadership for next-gen artificial intelligence (AI), and new enhancements to deliver more accessible software for the millions of Arm developers.

UDOO, known for embedded and single-board computing, has launched a pair of x86 equipped SBCs utilizing Intel's Apollo Lake SoCs and aimed at the low-power machine learning and edge AI markets. The UDOO VISION line of SBCs come in two distinct flavors at launch: VISION X5 and VISION X7. As the names imply, the VISION X5 comes equipped with an Intel Atom x5-E3940, while the VISION X7 has an Intel Atom x7-E3950. Neither of these SoCs is particularly fresh, with the designs dating back to 2014, however for the intended use case they should provide ample performance. UDOO states,"The UDOO VISION is the ultimate choice for computer vision projects thanks to the excellent performance of the Intel Apollo Lake SoC [System on Chip] and the Intel distribution of OpenVINO framework ready to be installed."

Aside from the processor differences the VISION X5 comes with 4 GB of LPDDR4 DRAM and 32 GB of eMMC storage, while the higher spec VISION X7 comes with 8 GB of LPDDR4 and 64 GB eMMC. Both models include an ATmega32U4 microcontroller, a 26-pin Arduino Leonardo's pinout for modularity, a COM port supporting RS232/RS422/RS485, two USB 2.0 headers, two USB 3.0 ports, dual Gigabit Ethernet LAN, M.2 E-Key for WLAN/Bluetooth expansion, M.2 B-Key for SATA SSD expansion, RTC, infrared, one mini DisplayPort, one eDP connector, and a fan header for the bundled full-cover active heatsink. UDOO lists the VISION X5 at $349 USD, and the VISION X7 at $419 USD.

Edge sensors, such as LiDAR, radar and 3D surround-view camera systems, are becoming more prevalent in the automotive market, especially with the growing adoption in autonomous driving. As more sensors are needed for autonomy, there are increasing needs for faster signal processing, reduced device costs and smaller form factors. Functional safety is also critical for many of these autonomous applications.

To address these market needs, we're introducing two additions to our AMD Automotive XA Artix UltraScale+ family: the XA AU10P and XA AU15P cost-optimized processors, which are automotive-qualified and optimized for use in advanced driver-assistance systems (ADAS) sensor applications. The Artix UltraScale+ devices extend the AMD portfolio of automotive-grade, functional-safety proven and highly scalable FPGA and adaptive SoCs, joining the automotive-grade Spartan 7, Zynq 7000 and Zynq UltraScale+ product families.

Imagination Technologies is bringing seamless visual experiences to cost-sensitive consumer devices with the new IMG CXM GPU range which includes the smallest GPU to support HDR user interfaces natively.

Consumers are looking for visuals on their smart home platforms that are as detailed, smooth, and responsive as the experience they are accustomed to on mobile devices. At the same time, ambitious content providers are aligning the look and feel of their applications' user interfaces with their cinematic content, by integrating advanced features such as 4K and HDR.

Chinese RISC-V developers Milk-V Technology and SOPHGO recently announced their collaborative open source Milk-V Pioneer developer motherboard and workstation based on the SOPHON SG2042 RISC-V server SoC. The SOPHON SG2042 is a 64-core, 2 GHz SoC based on T-Head Semiconductor's XuanTie C920 64-bit processor design which features clusters of one to four cores, each a 12-stage out-of-order multiple issue superscalar pipeline, and a 128-bit vector engine based on the preliminary RISC-V V Extension version 0.7.1. The SG2042 packs in 64+64 KB (I+D) L1 cache per core, 1 MB of L2 cache per core cluster, 64 MB of L3 system cache, a quad-channel DDR4 controller, and 32 lanes of PCI-E Gen 4. The SG2042 contains no integrated graphics solution.

The Milk-V Pioneer incorporates this highly threaded RISC-V SoC with a modular and expandable standard mATX motherboard featuring four DIMM slots with support for up to 128 GB of DDR4, three full-length PCI-E slots wired for Gen 4 x8, two M.2 M-Key PCI-E Gen 3 x4, one M.2 E-Key for PCI-E 3.0 x1 and USB 2.0, eight USB 3.2 10 Gbps ports, five SATA 6 Gbps ports, and a pair of 2.5G Ethernet ports. The bulk of this I/O runs off an ASMedia ASM 2824 PCI-E switch, however the PCI-E Gen 4 ports run directly off the SG2024 SoC. Milk-V Pioneer is also being offered as a prebuilt small form factor workstation which puts the board into a small portable chassis called the Pioneer Box. The Pioneer Box includes 64 GB of DDR4-3200, 1 TB M.2 SSD, an Intel X520-T2 10G network card, an AMD Radeon R5 230 graphics card for display, and a 350 W power supply.

Russian business news outlet Kommersant has learned from industry figures that prices of natively-designed computer processors have been on the rise since the beginning of 2023. Domestic manufacturers of PC, server and storage systems are requiring greater supplies of CPUs designed by Baikal Electronics and MCST - the publication posits that growing demand and logistical issues have become the root cause of recent climbs in cost - individuals involved in the computer hardware supply chain have suggested that some processor models have doubled in price. Sergey Ovchinnikov, the chief executive of Norsi-Trans (a server and data storage firm) provided comment: "Production of Russian chips at foreign fabs has become more complex, leading to extended logistics chains and, consequently, an increase in the cost of the final component." International trade sanctions have not prevented the arrival of fresh silicon into the region - Ovchinnikov claims that an unnamed foundry is able to supply (likely via proxy) Russian developers with computer processors.

Kommersant's investigation found out that Baikal's BE-T1000 CPU is now sold for roughly $110 (8900 Rubles) at a popular computer hardware e-tailer (ChipDip) in the region. The very basic dual core MIPS32r5 (28 nm) processor was readily available for $50 (3990 rubles) back in 2018, so its price has risen by 220% in recent times. TSMC was contracted as the manufacturer of Baikal's BE-T1000 CPU, and the Taiwanese foundry started producing these SoCs in 2016. A Baikal Electronics representative has denied any involvement in driving up MSRP, and states that it is up to distributors and retail outfits to determine prices. The company suspects that very old stock is being sold at inflated rates - Kommersant was unable to contact anyone at ChipDip for a statement.

MediaTek is rumored to have partnered up with NVIDIA in a new joint effort to create graphically powerful mobile chipsets. DigiTimes Asia reports that the two fabless companies are collaborating on a flagship-level smartphone SoC that could arrive in early 2024. MediaTek is hoping that this tech union will help advance its application processors with AI enhancements and greater gaming functionalities. Insider sources also claim that the partnership extends to the development of WOA (Windows on Arm) platform products for notebook applications.

DigiTimes believes that NVIDIA is seeking new market scope - outside of its normal staple of gaming and enterprise GPUs - opportunities within the smartphone and notebook market are part of an overall expansion strategy, including the teaming up with MediaTek. Arch rival AMD has been working with Samsung for a number of years on RDNA-based "Xclipse" iGPUs, as featured in several existing and upcoming flagship Exynos mobile chipsets, and Team Green is seemingly interested in doing something similar. MediaTek is keen to expand its processor presence in the notebook world - its current offerings only target the entry-level segment - and the alliance with NVIDIA could result in forthcoming mid-range and high-end WOA platform products.

MediaTek has been unveiling some new mobile chipsets this week, but keen-eyed news outlets have noticed that the Taiwanese fabless semiconductor company is simply renaming and relaunching hardware from last year, with some tweaks here and there. Today's announcement of the Dimensity 8050 SoC was almost immediately questioned - GSMArena noticed that this "new" model was a near dead ringer, in terms of specifications, for last year's mid-range Dimensity 1300 and 1200 smartphone chipsets. There are some upgrades in terms of memory bandwidth, and MediaTek boasts that the 8050 has been updated with its sixth generation HyperEngine technology.

Alarm bells were ringing when folks realized that the much older Dimensity 8000 SoC was built on a 5 nm process - the supposedly superior (in terms of model number hierarchy) 8005 is a 6 nm chip. Last week the mobile specialist site also spotted that MediaTek's Dimensity 7050 chipset was yet another example of the smartphone tech company rolling out a "rebranding phase." The news outlet pointed out that this newly revealed mobile CPU was just a renamed Dimensity 1080 - with the original model having hit the market in November 2022. MediaTek seems to renaming several older chipsets based on TSMC's 6 nm process - it is possible that this effort is part of a company drive to clear surplus silicon.

The latest AMD AGESA 1.0.0.7 AM5 platform microcode that the company recently released to improve stability of machines powered by Ryzen 7000X3D processors, more importantly, prevent them from physical damage due to increased voltage in voltage-assisted overclocking scenarios; reportedly impacts memory overclocking capabilities, too, reports g01d3nm4ng0. The "PROCHOT Control" and "PROCHOT Deassertation Ramp" toggles that were available in the oldest versions of AGESA for AM5, are not available in the latest production AGESA.

The memory compatibility is also affected. AMD recently added support for odd-density DDR5 memory modules, such as 24 GB and 48 GB, which make up 48 GB and 96 GB 2-module (dual-channel, four sub-channel) kits. It is possible to max out 192 GB, but while the older AGESA 1.0.0.6 allowed memory frequencies of up to DDR5-6000 with SoC voltage of 1.3 V, the newer AGESA is only stable up to DDR5-4400 at this density. To be fair, most motherboards advertise maximum memory frequencies of under DDR5-4800 for memory configurations where there are two DIMMs per channel, and both DIMMs are dual-rank (so four dual-rank DIMMs in all, which is the least optimal memory configuration from a memory frequency and latency perspective).

The ASUS ROG Ally handheld games console emerged last month and it was revealed to pack some impressive "custom" AMD hardware - the two companies have boasted that the collaboration has resulted in two special SoCs - the Ryzen Z1 and Ryzen Z1 Extreme. Silicon enthusiasts were quick to point out that the Z1 series sported similar specifications to mobile/ultra-portable chipsets in AMD's 7040U family - in particular the Ryzen 7 7840U looks almost identical to its gaming equivalent (Ryzen Z1 Extreme). Andrew E. Freedman at Tom's Hardware was curious and motivated enough to request clarification (about this situation) from AMD. Team Red were happy to respond and acknowledged the apparent similarities between the gaming and laptop chipset ranges, but also stated that Z1 APUs have been tweaked by company engineers to a certain degree.

Matthew Hurwitz, a client PR manager at AMD, provided a response to the Tom's Hardware-issued query: "The Ryzen Z1 series are purpose-built with handheld gaming in mind. To accomplish this, AMD engineers had to validate entirely new power ranges and optimize the voltage curves specifically for this use case - this optimization and validation work should not be trivialized. So while the technology building blocks (like 'Zen 4' and RDNA 3) are similar between the 7040 and Z1 series, the resulting models have very distinct characteristics customized for their use cases. In addition, the AMD Ryzen AI engine is not available on AMD Ryzen Z1 series processors." Hurwitz also confirmed that AMD's XDNA AI engine is merely disabled (so not removed at hardware level) on the two Z1 APUs - this feature is only enabled on the range-topping Ryzen 7 7840U model and mid-range Ryzen 5 7640U. So yes, there are small differences but AMD and ASUS have probably saved some money on development costs by creating and adopting the "slightly adjusted" Z1 SoC series.

Update May 6th: Tom's Hardware has amended their article (as of May 5, 5:03 p.m. ET) - another source within AMD has informed them about the Z1 and Z1 Extreme APUs having configurable TDPs of 9 W to 30 W. The original story - and AMD's website - claimed a range of 15-30 W.

AMD is reported to be reissuing its old Zen+ (12 nm) tech in order to meet demand for cheaper, lower-end systems in China, according to information released by Board Channels this week. The insider source claims that a new production order has been placed for Ryzen 3000G series APUs (requesting up to 30,000 units) and these processors are likely to be sold as part of hardware bundles with (similar vintage) low-end AM4-based motherboards - for example the B450 and A320 series, these older boards are still popular budget choices in China and readily available. The leak does not mention whether AMD is choosing to issue completely new hardware or if it is simply reproducing its 2019-era SKUs.

AMD released two Ryzen 3000G models back in 2019 - the 3400G and 3200G, both are quad-core Picasso APUs although the latter is lacking in simultaneous multithreading. It is not clear whether the super low budget AMD Athlon 3000G model will be included as part of the alleged 30K unit order. The 3000G series' onboard iGPUs (based on AMD's first generation Vega architecture) are likely preferred by the budget-conscious buyer since a discrete graphics card is not an essential part of builds intended for an office setting or a simple/functional home computer setup.

According to Tom's Hardware, Microsoft is busy hiring engineers to help the company design its own Arm based SoC for Windows 12. Based on job listings, Microsoft is adding people to its "Silicon team," which is currently involved in designing products for Microsoft's Azure, Xbox Surface and HoloLens products. That said, the specific job listings mentioned by Tom's Hardware mentions "optimizing Windows 12 for Silicon-ARM architecture" suggesting we're looking at a custom Arm SoC, with others mentioning "internally developed silicon components" and "building complex, state-of-the-art SOCs using leading silicon technology nodes and will collaborate closely with internal customers and partners."

That said, Microsoft is currently working with Qualcomm and the Microsoft SQ3 found in the Surface Pro 9 is the latest result of that partnership. This brings the question if Microsoft has decided to make its own chip to compete with the Apple M-series of silicon, or if Microsoft is simply looking at working closer with Qualcomm by hiring inhouse talent that can help tweak the Qualcomm silicon to better suit its needs. With Windows 12 scheduled for a 2024 release, it looks like we'll have to wait a while longer to find out what Microsoft is cooking up, but regardless of what it is, it looks like Windows on Arm isn't going anywhere.

It appears it's not only AMD that is eyeing a move to Samsung, when it comes to fabricating upcoming chips, as reports are now suggesting that Qualcomm is considering a second attempt at making flagship mobile SoCs at Samsung's foundry. However, in this case, we're talking 3 nm chips in the shape of the Snapdragon 8 Gen 4, which is expected to launch in devices sometime in 2024. This is said to be Qualcomm's first chip based on cores built by Nuvia, a company that Qualcomm acquired in 2021.

That said, Qualcomm will apparently not rely on Samsung alone, but will also be making the Snapdragon 8 Gen 4 at TSMC. This might be because of past experience with Samsung, but the report out of Taiwan, suggests that the chips made by Samsung's foundry business will be used in Samsung branded phones, whereas the TSMC made chips might end up in devices by Qualcomm's other customers. It could also be a bet for Qualcomm to try and get better pricing by both foundries or a means of hedging their bets, to see which foundry produces the better chips. Then there's the situation between the PRC and the ROC, which could potentially put Qualcomm in a situation where it has no chips, so going with Samsung could be a means of covering for all potential risk scenarios.

AOKZOE is trying to drum up interest for its latest handheld gaming console - the A1 Pro - with a countdown to a type of early bird sale starting tomorrow. Early adopters will be offered a special starter price of just $799 for the baseline version, and that cost of entry will climb to $999 later on at retail. AOKZOE boasts that the A1 Pro is the first handheld gaming device to pack an AMD 7 7840U APU - a customized version of this SoC (AMD Z1 processor series) is set to debut as part of the ASUS ROG Ally handheld system. The current AOKZOE A1 model is powered by an older AMD Ryzen 7 6800U APU, which sat at the heart of various laptops and mobile gaming devices in 2022. This year's A1 Pro models are powerful enough to take on Valve's Steam Deck (and the previously mentioned ROG Ally) thanks to impressive internal specifications - AOKZOE reckons that the Pro upgrade offer a 20% performance leap over previous gen devices (6800U).

The Zen 4-based Ryzen 7 7840U APU, part of the "Phoenix" range of mobile processors, is available in all configurations of the A1 Pro - the base model gets 32 GB of memory and 512 GB of storage, and the headliner has 64 GB of memory and 2 TB of storage. AOKZOE states that the A1 Pro utilizes the LPDDR5-6400 RAM and PCIe 3.0 x4 standards - their handheld system is also capable of running M.2 2280 PCIe 4.0 drives. The A1 Pro features an 8-inch FHD (1920 x 1200) IPS display - its nearest rivals have smaller 7-inch screens. Hardcore game controller enthusiasts will be happy to discover that hall effect sensor technology has been integrated into the new handheld's pair of analog sticks.

Samsung Electronics today reported financial results for the first quarter ended March 31, 2023. The Company posted KRW 63.75 trillion in consolidated revenue, a 10% decline from the previous quarter, as overall consumer spending slowed amid the uncertain global macroeconomic environment. Operating profit was KRW 0.64 trillion as the DS (Device Solutions) Division faced decreased demand, while profit in the DX (Device eXperience) Division increased.

The DS Division's profit declined from the previous quarter due to weak demand in the Memory Business, a decline in utilization rates in the Foundry Business and continued weak demand and inventory adjustments from customers. Samsung Display Corporation (SDC) saw earnings in the mobile panel business decline quarter-on-quarter amid a market contraction, while the large panel business slightly narrowed its losses. The DX Division's results improved on the back of strong sales of the premium Galaxy S23 series as well as an enhanced sales mix focusing on premium TVs.

The global economy has faced increased inflation risks and downstream inventory corrections in 2H22, which have affected IC design houses faster than wafer foundries, as they are far more sensitive and responsive to market reversals. TrendForce reports that adverse factors such as weak overall consumption, restrictions from China, and the slowdown of corporate IT spending and CSP demand have impacted the revenue performance of the world's top 10 IC design houses in 4Q22, leading to a QoQ decline of 9.2%, or approximately US$33.96 billion.

TrendForce predicts that the revenue of these top 10 companies keep declining—though with a slight convergence—into 1Q23, owing to ongoing inventory corrections across the entire supply chain as well as Q1 being the traditional off-season for consumer demand. Demand will continue to be weak despite new product launches and inventory replenishment in the supply chain.

Accelerating the integration of heterogeneous dies to enable the next level of system scalability and functionality, Synopsys, Inc. (Nasdaq: SNPS) has strengthened its collaboration with TSMC and Ansys for multi-die system design and manufacturing. Synopsys provides the industry's most comprehensive EDA and IP solutions for multi-die systems on TSMC's advanced 7 nm, 5 nm and 3 nm process technologies with support for TSMC 3DFabric technologies and 3Dblox standard. The integration of Synopsys implementation and signoff solutions and Ansys multi-physics analysis technology on TSMC processes allows designers to tackle the biggest challenges of multi-die systems, from early exploration to architecture design with signoff power, signal and thermal integrity analysis.

"Multi-die systems provide a way forward to achieve reduced power and area and higher performance, opening the door to a new era of innovation at the system-level," said Dan Kochpatcharin, head of Design Infrastructure Management Division at TSMC. "Our long-standing collaboration with Open Innovation Platform (OIP) ecosystem partners like Synopsys and Ansys gives mutual customers a faster path to multi-die system success through a full spectrum of best-in-class EDA and IP solutions optimized for our most advanced technologies."

The Financial Times this weekend has published details about an interesting development project that is currently in-the-works at British semiconductor specialist firm Arm Ltd. The article states that several executives in the industry have divulged (anonymously) that Arm's engineering team is designing a proprietary chip - these insider sources opine that this new creation could be one of the company's most advanced undertakings. The SoftBank-owned chipmaker is having a bumper year in terms of financial success and has invested in its future - it is speculated that their own semiconductor design will be showcased as a prototype product to potential new clients - with the main goal being to drum up more business and growth. Parent group SoftBank is likely pushing for maximum profit margins as it prepares Arm for an initial public offering (IPO) this year.

Arm's modus operandi involves partnering up with other chip manufacturers in order to license out its semiconductor intellectual properties. In turn these partners are expected to deal with the overall design and manufacturing processes of chips (plus sales of). Arm has teamed up with foundries TSMC and Samsung in the past to create prototypes for software testing purposes, but not much has been heard about those proofing projects in the following years. In an unusual turn (from certain industry perspectives) from its traditional working methodologies, it seems that Arm is embracing a different approach by producing its own compelling designs, with the hope of demonstrating greater potential to customers. FT's sources have provided evidence that Arm has expanded its operations and that a newly formed "solutions engineering" team is focused on prototyping new silicon for usage in mobile hardware and related devices.

Conflicting reports are flying around about Apple's next generation MacBook Air lineup, mostly surrounding suggestions of a firm release date or debut reveal at WWDC 2023. 9to5Mac claims that its insider sources have pointed to a new range of M3 chipset powered MacBook Air extra thin laptops offered up in two different screen sizes: 13-inch and 15-inch. An insider claimed last month that Apple's upcoming laptop lineup was in an advanced stage of production, and was far along enough to warrant an "imminent" launch window. A Taiwanese publication has presented new evidence this week, and it posits that Apple could drop M3 chipset-based laptops from announcement presentations organized for this year's Worldwide Developers Conference, which is set to take place from June 5 to 9.

According to the financial section of Taiwan's UDN news site, Apple's key decision makers could be in favor of fielding laptops based on its current generation M2 SoC, instead of an entry-level M3-based range, due to delays and changes in priority for the N3B node at TSMC foundries. This is seen as an odd move given reports from earlier this month of Apple requesting a reduction in factory output for its M2 chips, following a slump in demand. Apple could be changing its strategy with regards to the alleged surplus of M2 silicon - the article theorizes that the company will spend more time fitting the older generation chipsets into a new range of laptops and desktop computers. An M3-based product line could be delayed into late 2023, and it is alleged that TSMC has been instructed to concentrate mostly on manufacturing Apple's Bionix A17 mobile chipset via the cutting edge 3 nm FinFet technology process (N3B) - earmarked to debut on the iPhone 15 Pro in autumn 2023.

A technology tipster has been dropping multiple tidbits this week about Qualcomm's upcoming Snapdragon 8 Gen 3 mobile chipset - this follows a leak (from a different source, going back to mid-April) about the next generation Adreno 750 GPU getting tuned up for a battle against Apple's Bionic A17 in terms of graphics benchmarks. The latest leak points to the GPU being clocked at 900 MHz, rather than the rumored higher figure of 1.0 GHz speed (garnered from tests at Qualcomm's labs). The focus has now turned to the next generation flagship Snapdragon's CPU aspect, with information emerging about core clock speeds and multiple cluster configurations.

Revegnus suggests that the Snapdragon 8 Gen 3 (SD8G3) chipset will be packing a large primary core in the shape of Arm's Cortex-X4 CPU with a reported maximum clock speed of 3.40 GHz. Leaks from the past have posited that the SD8G3 would feature a fairly standard 1x Large + 5x Big + 2x Small CPU core layout (with clocks predicted to be: large Cortex X4 at 3.2 GHz, big Cortex-A720 at 3.0 GHz, and small Cortex-A520 at 2.0 GHz). An insider source has provided Revegnus with additional information about two different CPU core configurations - 1+5+2 and 2+4+2 - it is theorized that smartphone manufacturers will be offered the latter layout as an exclusive option for special edition flagship phones. The more powerful 2+4+2 variant is said to sacrifice a big core (A720) in favor of a dual Cortex X4 headliner, although the resultant thermal output of twin large cores could prove to be problematic.