标签： Intel 18A

The internal roll-up between big factories should be what all users are willing to see. With AMD’s power in 2025, some people are optimistic that AMD will bring new products, but some people will worry about a single company’s dominance. However, according to a series of recent news, Intel, a chip giant, is obviously not going to sit still. A series of things are foreshadowing that it will cause another industry shock in the coming long time! Let’s focus on sorting out these important news. Point 1: The 18A process is about to be mass-produced, and the performance of the standard TSMC’s 2nm The first priority in 2025 must be a technological breakthrough. Intel has said that it will launch the first batch of 18A process products in 2025, PantherLake for AIPC and ClearwaterForest for servers. The product of this 18A process process is understood to be directly benchmarked to TSMC’s 2nm process, with SRAM density close to TSMC’s 2nm, and will also introduce RibbonFET full surround gate transistor technology and PowerVia back power supply technology. The benefits are that the chip performance is increased by 25% and the power consumption is reduced by 36%. And the 18A process also has two options: HP high-performance library and HD high-density library. Compared with the existing Intel3 process, the performance is improved by 18% or the power consumption is reduced by 38% at 0.75V voltage, and the performance is improved by 25% or the power consumption is reduced by 36% at 1.1V. The process has been taped out for 18A at the Fab52 factory in Arizona and will be mass-produced by the end of the year. And Google, because big, Broadcom Zhiyuan Technology and other big factories have started 18A process for tape-out testing. Microsoft Azure, Amazon AWS, Broadcom and other top-tier clients have signed 18A foundry agreements with Intel. Point 2: XeSS super-division technology is upgraded again, the frame rate is increased by 4 times. Intel’s XeSS super-division technology has made further breakthroughs. AI-based frame generation technology (XeSS-FR) and low-latency optimization technology (XeLL) have achieved dual evolution of picture smoothness and operation response. According to the test, after matching the independent graphics card, the frame rate of many games has been improved by multiple levels, such as: “Diablo IV” increased by 4 times, “Assassin’s Creed: Shadow” increased by 2.4 times. The core display has also been significantly improved. With XeLL low-latency technology, the system delay can be reduced by an average of 45% in the actual test. At present, 19 games have adopted this technology, and more than 200 games have adopted it. The future performance in the game is very worth looking forward to. Key point 3:14A process is forward-looking, power consumption is reduced by 25%. Although this year is mainly based on 18A process, Intel has been preparing for the next generation of technology early. According to the news, the next generation 14A process technology has entered the early testing stage, and the next generation technology is mainly based on further breakthroughs in performance and energy efficiency. Through the introduction of PowerDirect direct contact power supply technology, the resistance is reduced by 30%, and the performance per watt is improved by 15% -20%. At the same time, the High-NAEUV lithography machine is used for the first time, and the transistor density is increased by 30% to 23.80 million/square millimeter. And the 14A process also has a dynamic optimization technology “TurboCell” that can dynamically adjust the voltage and frequency according to the load. It can improve the performance of high-frequency operation by 10%, and reduce the power consumption by 25% in low-load scenarios. Make the chip have high computing power while meeting the needs of long battery life. Key point 4: Advanced packaging technology matrix, 3D stacking + heterogeneous integration to improve the degree of freedom of the chip. In the field of packaging, Intel has completed the leap from 2D to 3D, from a single technology to a comprehensive layout of system-level solutions. Foveros Direct 3D packaging technology achieves an interconnect spacing of less than 5 microns through copper-copper hybrid bonding, which increases the density of traditional solder connections by 3 times and reduces power consumption by 40%, making it an ideal choice for AI chips and high-performance computing (HPC). The key technology of EMIB-T (Embedded Multi-Chip Interconnect Bridge-Silicon Via) is the introduction of TSV technology from 2.5D packages to support higher density signal transmission and power distribution, making the chip meet the needs of heterogeneous integration scenarios of different process chips. At the same time, the addition of two derivative solutions, Foveros-R and Foveros-B, has given a higher degree of freedom between chips and stronger support for the demand for high reliability. Point 5: Strategic transformation of the new leader: from IDM to open foundry, the yield rate has increased to 75%. Intel CEO Chen Liwu put forward the concept of “foundry is not selling capacity, but providing full chain value from design to system integration”, and established the “Core-particle Alliance” and “Value Chain Alliance” to integrate IP, EDA, and packaging resources to provide customers with a “one-stop” development platform. In terms of customer cooperation, Intel has cooperated with MediaTek, Qualcomm, Microsoft, etc. to completely transform into “open foundry”. In terms of company management, Chen Liwu put forward the concept of “the first day of startups”, breaking down hierarchical barriers and giving engineers more autonomy in innovation. And in the introduction of talents, it is also more inclined to the field of AI chip design, advanced packaging materials, and software-defined chips (SDSoC). Key point 6: Future product full-stack layout: AI chips, automotive electronics, and edge computing are fully blossoming. The key node in 2025 is the landing of the 18A process chip. With the performance of high performance and low power consumption of the chip and the super computing power and energy efficiency ratio in the AI field, it will give Apple’s M3 chip a strong response, and fill the gap between Qualcomm and Apple in edge AI. In 2026, Intel’s top priority is to do a good job in the 14A process chip. Nova Lake processors will support Chiplet design for the first time, allowing users to freely combine CPU, GPU and NPU modules to meet the challenges from AMD Zen5 and Apple server chips. At the same time, it focuses on various fields such as vehicle cameras, radar controllers, Internet of Things and autonomous driving. Through 12nm mature process products, 12nm autonomous driving domain controllers and 16nm-based low-power node chips for smart home and industrial sensors, it is not difficult to see that Intel’s current changes will not be limited to one field, but involve desktop, mobile end, autonomous driving, smart home and industrial and other aspects. And not only for chip performance and power consumption, but also for AI slowdowns, there will be new breakthroughs. Therefore, in the next one to two years, we should look forward to Intel’s new vitality, allowing more high-performance, low-power, and high-reliability products to be delivered to the public.

Fast Technology April 30th news, at today’s foundry business conference, Intel announced the latest process roadmap and shared the latest progress of the foundry business. Intel disclosed data show that in 2021 proposed “four years and five process nodes” plan to 2024, Intel’s global capital expenditure reached 90 billion US dollars. About 18 billion US dollars were invested in technology research and development, and 37 billion US dollars were invested in wafer plant equipment expenditure. Four years and five nodes have invested 90 billion dollars! Intel: 18A has been put into production for four years and five nodes this year. 90 billion US dollars have been invested! Intel: 18A mass production this year Intel said that the 18A process node has entered the risk pilot run stage and is expected to achieve mass production this year, while the next-generation 14A process after 18A will enter the risk production stage around 2027. 14A is expected to bring 15% -20% energy efficiency improvement, as well as a 1.3-fold increase in chip density. At the same time, several customers plan to tape 14A test chips. Compared with the PowerVia back power supply technology used by Intel 18A, Intel 14A will use PowerDirect direct contact power supply technology. Intel also announced two variants of the 18A process – 18A-P and 18A-PT, in which Intel 18A-P will bring more excellent performance. Early test wafers are currently in production and are compatible with Intel 18A design rules. The Intel 18A-PT is another Intel 18A evolution based on the performance and energy efficiency advancements of Intel 18A-P. It can be connected to the top chip through Foveros Direct 3D advanced packaging technology, and the hybrid bond interconnect spacing is less than 5 microns. Foveros Direct 3D is currently used in production by TSMC, and is best known to consumers as AMD’s 3D V-Cache products. In terms of mature nodes, the first 16-nanometer-based products of Intel’s foundry taping process have been produced in the wafer factory, and the 12-nanometer node and its evolved version are also being negotiated with major customers in cooperation with UMC. Four years of five nodes have been invested in $90 billion! Intel: Four years of five nodes in mass production of the 18A this year have been invested in $90 billion! Intel: 18A in mass production this year