本網站使用瀏覽器紀錄 (Cookies) 來提供您最好的使用體驗，我們使用的 Cookie 也包括了第三方 Cookie。相關資訊請訪問我們的隱私權與 Cookie 政策。如果您選擇繼續瀏覽或關閉這個提示，便表示您已接受我們的網站使用條款。 關閉
Hangzhou,China,January 29,2026--As the global technology industry accelerates its shift toward open architectures and on-device artificial intelligence, Chinese RISC-V chip company SpacemiT announced the launch of its new K3 AI CPU on January 29. The company aims to combine the open RISC-V instruction set with general-purpose and AI computing capabilities, offering a more flexible, power-efficient and cost-effective platform for intelligent terminals and edge computing. For decades, the processor market has been dominated by x86 and Arm architectures. However, as AI workloads gradually move from the cloud to end devices, there is growing interest in more open and customizable computing platforms. RISC-V, as a fully open-source instruction set architecture, is increasingly seen as a key foundation for the next generation of open computing ecosystems. Founded in 2021 and headquartered in Hangzhou, SpacemiT is one of the few Chinese semiconductor companies committed to a “pure RISC-V” strategy. The company focuses on integrating high-performance general computing and AI acceleration into a single chip, which it describes as an “AI CPU” approach. This design philosophy targets intelligent hardware scenarios that require high computing density, low power consumption and strong system integration. The K3 chip is the result of more than 1,200 days of development. According to the company, it is among the first mass-production-ready RISC-V AI CPUs compliant with the RVA23 specification. It also supports 1024-bit RISC-V Vector extensions (RVV) and native FP8 precision for AI inference. In terms of hardware configuration, K3 integrates eight high-performance X100 RISC-V CPU cores with a maximum frequency of 2.4GHz. SpacemiT said its single-core performance is broadly comparable to Arm’s Cortex-A76. The chip delivers up to 60 TOPS of AI compute and supports up to 32GB of LPDDR5 memory. SpacemiT noted that K3 is not designed to compete directly with high-end server CPUs or GPUs, but instead to enable local execution of medium-scale AI models and multimodal applications. The company said K3 can support models in the 30- to 80-billion-parameter range on a single chip, with typical system power consumption between 15 and 25 watts. On the software side, K3 adopts a co-design approach between hardware and software. It supports mainstream AI frameworks and compilers such as Triton and TileLang, and is compatible with major open-source AI ecosystems and Linux distributions. The company said this is intended to reduce the development barriers for deploying AI models on RISC-V platforms, bringing the experience closer to that of x86 and Arm systems. “We believe the long-term direction of computing architectures is a transition from closed to open systems,” said Chen Zhijian, founder and CEO of SpacemiT, at the launch event. “x86 is highly closed, Arm is semi-open, while RISC-V is fully open. In the long run, open instruction sets are more likely to become the foundation of global computing.” Chen added that RISC-V carries particular significance for China’s semiconductor industry. “In the past, Chinese computing chips were largely limited to domestic markets. Open architectures create a new path for Chinese chips to integrate more naturally into the global technology ecosystem.” K3 emphasizes a fusion of general computing, AI computing and data-coherent interconnects. Chen described this direction as the evolution toward a “next-generation AI CPU,” where traditional CPUs become increasingly intelligent. “In the AI era, CPUs can no longer be just control processors,” he said. “They must also provide native AI computing capabilities. This is similar to the shift from feature phones to smartphones — a fundamental change in the form of computing.” SpacemiT also disclosed that its previous-generation K1 chip has achieved shipments of more than 150,000 units and has been deployed in industrial control systems, robotics, edge computing platforms and open-source intelligent hardware. This commercial experience provides a foundation for the rollout of K3. The company said K3 has already received orders, with initial deliveries planned from the end of April 2026. The company continues to promote a “full-stack RISC-V” strategy, covering CPU IP, chip design, operating systems, compilers, AI software stacks and developer platforms. K3 supports multiple operating systems including Ubuntu, OpenHarmony and OpenKylin. SpacemiT is also launching supporting products such as PICO-ITX single-board computers, robot core boards and array server platforms, while opening its hardware reference designs to developers and system integrators. Hangzhou has recently emerged as a major hub for AI, semiconductor and open-source technology innovation in China. Industry observers note that a new generation of Chinese technology companies is taking shape in the region, strengthening China’s presence in advanced “hard-tech” sectors. SpacemiT is regarded as one of the representative players in this ecosystem. At the same time, the industry generally acknowledges that RISC-V still lags behind x86 and Arm in high-end computing, software ecosystem maturity and overall industrial scale. SpacemiT also recognizes that its current products are better suited to intelligent terminals and edge AI rather than competing directly with top-tier server processors or GPUs. “Our goal is not to confront global giants head-on,” Chen said. “Instead, we aim to establish differentiated advantages in the mid-range computing segment, using lower power consumption, higher integration and better cost efficiency to make AI computing accessible to more devices.” As artificial intelligence continues to move from centralized cloud platforms toward local deployment, power efficiency, system integration and open ecosystems are becoming key competitive factors. The launch of K3 represents a concrete step by China’s RISC-V community in combining open-source architectures with AI computing, and reflects China’s broader effort to explore new technological paths in the next generation of global computing.
【臺北訊】專業物聯網與人工智慧邊緣運算平臺研發製造大廠研揚科技（股票代碼：6579）宣布，攜手日本系統整合商歷經數月規格討論與試產驗證後，已於今年1月初正式開始出貨專為戶外型冷凍食品自動販賣機打造的嵌入式解決方案，進一步擴大其在日本智慧自動販賣機市場的布局。 自動販賣機長期被視為智慧零售的重要起點，近年更隨著無接觸購物需求升溫，帶動數位戶外廣告與自動貨架應用的快速成長。此次導入的PICO-M510 ODM專案，源自日本冷凍自動販賣機領導業者的需求，期望透過高可靠度的嵌入式系統，實現戶外智慧販賣機的穩定控制與高效率營運管理，提供冷凍餐食、零食、甜點及在地特色商品等多元販售服務。由於設備須長時間部署於戶外環境，且販售商品多為冷凍食品，系統的穩定性與耐用性成為專案成敗關鍵。研揚科技憑藉深耕日本市場多年的嵌入式研發實力，以及彈性、快速的ODM／OEM服務能力，獲得客戶青睞並迅速展開合作。 PICO-M510搭載整合Arm® Mali™-G57 MC2 GPU 的MediaTek Genio 510處理器，，並支援最高8GB LPDDR4記憶體。在自動販賣機有限的內部空間考量下，100mm x 72mm的Pico-ITX規格被選為最佳方案，同時整合多元I/O介面，包含三組RS-232／RS-485 COM連接埠與多個USB埠，滿足多樣化周邊設備的整合需求。 除硬體客製化外，本案亦涵蓋軟體層面的深度調整。因應客戶指定採用Debian 13作業系統，研揚研發團隊攜手聯發科技認證的第三方合作夥伴，為MediaTek Genio 510平台量身打造Debian 13系統支援影像，確保顯示介面具備流暢、即時的多媒體互動體驗。 為符合戶外應用需求，PICO-M510支援寬溫操作範圍（-20°C至70°C）與寬壓輸入（12V至24V），有效降低電源不穩定帶來的風險。同時，系統具備穩定的雲端連線能力，透過USB、RS-232與RS-485介面整合支付模組、POS終端機、收據印表機及各式感測器，可即時執行販售控制、庫存管理、溫溼度監測與馬達運作監控等核心任務。 此外，PICO-M510配置M.2 2230 E-Key插槽以支援Wi-Fi模組，並提供迷你PCIe插槽安裝4G模組，作為安全的雲端通訊管道，讓營運商能進行遠端監控、診斷與即時資料回傳，在不影響其他無線運作的情況下提升整體營運效率。 研揚科技RISC產品處產品經理林詩翔表示，此次專案充分展現研揚快速研發與跨夥伴協作的能力。由於專案同時涵蓋操作介面、冷藏功能與庫存管理系統，對於介面整合與板卡尺寸皆提出高度挑戰，但也為研揚團隊累積了寶貴經驗，進一步強化其在智慧零售與自動販賣機應用領域的競爭優勢。 此次專案每年預計有4000套的需求，研揚PICO-M510標準品預計將於2026年3月量產。更多PICO-M510產品規格，請與研揚科技國內業務處02-89191234分機1142 劉小姐聯絡。 關於研揚科技 研揚科技集團（研揚）是台灣專業物聯智能解決方案研發製造大廠，成立於1992年。研發製造並行銷全球IoT及AI邊緣運算解決方案，另有嵌入式電腦主板及系統、工業液晶顯示器、強固型平板電腦、工控機、網路安全設備以及相關配件等，提供OEM/ODM客戶及系統整合商完整且專業之軟硬體解決方案。同時，研揚有專屬團隊提供客製化服務，協助您從研發初期發想到產品製作、量產到售後服務，提供一貫之專業諮詢與服務，為您量身打造高品質產品。研揚目前提供多款AI邊緣運算產品及智慧城市、智慧零售及智慧製造等系統整合和解決方案。研揚是英特爾尊榮級會員(Prestige partner)，同時也是NVIDIA的首選夥伴(Preferred partner)。欲瞭解更多詳細資訊請參考研揚科技官方網站
公司將利用其後的種子資金推進其高效能 CPU 微架構的研發。該架構旨在滿足人工智能工作負載日益增長的運算需求。 俄勒岡州波特蘭2026年1月22日 /美通社/ -- AheadComputing, Inc. 是一家採用突破性微架構以提供業界頂尖 CPU 效能的先驅企業，於今天宣佈已在第二輪種子輪融資中募集得 3,000 萬美元資金，令公司迄今的總融資額達到 5,300 萬美元。 本輪融資由 Eclipse、Toyota Ventures 及 Cambium 共同領投，而 Corner、Trousdale Ventures、EPIQ、MESH 及 Stata 亦參與其中。 人工智能工作負載現正對超大規模數據中心、工作站、個人電腦和高級嵌入式系統的運算方式進行重塑。 儘管 GPU 效能備受關注，但 CPU 效能對於人工智能工作負載仍相當重要。然而它作為整體系統能力的關鍵組成部分卻往往受到忽略。 行業預測預計在 2030 年，所有數據中心的工作負載中將有 70% 為人工智能工作負載，而高效能 CPU 對於有效執行這些工作負載極為重要。 人工智能工作負載組合，現正朝向推理及代理形式的人工智能工作負載作出轉變，因此提高單核心 CPU 效能成為業界的首要任務。 AheadComputing 行政總裁兼聯合創辦人 Debbie Marr 表示：「我們的系統架構師和工程師團隊擁有超過 1,000 年的 CPU 設計經驗，他們超越傳統 CPU 創新的界限，不斷推動 CPU 效能向前發展。 因為每個人都值得擁有更佳的運算能力，所以這筆額外的資金讓我們得以繼續挑戰傳統規則，維持快速的轉型步伐，並研發速度最快的高效能通用 CPU。」 自 2024 年成立以來，AheadComputing 透過產品開發、與半導體生態系統合作夥伴的技術合作，以及與超大規模數據中心和運算提供商的客戶探索設計，取得了迅速進展。 其方法將 RISC‑V 的可擴展性與突破性微架構互相結合，證明開放式架構能為現代人工智能與數據中心應用提供頂級效能。 透過與整個生態系統的技術夥伴深入合作，AheadComputing 現正協助將 RISC-V 引入主流數據中心及人工智能基礎設施中。 Eclipse 合夥人暨 AheadComputing 董事局成員 Greg Reichow 表示：「在人工智能工作負載激增、效能的樽頸效應日益加劇，以及對具有更大擴展性和高效能 CPU 核心的迫切需求帶動下，運算行業正經歷根本性的轉變，而 AheadComputing 現正塑造一個龐大的可服務市場。 團隊路線圖採取了新穎的方法，製造出前所未有般強大的 CPU。 透過善用 RISC-V 的可擴展性並將之與突破性的微架構結合，團隊正在釋放業界多年來一直追求的效能和效率水平，並最終為現代 CPU 的效能奠定新標準。 這筆新資金將用於加強研發、軟件創新和測試晶片開發。 此外，AheadComputing 持續擴大團隊規模，目前人數接近 120 人，團隊人員在職業生涯中合共推出了超過 70 款產品。 有賴與 Alchip、Cadence、Skyechip 和 Tenstorrent 等生態系統合作夥伴進行關鍵合作，團隊目前正在研發首項產品。 如欲了解更多詳情，請瀏覽 aheadcomputing.com Corner：「人工智能需要更好的 CPU，而不僅是更大的 GPU。 AheadComputing 擁有世界一流的 CPU 架構體系與執行節奏，並已轉化作真正的里程碑，突破了以往單核心效能和效率的障礙。」 - Corner 普通合夥人 Marvin Tien。 MESH：「RISC-V 的廣泛採用最終將取決於一個簡單的臨界點：在最高運算領域保持效能持續的領先地位。 AheadComputing 是我們見過的少數幾支在架構方面既有抱負而又具執行深度，而且能夠達成該目標的團隊之一。 我們相信，它們具備得天獨厚的優勢，能為單核心 CPU 效能樹立新標桿，並且加快 RISC-V 在主流數據中心和人工智能基礎設施的擴展。 - MESH 管理合夥人 Edward Chyau ALCHIP:「運算行業現正處於轉折點。 Alchip 很高興能與 AheadComputing 合作，共同構建突破性的 CPU 效能，以滿足業界最迫切的需求。 隨著人工智能工作負載轉向推理和代理形式運算，AheadComputing 有望為高效能運算的可能性作出重新定義。 - 高級副總裁兼 Alchip 北美洲總經理 Dave Hwang Tenstorrent：「實現 CPU 效能的變革之路不在於追求逐步提升，而在於對基本情況作出重新思考。 你需要對核心微架構和目標作重新設計。 Debbie 與她在 AheadComputing 的團隊，正以能實際推動產業往前走的第一原理思維來解決這個問題。 團隊合共推出超過 70 款產品，並擁有數百項與運算相關的專利，技術洞察力與執行能力皆表露無遺。 這就是能帶來世代飛躍而非逐漸進展的工程水準。」 - Tenstorrent 行政總裁暨 AheadComputing 董事局成員 Jim Keller 關於 AheadComputingAheadComputing Inc. 是一家 IP 設計公司，專注於開發、授權和支援高效能微處理器核心及相關技術。 公司領導團隊在 CPU 架構及創新範疇具備數十年豐富經驗，致力透過尖端的 RISC-V 處理器來突破運算效能的界限。 AheadComputing 的解決方案為從雲端運算到人工智能和邊緣應用等各個行業提供支援，效率和可擴展性均無可比擬。 公司總部位於俄勒岡州波特蘭市，致力透過提供突破性的單核心性能並為行業樹立新標桿，以徹底改變運算格局。 如欲了解更多資訊，請瀏覽 www.aheadcomputing.com
The company will use the follow-on seed to advance the development of its high-performance CPU microarchitecture designed for the surging compute demands of AI workloads PORTLAND, Ore., Jan. 22, 2026 /PRNewswire/ -- AheadComputing, Inc., the company pioneering breakthrough microarchitecture to deliver industry-leading CPU performance, today announced it has raised $30M in a Seed2 round, bringing the company's total funding to $53M to date. The round was co-led by Eclipse, Toyota Ventures, and Cambium, with additional participation from Corner, Trousdale Ventures, EPIQ, MESH, and Stata. AI workloads are reshaping compute across hyperscale data centers, workstations, PCs, and high-end embedded systems. While GPU performance is taking center stage, CPU performance remains essential for AI workloads, yet is often overlooked as a critical component of overall system capability. Industry forecasts predict that 70% of all data center workloads will be AI workloads by 2030, and a high-performance CPU is essential to the efficient execution of these workloads. The AI workload mix is shifting towards inference and agentic AI workloads, making higher per-core CPU performance an industry priority. "Our team of system architects and engineers, with over 1000 years of combined CPU design experience, continues to push CPU performance forward and beyond the boundaries of traditional CPU innovation," said Debbie Marr, CEO and co-founder of AheadComputing. "This additional funding will allow us to continue to challenge traditional rules and sustain a fast pace of transformation and develop the fastest high-performance, general-purpose CPU because everybody deserves better compute." Since its founding in 2024, AheadComputing has made rapid progress through product development, technical collaborations with semiconductor ecosystem partners, and customer design exploration with hyperscalers and compute providers. Its approach combines the extensibility of RISC-V with a breakthrough microarchitecture, demonstrating that open architectures can deliver top-tier performance for modern AI and Data Center applications. By collaborating deeply with technical partners across the ecosystem, AheadComputing is helping bring RISC-V into mainstream data-center and AI infrastructure. "AheadComputing is shaping a massive addressable market at a time when the compute industry is undergoing a fundamental shift driven by surging AI workloads, escalating performance bottlenecks, and an urgent need for more scalable, high-performance CPU cores," said Greg Reichow, Partner at Eclipse and AheadComputing Board member. "The team's roadmap takes a novel approach by making CPUs more powerful than ever before. By leveraging RISC-V's extensibility and pairing it with a breakthrough microarchitecture, the team is unlocking levels of performance and efficiency that the industry has been chasing for years and ultimately, setting a new bar for what modern CPUs can deliver." This new capital will support enhancing R&D, software innovation, and test chip development. Additionally, AheadComputing continues to scale its team of nearly 120 people, which has collectively shipped 70+ products over the course of their careers. The team's first product is currently in development, which is made possible by key collaborations with ecosystem partners, including Alchip, Cadence, Skyechip, and Tenstorrent. For more information, visit aheadcomputing.com Corner:"AI needs better CPUs, not just bigger GPUs. AheadComputing brings a world-class CPU architecture pedigree and an execution cadence that's already translating into real milestones to break previous barriers for per-core performance and efficiency." - Marvin Tien, General Partner, Corner. MESH:"RISC-V's widespread adoption will ultimately be decided by a simple tipping point: sustained performance leadership at the highest end of compute. AheadComputing is one of the few teams we've seen with both the architectural ambition and the execution depth to hit that mark. We believe they're uniquely positioned to set a new bar for per-core CPU performance and accelerate RISC-V's expansion into mainstream data-center and AI infrastructure." - Edward Chyau, Managing Partner - MESH ALCHIP:"The compute industry is at an inflection point. Alchip is delighted to collaborate with AheadComputing as they architect breakthrough CPU performance precisely when the industry needs it most. As AI workloads shift toward inference and agentic computing, AheadComputing is positioned to redefine what's possible in high-performance computing." - Dave Hwang, SVP and Alchip NA GM Tenstorrent:"The path to transformative CPU performance isn't about chasing incremental gains—it's about fundamental rethinking. You have to redesign core microarchitecture and goals. Debbie and her team at AheadComputing are approaching this problem with the kind of first-principles thinking that actually moves the industry forward. This team has collectively shipped over 70 products and holds hundreds of compute patents, representing both technical insight and execution capability. This is the caliber of engineering that delivers generational leaps, not evolutionary steps." - Jim Keller, CEO of Tenstorrent and Board Member at AheadComputing About AheadComputingAheadComputing Inc. is an IP design house focused on developing, licensing, and supporting high-performance microprocessor cores and related technologies. With a leadership team boasting decades of experience in CPU architecture and innovation, the company is dedicated to pushing the boundaries of compute performance through cutting-edge RISC-V processors. AheadComputing's solutions empower industries ranging from cloud computing to AI and edge applications, providing unmatched efficiency and scalability. Headquartered in Portland, OR, the company is poised to revolutionize the computing landscape by delivering breakthrough per-core performance and setting new industry benchmarks. For more information, visit www.aheadcomputing.com
A12 藝術空間
RISC-V
請先登入後才能發佈新聞。
還不是會員嗎？立即 加入台灣產經新聞網會員 ，使用免費新聞發佈服務。 （服務項目） （投稿規範）
