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
MediaTek brings its design expertise in Arm-based SoC performance and power efficiency to groundbreaking device for AI researchers and developers LAS VEGAS, Jan. 7, 2025 /PRNewswire/ -- MediaTek today announced it has collaborated with NVIDIA on the design of the NVIDIA GB10 Grace Blackwell Superchip for NVIDIA Project DIGITS, a personal AI supercomputer. MediaTek is the world's No. 1 chip supplier for smartphones, smart TVs, Arm-based Chromebooks, Android tablets, and voice assistant devices (VAD). The company has invested heavily in bringing the best AI, connectivity and multi-media experiences to Arm-based system-on-a-chip (SoC) devices, across different platforms and users, with best-in-class power efficiency. MediaTek has brought all its technology expertise to this collaboration with NVIDIA to deliver a market-leading platform. "Our collaboration with NVIDIA on the GB10 Superchip aligns with MediaTek's vision of helping make great technology accessible to anyone," said MediaTek Vice Chairman and CEO Rick Tsai. "Along with NVIDIA, we are working to usher in a new era of innovation and make AI ubiquitous." "The age of AI is here. The combination of MediaTek's industry-leading CPU performance and power efficiency with NVIDIA's accelerated computing technologies will drive the next wave of innovation," said Jensen Huang, founder and CEO of NVIDIA. "Project DIGITS, with the new GB10 Superchip designed with MediaTek, makes our most powerful Grace Blackwell platform more accessible – placing it in the hands of developers, researchers and students to solve the most pressing issues of our time." Today's collaboration is the latest between the two companies, building on MediaTek's work with NVIDIA to bring drivers and passengers novel experiences inside the car with new MediaTek Dimensity Auto Cockpit chips. MediaTek's Dimensity Auto Cockpit chips integrate NVIDIA's next-gen GPU-accelerated AI computing and NVIDIA RTX graphics. Additionally, MediaTek has integrated NVIDIA TAO, an AI model training and optimization toolkit, with MediaTek's NeuroPilot SDK to deliver advanced edge AI capabilities to IoT applications. As part of MediaTek's vision to bring AI everywhere, MediaTek is delivering advanced AI capabilities across its portfolio, including its Dimensity portfolio for smartphones and tablets, Genio family for IoT devices, Pentonic series for smart TVs, Kompanio line for Arm-based Chromebooks, along with the Dimensity Auto platform for vehicles. To learn more about the NVIDIA GB10 Superchip and Project DIGITS personal AI supercomputer, please visit https://www.nvidia.com/en-us/. About MediaTek Inc. MediaTek Incorporated (TWSE: 2454) is a global fabless semiconductor company that enables nearly 2 billion connected devices a year. We are a market leader in developing innovative systems-on-chip (SoC) for mobile, home entertainment, connectivity and IoT products. Our dedication to innovation has positioned us as a driving market force in several key technology areas, including highly power-efficient mobile technologies, automotive solutions and a broad range of advanced multimedia products such as smartphones, tablets, digital televisions, 5G, Voice Assistant Devices (VAD) and wearables. MediaTek empowers and inspires people to expand their horizons and achieve their goals through smart technology, more easily and efficiently than ever before. We work with the brands you love to make great technology accessible to everyone, and it drives everything we do. Visit www.mediatek.com for more information. Media Enquiries: Kevin Keating, pr@mediatek.com
Back to media releasesNext media release LONDON, Jan. 7, 2025 /PRNewswire/ -- Norgine today announced that it completed its marketing authorisation application filing to European Medicines Agency (EMA) for eflornithine in high-risk neuroblastoma (HRNB). This follows the submissions in April 2024, via Project Orbis, in Australia, Switzerland and the United Kingdom. This milestone further supports Norgine's efforts to give patients access to eflornithine and bring a further treatment option in the field of paediatric oncology. Norgine and USWM, LLC (dba US WorldMeds), a Kentucky-based specialty pharmaceutical company, have an exclusive licensing agreement by which Norgine will register and commercialise eflornithine, also referred to as DFMO, in Europe, Australia and New Zealand. On 13 December 2023, the US Food and Drug Administration (FDA) approved eflornithine as the first oral maintenance therapy for HRNB, indicated to reduce the risk of relapse in adult and paediatric patients who have received certain prior therapies.[1] The approval decision was based on findings from a trial comparing outcomes from patients treated with eflornithine in Study 3b (NCT02395666)[2],[4] to control patients derived from Study ANBL0032 (NCT00026312; clinical-trial-derived external control arm)[3],[4]. The study with eflornithine treated patients showed improved event-free survival and overall survival when compared to outcomes for patients with HRNB treated with the standard of care (SoC).[1] Dr David Gillen, Chief Medical Officer at Norgine, added, "This submission via the EU Centralised Procedure represents another important step in the regulatory process for eflornithine and further emphasises Norgine's passion and commitment in attempting to secure additional treatment options for patients living with HRNB, a condition with a high level of unmet medical need." Janneke van der Kamp, CEO of Norgine added "Submitting this marketing authorisation to the EMA marks a pivotal step for patients facing this challenging cancer. We are committed to advancing innovative therapies that address the unmet needs of young patients and their families, and this milestone brings us closer to offering hope where it's most needed". www.norgine.com Follow @norgine Notes to Editors: HRNB background Children diagnosed with HRNB undergo an intense SoC regimen that still leaves them vulnerable to relapse and death, a risk that is highest for the first two years after completing treatment.[5] Approximately 30% of patients who attain remission following upfront therapy will relapse, and once relapsed, mortality significantly increases with a post-relapse 4-year overall survival of under 10%.[5], [6] Therefore, avoiding relapse is key to long-term survival, yet outside of the United States there are no approved therapies for sustaining remission following SoC treatment. The data demonstrate that using eflornithine after completion of upfront SoC treatment, as post-maintenance therapy extends remission and reduces risk of relapse in patients with HRNB. About Norgine Norgine is a uniquely positioned, specialty pharmaceutical and consumer healthcare company, with over €500 million of annual revenues and a 120-year track record of bringing life-changing products to patients and consumers across our core markets of Western Europe, Australia and New Zealand. Our integrated approach – strong commercial capabilities, deep medical, regulatory and clinical expertise, in-house manufacturing, robust supply networks, and best in class enabling functions – ensures that we can deliver high-quality, transformative medicines quickly and effectively to over 25 million patients annually. Today's Norgine is a nimble, innovative, and high-performing company that has been transformed by a relentless focus on operational excellence. This focus will enable us to secure the legacy of more than a century of innovation and doing the right thing by our patients, as we push the boundaries and take strides into new therapeutic areas. NORGINE and the sail logo are trademarks of the Norgine group of companies. References FDA approves eflornithine for adult and pediatric patients with high-risk neuroblastoma. FDA. News release. 13 December 2023. Available from: FDA approves eflornithine for adult and pediatric patients with high-risk neuroblastoma | FDA Clinical Trial NCT02395666; Preventative trial of difluoromethylornithine (DFMO) in high risk patients with neuroblastoma that is in remission. Available from: Study Details | Preventative Trial of Difluoromethylornithine (DFMO) in High Risk Patients With Neuroblastoma That is in Remission | ClinicalTrials.gov. Clinical Trial NCT00026312; Isotretinoin with or without dinutuximab,[1] aldesleukin, and sargramostim following stem cell transplant in treating patients with neuroblastoma. Available from: Study Details | Isotretinoin With or Without Dinutuximab, Aldesleukin, and Sargramostim Following Stem Cell Transplant in Treating Patients With Neuroblastoma | ClinicalTrials.gov Oesterheld J, Ferguson W, Kraveka JM, Bergendahl G, Clinch T, Lorenzi E et al. Eflornithine as Postimmunotherapy Maintenance in High-Risk Neuroblastoma: Externally Controlled, Propensity Score-Matched Survival Outcome Comparisons. 2024; 42 (1): 90-102. Basta NO, Halliday GC, Makin G, Birch J, Feltbower R, Bown N, et al. Factors associated with recurrence and survival length following relapse in patients with neuroblastoma. Br J Cancer. 2016;115:1048-57. London WB, Bagatell R, Weigel BJ, Fox E, Guo D, Van Ryn C, et al. Historical time to disease progression and progression-free survival in patients with recurrent/refractory neuroblastoma treated in the modern era on Children's Oncology Group early-phase trials. Cancer. 2017;123:4914-23.[2] Job code: UK-ONC-NP-2400019
LAS VEGAS, Jan. 7, 2025 /PRNewswire/ -- Digital Enhancement (Hangzhou) Co., Ltd (hereafter referred to as "Digital Enhancement") is set to unveil the world's first commercial-grade Radio Processing Unit (RPU) designed for Wi-Fi wireless access at the CES International Consumer Electronics Show in Las Vegas, USA. The world's first Radio Processing Unit (RPU) created by Digital Enhancement. This groundbreaking RPU and solution leverage Digital Enhancement's innovative "Digital RF" technology, delivering a 10x performance boost in Wi-Fi high-speed coverage. The innovation promises to redefine the wireless connectivity experience for consumer electronics, paving the way for a new era of seamless and high-performance wireless connections. The RPU employs state-of-the-art closed-loop training and real-time calibration architecture. Equipped with a high-performance hybrid analog-to-digital-to-analog predistortion algorithm, it significantly improves RF system performance through cutting-edge digital compensation technology. The RPU introduces an innovative "plug-in" enhancement model, decoupling RF performance from the baseband system-on-chip (SoC) for the first time. This independent design allows consumer electronics manufacturers to flexibly create new integrations based on product requirements, enabling a seamless plug-and-play experience. Built-in RPU acts as a "turbocharged engine" for RF systems, providing stronger signals and elevated user experiences. With RPU integration, Wi-Fi routers deliver broader high-speed coverage, while bridge devices achieve higher transmission speeds and longer ranges. Additionally, RPU enhances power amplifier (PA) output without increasing harmful emissions and wasting power as heat. This reduces reliance on costly and heavy directional antennas by lowering antenna gain requirements. For industrial Wi-Fi applications, the RPU ensures robust anti-aging performance, maintaining stable power output without speed degradation. Dr. Ziming Wang, Founder and CEO of Digital Enhancement, stated: "Wireless RF performance determines signal coverage and speed, directly impacting the user's connectivity experience. Digital Enhancement is the world's first innovator to miniaturize and simplify complex digital compensation algorithms used in high-power 5G macro base stations, bringing green digital RF technology to consumer electronics. Our unique plug-in solution offers industry a new avenue for product differentiation. Whether a product aims for a tenfold performance improvement, focuses on RF system efficiency and thermal management, or strives for out-of-band suppression to enable multi-device coexistence, this approach provides unparalleled flexibility. The RPU-equipped modular solutions we've introduced for Wi-Fi 6/7 wireless access include mass-production support for 500mW and 1W in the 5GHz-6GHz band at MCS11 rates, as well as lab data achieving 3W output when paired with nonlinear FEMs. Throughout our journey, we've been driven by a deep understanding of end-user application scenarios and a commitment to innovating technologies that meet their most fundamental connectivity needs." As AI+ continues to advance, wireless RF performance has become the critical gateway through which cloud computing power and services are delivered to users via consumer electronics. Traditional methods of "stacking resources" to improve performance often introduce side effects such as increased complexity, management challenges, handoff issues, and interference. It's akin to connecting multiple carts together and expecting the efficiency of a train. Digital Enhancement has introduced a game-changing innovation with its RPU, leveraging digital RF technology to simplify complexity. This disruptive, original solution marks a leap forward in enhancing consumer electronics performance, aligning with the industry's pursuit of green energy efficiency and sustainable development. Moving forward, Digital Enhancement plans to expand its global collaborations with Wi-Fi router manufacturers, industrial Wi-Fi module developers, and 5G CPE device providers, continuing to drive green digital RF solutions that empower high-performance wireless connectivity in consumer electronics. About Digital Enhancement Digital Enhancement, a pioneer in wireless communication, is committed to revolutionizing RF performance with next-generation digital technologies. The groundbreaking Radio Processing Unit (RPU) leverages advanced closed-loop training, real-time calibration, and a Hybrid Digital-Analog Predistortion (HDP) algorithm. This innovation significantly improves Power Amplifier (PA) linearity, transmission power, and system efficiency, setting a new standard in radio performance. The RPU's transformative design is poised to redefine applications across diverse wireless communication systems, including Wi-Fi, 5G, drones, satellite internet, and trunking communication. The Digital Enhancement team comprises scientists and engineers with expertise in mathematics, integrated circuits, software, and RF technologies. For more information, visit www.digienh.com.
AMD Ryzen™ AI Max、AMD Ryzen™ AI 300系列和AMD Ryzen™ 200系列處理器為新一代AI PC帶來令人驚豔的效能 AMD Ryzen™ AI Max PRO、AMD Ryzen™ AI 300 PRO及AMD Ryzen™ 200 PRO系列處理器為商用PC帶來頂尖效能 台北—2025年1月7日—AMD（NASDAQ: AMD）今日在CES 2025開展前夕發表全新處理器，進一步鞏固其在AI PC市場的領導地位，並為行動使用者提供最具創新性的PC處理器。AMD發表全新 Ryzen™ AI Max系列處理器，超越頂級輕薄筆電對高效能運算的需求；全新基於“Zen 5”架構的 Ryzen™ AI 300系列處理器，新增更多型號完善產品線；而延續AMD “Zen 4”架構的輝煌成就，AMD亦推出適用於日常生產力的Ryzen™ 200系列處理器。 此外，AMD擴展其商用AI PC產品線，將AMD PRO技術整合至Ryzen AI Max、Ryzen AI 300及Ryzen AI 200系列處理器中。Ryzen PRO系列處理器具備企業級安全性和管理工具，旨在協助保護現代企業並簡化IT營運流程。 AMD資深副總裁暨運算與繪圖事業群總經理Jack Huynh表示，隨著消費者和專業人士越來越重視AI PC的生產力優勢，AMD正進一步提升其在市場上的效能領導地位。藉由新一代支援AI的處理器，我們正將AI普及到所有裝置，並將工作站的強大效能帶到輕薄型筆電。 AMD Ryzen AI Max與Ryzen AI Max PRO系列處理器 全新Ryzen AI Max系列處理器徹底革新了新一代AI PC的可能性，為遊戲玩家、創作者和日常使用者提供令人驚豔的效能和運算能力。Ryzen AI Max處理器具備工作站級別的效能，搭載高達16個“Zen 5” CPU核心、高達40個AMD RDNA™ 3.5繪圖運算單元，以及具備高達50 TOPS AI處理能力註¹的AMD XDNA™ 2神經處理單元（NPU），整合在超便攜的尺寸中，實現最佳行動力。 搭載高達128GB的統一記憶體，其中高達96GB可用於繪圖處理，搭載Ryzen AI Max的系統可實現無縫可靠的多工處理，並具備支援極大型AI模型的能力。憑藉新增具備高達50 TOPS效能的NPU，Ryzen AI Max系列處理器是新一代AI PC的極致動力來源，可加速要求嚴苛的AI工作站和創作者軟體。 全新Ryzen AI Max PRO系列處理器旨在重新定義輕薄型工作站，讓使用者能夠處理大型工程和建築模型，並應付複雜的AI加速工作負載。配備AMD PRO技術，搭載Ryzen AI Max PRO系列處理器的工作站為商務級行動工作站樹立了全新標準。 搭載Ryzen AI Max和Ryzen AI Max PRO系列處理器的系統預計將於2025年第1季開始上市。 型號 核心數／執行緒 提升註2／基礎頻率 總快取 顯示核心型號 cTDP NPUTOPS 顯示 核心數 AMD Ryzen™ AI Max+ 395 16C/32T 高達5.1 /3.0 GHz 80MB AMD Radeon™ 8060S 45-120瓦 50 40 AMD Ryzen™ AI Max 390 12C/24T 高達5.0 / 3.2 GHz 76MB AMD Radeon™ 8050S 45-120瓦 50 32 AMD Ryzen™ AI Max 385 8C/16T 高達5.0 / 3.6 GHz 40MB AMD Radeon™ 8050S 45-120瓦 50 32 AMD Ryzen™ AI Max+ PRO 395 16C/32T 高達5.1 / 3.0 GHz 80MB AMD Radeon™ 8060S 45-120瓦 50 40 AMD Ryzen™ AI Max PRO 390 12C/24T 高達5.0 / 3.2 GHz 76MB AMD Radeon™ 8050S 45-120瓦 50 32 AMD Ryzen™ AI Max PRO 385 8C/16T 高達5.0 / 3.6 GHz 40MB AMD Radeon™ 8050S 45-120瓦 50 32 AMD Ryzen™ AI Max PRO 380 6C/12T 高達4.9 / 3.6 GHz 22MB AMD Radeon™ 8040S 45-120瓦 50 16 AMD Ryzen AI 300與Ryzen AI 300 PRO系列處理器 AMD推出全新Ryzen AI 300系列處理器，加入Ryzen AI 300系列家族，為筆記型電腦帶來頂級AI體驗。除了先前發表的Ryzen 9型號外，全新Ryzen AI 7和Ryzen AI 5處理器型號也將提供可靠的效能和AI功能。 全新Ryzen AI 300系列處理器搭載高達8個“Zen 5” CPU核心和最新的RDNA 3.5顯示架構。憑藉搭載AMD XDNA 2技術、具備業界領先效能的NPU註³，Ryzen AI 300系列處理器提供比第一代NPU高達5倍的效能，帶來更強大的AI運算能力註⁴。 為了滿足日常商務生產力需求，全新Ryzen AI 7 PRO 350和Ryzen AI 5 PRO 340處理器旨在支援新一代Microsoft Copilot+體驗。憑藉領先的峰值50+ NPU TOPS AI效能，搭載Ryzen AI 300 PRO 系列處理器的商用系統為企業提供支援AI人力轉型的運算能力。藉由AMD PRO技術，Ryzen AI 300 PRO系列處理器為行動商務專業人士提供卓越的安全性和管理功能。 搭載全新Ryzen AI 300處理器的系統預計將於2025年第1季開始上市。 型號 核心數／ 執行緒 提升註5／ 基礎頻率 總快取 顯示核心型號 cTDP NPUTOPS AMD Ryzen™ AI 7 350 8C/16T 高達5.0 / 2.0 GHz 24 MB AMD Radeon™ 860M 15-54瓦 50 AMD Ryzen™ AI 5 340 6C/12T 高達4.8 / 2.0 GHz 22 MB AMD Radeon™ 840M 15-54瓦 50 AMD Ryzen™ AI 7 PRO 350 8C/16T 高達5.0 / 2.0 GHz 24 MB AMD Radeon™ 860M 15-54瓦 50 AMD Ryzen™ AI 5 PRO 340 6C/12T 高達4.8 / 2.0 GHz 22 MB AMD Radeon™ 840M 15-54瓦 50 AMD Ryzen 200與Ryzen 200 PRO系列處理器 藉由AMD Ryzen 200系列處理器，AMD將“Zen 4”的效能和功能帶到FP8平台基礎架構中，將AI功能進一步向下延伸。Ryzen 200 PRO系列行動處理器旨在為日常專業人士提供高效且卓越的效能。Ryzen 200系列處理器搭載高達8個CPU核心和16執行緒、AMD RDNA 3顯示晶片以及高達16 NPU TOPS的效能，為必要的應用程式提供卓越的AI處理能力，並具備持續的效能和電池續航力，可供不間斷使用。 搭載Ryzen 200和Ryzen 200 PRO系列處理器的系統預計將於2025年第2季開始上市。 型號 核心數／ 執行緒 提升註6／ 基礎頻率 總快取 顯示核心型號 cTDP NPUTOPS AMD Ryzen™ 9 270 8C/16T 高達5.2 / 4.0 GHz 24MB AMD Radeon™ 780M 35-54瓦 16 AMD Ryzen™ 7 260 8C/16T 高達5.1 / 3.8 GHz 24MB AMD Radeon™ 780M 35-54瓦 16 AMD Ryzen™ 7 250 8C/16T 高達5.1 / 3.3 GHz 24MB AMD Radeon™ 780M 15-30瓦 16 AMD Ryzen™ 5 240 6C/12T 高達5.0 / 4.3 GHz 22MB AMD Radeon™ 760M 35-54瓦 16 AMD Ryzen™ 5 230 6C/12T 高達4.9 / 3.5 GHz 22MB AMD Radeon™ 760M 15-30瓦 16 AMD Ryzen™ 5 220 6C/12T 高達4.9 / 3.2 GHz 22MB AMD Radeon™ 740M 15-30瓦 N/A AMD Ryzen™ 3 210 4C/8T 高達4.7 / 3.0 GHz 12MB AMD Radeon™ 740M 15-30瓦 N/A AMD Ryzen™ 7 PRO 250 8C/16T 高達5.1 / 3.3 GHz 24 MB AMD Radeon™ 780M 15-30瓦 16 AMD Ryzen™ 5 PRO 230 6C/12T 高達4.9 / 3.5 GHz 22 MB AMD Radeon™ 760M 15-30瓦 16 AMD Ryzen™ 5 PRO 220 6C/12T 高達4.9 / 3.2 GHz 22 MB AMD Radeon™ 740M 15-30瓦 N/A AMD Ryzen™ 3 PRO 210 4C/8T 高達4.7 / 3 GHz 12 MB AMD Radeon™ 740M 15-30瓦 N/A AMD PRO技術 AMD PRO技術為使用者提供企業級管理能力和多層安全功能，協助IT決策者大規模管理企業電腦設備。隨著近期新增的雲端復原、供應鏈安全以及額外的偵測和復原流程，AMD PRO技術超越了市場需求，並為使用者提供持續的保護，以抵禦複雜的攻擊。 OEM合作夥伴及客戶持續推出搭載Ryzen核心的全新系統，引領AI PC的採用 OEM合作夥伴持續推出搭載AMD Ryzen處理器、支援AI的全新PC和工作站。憑藉其令人驚豔的效能、運算能力和相容性，這些新系統超越了對新一代Copilot+ PC的期望。在今年的CES展會上，AMD深化與各大OEM合作夥伴的合作關係，並宣布與戴爾科技集團進行新的策略性擴展，將在今年稍後推出搭載AMD Ryzen AI PRO處理器的全新Dell Pro系統。 微軟Windows+裝置副總裁Pavan Davuluri表示，很高興看到AMD和微軟長期以來的合作夥伴關係邁入下一個科技浪潮，將AI創新帶給我們的OEM合作夥伴。我們很高興擴大搭載AMD全新Ryzen AI產品的Copilot+ PC陣容，造福專業人士、內容創作者和主流消費者。 華碩共同執行長胡書賓表示，華碩始終站在科技的最前線，致力為我們的客戶帶來最高水準的效能。今天，我們宣布推出搭載Ryzen的全新系統，帶來頂尖的處理效能，讓客戶站在AI創新的最前沿。 HP資深副總裁暨先進運算與解決方案事業部總裁Jim Nottingham表示，HP與AMD合作找出客戶工作流程中的痛點，並以全新HP ZBook Ultra G1a和HP Z2 Mini G1a解決這些問題。搭載AMD Ryzen AI Max PRO系列處理器的工作站將率先在工作站上提供此架構。藉由重新定義高效能行動或迷你桌上型工作站的可能性，我們共同為客戶帶來同時處理複雜專業ISV和資料科學工作流程的能力，並無縫整合高效能運算與AI PC的功能。 聯想智慧型裝置事業群總裁Luca Rossi表示，聯想相信有意義的創新源於強大的合作夥伴關係。我們與AMD的合作證明了這一點，我們共同努力以先進的AI解決方案塑造運算的未來。藉由運用AMD最新一代的頂尖平台，我們正在為令人興奮的全新產品奠定基礎，這些產品旨在強化個人化、提升生產力並提供強大的安全性。敬請期待我們持續為創意專業人士、企業和遊戲玩家等使用者提供突破性的解決方案，突破效能、協作和創新的界限。 微星科技執行副總經理暨筆電事業部總經理郭緒光表示，在微星，我們以打造能協助遊戲玩家、創作者和專業人士提升運算體驗的產品為榮。全新Stealth A16 AI+和A18 AI+筆電搭載全新Ryzen AI 300系列處理器，為我們的客戶帶來全新水準的效能。 全球各地的客戶都站在採用AI PC的最前線，讓他們的員工能夠在其業務的各個階段無縫地加速創新。 Altair技術長Sam Mahalingam表示，Altair® Inspire™加速了模擬驅動的設計，讓所有使用者都能使用流體模擬。在GPU上執行流體模擬程式碼可提升效能和可擴充性，讓使用者能夠更快、更有效率地創新。藉由運用ROCm/HIP堆疊的功能，Altair團隊能夠快速將GPU支援擴展到AMD Radeon產品，包括Ryzen AI Max PRO處理器。 KeyShot首席科學家Henrik Wann Jensen表示，KeyShot很高興將KeyShot Studio高速GPU渲染的支援擴展到AMD Radeon。ROCm/HIP工具提供令人讚嘆的無縫啟用功能，我們尤其對Ryzen AI Max PRO上可用的大量幀緩衝區感到興奮，顯著提升了我們的渲染能力。 相關資源 · 更多詳情請參閱AMD CES 2025專頁 · 更多關於：Ryzen行動處理器 · 更多關於：Ryzen行動工作站處理器 · 更多關於：Ryzen PRO行動處理器 · 更多關於：AMD PRO技術 · 更多關於：Ryzen AI · 更多關於：Ryzen AI軟體 · Facebook：AMD粉絲專頁 · X：於@AMD追蹤AMD新訊 免責聲明 本新聞稿包含有關Advanced Micro Devices, Inc（AMD）的前瞻性陳述，包括AMD產品的特色、功能、效能、上市時間、時程以及預期收益，包括Ryzen™ AI Max、Ryzen AI 300系列、Ryzen 200系列處理器、Ryzen AI Max PRO、Ryzen AI 300 PRO、Ryzen 200 PRO系列處理器，以及AMD OEM合作的預期效益，這些陳述皆基於1995年《私人證券訴訟改革法案》（U.S. Private Securities Litigation Reform Act）的「安全港」（Safe Harbor）條款所訂定出。這些前瞻性聲明含有像「將會」、「可能」、「預期」、「相信」、「計劃」、「打算」、「估計」，或這些字詞和短語的其它類似詞彙。投資者應注意本資料中的前瞻性陳述僅根據本文公布當時的見解、假設以及預期，僅反映本文發布時的情況，且涉及到許多風險與不確定因素，可能會導致實際結果與預期存在重大差異。這類陳述受到特定已知與未知風險與不確定因素所影響，其中許多因素難以預測且大多非AMD所能掌控，並可能響應實際結果與其他未來事件和文中陳述有所出入，或是和前瞻性陳述資訊與陳述的暗示或預期狀況有所不同。可能導致實際結果和當前預期有所出入的實質因素包括但不限於：包括Intel公司佔據微處理器市場，及其侵略性經營手段；Nvidia公司佔據繪圖處理器市場，及其侵略性經營手段；AMD產品銷售的競爭市場；半導體產業的周期性；AMD產品銷售行業的市場狀況；AMD能及時推出具有預期功能和效能水準產品的能力；失去重要客戶；經濟與市場局勢不確定性；季度和季節性銷售模式；AMD充分保護其技術或其他知識產權的能力；不利的貨幣匯率波動；第三方廠商能及時製造足夠數量AMD的產品、或使用競爭對手的技術；基本設備、材料、載板或製造過程的可用性；達到AMD產品預期製造良率的能力；AMD的半客製化SoC產品產生營收的能力；潛在的安全漏洞；潛在的安全事件，包括IT中斷、數據丟失、數據洩露和網路攻擊；有關AMD產品訂購和發貨的不確定性；AMD依賴第三方廠商知識產權來及時設計和推出新產品；AMD依賴第三方廠商來設計、製造和供應主機板、軟體、記憶體和其他電腦平台零組件；AMD依賴Microsoft和其他軟體供應商的支持來設計和開發可在AMD產品上運行的軟體；AMD依賴第三方分銷商和外接合作夥伴；修改或中斷AMD內部業務流程和資訊系統的影響；AMD產品與部分或全部行業標準軟體和硬體的兼容性；缺陷產品所產生的有關費用；AMD供應鏈的效率；AMD依靠第三方供應鏈物流功能的能力；AMD有效控制其產品在灰色市場上銷售的能力；氣候變遷對AMD業務的長期影響；政府行動和法規的影響，例如出口法規，關稅和貿易保護措施；AMD實現遞延所得稅資產的能力；潛在的稅收負債；當前和將來的索賠和訴訟；環境法律，與衝突礦物有關的規定以及其他法律或法規的影響；政府、投資者、客戶和其他利益關係人對企業責任事務不斷變化的期望；與負責任地使用AI相關的問題；；管理AMD票據的協議、賽靈思票據的保證和循環信貸協議；併購、合資與／或投資可能對業務產生的影響，以及整合收購事業的能力；AMD完成ZT Systems收購的能力；合併公司資產之任何損耗可能產生的影響；政治，法律，經濟風險和自然災害；技術許可購買的未來減損；AMD吸引和留住人才的能力；AMD的股價波動。呼籲投資者詳閱公司呈交美國證管會各項財報中提及的風險與不確定因素，其中包括但不限於AMD最近的Form 10-K和10-Q報告。 註1：AMD Ryzen處理器的每秒兆次運算（TOPS）是在最佳情況下可執行的最大每秒運算次數，可能不具典型性。TOPS可能會因多種因素而異，包括特定系統配置、AI 模型和軟體版本。GD-243。註2：提升時脈頻率是在CPU執行突發性工作負載時可達到的最高頻率。加速時脈的可達成性、頻率和持續性會因多種因素而異，包括但不限於：散熱條件以及應用程式和工作負載的變化。GD-150。註3：根據截至2024年10月的AMD產品規格和競爭產品公告。AMD Ryzen™ AI PRO 300系列處理器的NPU提供高達55的峰值TOPS。這是目前企業中任何系統所能提供的最高TOPS。AI PC定義為配備包含神經處理單元（NPU）之處理器的筆記型電腦。STXP-06。註4：截至2024年9月，AMD效能實驗室在配備AMD Ryzen™ AI 7 PRO 360處理器（22W）、Radeon™ 880M顯示核心、32GB RAM、1TB SSD、VBS=ON、Windows 11 Pro的Lenovo ThinkPad T14s Gen 6上進行測試，與配備Intel Core Ultra 7 165U處理器（15W，已啟用vPro）、Intel整合式顯示核心、VBS=ON、32GB RAM、512GB NVMe SSD、Microsoft Windows 11 Professional的Dell Latitude 7450在應用程式中（最佳效能模式）進行比較：Cinebench R24 nT。筆記型電腦製造商的配置可能有所不同，導致結果不同。STXP-13。註5：提升時脈頻率是在CPU執行突發性工作負載時可達到的最高頻率。加速時脈的可達成性、頻率和持續性會因多種因素而異，包括但不限於：散熱條件以及應用程式和工作負載的變化。GD-150。註6：提升時脈頻率是在CPU執行突發性工作負載時可達到的最高頻率。加速時脈的可達成性、頻率和持續性會因多種因素而異，包括但不限於：散熱條件以及應用程式和工作負載的變化。GD-150。
LAS VEGAS and SEOUL, South Korea, Jan. 6, 2025 /PRNewswire/ -- STRADVISION, a global leader in AI-based vision perception technology, will showcase its latest innovation at CES® 2025 in Las Vegas. The company is set to showcase its latest breakthrough at CES® 2025 in Las Vegas. The company will reveal the production-ready version of its SVNet 3D Perception Network, originally introduced as a prototype at CES 2024. STRADVISION's demonstration will be hosted at the Westgate Hotel Hospitality Suite #2951, exclusively for industry professionals from January 7th to 10th, 2025. Experience the full interactive Multichannel News Release here: https://www.multivu.com/stradvision/9311851-en-stradvision-brings-production-ready-ai-vision-ces-2025 Revolutionizing Autonomous Driving Technology The SVNet 3D Perception Network marks a transformative leap in vision perception for advanced driver assistance systems (ADAS) and autonomous driving (AD). This cutting-edge deep learning solution converts 2D camera data into highly precise 3D environmental maps, enabling vehicles to "see" their surroundings with unparalleled accuracy. Since its initial debut, the technology has achieved remarkable advancements: Enhanced Maturity and Vision: The inclusion of SurroundVision supports high-level autonomous driving (Level 2+ and beyond), operating across a broader range of Operational Design Domains (ODD). This includes diverse weather conditions, challenging climates, and complex environments, paving the way for greater environmental adaptability. New Parking Capabilities: A major milestone, the SVNet 3D Perception Network now introduces autonomous parking capabilities, signaling a significant step toward full vehicle autonomy. Mass Production Readiness: Production-ready software development will conclude in 2025, with the Start of Production (SoP) targeted for 2026. Global Expansion: STRADVISION is extending manufacturing into new regions, reinforcing its commitment to addressing global demand and expanding its market reach. These advancements position the SVNet 3D Perception Network as a foundational technology for next-generation ADAS/AD-equipped vehicles, offering unmatched scalability and functionality. Pioneering Milestones and Global Impact STRADVISION is on track to complete production-ready software by the end of 2025, marking the culmination of its mass production development journey. The Start of Production (SoP) is planned for 2026, accompanied by strategic expansion into new manufacturing regions to support its ambitious global market strategy. Exclusive Live Demonstration at CES 2025 Visitors at CES 2025 will have the opportunity to witness the capabilities of the SVNet 3D Perception Network through a live demonstration based on the various SoC platforms. This showcase will highlight the network's MultiVision capabilities, including its new parking functionality, demonstrating its readiness for real-world deployment. "Transforming the SVNet 3D Perception Network from a prototype to production-ready software within a year underscores STRADVISION's unwavering commitment to innovation and excellence," said Junhwan Kim, CEO of STRADVISION. "CES 2025 provides an exciting platform to demonstrate how this groundbreaking technology is redefining adaptability and functionality in the global automotive industry." For more information on STRADVISION and its industry-leading technologies, please visit STRADVISION. All About STRADVISION SVNet 3D Perception Network - 6 Channel Multivision STRADVISION Data Workflow & Management FrontVision Object Detection - Far range Line Parking Space Detection - Oblique parking slot SurroundVision - Visualization
First-ever collaboration introduces a robust perception stack for automated driving STRADVISION's 3D Perception SVNet enables deep learning-based embedded perception algorithms using AMD Versal™ AI Edge Series Adaptive SoC STRADVISION to host AMD Versal SoC-powered demos during CES® 2025 in Las Vegas LAS VEGAS, Jan. 6, 2025 /PRNewswire/ -- STRADVISION, a trailblazer in AI-based vision perception technology, proudly announces a collaboration with AMD for the first time to combine STRADVISION's cutting-edge 3D Perception SVNet with advanced processing technology from AMD to deliver high-performance perception solutions for automated driving systems. At CES® 2025, STRADVISION will unveil a joint technology demonstration with AMD that features STRADVISION's 3D Perception SVNet, powered by the AMD Versal™ AI Edge Series adaptive SoC, utilizing an 8MP front-facing camera. This showcase underscores STRADVISION's commitment to enhancing ADAS (Advanced Driver Assistance Systems) and autonomous driving technologies with cutting-edge adaptive computing hardware from AMD. AMD Versal™ AI Edge Series delivers high performance, low latency AI inference for intelligence in automated driving and other demanded AI-driven embedded systems. Designed for sensor fusion and AI algorithm development, the Versal AI Edge series delivers scalable solutions that address diverse performance and power requirements, from edge to endpoint applications. This collaboration combines AMD adaptive computing hardware with STRADVISION's industry-leading perception software, offering a comprehensive perception stack tailored for real-world driving conditions and delivering reliable, scalable solutions to automotive manufacturers worldwide. "Our work with AMD represents a pivotal moment for STRADVISION," said Philip Vidal, CBO of STRADVISION. "Combining cutting-edge real-time processing technology from AMD with our advanced 3D perception network, 'SVNet' enables us to redefine industry standards for performance, reliability, and scalability in automated driving systems." "STRADVISION is helping accelerate autonomous vehicles by increasing the access to ADAS technologies by reducing its cost without compromising its capability," said Wayne Lyons, Senior Director of Marketing, Automotive Segment, AMD. "Together, we're addressing the growing demand for scalable, high-performance solutions that enhance the safety and functionality of automated driving systems." By joining forces, STRADVISION and AMD are poised to address the needs of the evolving mobility landscape, providing a robust, scalable perception stack optimized for ADAS and autonomous driving systems. This relationship reflects both companies' dedication to shaping the future of automated driving. For more information on STRADVISION and its industry-leading technologies, please visit STRADVISION. CES 2025 Demo Details Attendees of CES 2025 can experience the 3D Perception SVNet demonstration at both STRADVISION's booth and AMD automotive demo space. This showcase highlights the seamless integration of STRADVISION's AI-powered vision technology with AMD processors, providing a glimpse into the future of automated driving. Dates: January 7–10, 2025 Locations: STRADVISION booth at Westgate Hotel Hospitality Suite #2951, Las Vegas, and AMD auto demos at the LVCC, West Hall, Room W223 About STRADVISION Founded in 2014, STRADVISION is an automotive industry pioneer in artificial intelligence-based vision perception technology for ADAS. The company is accelerating the advent of fully autonomous vehicles by making ADAS features available at a fraction of the market cost compared with competitors. STRADVISION's SVNet is being deployed on various vehicle models in partnership with OEMs; can power ADAS and autonomous vehicles worldwide; and is serviced by over 300 employees in Seoul, San Jose, Detroit, Tokyo, Shanghai, and Dusseldorf. STRADVISION has been honored with Frost & Sullivan's 2022 Global Technology Innovation Leadership Award, the Gold Award at the 2022 and 2021 AutoSens Awards for Best-in-Class Software for Perception Systems, and the 2020 Autonomous Vehicle Technology ACES Award in Autonomy (software category). In addition, STRADVISION and its software have achieved TISAX's AL3 standard for information security management, as well as being certified to the ISO 9001:2015 for Quality Management Systems and ISO 26262 for Automotive Functional Safety. AMD, the AMD Arrow logo, Versal, and combinations thereof are trademarks of Advanced Micro Devices, Inc.
A12 藝術空間
SoC
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）
