Workflow
彤央系列边端算力产品
icon
Search documents
港股异动 | 天数智芯(09903)涨超20%刷新上市新高 通用GPU市场具备广阔发展前景
智通财经网· 2026-02-26 06:38
消息面上,近年来,AI的发展,尤其是大语言模型的兴起,推动算力需求大幅增长。根据弗若斯特沙 利文的资料,中国通用GPU市场快速扩张,2024年的出货量达到1.6百万片,2022年至2024年的复合年 增长率为72.8%。预计市场将维持强劲增长,于2025年至2029年,出货量预计以33.0%的复合年增长率 增长。随着中国通用GPU公司出货量的增长速度超越国际竞争对手,国内市场占有率持续攀升。 公开资料显示,天数智芯提供针对不同行业的通用GPU产品及AI算力解决方案。公司的产品组合主要 包括通用GPU芯片及加速卡,以及定制AI算力解决方案(包括通用GPU服务器及集群),天数智芯通用 GPU产品涵盖天垓及智铠系列,兼容国内外主流AI生态以及各类深度学习框架。今年1月,该公司公布 四代芯片架构路线图,预期于2027年超越英伟达Rubin架构;同时推出"彤央"系列边端算力产品。 智通财经APP获悉,天数智芯(09903)涨超20%,高见287港元刷新上市新高。截至发稿,涨19.52%,报 285港元,成交额3.7亿港元。 ...
天数智芯尾盘涨超13% 公司近期发布芯片四代架构路线图对标英伟达
Zhi Tong Cai Jing· 2026-02-10 07:37
Core Viewpoint - TianShu ZhiXin (09903) experienced a significant stock price increase of over 13%, currently trading at 193 HKD with a transaction volume of 1.81 billion HKD, indicating strong market interest in the company [1] Company Overview - TianShu ZhiXin provides general GPU products and AI computing solutions tailored for various industries. The product portfolio includes general GPU chips and accelerator cards, as well as customized AI computing solutions, which encompass general GPU servers and clusters [1] - The company's general GPU products include the TianYuan and ZhiKai series, which are compatible with major domestic and international AI ecosystems and various deep learning frameworks [1] Product Development - Recently, TianShu ZhiXin released a roadmap for its fourth-generation chip architecture, with expectations to surpass NVIDIA's Rubin architecture by 2027 [1] - The company also unveiled a new generation of edge computing products, the "TongYang" series, claiming superior performance in multiple real-world testing scenarios compared to NVIDIA's AGX Orin [1]
天数智芯逆市涨超4% 近日公布四代架构路线图与彤央边端产品
Zhi Tong Cai Jing· 2026-01-30 06:47
Core Viewpoint - Tianshu Zhixin (09903) has announced a roadmap for its fourth-generation chip architecture, aiming to surpass NVIDIA's Rubin architecture by 2027, which has positively impacted its stock price, increasing by 4.26% to HKD 178.5 with a trading volume of HKD 139 million [1] Group 1: Chip Architecture Roadmap - The company plans to exceed NVIDIA's Hopper architecture with its Tianshu Tian Shu architecture by 2025 [1] - The Tianshu Tian Xuan architecture is set to match NVIDIA's Blackwell architecture in 2026 [1] - The Tianshu Tian Ji architecture aims to surpass Blackwell in 2026 [1] - The Tianshu Tian Quan architecture is expected to exceed Rubin by 2027 [1] - After 2027, the company will shift focus to breakthrough computing chip architecture design [1] Group 2: Product Launch - Tianshu Zhixin has launched the "Tongyang" series of edge computing products [1] - The TY1000 has demonstrated performance exceeding NVIDIA's AGX Orin in tests related to computer vision, natural language processing, and the DeepSeek32B large model [1]
港股异动 | 天数智芯(09903)逆市涨超4% 近日公布四代架构路线图与彤央边端产品
智通财经网· 2026-01-30 06:46
Core Viewpoint - Tianshu Zhixin (09903) has announced a roadmap for its fourth-generation chip architecture, aiming to surpass NVIDIA's Rubin architecture by 2027, which has positively impacted its stock price, increasing by 4.26% to HKD 178.5 with a trading volume of HKD 139 million [1] Group 1: Chip Architecture Roadmap - The company plans to exceed NVIDIA's Hopper architecture with its Tianshu Tianshu architecture by 2025 [1] - The Tianshu Tianxuan architecture is set to match NVIDIA's Blackwell architecture in 2026 [1] - The Tianshu Tianji architecture is expected to surpass Blackwell in 2026 [1] - By 2027, the Tianshu Tianquan architecture aims to exceed NVIDIA's Rubin architecture [1] - After 2027, the company will shift focus to breakthrough computing chip architecture design [1] Group 2: Product Launch - Tianshu Zhixin has launched the "Tongyang" series of edge computing products [1] - The TY1000 has demonstrated performance exceeding NVIDIA's AGX Orin in tests related to computer vision, natural language processing, and DeepSeek 32B large models [1]
国产算力大反攻!天数智芯(09903)抛出四代架构“超车”路线图 彤央边端性能超越英伟达 300+标杆客户落地 万亿赛道格局生变
智通财经网· 2026-01-26 11:02
智通财经APP获悉,AI算力国产替代迎来标志性突破!1月26日,刚刚在港股上市不到一个月的天数智芯(09903)高调披露四代架构技术路线图,明确三年间 将逐步超越英伟达 Hopper、Blackwell、Rubin三大核心架构,同时发布的"彤央"系列边端产品实测性能超越行业标杆英伟达AGX Orin,更首次曝光覆盖互联 网、金融、医疗、交通等领域的300+标杆客户清单与超1000次部署成果,用商业化落地数据宣告国产通用GPU正式进入"性能反超、规模放量"的新阶段,千 亿级算力赛道国产替代进程全面提速。 作为新质生产力的核心引擎,通用GPU被视为AI产业的"皇冠明珠",长期由海外巨头垄断。天数智芯此次技术与商业的双重突破,不仅打破了高端算力领域 的"卡脖子"困境,更为科技产业投资提供了极具价值的核心标的,其背后的技术壁垒、商业化逻辑与行业影响值得深度拆解。 四代架构剑指英伟达:2027年完成全面超越,"高质量算力"重构行业标准 在芯片行业,架构路线图直接决定企业长期竞争力。天数智芯AI与加速计算技术负责人单天逸现场抛出的四代架构路线图,堪称国产算力的"超车宣言": 2025年已经推出天数天枢架构,性能超越英伟达 ...