破冰！寒武纪在HBM上的“弯道超车”

AI芯界

2025/11/06

经过一年使用，寒武纪590 ASIC架构与H20 GPU不相上下的性能的数据，，寒武纪在软件领域持续发力，剑指超越CUDA生态，在硬件层面ASIC针对大量卷积运算与池化运算，从硬件底层出发集成专门用于卷积运算的硬件加速单元。相较于GPU依赖通用并行计算架构并通过软件优化完成运算，ASIC能更直接、高效地执行卷积操作，在计算速度和能耗效率上已能与英伟达的GPU持平。国内互联网大厂的大模型训练对内存...

网页链接

免责声明：投资有风险，本文并非投资建议，以上内容不应被视为任何金融产品的购买或出售要约、建议或邀请，作者或其他用户的任何相关讨论、评论或帖子也不应被视为此类内容。本文仅供一般参考，不考虑您的个人投资目标、财务状况或需求。TTM对信息的准确性和完整性不承担任何责任或保证，投资者应自行研究并在投资前寻求专业建议。

热议股票

{"basename":"/hans","ssrTDKData":{"titleTemplate":"%s - 老虎证券","title":"老虎证券全球投资理财平台| 一站式投资美股新股港股A股","description":"老虎证券助您一站式投资美股，新股，港股，A股等全球金融理财产品。新加坡华人最信赖的在线投资平台，现在加入即享低费用，24/5 无时差炒美股投资理财！","keywords":"老虎证券,老虎证券开户,老虎券商,老虎证券官网,老虎证券app,tigertrade老虎证券,股票,炒股,新加坡股票交易平台,投资,投资理财","social":{"ogDescription":"老虎证券助您一站式投资美股，新股，港股，A股等全球金融理财产品。新加坡华人最信赖的在线投资平台，现在加入即享低费用，24/5 无时差炒美股投资理财！","ogImage":"https://c1.itigergrowtha.com/portal5/static/media/og-logo.be62fbe1.png","ogUrl":"https://www.itiger.com/hans/news/2581079675"},"companyName":"老虎证券"},"pageData":{"isMobile":false,"isTiger":false,"isTTM":true,"region":"SGP","license":"TBSG","edition":"fundamental"},"isCrawlerRequest":true,"__swrFallback__":{"@#url:\"https://stock-news.skytigris.cn/v3/news\",params:#id:\"2581079675\",edition:\"fundamental\",auth_exemption:1,,,undefined,":{"share":"https://ttm.financial/m/news/2581079675?lang=zh_CN&edition=fundamental","thumbnail":"","is_english":false,"pubTime":"2025-11-06 20:54","share_image_url":"https://static.laohu8.com/9a95c1376e76363c1401fee7d3717173","id":"2581079675","market":"us","top_or_hot":-1,"title":"破冰！寒武纪在HBM上的“弯道超车”","media":"AI芯界","content":"<div>\n<p>经过一年使用，寒武纪590 ASIC架构与H20 GPU不相上下的性能的数据，，寒武纪在软件领域持续发力，剑指超越CUDA生态，在硬件层面ASIC针对大量卷积运算与池化运算，从硬件底层出发集成专门用于卷积运算的硬件加速单元。相较于GPU依赖通用并行计算架构并通过软件优化完成运算，ASIC能更直接、高效地执行卷积操作，在计算速度和能耗效率上已能与英伟达的GPU持平。国内互联网大厂的大模型训练对内存...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20251106233955a48dcd88&s=b\">网页链接</a>\n\n</div>\n","source":"tencent","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>破冰！寒武纪在HBM上的“弯道超车”</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n破冰！寒武纪在HBM上的“弯道超车”\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-11-06 20:54 北京时间&nbsp;&nbsp;&nbsp;<a href=http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20251106233955a48dcd88&s=b><strong>AI芯界</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>经过一年使用，寒武纪590 ASIC架构与H20 GPU不相上下的性能的数据，，寒武纪在软件领域持续发力，剑指超越CUDA生态，在硬件层面ASIC针对大量卷积运算与池化运算，从硬件底层出发集成专门用于卷积运算的硬件加速单元。相较于GPU依赖通用并行计算架构并通过软件优化完成运算，ASIC能更直接、高效地执行卷积操作，在计算速度和能耗效率上已能与英伟达的GPU持平。国内互联网大厂的大模型训练对内存...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20251106233955a48dcd88&s=b\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"ASIC","symbol_name":"Ategrity Specialty Holdings","start_time":0,"source_url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20251106233955a48dcd88&s=b","article_id":"2581079675","we_media_id":null,"thumbnails":[],"rights":{"source":"tencent","url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20251106233955a48dcd88&s=b","rn_cache_url":null,"customStyle":"body{padding-top:10px;}#news_title{font-weight:bold;#titleStyle#;}#news_description span{font-size:12px;#descriptionStyle#;}.footer-note{#statement#}","selectors":".mod-LoadTzbdNews, body","filters":".relate-stock, .hot-list, .recom-box, .wx-sou","directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2581079675","pubTimestamp":1762433641,"columns":[],"sourceInfo":{"source_id":"tencent","name":"腾讯"},"weMediaInfo":null,"summary":"经过一年使用，寒武纪590 ASIC架构与H20 GPU不相上下的性能的数据，，寒武纪在软件领域持续发力，剑指超越CUDA生态，在硬件层面ASIC针对大量卷积运算与池化运算，从硬件底层出发集成专门用于卷积运算的硬件加速单元。国产芯片凭借寒武纪利用ASIC架构的这些特性，在不使用HBM的情况下另辟蹊径，大量使用GDDR5，无论如何HBM也再也无法限制我们独有的ASIC架构发展。","collect":0,"end_time":0,"defaultTopTitle":"qq.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"ASIC":"Ategrity Specialty Holdings","BK4605":"半导体精选","LU1861214812.USD":"Blackrock Future of Transport A2 USD","IE00BZ199S13.USD":"BNY MELLON MOBILITY INNOVATION \"B\" (USD) ACC","LU0348723411.USD":"ALLIANZ GLOBAL HI-TECH GROWTH \"A\" (USD) INC","IE00BD6J9T35.USD":"NEUBERGER BERMAN NEXT GENERATION MOBILITY \"A\" (USD) ACC","BK4512":"苹果概念","LU1861219969.SGD":"Blackrock Future of Transport A2 SGD-H","LU1720051108.HKD":"ALLIANZ GLOBAL ARTIFICIAL INTELLIGENCE \"AT\" (HKD) ACC","LU1720051017.SGD":"Allianz Global Artificial Intelligence AT Acc H2-SGD","LU2357305700.SGD":"Allianz Global Artificial Intelligence ET H2-SGD","LU1854104046.USD":"M&G (LUX) POSITIVE IMPACT \"A\" (USD) ACC","LU1861215975.USD":"贝莱德新一代科技基金 A2","BK4585":"ETF&股票定投概念","ON":"安森美半导体","LU1548497426.USD":"安联环球人工智能AT Acc","BK4141":"半导体产品","LU2360107325.USD":"BGF FUTURE OF TRANSPORT \"A4\" (USD) INC","LU0124384867.USD":"贝莱德新能源基金A2","LU1861220033.SGD":"Blackrock Next Generation Technology A2 SGD-H","LU2298322129.HKD":"BGF SUSTAINABLE ENERGY \"A2\" (HKDHDG) ACC","BK4107":"财产与意外伤害保险","LU0724618433.USD":"BGF NEW ENERGY \"A4\" (USD) INC","LU1978683503.SGD":"Blackrock Sustainable Energy A2 SGD-H","IE00BFMHRM44.USD":"NEUBERGER BERMAN GLOBAL EQUITY MEGATRENDS \"A\" (USD) ACC","LU1854103824.USD":"M&G (LUX) POSITIVE IMPACT \"A\" (USD) INC","BK4588":"碎股"},"translate_title":"Ice breaker! Cambrian's \"corner overtaking\" on HBM","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"ASIC":0.9,"ON":0.9},"content_text":"经过一年使用，寒武纪590 ASIC架构与H20 GPU不相上下的性能的数据，，寒武纪在软件领域持续发力，剑指超越CUDA生态，在硬件层面ASIC针对大量卷积运算与池化运算，从硬件底层出发集成专门用于卷积运算的硬件加速单元。相较于GPU依赖通用并行计算架构并通过软件优化完成运算，ASIC能更直接、高效地执行卷积操作，在计算速度和能耗效率上已能与英伟达的GPU持平。国内互联网大厂的大模型训练对内存带宽和容量的需求高涨，HBM面临成本高昂、供应被棒子受限等难题。ASIC架构采用的流水线架构，将AI计算任务细分为多个阶段，由专门硬件单元精准处理，实现数据的连续流动与并行处理，充分挖掘硬件资源潜力，大幅提升计算吞吐量。590新一代架构更是聚焦大模型场景，支持原生FB4格式及多卡全互联交换芯片，有效提升训练与推理效率。在处理AI计算任务时，ASIC能更直接高效地执行计算，减少对高带宽内存的依赖。ASIC架构对内存高效利用的重视，通过优化内存管理和数据流动方式，采用数据压缩技术，在确保数据准确性的前提下减少数据量，进而降低内存带宽需求。智能缓存机制能依据计算任务特点，合理分配和利用缓存资源，提高数据重复利用率，减少从外部内存读取数据的次数。它通过减少对外部存储器的访问，降低功耗和延迟，提升系统整体性能。国产芯片凭借寒武纪利用ASIC架构的这些特性，在不使用HBM的情况下另辟蹊径，大量使用GDDR5，无论如何HBM也再也无法限制我们独有的ASIC架构发展。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"isVideo":false,"video":null,"symbols":[],"gpt_button":1,"need_auth":false,"code":"91000000","status":"200"}}}