[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"content-doc-dciocbbd8c98":3},{"user":4,"document":8,"mainDocument":27,"columnUrl":29,"subscription":30,"footer":42,"text":77},{"isAuthenticated":5,"isAdmin":5,"displayName":6,"avatarUrl":6,"nid":6,"groupLevel":7},false,"",-10,{"id":9,"fullTitle":10,"subTitle":6,"url":11,"columnId":12,"columnName":13,"columnUrl":14,"summary":6,"contentHtml":15,"mainContentHtml":6,"posterUrl":16,"createDate":17,"displayDate":18,"displayDateSlash":19,"pageviews":20,"tags":21,"hidden":5,"isSubContent":5,"replyDocOrTargetId":6,"contentType":23,"videoId":6,"liveVideoUrl":6,"duration":24,"price":24,"priceText":25,"priceBadgeText":25,"priceBadgeClass":26,"freeForMinGroupLevel":24,"redirectUrl":6,"readyToStream":5},"dciocbbd8c98","容量暴涨64倍！闪迪新专利破HBM瓶颈，这就是我为何盈利50倍，仍旧没卖SNDK的原因","\u002Fdoc\u002Fdciocbbd8c98","col18178739ee","美股资讯","\u002Fcol\u002Fcol18178739ee","\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">近日，闪迪\u003C\u002Fspan>\u003C\u002Fspan> SanDisk\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">公布了一项新专利\u003C\u002Fspan>\u003C\u002Fspan>HBF\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">，可能是存储史上的一个重要转折，先科普一下什么叫存储角，\u003C\u002Fspan>\u003C\u002Fspan>AI\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">跑大模型的时候，数据要从存储里读到计算芯片里，但存储的速度追不上芯片，导致算力被浪费。这就是\u003C\u002Fspan>\u003C\u002Fspan>AI\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">行业头疼了十几年的存储墙。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cfigure class=\"image image_resized\" style=\"width:76.64%;\">\u003Cimg style=\"aspect-ratio:1207\u002F862;\" src=\"https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202606-stk\u002F636854354SNDK-W-2026-06-22_08-08-19.jpg\" width=\"1207\" height=\"862\">\u003C\u002Ffigure>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">之前行业的解法是\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">，但\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">单组容量只有\u003C\u002Fspan>\u003C\u002Fspan>32~64 GB, \u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">跑万亿参数大模型至少需要\u003C\u002Fspan>\u003C\u002Fspan>64\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">块\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">堆叠，功耗和成本都极高。闪迪的新思路是直接用\u003C\u002Fspan>\u003C\u002Fspan>NAND\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">闪存堆叠在计算芯片正下方，配合\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">一起工作，最高能到\u003C\u002Fspan>\u003C\u002Fspan>4 TB, \u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">是\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">的\u003C\u002Fspan>\u003C\u002Fspan>64\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">倍。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">这意味着什么？单个\u003C\u002Fspan>\u003C\u002Fspan>AI GPU\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">就能跑\u003C\u002Fspan>\u003C\u002Fspan>1.8\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">万亿参数的大模型推理，首次令牌生成时间降低\u003C\u002Fspan>\u003C\u002Fspan>41\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">倍，存储终于从\u003C\u002Fspan>\u003C\u002Fspan>\u003Cspan lang=\"ZH-CN\"> \u003C\u002Fspan>“\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">等算力\u003C\u002Fspan>\u003C\u002Fspan>” \u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">变成了\u003C\u002Fspan>\u003C\u002Fspan>\u003Cspan lang=\"ZH-CN\"> \u003C\u002Fspan>“\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">喂算力\u003C\u002Fspan>\u003C\u002Fspan>”\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">为此，闪迪正积极探索新方案，先是推出\u003C\u002Fspan>\u003C\u002Fspan>HBF\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">高带宽闪存方案，模仿\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">垂直堆叠思路，依靠\u003C\u002Fspan>\u003C\u002Fspan>TSV\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">硅通孔多层互联，将多个\u003C\u002Fspan>\u003C\u002Fspan>NAND\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">层垂直堆叠，\u003C\u002Fspan>\u003C\u002Fspan>HBF\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">单堆容量最高可达\u003C\u002Fspan>\u003C\u002Fspan>4TB\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">，明显高于当前\u003C\u002Fspan>\u003C\u002Fspan>HBM\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">水平。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">不过，该方案目前仅停留在专利阶段，封装复杂度、散热功耗、量产成本都是待攻克难题，商业化面临多重挑战。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">该方案的关键在于\u003C\u002Fspan>\u003C\u002Fspan>CBA\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">堆叠工艺。\u003C\u002Fspan>\u003C\u002Fspan>CBA\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">全称\u003C\u002Fspan>\u003C\u002Fspan>CMOS directly Bonded to Array\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">（控制电路直接键合存储阵列），是闪迪和铠侠联合研发的新一代\u003C\u002Fspan>\u003C\u002Fspan>3D\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">闪存堆叠技术，其优势在于，存储与控制晶圆分开制作，互不干扰，闪存堆叠层数、读写性能大幅提升，但对晶圆纳米级贴合精度要求极高，设备与双片硅片将大幅拉高制造成本，量产良率管控难度大。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">另外，根据美股大数据\u003C\u002Fspan>\u003C\u002Fspan> StockWe.com \u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">获悉，成本问题同样严峻，初步估算采用该架构的\u003C\u002Fspan>\u003C\u002Fspan>AI\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">加速器单价将上涨\u003C\u002Fspan>\u003C\u002Fspan>40%\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">，这可能限制其在消费级市场的推广。散热设计也需要重新构建，垂直堆叠结构无疑会增加热点密度。\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>\u003Cp>\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">你们觉得这项专利会是它冲击\u003C\u002Fspan>\u003C\u002Fspan>AI\u003Cspan style=\"font-family:DengXian;\">\u003Cspan lang=\"ZH-CN\">存储市场的王牌吗？\u003C\u002Fspan>\u003C\u002Fspan>\u003C\u002Fp>","https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202606-stk\u002FUploaderv1igillxo2a_2026_06_22_08_28_19.jpg","2026-06-22T15:28:08.78","2026.06.22","2026\u002F06\u002F22",36999,[22],"SNDK","Article",0,"免费","success",{"id":9,"fullTitle":10,"subTitle":6,"url":11,"columnId":12,"columnName":13,"columnUrl":14,"summary":6,"contentHtml":15,"mainContentHtml":6,"posterUrl":16,"createDate":17,"displayDate":18,"displayDateSlash":19,"pageviews":20,"tags":28,"hidden":5,"isSubContent":5,"replyDocOrTargetId":6,"contentType":23,"videoId":6,"liveVideoUrl":6,"duration":24,"price":24,"priceText":25,"priceBadgeText":25,"priceBadgeClass":26,"freeForMinGroupLevel":24,"redirectUrl":6,"readyToStream":5},[22],"\u002Fcol\u002Fstocknews",{"visible":5,"marketingHtml":31,"services":32,"recentDocuments":41},"\u003Cfigure class=\"image\">\u003Ca href=\"https:\u002F\u002Fstockwe.com\u002Fdoc\u002Fdcio537efad5\" target=\"_blank\" rel=\"noopener noreferrer\">\u003Cimg style=\"display:block;margin-left:auto;margin-right:auto;\" src=\"https:\u002F\u002Fstockwewebfiles.blob.core.windows.net\u002Fweb-202408-stk\u002F1586109431mceclip0.jpg\">\u003C\u002Fa>\u003C\u002Ffigure>\u003Cdiv class=\"text-center\">\u003Ch2 class=\"card-title mx-auto\">\u003Cbr>\u003Ca target=\"_blank\" rel=\"noopener noreferrer\" href=\"https:\u002F\u002Fstockwe.com\u002Fdoc\u002Fdcio537efad5\">案例介绍：英伟达深度研究报告\u003C\u002Fa>\u003C\u002Fh2>\u003C\u002Fdiv>",[33,37],{"productId":34,"serviceName":35,"priceText":36},"prod_PPxdDdK87QaiLv","月付","$12.95美元",{"productId":38,"serviceName":39,"priceText":40},"prod_PPxeMs3bix1da5","年付","$149.00美元",[],{"links":43,"images":68,"summaryHtml":73,"aboutTitle":74,"aboutHtml":75,"copyrightHtml":76},[44,47,50,53,56,59,62,65],{"label":45,"url":46},"深度报告","\u002Fcol\u002FdepthReport",{"label":48,"url":49},"VIP会员","\u002Fplan",{"label":51,"url":52},"期权推荐","\u002FOption",{"label":54,"url":55},"低价暴涨股","\u002FPenny",{"label":57,"url":58},"常见问题","https:\u002F\u002Fstockwe.com\u002FFAQ",{"label":60,"url":61},"美股课程","\u002Fcol\u002Fvideos",{"label":63,"url":64},"免责声明","\u002Fdisclaimer",{"label":66,"url":67},"联系我们","\u002FContactUs",[69,70,71,72],"https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202509-stk\u002FUploaderzic2tuwsol2_2025_09_11_18_21_07.gif","https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202509-stk\u002FUploadercakzdvydksw_2025_09_03_09_00_56.png","https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202509-stk\u002FUploadergtjyagwvoyk_2025_09_14_08_32_05.png","https:\u002F\u002Fstockwebsiteblob.blob.core.windows.net\u002Fweb-202509-stk\u002FUploader3u0tt4jhlqh_2025_09_23_22_30_48.png","邮箱: buy@TradesMax.com 美国电话 626-378-3637","公司介绍","\u003Cp class=\"MsoNormal\">美股大数据 StockWe.com 是一个美国领先的金融和美股信息大数据提供商，紧盯华尔街金融市场和行情，2008年成立于美国硅谷，创始人是前纽约证券交易所资深分析师Ken，联合多位摩根斯坦利分析师，谷歌 Meta工程师利用AI和大数据，配合十多年美股实战经验和业内量化交易模型，每天处理千万级股票数据：挖掘潜力大牛股，捕捉期权异动大单，实时主力资金流向、机构持仓变化、川普突发新闻，精准买卖信号第一时间发到您手机APP。\u003C\u002Fp>","专业美股投资者都在这里",{"loading":78,"search":79,"searchPlaceholder":79,"hotContent":80,"draft":81,"noData":82,"searchNoData":83,"edit":84,"editVideo":85,"courseContent":86,"more":87,"buyNow":88,"subscribeNow":89,"encoding":90,"paidContent":91},"Loading...","搜索","热门内容","草稿","目前没有任何内容公布","当前检索内容没有数据","编辑","编辑视频","课程内容","更多","立即购买后观看","- 立即订阅 -","视频编码中...","付费内容"]