Nvidia CEO Says Moore’s Law Is Dead

发布时间:2017-06-02 00:00
来源:EE Times

Nvidia CEO Jensen Huang has become the first head of a major semiconductor company to say what academics have been suggesting for some time: Moore’s Law is dead.

Moore’s Law, named after Intel cofounder Gordon Moore, reflects his observation in 1965 that transistors were shrinking so fast that every year twice as many could fit onto the same surface of a semiconductor. In 1975, the pace shifted to a doubling every two years.

The enablers of an architectural advance every generation — increasing the size of pipelines, using superscalar tweaks and speculative execution — are among the techniques that are now lagging in the effort to keep pace with the expected 50 percent increase in transistor density each year, Huang told a gathering of reporters and analysts at the Computex show in Taipei.

“Microprocessors no longer scale at the level of performance they used to — the end of what you would call Moore’s Law,” Huang said. “Semiconductor physics prevents us from taking Dennard scaling any further.”

Nvidia CEO Jensen Huang notes the divergence between semiconductor technology and microprocessor performance at Taipei's Computex show.

Nvidia CEO Jensen Huang notes the divergence between semiconductor technology and microprocessor performance at Taipei’s Computex show.

Dennard scaling, also known as MOSFET scaling, is based on a 1974 paper co-authored by Robert H. Dennard, after whom it is named. Originally formulated for MOSFETs, it states, roughly, that as transistors get smaller their power density stays constant, so that power use stays in proportion with area.

The diminishing returns from Moore’s Law and Dennard scaling have seen the semiconductor industry enter a mature stage in which just a handful of chipmakers can afford the multibillion dollar investments required to push the process technology forward. By now, only a few chip designers have the deep pockets to double down on fabricating silicon at the 16nm and 14nm nodes, design rules where the distinction has become increasingly blurred.

That stagnation in the progress of technology has also led to rapid industry consolidation in recent years that’s resulted in a flurry of multi-billion dollar mergers and acquisitions.

 Nvidia’s Huang predicts further advances to come from GPU computing.

Nvidia’s Huang predicts further advances to come from GPU computing.

Even so, Huang suggested a modus vivendi for the semiconductor industry that plays into graphics processors, the products that Nvidia expects will enable continuing advances for years to come. Deep learning will use the processing power of GPUs that Nvidia makes as part of a new architecture that will take the company into artificial intelligence, outside the computer gaming business Nvidia has dominated, according to Huang.

The semiconductor industry is exploring a number of pathways beyond Moore’s Law. Some upstart Chinese chipmakers are taking a stake in Fully Depleted Silicon-On-Insulator FD-SOI.  Others see a future in going beyond planar design to three-dimensional chips.

Nvidia’s bet on artificial intelligence to take the silicon industry forward is bullish, according to Randy Abrams, an analyst with Credit Suisse in Taipei.

Nvidia has highlighted its Volta GPU on 12nm at an 815mm die size, taking up the same surface area as 7 iPhone processors, and connected to 16GB of high bandwidth memory using Taiwan Semiconductor Manufacturing Co.’s (TSMC) silicon interposer technology. A configuration of eight of these chips in Nvidia’s DGX-1 deep learning / high performance computing machine sells for $149,000.


NVIDIA(辉达)宣布将在NVIDIA Aerial A100 AI-on-5G平台中扩大支援采用Arm架构CPU的产品,为5G产业生态系带来更多选择。此举将使OEM业者能够提供业界标准的伺服器,助力各地的企业在边缘部署智慧服务,这些伺服器皆搭载ARM 架构CPU,并透过Aerial 5G运行NVIDIA AI企业软体。 AI-on-5G晶片发展蓝图 这些NVIDIA认证系统将简化建立及部署自我託管式vRAN的方式,融合人工智慧(AI)及5G网路的能力,提供给私人企业、网路设备公司、软体业者与电信服务供应商。NVIDIA Aerial A100 AI-on-5G运算平台採用NVIDIA Aerial软体开发套件,以及在NVIDIA BlueField-3 A100中配有16个Arm Cortex-A78处理器,形成一个独立的聚合卡,在云端原生的5G vRAN上提供企业边缘AI应用程式,不仅能提高每瓦效能,还可缩短部署时间。 在BlueField-3 A100中加入NVIDIA的AI 软体函式库与Aerial 5G SDK,可以缩短部署时间并推动多项超低延迟的企业AI专案,包括用于产品开发和製造的精密机器人、自动导引车和数位分身。 NVIDIA Aerial A100 AI-on-5G平台Ampere GPU与BlueField-3 DPU NVIDIA AI Enterprise让在混合云环境中运行的大量加速CUDA应用程式、AI框架、预先训练模型和软体开发套件之间可以相容。在经过最佳化后,可以横跨多个节点扩大作业负载的规模,以支援运用GPU虚拟化技术的大型深度学习训练模型。 BlueField-3 A100可以部署于x86与Arm架构的CPU。将Arm技术结合BlueField-3 A100,企业与网路营运商将能够部署软体定义的5G网路基地台及AI应用程式,并可升级各项功能与效能,同时发挥基础设施建设的投资价值。 BlueField-3是为AI与加速运算而打造的资料处理器,协助各企业提供具有高效能表现及资料中心安全性的AI应用程式。它针对5G网路连线、多租户(multi-tenant)、云端原生环境进行最佳化调整,在边缘提供软体定义与硬体加速的网路、储存、安全性及管理服务。 NVIDIA 4月时宣佈与富士通(Fujitsu)、Google Cloud、Mavenir、Radisys及Wind River合作,开发用于NVIDIA AI-on-5G平台的解决方案。备注:图文源自网络,如有侵权请联系删除!
2021-09-08 00:00 阅读量:1034
就在日前包括英特尔 (intel) 及 AMD 都陆续公布第 1 季财报,营收、盈利方面都有不错的成绩之后。5月10日,英伟达(NVIDIA)公布 2019 财年的第 1 季财报。NVIDIA第一财季营收为32.07亿美元,较上年同期的19.37亿美元增长66%;净利润为12.44亿美元,较上年同期的5.07亿美元增长145%。先前华尔街分析师预期,英伟达 (NVIDIA) 在 2018 年第 1 季的营收年成长将会大增超过 50%。如今成绩揭晓,2018 年第 1 季营收达到 32.1 亿美元,较 2017 年同期成长 66%,较 2017 年第 4 季也成长 10%,创下历史新高数字。根据 NVIDIA 所公布的 2018 年第 1 季财报显示,该季营收达到 32.1 亿美元,较 2017 年同期成长 66%,较 2017 年第 4 季也成长 10%。以非会计准则来计算,毛利率达到 64.7%,每股 EPS 较 2017 年同期大增 141%,也较 2017 年第 4 季也增加 19%,达到 2.05 美元。根据日前,华尔街分析师发布的财测分析指出,NVIDIA 第 1 季的营收将落在 28.84 亿到 29.1 亿美元之间,较 2018 年第 1 季的 19.37 亿美元,其成长达到 50%。毛利率在 63% 左上下,每股 EPS 落在 1.44 到 1.47 美元区间的说法,NVIDIA 在 2018 年第 1 季的财报都优于这样的预测数字,而这也是 NVIDIA 创下连续第 11 季财报优于财测的纪录。以部门划分来看的话,游戏业务第一财季营收为17.2亿美元,同比增长68%,较上一季减少 1%;数据中心业务第一财季营收达创纪录7.01亿美元,同比增长71%;专业可视化(Professional visualization)业务第一财季营收为2.51亿美元,同比增长22%,较上一季减少 1%;汽车业务营收 1.45 亿美元,较2017年同期增加 4%,较上一季增 10%。……NVIDIA表示, OEM & IP业务营收 3.87 亿美元,较 2017 年同期年增 148%,也较上一季增 115%。这一部分包含密码货币挖矿相关 GPU 营收,矿卡功不可没。最后,在 GPU 事业体的营收部分,金额来到 7.65 亿美元,较 2017 年同期年增 77%,也较上一季增 11%。Tegra 处理器事业体营收则是 4.42 亿美元,较 2017 年同期年增 33%,较上一季减少 2%。以上这些部门或事业体的营收表现均优于分析师的预期。至于 NVIDIA 面临的风险,分析师认为中美贸易战值得注意。由于 NVIDIA 来自美国市场的营收占其 25%,但 66% 的成本来自亚洲地区。如果美国是针对「Made in China」的产品课征惩罚性关税,那么 NVIDIA 受影响的成本就会来到 4% 左右。不过,如果关税课征对象仅止于「Made by China」的产品,则 NVIDIA 受影响的成本就只有 0.2%。对于第 2 季的营运展望,NVIDIA 财务长 Colette Kress 表示,受惠于第 1 季初供给吃紧,但目前情况已经解除的情况下, GPU 的通路价格回稳,将会使得之前被涨价所苦的玩家能以合理价格取得新的高效能绘图晶片,这也将带动业绩,使得第 2 季的营收将会落在 31 亿美元,上下 2 个百分点的区间。而这样的数字也超越了了市场分析师预估 29.5 亿美元的数字。
2018-05-14 00:00 阅读量:847
  • 一周热料
  • 紧缺物料秒杀
型号 品牌 询价
CD74HC4051QPWRQ1 Texas Instruments
PCA9306DCUR Texas Instruments
TPS5430DDAR Texas Instruments
TPIC6C595DR Texas Instruments
TL431ACLPR Texas Instruments
TXB0108PWR Texas Instruments
型号 品牌 抢购
TPS5430DDAR Texas Instruments
ULQ2003AQDRQ1 Texas Instruments
TXS0104EPWR Texas Instruments
TPS61021ADSGR Texas Instruments
TPS63050YFFR Texas Instruments
TPS61256YFFR Texas Instruments
AMEYA360商城(www.ameya360.com)上线于2011年,现 有超过3500家优质供应商,收录600万种产品型号数据,100 多万种元器件库存可供选购,产品覆盖MCU+存储器+电源芯 片+IGBT+MOS管+运放+射频蓝牙+传感器+电阻电容电感+ 连接器等多个领域,平台主营业务涵盖电子元器件现货销售、 BOM配单及提供产品配套资料等,为广大客户提供一站式购 销服务。