硅光学有望推动数据中心脱胎换骨

    泰西称：“英特尔提出的、由硅光子学所支撑的架构则几乎是按照完全相反的方向开发的。实际上，他们是将主要部件分开放置，并用延迟率很低、带宽极高的连接方式来弥补处理效率的降低。”

    这正是超大容量光速数据传输载体得以成为关键支撑要素，并可能改变计算系统设计模式的用武之地。泰西称，如果要做大数据分析或是操作实时交易数据库，那就会想要一个大型的连续存储数据池，而不是在整个数据中心的每台机架服务器上零星分布，依靠数据线连接的那种存储数据。靠现有的架构无法做到这一点，但凭借能克服延迟的硅光学芯片的高速传输能力，数据中心设计师就能大胆设想了，还能为需要极高运算效率的特定任务定制计算阵列。穆塞尔称，关键在于效率。联网的机架服务器的运行和冷却都需要消耗大量电力。而与现有的数据传输技术相比，硅光学芯片产生的热能更少。同时，如果能让设计师通过集中冷却某些最需要降温的部位、而不是平均冷却设备从而进一步降低能耗，这种技术还能让他们自由构思数据中心和超大规模计算设施与现有模式完全不同的构建方式。

    穆塞尔称：“这确实是模式方面的一个大转变，而如果他人无法做到这一点——即如果这种技术能大幅降低联网成本，同时通过降低联网的能耗从而减少总能耗——那就是关键价值所在。而且这还能让英特尔保护自己的主要业务，即处理器。”

    穆塞尔表示，英特尔以生产业内最大的处理器而著称，但这些处理器也极为耗能。如果英特尔能降低系统内其他地方的能耗，面对那些可能靠体积更小、能耗更低的处理器打江山的对手，它就能让它们的价值主张大打折扣。他说：“现在能够随心所欲地制造计算系统了，因为英特尔能降低联网的能耗。”

    不过这种构建模式的转变不可能一夜之间实现。泰西表示，对很多应用来说，硅光学技术还太过昂贵（英特尔还未公布官方定价），而且对现在很多注重数据应用的公司来说，大规模计算的其他方面更加重要。除了这项技术本身还不够成熟外，目前联网能耗也还没有达到让全面上马硅光学技术的高额成本显得合情合理的地步。泰西说：“再过几年，到2020年左右局面就会改观。”

    不过，正如穆塞尔所指出的，对英特尔的硅光学技术来说，事情不只是将激光硅芯片植入所有数据中心这么简单。它事关创造一种全新的模式，让英特尔的芯片制造这个核心业务及其他大规模计算基础设施能获得更大的发展。

    泰西说：“硅光学技术有点像特洛伊木马，专为基于X86（基于英特尔技术）处理器打造大规模计算系统服务。这是一种创新突破，如果我是英特尔，这也是对抗IBM这种对手的绝好一招。”

    穆塞尔同意这种说法。

    他说：“这不光是靠硅光学带来收入的问题，而是关系到英特尔能否改变业界游戏规则的大事。”（财富中文网）

    译者：清远  

    "This architecture that Intel is proposing, enabled by silicon photonics, is almost diametrically opposed," Teich says. "They're actually going to separate the major components and make up for it with a low-latency, high bandwidth connection between them."

    That's where speed-of-light, high-volume data transmission is a critical enabler and potential paradigm-shifter. Ideally, Teich says, if you're doing big data analytics or operating a real-time transactional database, you would want one large, contiguous pool of storage rather than storage distributed across the entire data center, a little on each rack, networked together with cables.You can't do that with current architectures, but with silicon photonics high-speed capability taking latency issues out of the equation, data center designers will be liberated to dream big, as well as to tailor certain arrays for maximum efficiency for the tasks for which they will be used.Efficiency is key here, Mushell says. A great deal of power consumption is tied up in networking server racks together, as well as in keeping them cool. Silicon photonics produces less heat as a by-product than current data transmission tech, and liberating designers to think differently about the way data centers and hyperscale facilities are organized should allow them to further reduce energy load by concentrating cooling to the places it's most needed rather than distributing it evenly throughout the facility.

    "It's really a shift in paradigm, and if no one else can do that -- if this alleviates that networking cost and can reduce the overall power consumption by reducing the consumption from networking -- that's where the key value is," Mushell says. "And it also allows Intel to protect its main line of business, which is processors."

    Intel is known for building the biggest processors in the business, Mushell notes, but those processors are also power-hungry. If Intel can alleviate power consumption elsewhere in the system, it reduces the value proposition for competitors who might enter the space offering smaller but less power-hungry processors. "You can now build whatever you want," he says, "because we're going to reduce the power consumption from networking."

    The paradigm shift won't happen overnight, however. Silicon photonics remains prohibitively expensive for many applications (Intel hasn't yet released official pricing information), Teich says, and there are other aspects of large-scale computing that are higher priorities for many data-focused companies right now. Aside from the technology being somewhat immature, network power consumption isn't quite enough of an economic pain point to justify the huge cost of implementing silicon photonics across the board. "All this will play out mid-decade, late-decade," Teich says.

    But, as Mushell noted, for Intel silicon photonics isn't just about integrating laser-embedded silicon chips into every data center in the business. It's about creating a new paradigm that positions Intel's core business of producing processors and other large-scale computing infrastructure to thrive.

    "Silicon photonics is kind of a trojan horse for building large-scale systems out of X86 [Intel-based] processors," Teich says. "It's non-traditional, and if I'm Intel it's a brilliant play as a way to go up against, say, IBM."

    Mushell agrees.

    "It's not just about bringing revenue from [silicon photonics]," he says. "It's about Intel changing the game."