從現(xiàn)在起僅僅五年，到2025年，傳感器將每天產(chǎn)生超字節(jié)的數(shù)據(jù)(根據(jù) IBS和希捷它將通過(guò)下一代網(wǎng)絡(luò)以盡可能低的延遲傳輸。 Zettabytes的數(shù)據(jù)將存儲(chǔ)在全球數(shù)據(jù)中，消費(fèi)者對(duì)其所有需求的即時(shí)響應(yīng)的期望將越來(lái)越普遍。 為了實(shí)現(xiàn)這一點(diǎn)，網(wǎng)絡(luò)、存儲(chǔ)和計(jì)算必須“超尺度”，以達(dá)到難以理解的速度和容量，并將術(shù)語(yǔ)“超尺度計(jì)算”統(tǒng)一起來(lái)”。 這將是Arm Dev峰會(huì)的一個(gè)大話(huà)題，影響著我們對(duì)消費(fèi)者的所有生活。

超尺度計(jì)算的范圍遠(yuǎn)遠(yuǎn)超過(guò)數(shù)據(jù)中心。 在Cadence，我們認(rèn)為這是感知數(shù)據(jù)的循環(huán)，通過(guò)網(wǎng)絡(luò)傳輸數(shù)據(jù)，并對(duì)其進(jìn)行處理和存儲(chǔ)，以最終使這些數(shù)據(jù)具有意義，從而產(chǎn)生可操作的結(jié)果。 當(dāng)觀察到支持超尺度計(jì)算的相關(guān)技術(shù)時(shí)，Arm-Cadence伙伴關(guān)系幾乎觸及了這個(gè)周期的每個(gè)方面。 它可以通過(guò)下一代網(wǎng)絡(luò)在傳感器及其模擬/混合信號(hào)挑戰(zhàn)中看到，因?yàn)槲覀冋谙蛘诎l(fā)生高性能計(jì)算的數(shù)據(jù)中心推出5G。 該行業(yè)正在經(jīng)歷計(jì)算、存儲(chǔ)、內(nèi)存和網(wǎng)絡(luò)的基本轉(zhuǎn)變，如上文所述 超尺度計(jì)算的四個(gè)支柱. Where data is processed outside the data center—at the inner edge, or outer edge, or the sensing nodes—is highly dependent on the application requirements and depends on the latency requirements at which users expect results. The following graph illustrates the journey of data from sensors, through networks to the data center, together with some of the latencies that users must expect depending on where data is processed.

?

在這一點(diǎn)上，我們的消費(fèi)者都期望來(lái)自我們的健身跟蹤器、消費(fèi)者行為和駕駛行為的數(shù)據(jù)被發(fā)送到云中進(jìn)行處理。 云的使用對(duì)EDA也有相當(dāng)深遠(yuǎn)的影響。

在Cadence LIVE Americas，來(lái)自Amazon AWS的Nafea Bshara，Annapurna Labs的聯(lián)合創(chuàng)始人，詳細(xì)介紹了他們自己以及他們客戶(hù)的云使用情況。 一些數(shù)據(jù)在一篇名為“”的博客文章中進(jìn)行了總結(jié)“ 爬上安納普爾納到云 包括一些實(shí)際客戶(hù)使用數(shù)據(jù)。 對(duì)于下一個(gè)芯片，在更先進(jìn)的技術(shù)下，通過(guò)優(yōu)化更新、更快服務(wù)器的使用，客戶(hù)的總體支出較少。

Cost per throughput is the metric to watch. And availability versus demand considerations can add flexibility. Bshara described how, during certain times of a project, Amazon AWS spot instances—spare capacity—were leveraged at up to 90 percent lower cost. In addition, users have the flexibility in the cloud to choose instances that are nominally slower but provide better cost per throughput. It is all demand based, almost like theatre tickets as I outlined in “ 什么“漢密爾頓-美國(guó)音樂(lè)劇”門(mén)票和仿真有共同之處 ”“很久以前了。

That said, Arm, Cadence and AWS have partnered to make key EDA capabilities available on AWS Graviton2 in the cloud as well. The focus is on the tools that consume the most cycles—simulation and characterization, specifically Xcelium Logic Simulation, Liberate Characterization and Spectre? Simulation. In a session called “Scalable Cloud-Based Simulation and Characterization”, Arm’s Bhumik Patel, my colleague Brandon Bautz and myself will show some of the results during the Arm DevSummit. More resources below.

這里是我們的超尺度計(jì)算未來(lái)，以及EDA工具在ARM架構(gòu)上也可用。