投稿時間:2021-02-19 03:36:03 RSSフィード2021-02-19 03:00 分まとめ(47件)

カテゴリー等	サイト名等	記事タイトル・トレンドワード等	リンクURL	頻出ワード・要約等/検索ボリューム	登録日
IT	気になる、記になる…	｢Apple TV｣アプリが｢Chromecast with Google TV｣で利用可能に	https://taisy0.com/2021/02/19/136066.html	apple	2021-02-18 17:20:55
IT	気になる、記になる…	Microsoft、｢Surface Duo｣をイギリス・ドイツ・フランス・カナダで発売	https://taisy0.com/2021/02/19/136062.html	android	2021-02-18 17:09:30
IT	気になる、記になる…	新型コロナ接触通知アプリ｢COCOA｣に新たな不具合	https://taisy0.com/2021/02/19/136060.html	cocoa	2021-02-18 17:03:02
AWS	AWS Architecture Blog	Field Notes: Protecting Domain-Joined Workloads with CloudEndure Disaster Recovery	https://aws.amazon.com/blogs/architecture/field-notes-protecting-domain-joined-workloads-with-cloudendure-disaster-recovery/	Field Notes Protecting Domain Joined Workloads with CloudEndure Disaster RecoveryCo authored by Daniel Covey Solutions Architect at CloudEndure an AWS Company and Luis Molina Senior Cloud Architect at AWS nbsp When designing a Disaster Recovery plan one of the main questions we are asked is how Microsoft Active Directory will be handled during a test or failover scenario In this blog we go through some of …	2021-02-18 17:38:55
AWS	AWS Machine Learning Blog	Machine learning on distributed Dask using Amazon SageMaker and AWS Fargate	https://aws.amazon.com/blogs/machine-learning/machine-learning-on-distributed-dask-using-amazon-sagemaker-and-aws-fargate/	Machine learning on distributed Dask using Amazon SageMaker and AWS FargateAs businesses around the world are embarking on building innovative solutions we re seeing a growing trend adopting data science workloads across various industries Recently we ve seen a greater push towards reducing the friction between data engineers and data scientists Data scientists are now enabled to run their experiments on their local machine and port to …	2021-02-18 17:44:30
js	JavaScriptタグが付けられた新着投稿 - Qiita	Aspidaに感動しちゃった件について	https://qiita.com/yoshii0110/items/d3db124865fb8131ff51	GitHubAspidaAspidaの利点HTTPクライアントであるaxios、ky、fetchを使用したAPIリクエストレスポンスに型を付与できる点リクエストを文字列ではなく、プロパティ経由で行えるようになる点試してみる今回は、Swaggerをaspidaの型定義ファイルに一発変換してみたいと思います。	2021-02-19 02:01:06
Program	[全てのタグ]の新着質問一覧｜teratail（テラテイル）	ComposerをインストールしたあとにPHPを再インストールしても問題ないですか？	https://teratail.com/questions/323437?rss=all	ComposerをインストールしたあとにPHPを再インストールしても問題ないですかWindowsを使用しています。	2021-02-19 02:51:00
Program	[全てのタグ]の新着質問一覧｜teratail（テラテイル）	[React]投稿一覧コンポーネントだけをスクロールさせたい	https://teratail.com/questions/323436?rss=all	React投稿一覧コンポーネントだけをスクロールさせたい前提・実現したいことTwitterクローンのようなアプリをReactnbspHooksnbspReduxnbspToolKitでつくっています。	2021-02-19 02:13:49
Ruby	Rubyタグが付けられた新着投稿 - Qiita	【Ruby入門】Ruby版！APG4b(第一章)	https://qiita.com/yurukumo/items/dd1fce45592222c573bd	putsRubyで文字列この場合はHelloworldのことを出力するにはputs引数引数といった感じで引数と書いてある部分に文字列を書きます。	2021-02-19 02:11:57
AWS	AWSタグが付けられた新着投稿 - Qiita	Serverless Meetup Japan Virtual #16 の「ZoomでMeetUp枠」に参加しました！	https://qiita.com/y-sugichan/items/8100f42a1ac4d51913ba	ENI問題はAWSさんのお陰で解決しつつあるものの、つきまとうコネクションプール問題…これを早速導入されているのは非常に熱いものでした気になっていたので「使っていて困ったことやトラブルはありましたか」と質問してみましたが…特になかったとのことですさすがAWSさん、素晴らしいサービスをありがとうございます感謝ただ、気をつけるべき事項についてはAWS下川さんがTweetしてくださった以下の記事がありますので、一読せねばですオンラインセミナー「RDSLambdaが始まる。	2021-02-19 02:24:33
Apple	AppleInsider - Frontpage News	Chromecast with Google TV now supports Apple TV app, Apple TV+	https://appleinsider.com/articles/21/02/18/chromecast-with-google-tv-now-supports-apple-tv-app-apple-tv	Chromecast with Google TV now supports Apple TV app Apple TV Google has rolled out support for Apple s TV app and its Apple TV streaming service to its Chromecast with Google TV hardware meaning users can now watch Apple originals on the Google hardware Credit GoogleThe search giant said back in December that the Apple TV app would be coming to its set top device in early On Thursday Google announced that the Apple TV app is now globally available on its new streaming hardware Read more	2021-02-18 17:23:45
Apple	AppleInsider - Frontpage News	Apple evaluating tunable lens & software combo to improve wearable AR performance	https://appleinsider.com/articles/21/02/18/apple-evaluating-tunable-lens-software-combo-to-improve-wearable-ar-performance	Apple evaluating tunable lens amp software combo to improve wearable AR performanceApple is researching how to blend virtual objects more seamlessly into the real world with Apple Glass and how to correctly display AR at the periphery of a wearer s view Apple Glass render by iPhone lov er on InstagramFollowing many previous reports regarding the image quality of Apple Glass the company continues to research just what ーand when ーa wearer will see Apple AR Three newly revealed patent applications all concentrate on the issues of mixing virtual objects with real ones Read more	2021-02-18 17:13:12
海外TECH	Engadget	What it takes to get a job building robotic Mars explorers for NASA	https://www.engadget.com/what-it-takes-to-get-a-job-building-the-nasa-robots-exploring-mars-173048464.html	What it takes to get a job building robotic Mars explorers for NASAAfter a thankfully uneventful seven month journey NASA s Mars mission is set to safely reach the Red Planet and insert itself into orbit on Thursday ahead of deploying the Perseverance rover and Ingenuity helicopter prototype that it s been t	2021-02-18 17:30:48
海外TECH	Engadget	TikTok will offer behind-the-scenes UFC livestreams	https://www.engadget.com/tiktok-ufc-content-partnership-172656182.html	TikTok will offer behind the scenes UFC livestreamsUFC fans on TikTok will soon see more mixed martial arts content on the video app It amp s all thanks to a new multi year agreement between the two companies via Deadline According to TikTok s announcement it will work with the UFC to produce an	2021-02-18 17:26:56
海外科学	NYT > Science	Meet Elizabeth Ann, the First Cloned Black-Footed Ferret	https://www.nytimes.com/2021/02/18/science/black-footed-ferret-clone.html	diversity	2021-02-18 17:26:48
海外科学	NYT > Science	Clinical Trials Are Moving Out of the Lab and Into People’s Homes	https://www.nytimes.com/2021/02/18/health/clinical-trials-pandemic.html	Clinical Trials Are Moving Out of the Lab and Into People s HomesAfter the pandemic forced thousands of trials to shut down researchers found clever ways to conduct human studies remotely ーwhile reaching more people quickly and cheaply	2021-02-18 17:02:23
金融	金融庁ホームページ	金融審議会「市場制度ワーキング・グループ」（第6回）議事次第を公表しました。	https://www.fsa.go.jp/singi/singi_kinyu/market-system/siryou/20210218.html	金融審議会	2021-02-18 18:00:00
海外ニュース	Japan Times latest articles	Olympics minister Seiko Hashimoto appointed Tokyo Games chief	https://www.japantimes.co.jp/news/2021/02/18/national/hashimoto-tokyo-games-chief/	relay	2021-02-19 03:21:56
海外ニュース	Japan Times latest articles	Suga visits Tokyo hospital to observe COVID-19 vaccination program	https://www.japantimes.co.jp/news/2021/02/18/national/suga-vaccination-hospital-visit/	Suga visits Tokyo hospital to observe COVID vaccination programThe program is expected to expand to hospitals across the nation next week with medical staff in the first phase to take part	2021-02-19 02:34:48
海外ニュース	Japan Times latest articles	Olympic COVID-19 working committee responds to outside criticism	https://www.japantimes.co.jp/news/2021/02/18/national/olympic-covid-19-committee-criticism/	criticism	2021-02-19 02:25:14
海外ニュース	Japan Times latest articles	Pep Guardiola urges Manchester City to embrace ‘beautiful challenge’ of hectic schedule	https://www.japantimes.co.jp/sports/2021/02/18/soccer/pep-guardiola-manchester-city/	Pep Guardiola urges Manchester City to embrace beautiful challenge of hectic scheduleManchester City manager Pep Guardiola said it would be easy to feel overwhelmed by the club s packed schedule but called on his players to embrace	2021-02-19 03:39:28
海外ニュース	Japan Times latest articles	Naomi Osaka ponders if switch to Greek food helped predict semifinal triumph	https://www.japantimes.co.jp/sports/2021/02/18/tennis/naomi-osaka-ponders-switch-greek-food-helped-predict-semifinal-triumph/	Naomi Osaka ponders if switch to Greek food helped predict semifinal triumphNaomi Osaka was left wondering whether a decision to eat Greek food foretold her win over Serena Williams after she reached the Australian Open final	2021-02-19 03:29:56
海外ニュース	Japan Times latest articles	Jennifer Brady sets up date with Naomi Osaka in Australian Open final	https://www.japantimes.co.jp/sports/2021/02/18/tennis/jennifer-brady-naomi-osaka-australian-open-final/	Jennifer Brady sets up date with Naomi Osaka in Australian Open finalJennifer Brady edged Karolina Muchova in a tense Australian Open semifinal on Thursday to set up a title match with Naomi Osaka The	2021-02-19 02:13:34
ニュース	BBC News - Home	Coronavirus: Starmer targets savers and NI extends lockdown	https://www.bbc.co.uk/news/uk-56114533	pandemic	2021-02-18 17:23:30
ニュース	BBC News - Home	Dolly Parton asks for statue plans to go on hold	https://www.bbc.co.uk/news/entertainment-arts-56116505	fundraiser	2021-02-18 17:23:47
ニュース	BBC News - Home	Gulf War syndrome 'not caused by depleted uranium'	https://www.bbc.co.uk/news/uk-56116101	agent	2021-02-18 17:20:00
ニュース	BBC News - Home	Summerseat house explosion: Woman dead and two people injured	https://www.bbc.co.uk/news/uk-england-manchester-56108602	injuredanother	2021-02-18 17:13:32
ニュース	BBC News - Home	Curran will not rejoin England Test squad in India	https://www.bbc.co.uk/sport/cricket/56119003	Curran will not rejoin England Test squad in IndiaAll rounder Sam Curran will not rejoin England s Test squad for the fourth test against India as planned because of the logistical challenge in getting him to Ahmedabad	2021-02-18 17:39:14
ニュース	BBC News - Home	Covid-19 in the UK: How many coronavirus cases are there in your area?	https://www.bbc.co.uk/news/uk-51768274	cases	2021-02-18 17:12:34
ニュース	BBC News - Home	Vaccine passports: Do I need one for going out, work and travel?	https://www.bbc.co.uk/news/explainers-55718553	vaccine	2021-02-18 17:52:17
ニュース	BBC News - Home	How many have been vaccinated in your area?	https://www.bbc.co.uk/news/health-55274833	Detail Nothing	2021-02-18 17:38:54
ビジネス	ダイヤモンド・オンライン - 新着記事	「何もやる気が起きず、スマホを見てるだけ」の人生を変えたいなら必要なたった一つのツール - 独学大全	https://diamond.jp/articles/-/255028	読書	2021-02-19 02:55:00
ビジネス	ダイヤモンド・オンライン - 新着記事	グーグル社員が自分のスマホからGmailを削除したワケ - 時間術大全	https://diamond.jp/articles/-/262796	gmail	2021-02-19 02:53:00
ビジネス	ダイヤモンド・オンライン - 新着記事	精神科医が語る「発達障害で20回転職を繰り返す人」に足りていないたった一つの行動 - 発達障害サバイバルガイド	https://diamond.jp/articles/-/263028	精神科医が語る「発達障害で回転職を繰り返す人」に足りていないたった一つの行動発達障害サバイバルガイド『ストレスフリー超大全』の著者で、精神科医の樺沢紫苑さんは、借金玉さんの著書『発達障害サバイバルガイド』について、「このリアリティ、具体性は当事者の経験あってのもの。	2021-02-19 02:51:00
ビジネス	ダイヤモンド・オンライン - 新着記事	マリー・アントワネットも悩まされた、ベルサイユ宮殿の残念な真実 - 世界史は化学でできている	https://diamond.jp/articles/-/262603	文理が融合された多面的な“化学に魅了されっぱなしだ」と絶賛されたその内容の一部を紹介します。	2021-02-19 02:49:00
ビジネス	ダイヤモンド・オンライン - 新着記事	「頭の柔らかい人」がしている、当たり前を疑う習慣 - 考える術	https://diamond.jp/articles/-/259500	特別公開	2021-02-19 02:47:00
ビジネス	ダイヤモンド・オンライン - 新着記事	会社の儲け＝営業キャッシュフローは 一言で言うと、 何と何の差額のこと？ - たった10日で決算書がプロ並みに読めるようになる！会計の教室	https://diamond.jp/articles/-/263147	違い	2021-02-19 02:45:00
ビジネス	ダイヤモンド・オンライン - 新着記事	手軽に始める独学マクロ！　より便利なExcelマクロが作れる「セル選択」の方法とは？ - 4時間のエクセル仕事は20秒で終わる	https://diamond.jp/articles/-/263194	cells	2021-02-19 02:43:00
ビジネス	ダイヤモンド・オンライン - 新着記事	「不況に強い個人投資家、弱い個人投資家」決定的な差 - ゴールド投資	https://diamond.jp/articles/-/260744	youtuber	2021-02-19 02:41:00
ビジネス	ダイヤモンド・オンライン - 新着記事	最大のリスクは投資しないこと - 10万円から始める！　小型株集中投資で1億円　実践バイブル	https://diamond.jp/articles/-/261331	最大のリスクは投資しないこと万円から始める小型株集中投資で億円実践バイブル大好評シリーズ万部突破ふつうの会社員でも年あれば、気づいたときには億円小型株は伸びしろが大きいわりに、目を付けている投資家が少ない。	2021-02-19 02:39:00
ビジネス	ダイヤモンド・オンライン - 新着記事	がん・心不全の患者さんに知っていてほしい、 現場の緩和ケアチームの悩みとは - 後悔しない死の迎え方	https://diamond.jp/articles/-/261853	緩和ケア	2021-02-19 02:37:00
ビジネス	ダイヤモンド・オンライン - 新着記事	「旅はつまらない」と思う人に決定的に欠けていること - だから、この本。	https://diamond.jp/articles/-/262989	決定的	2021-02-19 02:35:00
ビジネス	ダイヤモンド・オンライン - 新着記事	もう売上高や利益の競争は古い！　風の時代は「組織文化」で違いを打ちだす - 中竹竜二のウィニングカルチャー	https://diamond.jp/articles/-/263320	中竹竜二	2021-02-19 02:31:00
ビジネス	ダイヤモンド・オンライン - 新着記事	ビジネスシーンで劇的に印象が上がる3つのキャラクターの演じ分けとは？ - 仕事のしぐさ図鑑	https://diamond.jp/articles/-/263323	ビジネスシーンで劇的に印象が上がるつのキャラクターの演じ分けとは仕事のしぐさ図鑑その場の状況にあわせたふるまいができると、ぐっと印象が上がるもの。	2021-02-19 02:29:00
ビジネス	ダイヤモンド・オンライン - 新着記事	英語「J」の発音は「じぇい」ではありません。正しく発音できますか？ - 英語の声トレ	https://diamond.jp/articles/-/263318	英語	2021-02-19 02:25:00
北海道	北海道新聞	知事リコール署名偽造で任意聴取　愛知県警、広告会社社長を	https://www.hokkaido-np.co.jp/article/513042/	任意聴取	2021-02-19 02:15:00
GCP	Cloud Blog	Benchmarking rendering software on Compute Engine	https://cloud.google.com/blog/topics/developers-practitioners/benchmarking-rendering-software-compute-engine/	Benchmarking rendering software on Compute EngineFor our customers who regularly perform rendering workloads such as animation or visual effects studios there is a fixed amount of time to deliver a project When faced with a looming deadline these customers can leverage cloud resources to temporarily expand their fleet of render servers to help complete work within a given timeframe a process known as burst rendering To learn more about deploying rendering jobs to Google Cloud see Building a Hybrid Render Farm When gauging render performance on the cloud customers sometimes reproduce their on premises render worker configurations by building a virtual machine VM with the same number of CPU cores processor frequency memory and GPU While this may be a good starting point the performance of a physical render server is rarely equivalent to a VM running on a public cloud with a similar configuration To learn more about comparing on premises hardware to cloud resources see the reference article Resource mappings from on premises hardware to Google Cloud With the flexibility of cloud you canright size your resources to match your workload You can define each individual resource to complete a task within a certain time or within a certain budget  But as new CPU and GPU platforms are introduced or prices change this calculation can become more complex How can you tell if your workload would benefit from a new product available on Google Cloud This article examines the performance of different rendering software on Compute Engine instances We ran benchmarks for popular rendering software across all CPU and GPU platforms across all machine type configurations to determine the performance metrics of each The render benchmarking software we used is freely available from a variety of vendors You can see a list of the software we used in the table below and learn more about each in Examining the benchmarks Note Benchmarking of any render software is inherently biased towards the scene data included with the software and the settings chosen by the benchmark author You may want to run benchmarks with your own scene data within your own cloud environment to fully understand how to take advantage of the flexibility of cloud resources Benchmark overviewRender benchmark software is typically provided as a standalone executable containing everything necessary to run the benchmark a license free version of the rendering software itself the scene or scenes to render and supporting files are all bundled in a single executable that can be run either interactively or from a command line Benchmarks can be useful for determining the performance capabilities of your configuration when compared to other posted results Benchmarking software such as Blender Benchmark use job duration as their main metric the same task is run for each benchmark no matter the configuration The faster the task completes the higher the configuration is rated Other benchmarking software such as V Ray Bench examines how much work can be completed during a fixed amount of time The amount of computations completed by the end of this time period provides the user with a benchmark score that can be compared to other benchmarks Benchmarking software is subject to the limitations or features of the renderer on which they re based For example software such as Octane or Redshift cannot take advantage of CPU only configurations as they re both GPU native renderers V Ray from ChaosGroup can take advantage of both CPU and GPU but performs different benchmarks depending on the accelerator and therefore cannot be compared to each other We tested the following render benchmarks Choosing instance configurationsAn instance on Google Cloud can be made up of almost any combination of CPU GPU RAM and disk In order to gauge performance across a large number of variables we defined how to use each component and locked its value when necessary for consistency For example we let the machine type determine how much memory was assigned to each VM and we created each machine with a GB boot disk Number and type of CPUGoogle Cloud offers a number of CPU platforms from different manufacturers Each platform referred to as Machine Type in the Console and documentation offers a range of options from a single vCPU all the way up to the m megamem Some platforms offer different generations of CPUs and new generations are introduced on Google Cloud as they come on the market We limited our research to predefined machine types on N N ND E C M and M CPU platforms All benchmarks were run on a minimum of vCPUs using the default amount of memory allocated to each predefined machine type Number and type of GPUFor GPU accelerated renderers we ran benchmarks across all combinations of all NVIDIA GPUs available on Google Cloud To simplify GPU renderer benchmarks we used only a single predefined machine type the n standard as most GPU renderers don t take advantage of CPUs for rendering with the exception of V Ray s Hybrid Rendering feature which we didn t benchmark for this article Not all GPUs have the same capabilities some GPUs support NVIDIA s RTX which can accelerate certain raytracing operations for some GPU renderers Other GPUs offer NVLink which supports faster GPU to GPU bandwidth and offers a unified memory space across all attached GPUs The rendering software we tested works across all GPU types and is able to leverage these types of unique features if available For all GPU instances we installed NVIDIA driver version available from NVIDIA s public download driver page as well as from our public cloud bucket This driver runs CUDA Toolkit and supports features of the new Ampere architecture of the A s Note Not all GPU types are available in all regions To view available regions and zones for GPUs on Compute Engine see GPUs regions and zone availability Type and size of boot diskAll render benchmark software we used takes up less than a few GB of disk so we kept the boot disk for each test instance as small as possible To minimize cost we chose a boot disk size of GB for all VMs A disk of this size will only deliver modest performance but rendering software typically ingest scene data into memory prior to running the benchmark disk I O has little effect on the benchmark RegionAll benchmarks were run in the us central region We located instances in different zones within the region based on resource availability  Note Not all resource types are available in all regions To view available regions and zones for CPUs on Compute Engine see available regions and zones To view available regions and zones for GPUs on Compute Engine see GPUs regions and zone availability Calculating benchmark costsAll prices in this article are calculated inclusive of all instance resources CPU GPU memory and disk for only the duration of the benchmark itself Each instance incurs startup time driver and software installation and latency prior to shutdown following the benchmark We didn t add this extra time to the costs shown which could be reduced by baking an image or by running within a container  Prices are current at the time of writing based on resources in the us central region and are in USD All prices are for on demand resources most rendering customers will want to use preemptible VMs which are well suited for rendering workloads but for the purposes of this article it s more important to see the relative differences between resources than overall cost See the Google Cloud Pricing Calculator for more details To come up with hourly costs for each machine type we added together the various resources that make up each configuration cost hr vCPUs RAM GB boot disk GB GPU if any To get the cost of an individual benchmark we multiplied the duration of the render by this cost hr total cost cost hr render durationCost performance indexCalculating cost based on how long a render takes only works for benchmarks that use render duration as a metric Other benchmarks such as V Ray and Octane calculate a score by measuring the amount of computations possible within a fixed period of time For these benchmarks we calculate the Cost Performance Index CPI of each render which can be expressed as CPI Value CostFor our purposes we substitute Value with Score and Cost with the hourly cost of the resources CPI score cost hrThis gives us a single metric that represents both price and the performance of each instance configuration Calculating CPI in this manner makes it easy to compare results to each other within a single renderer the resulting values themselves aren t as important as how they compare to other configurations running the same benchmark  For example examine the CPI of three different configurations rendering the V Ray Benchmark To make these values easier to comprehend we can normalize them by defining a pivot point a target resource configuration that has a CPI of In this example we use n standard as our target resource This makes it easier to see that the nd standard has a CPI that s around higher than that of the n standard For CPU benchmarks we defined the target resource as an n standard For GPU benchmarks we defined the target resource as an n standard with a single NVIDIA P A CPI greater than indicates better cost performance compared to the target resource and CPI less than indicates lower cost performance compared to the target resource For formula for calculating CPI using the target resource can be expressed as CPI score cost hr target score target cost hr We use CPI in the Examining the benchmarks section Comparing instance configurationsOur first benchmark examines the performance differences between a number of predefined N machine type configurations When we run the Blender Benchmark on a selection of six configurations and compare duration and the cost to perform the benchmark cost hr x duration we see an interesting result The cost for each of these benchmarks is almost identical but the duration is dramatically different This tells us that the Blender renderer scales well as we increase the number of CPU resources For a Blender render if you want to get your results back quickly it makes sense to choose a configuration with more vCPUs When we compare the N CPU platform to other CPU platforms we learn even more about Blender s rendering software Compare the Blender Benchmark across all CPU platforms with vCPUs The graph above is sorted according to cost with least expensive on the right The ND CPU platform which uses AMD EPYC Rome CPUs is the lowest cost and completes the benchmark in the shortest amount of time This may indicate that Blender can render more efficiently on AMD CPUs a fact that can also be observed on their public benchmark results page The C CPU platform which uses Intel Cascade Lake CPUs comes in a close second possibly because it offers the highest sustained frequency of GHz Note While a few pennies difference may seem trivial for a single render test a typical animated feature is minutes seconds in duration At frames per second that s approximately frames to be rendered for a single iteration Some elements can go through tens or even hundreds of iterations before final approval A miniscule difference at this scale can mean a massive difference in cost by the end of a production CPU vs GPUBlender Benchmark allows you to compare CPU and GPU performance using the same scenes and metrics The advantage of GPU rendering is revealed when we compare the previous CPU results to that of a single NVIDIA T GPU The Blender Benchmark is both faster and cheaper when run in GPU mode on an n standard with a single NVIDIA T GPU attached When we run the benchmark on all GPU types the results can vary widely in both cost and duration GPU performanceSome GPU configurations have a higher hourly cost but their performance specifications give them a better cost to performance advantage than lower cost resources For example the FP performance of the NVIDIA Tesla A TFLOPS is times higherthan that of the T TFLOPS yet the A is around times the cost In the above diagram the P V and A cost almost the same yet the A finished the render almost twice as fast as the P By far the most cost effective GPU in the fleet is the NVIDIA T but it didn t outperform the P V or A for this particular benchmark All GPU benchmarks except the A which used the a highgpu g configuration used the n standard configuration with a GB PD SSD boot disk We can also examine how the same benchmark performs on an instance with more than one GPU attached The NVIDIA V configuration may complete the benchmark fastest but it also incurs the highest cost The GPU configuration with the highest value appears to be x NVIDIA T GPUs which complete the work fast enough to cost less than the x NVIDIA T GPU Finally we compare all CPU and GPU configurations The Blender Benchmark returns a duration not a score so we can use the cost of each benchmark to represent CPI In the graph below we use the n standard with a CPI of as our target resource to which we compare all other configurations This confirms that the highest value configuration to run the Blender Benchmark is the x NVIDIA T GPU configuration running the benchmark in GPU mode Diminishing returnsRendering on multiple GPUs can be more cost effective than on a single GPU The performance boost some renderers can gain from multiple GPUs can exceed that of the cost increase which is linear The performance gains start to diminish as we add multiple Vs therefore the value is also diminished when you factor in the increased cost This observed flattening of the performance curve is an example of Amdahl s Law Adding resources to scale performance can result in a performance increase but only up to a point after which you tend to experience diminishing returns in performance Many renderers are not capable of parallelization and therefore cannot scale linearly as resources are added As with GPU resources the same can be observed across CPU resources In this diagram we observe how benchmark performance gains diminish as the number of ND vCPUs climbs The above diagram shows that performance gains start to diminish above vCPUs where the cost surprisingly drops a bit before climbing again Running the benchmarksTo ensure accurate repeatable results we built a simple programmatic reproducible testing framework that uses simple components of Google Cloud We could also have used an established benchmarking framework such as PerfKit Benchmarker  To observe the raw performance of each configuration we ran each benchmark on a new instance running Ubuntu We ran each benchmark configuration six times in a row discarding the first pass to account for local disk caching or asset load and averaged the results of the remaining passes This method of course doesn t necessarily reflect the reality of a production environment where things like network traffic queue management load and asset synchronization may need to be taken into consideration Our benchmark workflow resembled the following diagram Examining the benchmarksThe renderers we benchmarked all have unique qualities features and limitations Benchmark results revealed some interesting data some of which is unique to a particular renderer or configuration and some of which we found to be common across all rendering software Blender benchmarkBlender Benchmark was the most extensively tested of the benchmarks we ran Blender s renderer called Cycles is the only renderer in our tests that is able to run the same benchmark on both CPU and GPU configurations allowing us to compare the performance of completely different architectures Blender Benchmark is freely available and is open source so you can even modify the code to include your own settings or render scenes The Blender Benchmark includes a number of different scenes to render All our Blender benchmarks rendered the following scenes bmwclassroomfishy catkoropavillon barcelonaYou can learn more about the above scenes on the Blender Demo Files page Download Blender Benchmark version used for this article Blender Benchmark documentationBlender Benchmark public resultsBenchmark observationsBlender Cycles appears to perform in a consistent fashion as resources are increased across all CPU and GPU configurations although some configurations are subject to diminishing returns as noted earlier Next we examine cost With a few exceptions all benchmarks cost between and no matter how many vCPUs or GPUs were used This may be more of a testament to how Google Cloud designed its resource cost model but it s interesting to note that each benchmark performed the exact same amount of work and generated the exact same output Investigating the design of Blender Cycles and how it manages resource usage is beyond the scope of this article however the source code is freely available for anyone to see should they be interested in learning more The CPI of Blender is the inverse of the benchmark cost but comparing it to our target resource the n standard reveals the highest value configurations to be any combination of T GPUs The lowest value resources are the M machine types due to their cost premium and the diminishing performance returns we see in the larger vCPU configurations V Ray benchmarkV Ray is a flexible renderer by ChaosGroup that is compatible with many D and D applications as well as real time game engines V Ray Benchmark is available as a standalone product for free account registration required and runs on Windows Mac OS and Linux V Ray can render in CPU and GPU modes and even has a hybrid mode where it uses both V Ray may run on both CPU and GPU but their benchmarking software renders different sample scenes and uses different units to compare results on each platform CPU uses vsamples GPU uses vpaths We have grouped our V Ray benchmark results into separate CPU and GPU configurations Download V Ray Benchmark version used for this article V Ray Bench documentationV Ray Bench public resultsBenchmark observationsFor CPU renders using mode vray for the benchmark V Ray appears to scale well as the number of vCPUs increases and can take good advantage of the more modern CPU architectures offered on GCP particularly the AMD EPYC in the ND and the Intel Cascade Lake in the M Ultramem machine types Looking at the CPI results there appears to be a sweet spot where you get the most value out of V Ray somewhere between and vCPUs Scores for vCPU configurations all tend to be lower than the average of each machine type and the larger configurations start to see diminishing returns as the vCPU count climbs The M and M Ultramem configurations are well below the CPI of our target resource the n standard as they have a cost premium that offsets their impressive performance If you have the budget however you will get the best raw performance out of these machine types The best value appears to be from the ND standard if your workload can fit into GB of RAM In GPU mode using mode vray gpu cuda V Ray supports multiple GPUs well scaling in a near linear fashion with the number of GPUs It also appears that V Ray is able to take good advantage of the new Ampere architecture on the A GPUs showing a boost in performance over the V This boosted performance comes at a cost however The CPI for the x and xA configurations are only slightly better than the target resource xP and the x x and x configurations get increasingly expensive compared to performance capabilities  As with all the other benchmarks all configurations of the T GPU revealed the highest value GPU in the fleet Octane benchOctane Render by OTOY is an unbiased GPU only renderer that is integrated with most popular D D and game engine applications Octane Bench is freely available for download and returns a score based on the performance of your configuration Scores are measured in Ms s mega samples per second and are relative to the performance of OTOY s chosen baseline GPU the NVIDIA GTX See Octane Bench s results page for more information on how the Octane Bench score is calculated Download Octane Bench version used for this article Octane Bench documentationOctane Bench public resultsBenchmark observationsOctane Render scores relatively high across most GPUs offered on GCP especially the a megagpu g machine type which took the top score in their results when first publicly announced All configurations of the T delivered the most value but P s and A s scored above the target resource Interestingly adding multiple GPUs improved the CPI in all cases which is not always the case with the other benchmarks Redshift renderRedshift Render is a GPU accelerated biased renderer by Maxon and integrates with D applications such as Maya DS Max Cinema D Houdini and Katana Redshift includes a benchmarking tool as part of the installation and the demo version does not require a license to run the benchmark To access the resources below sign up for a free account here Download Redshift version used for this article Redshift Benchmark documentationRedshift Benchmark public resultsBenchmark observationsRedshift Render appears to scale in a linear manner as the number of GPUs is increased When benchmarking on the NVIDIA A GPUs we start to see some limitations Both the xA and xA configurations deliver the same results and are only marginally faster than the xA configuration Such a fast benchmark may be pushing the boundaries of the software itself or may be limited by other factors such as the write performance of the attached persistent disk The NVIDIA T GPUs have the highest CPI by far due to their low cost and competitive compute performance particularly when multiple GPUs are used Unfortunately the limitations noted in the x and xA GPUs result in a lower CPI but this could be due to the limits of this benchmark architecture and example scene TakeawaysThis data can help customers who run rendering workloads decide which resources to use based on their individual job requirements budget and deadline Some simple takeaways from this research If you aren t time constrained and your render jobs don t require lots of memory you may want to choose smaller preemptible configurations with higher CPI such as the ND or E machine types If you re under a deadline and less concerned about cost the M or M machine types for CPU or A machine types for GPU can deliver the highest performance but may not be available as preemptible or may not be available in your chosen region ConclusionWe hope this research helps you better understand the characteristics of each compute platform and how performance and cost can be related for compute workloads Here are some final observations from all the render benchmarks we ran For CPU renders ND machine types appear to provide the best performance at a reasonable cost with the greatest flexibility up to vCPUs on a single VM  For GPU renders the NVIDIA T delivers the most value due to its low price and Turing architecture which is capable of running both RTX and TensorFlow workloads You may not be able to run some larger jobs on the T however as each GPU is limited to GB of memory If you need more GPU memory you may want to look at a GPU type that offers NVLink which unifies the memory of all attached GPUs For sheer horsepower the M machine types offer massive core counts up to vCPUs running at GHz with an astounding amount of memory up to GB This may be overkill for most jobs but a fluid simulation in Houdini or a k architectural render may need the extra resources to successfully complete  If you are in a deadline crunch or need to address last minute changes you can use the CPI of various configurations to help you cost model production workloads When combined with performance metrics you can accurately estimate how much a job should cost how long it will take and how well it will scale on a given architecture The A GPUs in the A machine type offer massive gains over previous NVIDIA GPU generations but we weren t able to run all benchmarks on all configurations The Ampere platform was relatively new when we ran our tests and support for Ampere hadn t been released for all GPU capable rendering software Some customers choose resources based on the demands of their job regardless of value For example a GPU render may require an unusually high amount of texture memory and may only successfully complete on a GPU type that offers NVLink In another scenario a render job may have to be delivered in a short amount of time regardless of cost Both of these scenarios may steer the user towards the configuration that will get the job done rather than the one with the highest CPI No two rendering workloads are the same and no single benchmark can provide the true compute requirements for any job You may want to run your own proof of concept render test to gauge how your own software plugins settings and scene data perform on cloud compute resources Other benchmarking resourcesBear in mind we didn t benchmark other metrics such as disk memory or network performance See the following articles for more information or to learn how to run your own benchmarks on Google Cloud Benchmarking persistent disk performance Benchmarking local SSD performance PerfKitBenchmarker results for Linux and Windows VM instances Using netperf and ping to measure network latency Resource mappings from on premises hardware to Google Cloud Related ArticleCompute Engine explained Choosing the right machine family and typeAn overview of Google Compute Engine machine families and machine types Read Article	2021-02-18 17:20:00