The Securities Technology Analysis Center (STAC®), an organization that improves technology discovery and assessment in the finance industry through dialog and research, recently audited the STAC-M3™ benchmark suite on Google Cloud (SUT ID KDB211210). These enterprise tick-analytics benchmarks assess the ability of a solution stack such as database software, servers, and storage, to perform a variety of I/O-intensive and compute-intensive operations on historical market data.

Following up on our previous STAC-M3 benchmark audit (SUT ID KDB181001), a redesigned Google Cloud architecture leveraged the most recent version of kdb+ 4.0, the time-series database from KX, and achieved significant improvements: 35 out of 41 benchmarks ran faster in the new cluster – by up to 18x faster than Google Cloud’s prior results. Key highlights include the following:

Compared to the previous STAC-M3 Antuco suite results on Google Cloud:

• Was faster in 13 of 17 mean response-time benchmarks
• Was 18x faster – a 94% reduction in run time – in the version of Year-High Bid that allows caching (STAC-M3.ß1.1T.YRHIBID-2.TIME), which also set an overall record for all published results
• Had 9x higher throughput in Year-High Bid (STAC-M3.ß1.1T.YRHIBID.MBPS)

Compared to the previous STAC-M3 Kanaga suite results on Google Cloud:

• Was faster in 22 of 24 mean response-time benchmarks
• Was over 10x faster in all four Market Snapshot workloads (STAC-M3.ß1.10T.YR[2,3,4,5]-MKTSNAP.TIME)
• Had 5x the throughput in Year-High Bid involving 2 years of data (STAC-M3.ß1.1T.2YRHIBID.MBPS)

“The STAC-M3 standard was designed by financial firms to reveal the performance of tick analytics stacks. Generational improvements like those exhibited by Google Cloud’s most recent STAC-M3 audit, are important data points for firms evaluating new architectures for performance and scale,” said Peter Nabicht, President of STAC.

These performance results may translate to real-world advantages that may be difficult for investment firms to achieve in static and costly on-premises environments: immediate answers in high data velocity markets, more thoroughly explored research theories by adding data or new quantitative approaches, and reduced costs by releasing cloud resources more quickly.

STAC-M3: High-speed tick analytics

Designing for record-breaking results

In our STAC-M3 audit, the stack under test (SUT) was designed to take advantage of horizontal scalability in the cloud by sharding data across independent compute nodes. The cluster of 12 Google Compute Engine N2 instances was powered by Intel Cascade Lake, with each node using 32 vCPUs, 160GiB of memory, and 9TiB of local NVMe SSDs. The full STAC-M3 Antuco and Kanaga data set was split across the cluster and kdb+ scripts distributed queries between nodes.

This configuration was the sweet spot for this particular workload, but this architecture does not need to be limited to 12 nodes for other workloads – the data sharding algorithm could scale to any number of nodes as required by workload demands. Since scaling out the cluster in this manner increases the total pool of available storage, this architecture can continue scaling out to petabytes of storage across hundreds of nodes.

The ability to spawn large clusters with hundreds of thousands of processors on demand at low cost, and to delete the resources when jobs complete, not only changes the economics of running computations on large financial data sets, it also opens up opportunities to explore solutions to new types of problems that were previously overlooked due to the constraints of fixed hardware on-premises. You can check the pricing of this VM configuration using the Google Cloud Pricing Calculator. The costs can be reduced even further by using preemptible VMs.

While the new cluster used a similar number of nodes, cores, and total memory as the previously-audited cluster, the redesigned architecture allowed us to harness the low latency and high throughput of Local NVMe SSDs.

Resources on demand

The cluster was created on demand using Terraform and Ansible during testing and auditing. The use of infrastructure as code (IaC) techniques ensured that the cluster, fully loaded with the STAC-M3 data set, could be created when needed and then removed when benchmarking was complete. It also meant that the cluster configuration was enforced by code on each deployment, eliminating configuration variance and drift. The full IaC definition to create the cluster can be retrieved from the report in the STAC Vault.

Each time the cluster was created, data was streamed to Local SSDs from Google Cloud Storage, our reliable and secure object storage, at up to the line rate of 32Gbps per node. The entire 57TiB STAC-M3 Antuco and Kanaga data was replicated from Cloud Storage to local storage in approximately 20 minutes.

Since each node was independent and responsible for its own shard of data, doubling the cluster size would cut the synchronization time in half, or copy twice as much data in the same amount of time. Using higher bandwidth options of up to 100Gbps would triple the possible throughput for a relatively small incremental cost, trading an approximately 11%-23% price increase at current list prices for a 200% data synchronization performance increase. Taking advantage of fast networking to cache sharded data in parallel to a large cluster makes storing bulk data in Cloud Storage viable for even the largest workloads.

For quants working on vast data sets in sprawling compute clusters, the ability to fully describe infrastructure as declarative code, create elastic resources on demand, cache data quickly from cheap bulk storage, and turn resources off when computations complete is a dramatic change compared to waiting months to grow on-premises clusters – and a compelling reason to use cloud infrastructure.

To see how we designed and optimized the cluster for API-driven cloud resources, read our new whitepaper.

STAC-A2™: Calculating derivatives risk

In 2018, we showed that cloud instances can outperform bare metal when analyzing large tick history data sets in the demanding suite of STAC-M3 benchmarks. Last year, Google Cloud’s partner Appsbroker showed that the same was true for calculating derivatives risk in STAC-A2 on Google Cloud. You can read about how Appsbroker built its record-breaking STAC-A2 compute cluster on Google Cloud in its blog post, or access the STAC Report directly. Here are the highlights:

Compared to all other publicly reported solutions, this solution, based on a cluster of 10 virtual machines, had:

• The highest throughput (STAC-A2.β2.HPORTFOLIO.SPEED)
• The fastest cold time in the large problem size (STAC-A2.β2.GREEKS.10-100k-1260.TIME.COLD)

Compared to a solution involving an 8-node, on-premises cluster (SUT ID INTC181012), this 10-node, cloud-based solution:

• Had 5 times the maximum paths (STAC-A2.β2.GREEKS.MAX_PATHS)
• Had 10% greater throughput (STAC-A2.β2.HPORTFOLIO.SPEED)
• Was 18% faster in cold runs of the large problem size (STAC-A2.β2.GREEKS.10-100k-1260.TIME)
• Was 9% faster in cold runs of the baseline problem size (STAC-A2.β2.GREEKS.TIME.COLD)

Finding market advantages with Google Cloud

Across the investment management industry, every firm is seeking many of the same competitive advantages. However, finding unique opportunities and managing larger and larger data sets is becoming a major strain. Cloud is fundamentally changing how quants tackle the problem while empowering them to manage risk and generate higher returns.

Building on-premises computing clusters with tens or hundreds of thousands of cores and petabytes of storage requires huge up-front investments and lead time measured in months or years. Google Cloud makes the same scale available to its customers, provisioned on demand and paid per use. More importantly, the elasticity of cloud resources enables agility that is simply not available in a fixed data center cluster – the agility to explore, experiment, iterate, and respond to markets faster than before.

Scaling out to tens of thousands of cores in minutes and then removing the resources immediately not only changes the speed at which questions can be answered; it encourages different and more frequent questions, asked simultaneously on many independent clusters, free from the constraints of fixed on-premises hardware.

It is this flexibility and power that enables financial services firms to leverage larger data sets and get results, backtest, research, and analyze large amounts of data, faster and whenever they need it.

Download our whitepaper to learn more about our latest STAC-M3 tick history analytics benchmark results and how to optimize cloud infrastructure for high-speed market data analysis.

The financial services industry is evolving at a rapid pace, with shifting consumer expectations, new technologies, and developing regulatory requirements. Financial services firms need the right technology to help them stay agile and prepare for the future. 

The cloud is a key point of leverage for firms looking to improve performance across a broad range of activities. Moving to the public cloud can advance operational resiliency, improve staff productivity, increase regulatory compliance and enhance business model innovation. 

However, there are a number of financial services companies that are still hesitant in their cloud journeys. The barriers to adoption vary, from the complexity of legacy systems, to trust and skills gaps, regulatory uncertainty, and fragmentation of compliance requirements. Although many companies have embraced the benefits of cloud technology, more robust cloud adoption—especially around core back-office functions—will require additional facilitation, including through regulatory harmonization and streamlining.

A new comprehensive study on cloud adoption in financial services

To better understand the challenges and opportunities of cloud adoption in financial services Google Cloud, together with the Harris Poll, surveyed more than 1,300 leaders from the financial services industry across the United States, Canada, France, Germany, United Kingdom, Hong Kong, Japan, Singapore and Australia. 

There were five noteworthy takeaways from the study:  

1. A vast majority of financial services companies are already using some form of public cloud. A large number of surveyed financial services companies (83%) report they are deploying cloud technology as part of their primary computing infrastructures. Of those using cloud technology, the most popular architecture of choice is hybrid cloud (38%), followed by single cloud (28%), and multicloud (17%). Notably, of respondents without a multicloud deployment, 88% reported they are considering adopting a multicloud strategy in the next 12 months.

2. Financial services institutions in North America are leading in cloud adoption. Of the financial services companies who are implementing a cloud strategy, the highest levels of cloud workload adoption were reported in North America, with institutions in the U.S. (54%) and Canada (52%) leading the way. The lowest level of cloud adoption was reported in Japan (42%).

3. As financial services companies continue to use the cloud, more core functionalities can and will be migrated. While many financial services companies have migrated substantial workloads to the cloud, the industry is far from full adoption when it comes to core, back-office workloads. Of financial services companies currently using a majority cloud strategy in the United States, for example, only half (54%) of their workloads are fully deployed in the cloud. Data and IT security (74%), regulatory reporting (57%), and fraud detection and prevention (57%) rank among the highest workload adoption. Core underwriting activity (40%) and data reconciliation (48%) ranked lowest. Across Europe, cloud usage for core activities like underwriting also scored low with the UK listing only 30% adoption.

4. Among respondents, there is a very strong positive perception of the potential for cloud technology to assist in business operations and regulatory compliance. Nearly all respondents (>88%) agreed that cloud adoption can:

1. help adapt to changing customer behaviors and expectations,  
2. enhance operational resilience, 
3. support the creation of innovative new products and services, 
4. enhance financial services institutions’ data security capabilities, and 
5. better connect siloed legacy software infrastructure within financial services institutions. 

5. Certain regulator-induced challenges, including the complexity of sectorial compliance frameworks and fragmentation, create hurdles to cloud adoption for financial services companies. While 88% of respondents had a positive view of current regulatory efforts to provide guidance and clarity for cloud implementation, the results showed that more needs to be done to facilitate adoption. Most respondents (84%) agree that regulatory reviews and approvals take too long because of regulatory fragmentation across regulatory bodies. And 78% say that regulatory uncertainty over the use of public cloud prevents their organizations from adopting cloud technologies that would otherwise provide benefit to them. Additionally, a third of all on-premises respondents (38%) say that the large investment of resources for the regulatory approval process is a reason why they’re not using cloud services.

“While many banks have already deployed hybrid cloud environments, others are still in various stages of planning and deploying,” said Jerry Silva, research vice president for IDC Financial Insights. “Clearly, hybrid infrastructure is a reality, and financial institutions must focus not only on leveraging the modern infrastructure model to gain efficiencies, resilience and agility, but also on taking the necessary steps to manage such environments, including the security and compliance of cloud services.”

Future recommendations for financial services regulators

Financial services firms should continue to maximize the potential of technology by migrating more core workloads to the cloud, and actively considering multicloud and hybrid-cloud strategies. Such strategies enhance resiliency of existing IT infrastructure and reduce concerns over vendor lock-in. 

The research also points to steps that regulators could take to provide additional clarity and guidance, such as aligning regulatory reviews across agencies to avoid fragmentation; developing regulatory “safe harbors” for cloud adopters based on adherence to accepted standards and best practices; training regulatory staff on emerging tech; and advancing data reporting requirements via cloud and related technologies.

In the past few years, many regulators across the globe have taken a robust approach to rationalizing rules and guidance to cloud adoption in the financial sector, which has helped significantly stimulate adoption. But further assurances and harmonization of best practices around supervision is needed to advance risk-based and secure digital innovation.  

At Google Cloud, we’re committed to working with financial services customers and regulators to provide them with controls and assurances on risk management, data locality, transparency, and compliance. We are constantly engaging with regulators to share information, respond to their considerations and concerns, and address questions in the interest of transparency and building trust. 

To learn more about these findings and more, download our infographic and our full report. 

^{Research methodology}

^{The survey was conducted online by the Harris Poll on behalf of Google Cloud, from December 7, 2020, to January 4, 2021, among 1,363 senior executives in France (n=113), Germany (n=178), the UK (n=192), Hong Kong (n=99), Indonesia (n=100), Japan (n=142), Singapore (n=71), Australia (n=134), Canada (134), and the United States (n=200) who are employed full-time, part-time, or self-employed whose main functional role is in risk/compliance or IT at a company in the banking, finance, or financial services industry with a title of director level or higher. The data in each country were weighted by the number of employees to bring them into line with actual company size proportions in the population. A global post-weight was applied to ensure equal weight of each country in the global total.}

When moving software applications from on-premise hardware to the cloud, it often “just works,” but it’s never guaranteed. This is especially the case for applications that are hardware intensive. This blog post examines what happened when a media company took software for real-time video broadcasts into the cloud. We’ll share how we, Google Cloud, collaborated with media software provider Vizrt to meet the demanding requirements of an eSports broadcaster. Together, we delivered a solution that not only met but exceeded the expected performance from a cloud-based deployment.

Video broadcasting in the cloud

Video broadcasts are a very hardware-intensive workflow. By needing to process and store data streams in near-real-time, broadcasts stress GPU, memory, disk, and CPU. In addition, the performance requirements quickly increase as producers add additional video streams into the mix, such as in this case, an eSports broadcast.

Vizrt’s customer wanted to increase their broadcast production by doubling the amount of camera feeds from 8 to 16, to have a more compelling and elaborate production.

At the heart of the eSports broadcasters’ production was Viz Vectar Plus, Vizrt’s software-based 4K switcher. While the client wanted to move more of its production into the cloud, Viz Vectar Plus was designed initially for on-premise hardware. So, when they tried a straightforward “lift and shift ” to the cloud, it surprised no one that the software didn’t run as well. They turned to Google Cloud and Vizrt to make it run the way they needed it to. 

Troubleshooting lift and shift

Initially, we suspected that the issue could be in the design of the cloud deployment, i.e., the configuration of the VM hosting the software. So the focus of our troubleshooting was to find a cloud configuration that 1) made sure the software worked to spec and 2) did so optimally considering costs, robustness, and performance. Furthermore, we wanted to ensure that all components met performance specifications, particularly throughput, IOPS, and network bandwidth, as this was a video media application. Only after we validated the cloud deployment would we ask Vizrt to investigate the code itself. We would:

1. Set up a test environment.
2. Benchmark the environment.
3. Test various configurations.
4. Validate that the vendor software was optimally using the configuration.  

This high-level methodology is straightforward. However, we approached the details in a particular order, considering we were optimizing for broadcast video. We honed in on the optimal cloud configuration by testing the following elements, prioritized in order of expected impact:  

1. VM type: The VM type largely dictates the available memory and CPU configurations. However, because this was a VM workflow, we had to pick N1’s. Today, they are the only VM type that can be attached to GPUs, which are practically a requirement for broadcast video.  
2. Disk type: Video broadcasts require high I/O speeds to handle high-quality video streams. We went from an HDD to a much-faster SSD. 
3. CPU size: We increased the VM CPU cores from 16 in increments up to 32. Increasing CPU size indeed increased performance, but did not return the level of performance we needed.
4. SSD size: We increased the SSD size (and the accompanying higher IOPS and throughput that comes with increasing the size) enabling more simultaneous recordings. Again, this only partially worked. 
5. Disk count. We noticed read/write problems when the application was reading/writing with a single drive. There are two typical ways to approach this: 1) Separate read/writes tasks among two discs and 2) striping the data streams across discs. Implementing these had improved but marginal improvements in performances.  

After our testing, we arrived at the following optimal configuration:

• VM: n1-standard-32 instance w/ 500Gb boot drive
• GPU: 1 T4 GPU 
• SSD: 1 persistent disk with 1TB*

* We would later determine that two SSDs for separate read and write operations would be more optimal

This configuration was able to produce between 6 – 12 streams. Compared to the on-premise target of 8 streams, this was about as good but was not the customer’s target of 16. So we would need Vizrt to take the ball from here to optimize the software itself.

Optimizing media applications for cloud

We provided Vizrt our recommended configuration, performance notes, and the following best practices that are generally applicable to cloud-based video workloads:

• Separate read and write operations to two different disks to enable higher performance for both operations. 
• A second 1 TB SSD persistent disk can be attached to the VM instance to increase performance.

With this information, Vizrt engineers worked their magic, providing daily patches to test; with each daily iteration the overall solution was found quickly. Not only were they able to meet the broadcaster’s request of 16 feeds, but they were also able to go even further to 44. Over a 5x improvement by optimizing for the cloud! 

Teamwork in troubleshooting 

Because of the specialized nature of media and entertainment, workflow situations across multiple companies are common as specialized applications hand their work from one to another. 

“By working in partnership with Google Cloud we managed to build a system that can scale in ways that probably none of us thought would be possible. This allowed Viz Vectar Plus to run fully in the cloud using NDI and opened up amazing possibilities for making shows,” Dr. Andrew Cross, President R&D, Vizrt Group. “We ended up with great feedback from the customer, who were appreciative of how Google Cloud and Vizrt collaborated on a solution.”

The results speak for themselves: A satisfied customer with over a 5x improvement in results. That’s what we call a good game.

Bootstrap your Startup with our technical guided series

At Google Cloud, we want to provide you with the access to all the tools you need to grow your business. Through the Google Cloud Technical Guides for Startups, leverage industry leading solutions with how-to video guides and resource handbooks curated for startups.

This multi-series contains 3 chapters: Start, Build and Grow, which matches your startup’s stage of growth:

• The Start Series: Begin by building, deploying and managing new applications on Google Cloud from start to finish.
• The Build Series: Optimize and scale existing deployments to reach your target audiences.
• The Grow Series: Grow and attain scale with deployments on Google Cloud.

Kick off with The Start Series

The Start Series is designed to help your startup begin building, deploying and managing new applications on Google Cloud from start to finish. The series contains 12 videos and is dedicated to those who are starting out their cloud journey with Google Cloud. From setting up your project, to choosing the right compute option, to configuring your networking to managing your databases, and understanding support and billing – the Start Series guides you at every step of the journey.

Check out our website and our Google Cloud Technical Guides for Startups full playlist.

Coming up next – The Build Series

Launch into the next part of the journey continuing from the Start Series, with the upcoming Build Series, where we will be focusing on the optimization and scaling of existing deployments to help your startups reach your target audiences.

Join us by checking out the video series on the Google Cloud Tech channel, and subscribe to stay up to date.

See you in the cloud!

Meeting the rapidly growing demands of our customers’ high performance computing and data-intensive workloads requires deep innovation — at Google Cloud, we know we can’t rely on ever-faster CPUs alone, like Moore’s Law has enabled in the past. Customers can either optimize their workloads for a given platform, or we can offer them a platform that is optimized for their specific needs. At Google Cloud, we choose the latter.

Today, we have an exciting new release resulting from these efforts: the new C3 machine series powered by the 4th Gen Intel Xeon Scalable processor and Google’s custom Intel Infrastructure Processing Unit (IPU). Along with the recently announced Hyperdisk block storage which offers 80% higher IOPS per vCPU for high-end database management system (DBMS) workloads when compared to other hyperscalers. C3 machine instances can deliver strong performance gains to enable high performance computing and data-intensive workloads. Customers such as Snap, for example, have seen approximately a 20% increase in performance for a key workload over the previous generation C2.

The C3 machine series is just the latest example of this architectural approach. For over two decades, Google has purpose-built and designed some of the world’s most efficient and scalable computing systems to meet the needs of our customers. We built the Tensor Processing Unit (TPU) to power real-time voice search, photo object recognition, and interactive language translation; unveiled Titan, a secure, low-power microcontroller to help ensure that every machine boots from a trusted state; and launched Video Coding Units (VCUs) to enable video distribution that addresses a range of formats and client requirements. We engineer golden paths from silicon to the console, using a combination of purpose-built infrastructure, prescriptive architectures, and an open ecosystem to deliver what we term workload-optimized infrastructure.

Getting to know the C3 machine series

The Compute Engine C3 machine series, now available in Private Preview, is the first VM in the public cloud with the 4th Gen Intel Xeon Scalable processor and with Google’s custom Intel IPU. C3 machine instances use offload hardware for more predictable and efficient compute, high-performance storage, and a programmable packet processing capability for low latency and accelerated, secure networking.

“We are pleased to have co-designed the first ASIC Infrastructure Processing Unit with Google Cloud, which has now launched in the new C3 machine series. A first of its kind in any public cloud, C3 VMs will run workloads on 4th Gen Intel Xeon Scalable processors while they free up programmable packet processing to the IPUs securely at line rates of 200Gb/s. This Intel and Google collaboration enables customers through infrastructure that is more secure, flexible, and performant.” – Nick McKeown, Senior Vice President, Intel Fellow and General Manager of Network and Edge Group

The System on a Chip hardware architecture introduced in C3 VMs can enable better security, isolation, and performance. In the future, this purpose-built architecture will also allow us to offer a richer product portfolio, such as support for native bare-metal instances.

Hyperdisk block storage and 200 Gbps networking

Block storage and VMs go hand in hand. Last month, we announced the Preview release of Hyperdisk, our next-generation block storage. The new architecture decouples compute instance sizing from storage performance to deliver 80% higher IOPS per vCPU than other leading hyperscale cloud provider. And compared with the previous generation C2, C3 VMs with Hyperdisk deliver 4x higher throughput and 10x higher IOPS. Now, you don’t have to choose expensive, larger compute instances just to get the storage performance you need for data workloads such as Hadoop and Microsoft SQL Server.

To enable high performance computing workloads, C3 VMs also feature 200 Gbps low-latency networking powered by our custom IPU, as well as line-rate encryption using the open source PSP protocol.

What our customers and partners are saying

“We were pleased to observe a 20% increase in performance over the current generation C2 VMs from Google Cloud in testing with one of our key workloads. These continued performance improvements enable better end user experience and application cost efficiency.” – Aaron Sheldon, Sr. Software Engineer, Snap Inc.

“Based on the initial performance data, running weather research and forecasting (WRF) on C3 clusters can deliver as much as 10x quicker time to results for about the same computational cost. This will significantly accelerate R&D for our customers in weather, environment, and engineering domains.” — Michael Wilde, CEO, Parallel Works Inc.

“In early testing with our flagship products, including Ansys Fluent, Mechanical and LS-DYNA, on the new Google Cloud C3 VM, we’re seeing up to 3x performance gains over C2 VMs due to higher memory bandwidth and lower network latency.” – Shane Emswiler, Senior Vice President of Products, Ansys

Where we are headed

With the exponential rise in the complexity of cloud infrastructure, we as an industry must turn to automation to manage these platforms efficiently at scale. Along with Infrastructure as Code, custom chips like the Titan, the TPU and the IPU, pave the way for a not-so-distant future where we’ll automate over half of all infrastructure decisions, configuring systems dynamically in response to usage patterns. At Google Cloud, we are committed to continuing our long history of hardware innovation with a focus on workload optimization and automation.

To learn more about C3 VMs and Hyperdisk, check out our session at NEXT ‘22, How Google Cloud optimizes infrastructure for your workloads. To request access to the C3 VMs or Hyperdisk, please reach out to your sales representative or account manager.