Start-up Aims AI at Automated Tuning of Complex Systems

By Doug Black

February 22, 2018

Today’s bigger, more complex, connected and intelligent systems have an exponentially higher number of connections, dependencies, interfaces, protocols and processing architectures that, if not optimized, will hamstring performance. For performance engineers still using manual tuning methods, systems optimization is a time-eating hydra-headed monster that poses a virtually infinite number of possible adjustments and configurations for trial-and-error testing.

Enter AI.

Start-up Concertio today launched what it said is the first machine learning-based tool aimed at making applications and systems operate for maximized performance by optimizing the myriad of configuration settings used in complex systems. While its initial product, Optimizer Studio, automates systems diagnostics and generates a “grocery list” of adjustments that systems engineers and IT managers then review and implement, the next iteration of the technology (Optimizer Runtime) will automate both diagnostics and tuning implementation.

None less than Mellanox has tested Concertio’s effectiveness on its own networking technology. As part of today’s launch, Concerto announced the results of a test involving Mellanox’s ConnectX-3 Pro Ethernet cards that compared performance after automated testing by Optimizer Studio against manual tuning methods used by Mellanox performance engineers.

The network cards were delivered in their off-the-shelf default settings, and then the Mellanox engineers and Concertio were informed of the workload the cards would be used for. Optimizer Studio ran against nine ConnectX-3 Pro specific knobs representing millions of option combinations. The tool’s workload classification engine and reinforcement learning techniques modeled the target workload, detecting different workload phases, and experimenting with various knob configurations in each phase. It then produced a report showing the optimal settings for the specific use-case.

The test result: Concertio won.

“In the comparison test, Optimizer Studio’s automated run improved performance in the target use-case by 80 percent, surpassing the 62 percent we achieved by manual tuning,” said Amir Ancel, performance group director at Mellanox. “Optimizer Studio’s automated tuning algorithms allow us to focus on high-level optimization, leaving the mundane low-level parameter optimizations to software.”

Built for traditional datacenters, hyperscale datacenters and high-performance computing systems in the cloud or on-premises, Optimizer Studio monitors and learns from the interactions between applications and systems, according to Concertio.

As of now, the tools support Linux-based systems running on Intel CPUs. Concertio said it intends to broaden its portfolio of supported technologies in upcoming product iterations.

“Tuning used to be easy,” Dr. Tomer Morad, Concertio co-founder and CEO, shared. “There were only a handful of knobs, and you’d put a performance engineer on that and tweak some settings and get some good results. But today we are already in the hundreds of knobs. It’s exploding and become almost impossible to get to a very good result because the parameter space is practically limitless. If you have 100 binary knobs it’s practically limitless, you cannot check everything. So you need some kind of automatic tool to help you with that.”

Tuning variables, called tunable knobs, include settings across hardware, firmware, the operating system and applications such as:

  • CPU hardware, including symmetric multi-threading, cache prefetching and cache partitioning configuration; peripheral hardware, including PCIe maximum read request size, network interrupt affinity and network task offloading
  • Firmware, including power states of the CPU
  • Operating system, including choice of IO or task scheduler, NUMA balancing and memory migration, thread affinity and page cache
  • Applications, including application framework settings (e.g., Spark), application component (e.g., MongoDB database) settings, and application-defined knobs

With so many variables, Morad said, performance engineers can’t be expected to know about all of the available knobs, and to predict their effects on one another. IT professionals must also occasionally tune their systems, but it’s difficult for them to maintain experts on all system internals, he said. Too often, engineers test and set optimal settings for a few knobs they are more familiar with, leaving the rest in default settings that were in place when the equipment was delivered. In some cases, he said, system tuning is overlooked entirely due to the complexity involved, and systems remain at inefficient under-performing factory settings.

Beyond application performance tuning, Morad said the tool can be used for cutting cloud and data center costs by finding system configurations that use fewer resources, and it can be utilized by hardware and software product vendors to identify optimized off-the-shelf configurations for shipment to customers or reseller. It also can be used for maximizing public benchmark performance for marketing purposes (including LINPACK).

Privately-held Concertio (previously called DatArcs) was founded in 2016 and is based in New York City. The company is part of the Runway Program at the Jacobs Technion-Cornell Institute of Cornell Tech in New York, and it’s with the Intel Ingenuity Partner Program.

“Tailor-tuned systems can significantly outperform baseline general-purpose systems, but the number of configurable settings has reached into the hundreds – way too many for any human team to effectively tune and test,” said Concertio co-founder and CTO Andrey Gelman. “It used to be merely a gap that could be bridged by human tuning and testing, but with the increasing hardware and software complexity, it’s exploding into a chasm where human performance tuning is netting diminishing returns, leaving these expensive systems bottlenecked and inefficient.”

A version of this article originally appeared on our sister site, EnterpriseTech.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

NSF Extends Access to Its Leadership Systems Blue Waters & Frontera

December 14, 2018

The National Science Foundation is seeking supplemental requests for access on its leadership-class computers Blue Waters and Frontera to enable "fundamental science and engineering research that would otherwise not be p Read more…

By Staff

CFD on ORNL’s Titan Simulates Cleaner, Low-MPG ‘Opposed Piston’ Engine

December 13, 2018

Pinnacle Engines is out to substantially improve vehicle gasoline efficiency and cut greenhouse gas emissions with a new motor based on an “opposed piston” design that the company hopes will be widely adopted while t Read more…

By Doug Black

Contract Signed for New Finnish Supercomputer

December 13, 2018

After the official contract signing yesterday, configuration details were made public for the new BullSequana system that the Finnish IT Center for Science (CSC) is procuring from Atos in two phases over the next year-an Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

AI Can Be Scary. But Choosing the Wrong Partners Can Be Mortifying!

As you continue to dive deeper into AI, you will discover it is more than just deep learning. AI is an extremely complex set of machine learning, deep learning, reinforcement, and analytics algorithms with varying compute, storage, memory, and communications needs. Read more…

IBM Accelerated Insights

4 Ways AI Analytics Projects Fail — and How to Succeed

“How do I de-risk my AI-driven analytics projects?” This is a common question for organizations ready to modernize their analytics portfolio. Here are four ways AI analytics projects fail—and how you can ensure success. Read more…

Nvidia Leads Alpha MLPerf Benchmarking Round

December 12, 2018

Seven months after the launch of its AI benchmarking suite, the MLPerf consortium is releasing the first round of results based on submissions from Nvidia, Google and Intel. Of the seven benchmarks encompassed in version Read more…

By Tiffany Trader

Contract Signed for New Finnish Supercomputer

December 13, 2018

After the official contract signing yesterday, configuration details were made public for the new BullSequana system that the Finnish IT Center for Science (CSC Read more…

By Tiffany Trader

Nvidia Leads Alpha MLPerf Benchmarking Round

December 12, 2018

Seven months after the launch of its AI benchmarking suite, the MLPerf consortium is releasing the first round of results based on submissions from Nvidia, Goog Read more…

By Tiffany Trader

IBM, Nvidia in AI Data Pipeline, Processing, Storage Union

December 11, 2018

IBM and Nvidia today announced a new turnkey AI solution that combines IBM Spectrum Scale scale-out file storage with Nvidia’s GPU-based DGX-1 AI server to pr Read more…

By Doug Black

Mellanox Uses Univa to Extend Silicon Design HPC Operation to Azure

December 11, 2018

Call it a corollary to Murphy’s Law: When a system is most in demand, when end users are most dependent on the system performing as required, when it’s crunch time – that’s when the system is most likely to blow up. Or make you wait in line to use it. Read more…

By Doug Black

Topology Can Help Us Find Patterns in Weather

December 6, 2018

Topology--the study of shapes--seems to be all the rage. You could even say that data has shape, and shape matters. Shapes are comfortable and familiar concepts, so it is intriguing to see that many applications are being recast to use topology. For instance, looking for weather and climate patterns. Read more…

By James Reinders

Zettascale by 2035? China Thinks So

December 6, 2018

Exascale machines (of at least a 1 exaflops peak) are anticipated to arrive by around 2020, a few years behind original predictions; and given extreme-scale performance challenges are not getting any easier, it makes sense that researchers are already looking ahead to the next big 1,000x performance goal post: zettascale computing. Read more…

By Tiffany Trader

Robust Quantum Computers Still a Decade Away, Says Nat’l Academies Report

December 5, 2018

The National Academies of Science, Engineering, and Medicine yesterday released a report – Quantum Computing: Progress and Prospects – whose optimism about Read more…

By John Russell

Revisiting the 2008 Exascale Computing Study at SC18

November 29, 2018

A report published a decade ago conveyed the results of a study aimed at determining if it were possible to achieve 1000X the computational power of the the Read more…

By Scott Gibson

Quantum Computing Will Never Work

November 27, 2018

Amid the gush of money and enthusiastic predictions being thrown at quantum computing comes a proposed cold shower in the form of an essay by physicist Mikhail Read more…

By John Russell

Cray Unveils Shasta, Lands NERSC-9 Contract

October 30, 2018

Cray revealed today the details of its next-gen supercomputing architecture, Shasta, selected to be the next flagship system at NERSC. We've known of the code-name "Shasta" since the Argonne slice of the CORAL project was announced in 2015 and although the details of that plan have changed considerably, Cray didn't slow down its timeline for Shasta. Read more…

By Tiffany Trader

IBM at Hot Chips: What’s Next for Power

August 23, 2018

With processor, memory and networking technologies all racing to fill in for an ailing Moore’s law, the era of the heterogeneous datacenter is well underway, Read more…

By Tiffany Trader

House Passes $1.275B National Quantum Initiative

September 17, 2018

Last Thursday the U.S. House of Representatives passed the National Quantum Initiative Act (NQIA) intended to accelerate quantum computing research and developm Read more…

By John Russell

Summit Supercomputer is Already Making its Mark on Science

September 20, 2018

Summit, now the fastest supercomputer in the world, is quickly making its mark in science – five of the six finalists just announced for the prestigious 2018 Read more…

By John Russell

AMD Sets Up for Epyc Epoch

November 16, 2018

It’s been a good two weeks, AMD’s Gary Silcott and Andy Parma told me on the last day of SC18 in Dallas at the restaurant where we met to discuss their show news and recent successes. Heck, it’s been a good year. Read more…

By Tiffany Trader

US Leads Supercomputing with #1, #2 Systems & Petascale Arm

November 12, 2018

The 31st Supercomputing Conference (SC) - commemorating 30 years since the first Supercomputing in 1988 - kicked off in Dallas yesterday, taking over the Kay Ba Read more…

By Tiffany Trader

TACC’s ‘Frontera’ Supercomputer Expands Horizon for Extreme-Scale Science

August 29, 2018

The National Science Foundation and the Texas Advanced Computing Center announced today that a new system, called Frontera, will overtake Stampede 2 as the fast Read more…

By Tiffany Trader

Leading Solution Providers

SC 18 Virtual Booth Video Tour

Advania @ SC18 AMD @ SC18
ASRock Rack @ SC18
DDN Storage @ SC18
HPE @ SC18
IBM @ SC18
Lenovo @ SC18 Mellanox Technologies @ SC18
NVIDIA @ SC18
One Stop Systems @ SC18
Oracle @ SC18 Panasas @ SC18
Supermicro @ SC18 SUSE @ SC18 TYAN @ SC18
Verne Global @ SC18

HPE No. 1, IBM Surges, in ‘Bucking Bronco’ High Performance Server Market

September 27, 2018

Riding healthy U.S. and global economies, strong demand for AI-capable hardware and other tailwind trends, the high performance computing server market jumped 28 percent in the second quarter 2018 to $3.7 billion, up from $2.9 billion for the same period last year, according to industry analyst firm Hyperion Research. Read more…

By Doug Black

Contract Signed for New Finnish Supercomputer

December 13, 2018

After the official contract signing yesterday, configuration details were made public for the new BullSequana system that the Finnish IT Center for Science (CSC Read more…

By Tiffany Trader

Nvidia’s Jensen Huang Delivers Vision for the New HPC

November 14, 2018

For nearly two hours on Monday at SC18, Jensen Huang, CEO of Nvidia, presented his expansive view of the future of HPC (and computing in general) as only he can do. Animated. Backstopped by a stream of data charts, product photos, and even a beautiful image of supernovae... Read more…

By John Russell

Germany Celebrates Launch of Two Fastest Supercomputers

September 26, 2018

The new high-performance computer SuperMUC-NG at the Leibniz Supercomputing Center (LRZ) in Garching is the fastest computer in Germany and one of the fastest i Read more…

By Tiffany Trader

Houston to Field Massive, ‘Geophysically Configured’ Cloud Supercomputer

October 11, 2018

Based on some news stories out today, one might get the impression that the next system to crack number one on the Top500 would be an industrial oil and gas mon Read more…

By Tiffany Trader

Intel Confirms 48-Core Cascade Lake-AP for 2019

November 4, 2018

As part of the run-up to SC18, taking place in Dallas next week (Nov. 11-16), Intel is doling out info on its next-gen Cascade Lake family of Xeon processors, specifically the “Advanced Processor” version (Cascade Lake-AP), architected for high-performance computing, artificial intelligence and infrastructure-as-a-service workloads. Read more…

By Tiffany Trader

Google Releases Machine Learning “What-If” Analysis Tool

September 12, 2018

Training machine learning models has long been time-consuming process. Yesterday, Google released a “What-If Tool” for probing how data point changes affect a model’s prediction. The new tool is being launched as a new feature of the open source TensorBoard web application... Read more…

By John Russell

The Convergence of Big Data and Extreme-Scale HPC

August 31, 2018

As we are heading towards extreme-scale HPC coupled with data intensive analytics like machine learning, the necessary integration of big data and HPC is a curr Read more…

By Rob Farber

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This