Download PDF
[PDF 224KB]
Incremental performance gains for engineering simulations can improve productivity and shrink product development timelines and time to market. Doubling performance can transform entire workflows, allowing design teams to run more and larger simulations in less time to improve innovation, quality, safety, reliability, manufacturability, and time to market.
ANSYS and Intel worked closely together to deliver up to 2.2x higher performance, for ANSYS Mechanical by optimizing the application code for the multi-core Intel® Xeon® processor E5-2600 v2 and v3 families and the many-core Intel® Xeon Phi™ coprocessor. The combination offers tremendous new performance potential for structural mechanics simulations, at relatively low cost and without altering the end-user experience or complicating the IT environment.
A Smarter, Faster Pathway to High Quality Designs
ANSYS Mechanical software is a comprehensive Finite Element Analysis (FEA) tool for structural analysis, including linear, nonlinear, and dynamic studies. Design and analysis teams can take advantage of user-friendly tools and an extensive assortment of element libraries and structural simulation options to explore a wide range of mechanical design problems.
ANYS Mechanical also offers thermal analytics and coupled-physics capabilities for acoustic, piezoelectric, thermal-structural, and thermoelectric analysis. The quality and flexibility of the simulation environment makes it possible to predict product behavior and reliability across a wide range of complex, real-world scenarios.
Dramatic Performance Gains with Intel Xeon Phi Coprocessors
The Intel Xeon processor E5-2600 v3 family provides core-optimized processors with up to 18 cores at 2.3 GHz per processor socket to speed performance for highly parallel applications and up to 3.5 GHz frequency-optimized processors with lower core counts. An Intel Xeon Phi coprocessor delivers extremely high levels of parallelism with up to 61 cores and 244 threads.
ANSYS worked with Intel to optimize ANSYS Mechanical for the latest Intel® processor and coprocessor innovations using Intel® Software Development products, such as the Intel® Math Kernel Library (MKL), Intel® compilers, and the Intel® VTune™ Performance Analyzer. Based on these efforts, both the Windows* and Linux* versions of ANSYS Mechanical 16.0 (including the SMP and DMP versions of each) can utilize one or more Intel Xeon Phi coprocessors when present on the server or workstation platform. Highly parallel matrix mathematics code segments are offloaded to the coprocessor to increase throughput. The application workload is automatically balanced across the processors and coprocessor to optimize total throughput.
ANSYS and Intel engineers ran benchmarks to measure the performance benefits across a mix of current and previous generation software and hardware (two-socket servers). The following results indicate the performance gains achieved in each upgrade scenario:
- Upgrade previous-generation hardware and add a coprocessor for up to 3.1x higher performance1,2. Gains of up to 3.1x were achieved for ANSYS Mechanical 16.0 DMP when upgrading from the Intel Xeon processor E5-2600 v2 family to the Intel Xeon processor E5-2600 v3 family and adding one or more Intel Xeon Phi coprocessors.
- Add one or more coprocessors to a current-generation hardware/software platform for up to 1.7x higher performance1,2. Adding an Intel Xeon Phi coprocessor to a server powered by the Intel Xeon E5-2600 v3 family increased performance by up to 1.7x for ANSYS Mechanical 16.0. You can add an additional Intel Xeon Phi coprocessor for even greater performance.
Increasing Value through Ongoing Collaboration
Future Intel Xeon processors and Intel Xeon Phi coprocessors will continue to raise the bar for performance, parallelism, and energy-efficiency. ANSYS and Intel will continue to work together to deliver optimized and tested solutions that deliver better value together. Since ANSYS licensing models allow no-cost upgrades to the latest software releases, refreshing to the latest Intel server platforms provides a reliable, low-risk method for regularly increasing the overall capability and value of mission-critical simulation tools.
ANSYS Mechanical 16.0 V15ln-2 DMP
1 Source: Intel and ANSYS performance tests, October 2014. Previous-generation server configuration: 2 x Intel® Xeon® processor E5-2697 v2 (12 cores, 2.7 GHz, 8GT/s, 130W), 64 GB DDR3-1600 MHz memory (8 x 8GB), 1 x 600 GB SAS HDD storage, Red Hat Enterprise Linux Server release 6.5, ANSYS Mechanical 16.0 DMP. New server configuration: 2 x Intel® Xeon® processor E5-2697 v3 (14 cores, 2.6 GHz, 9.6 GT/s, 145W), 64 GB DDR4-2133 MHz memory (8 x 8GB), Intel® Data Center Solid-State Drive S35000 Series 800 GB, Red Hat Enterprise Linux Server release 6.5, ANSYS Mechanical 16.0 DMP. Performance measured on each system with and without one Intel® Xeon Phi™ 7120 coprocessor.
2 Software and workloads used in performance tests may have been optimized for performance only on Intel microprocessors. Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products.