I’m All Bound Up! : A Brief Discussion on What It Means To Be Compute Bound or I/O Bound

Categories:

CUBE-HVPC-512-core-closeup2-1000hWe often get questions from our customers, both ANSYS product and CUBE HVPC users, on how to get their jobs to run faster. Should they get better disk drives or focus on CPU performance. We have found that disk drive performance often gets the blame when it is undeserving. To help figure this out, the first thing we do t is look at the output from an ANSYS Mechanical/Mechanical APDL run. Here is an email, slightly modified to leave the user anonymous, that shows our most recent case of this:

From: David Mastel – PADT, Inc.
To: John Engineering

Subject: Re: Re: Re: Relatively no difference between SSD vs. SAS2 15k RPM solve times?

Hi John, so I took a look at your ANSYS Mechanical output files – Based on the problem you are running the machine is Compute Bound. Here is the process on how I came to that conclusion. Additionally, at the end of this email I have included a few recommendations.

All the best,
David

Example 1:

The bottom section of an ANSYS out file for a 2 x 240GB
Samsung 843 SSD RAID0 array:

Total CPU time for main thread                    :      105.9 seconds
Total CPU time summed for all threads             :      119.1 seconds

Elapsed time spent pre-processing model (/PREP7)  :        0.0 seconds
Elapsed time spent solution – preprocessing       :       10.3 seconds
Elapsed time spent computing solution             :       83.5 seconds
Elapsed time spent solution – postprocessing      :        3.9 seconds
Elapsed time spent post-processing model (/POST1) :        0.0 seconds

Equation solver computational rate                :   319444.9 Mflops
Equation solver effective I/O rate                :    26540.1 MB/sec

Maximum total memory used                         :    48999.0 MB
Maximum total memory allocated                    :    54896.0 MB
Maximum total memory available                    :        128 GB

+—— E N D   D I S T R I B U T E D   A N S Y S   S T A T I S T I C S ——-+

*—————————————————————————*
|                                                                           |
|                       DISTRIBUTED ANSYS RUN COMPLETED                     |
|                                                                           |
|—————————————————————————|
|                                                                           |
|            Release 14.5.7         UP20130316         WINDOWS x64          |
|                                                                           |
|—————————————————————————|
|                                                                           |
| Database Requested(-db)   512 MB    Scratch Memory Requested       512 MB |
| Maximum Database Used     447 MB    Maximum Scratch Memory Used   4523 MB |
|                                                                           |
|—————————————————————————|
|                                                                           |
|        CP Time      (sec) =        119.01       Time  =  15:41:54         |
|        Elapsed Time (sec) =        117.000       Date  =  10/21/2013      |
|                                                                           |
*—————————————————————————*

For a quick refresher on what it means to be compute bound or I/O bound, let’s review what ANSYS Mechanical APDL tells you.

When looking at your ANSYS Mechanical APDL (this file is created during the solve in ANSYS Mechanical, since ANSYS Mechanical is just running ANSYS Mechanical APDL behind the scenes) out files; I/O bound and Compute bound are essentially the following:

I/O Bound:

  1. When Elapsed Time greater than Main Thread CPU time

Compute Bound:

  1. When Elapsed time is equals (approx) to Main Thread CPU time

Example 2:
CUBE HVPC – Samsung 843 – 240GB SATA III SSD 6Gbps – RAID 0
Total CPU time for main thread :  105.9  seconds
Elapsed Time (sec) :   117.000        seconds

CUBE HVPC – Hitachi 600GB SAS2 15k RPM – RAID 0
Total CPU time for main thread  :  109.0 seconds
Elapsed Time (sec) :   120.000       seconds

Recommendations for a CPU compute bound ANSYS server or workstation:

When computers are compute bound I normally recommend the following.

  1. Add faster processors – check!
  2. Use more cores for solve – I think you are in the process of doing this now?
  3. Instead of running SMP go DMP – unable to use DMP with your solve
  4. Add an Accelerator card (NVidia Tesla K20x). Which unfortunately does not help in your particular solving situation.

Please let me know if you need any further information:

David

David Mastel
Manager, Information Technology

Phoenix Analysis & Design Technologies
7755 S. Research Dr, Suite 110
Tempe, AZ  85284
David.Mastel@PADTINC.com

The hardware we have available changes every couple of months or so, but right now, for a user who is running this type of ANSYS Mechanical/Mechanical APDL model, we are recommending the following configuration:

CUBE HVPC Recommended Workstation for ANSYS Mechanical: CUBE HVPC w16-KGPU

CUBE HVPC
MODEL

COST

CHASIS

PROCESSOR

CORES

MEMORY

CUBE HVPC
w16i-kgpu

$ 16,164.00

Mid-Tower
(black quiet edition)

Dual Socket INTEL XEON
e5-2687 v2,
16 cores
@ 3.4GHz

16 = 2 x 8

128GB DDR3-1866 ECC REG

STORAGE

RAID
CONTROLLER

GRAPHICS

ACCELERATOR

OS

OTHER

4 x 240GB
SATA II SSD 6 Gbps
2 x 600GB
SAS2 6Gbps
(2.1 TB)

SMC LSI 2208
6Gbps

NVIDIA
QUADRO K5000

NVIDIA
TESLA K20

Microsoft
Windows 7
Professional 64-bit

ANSYS R14.5.7
ANSYS R15

Cube_logo_Trg_Wide_150w

Here are some references to the some basic information and the systems we recommend:
http://www.intel.com
http://en.wikipedia.org/wiki/CPU_bound
http://en.wikipedia.org/wiki/I/O_bound
http://www.supermicro.com
http://www.cube-hvpc.com
http://www.ansys.com
http://www.nvidia.com

Categories

Get Your Ansys Products & Support from the Engineers who Contribute to this Blog.

Technical Expertise to Enable your Additive Manufacturing Success.

PADT’s Pulse Newsletter

Keep up to date on what is going on at PADT by subscribing to our newsletter.


By submitting this form, you are consenting to receive marketing emails from: . You can revoke your consent to receive emails at any time by using the SafeUnsubscribe® link, found at the bottom of every email. Emails are serviced by Constant Contact

Share this post:

Upcoming Events

11/15/2023

2023 Governor’s Celebration of Innovation Awards

11/15/2023

Twin Builder Updates in Ansys 2023 R2 - Webinar

11/01/2023

Webinar: Additive's Role in Factory 4.0

10/25/2023

Ansys LevelUp 2023

10/25/2023

Nerdtoberfest 2023

10/25/2023

Mechanical Updates in Ansys 2023 R2 (3) - Webinar

10/18/2023

2023 Southern Arizona Tech + Business Expo

10/18/2023

Fluent GPU Solver Updates in Ansys 2023 R2 - Webinar

10/09/2023

Structural Updates in Ansys 2023 R2 (2) - Webinar

10/02/2023

Colorado Life Sciences Innovation Forum 2023

09/27/2023

2023 AZ Bio Awards

09/26/2023

Experience Stratasys Truck Tour - Houston

09/22/2023

AIAA Rocky Mountain Section Technical Symposium 2023

09/22/2023

Experience Stratasys Truck Tour - Dallas, TX

09/21/2023

Accelerating the Energy Transition through Simulation

09/20/2023

3D Printing vs. CNC Machining - Webinar

09/13/2023

Maxwell Updates in Ansys 2023 R2 - Webinar

09/12/2023

Sandia Science & Technology Park 25th Anniversary

09/12/2023

Experience Stratasys Truck Tour - Tempe, AZ

09/08/2023

26th Annual New Mexico Flying 40 Awards

09/08/2023

New Mexico Tech Summit

09/07/2023

New Mexico Tech Summit

08/30/2023

Structures Updates in Ansys 2023 R2 (1) - Mechanical, Post & Graphics

08/23/2023

Improved Injection Molding with Additive - Webinar

08/22/2023

SPIE Optics & Photonics Exhibition 2023

08/16/2023

Fluids Updates in Ansys 2023 R2 - Webinar

08/04/2023

Experience Stratasys Truck Tour - Salt Lake City, Utah

08/01/2023

Experience Stratasys Truck Tour - Denver Colorado

07/26/2023

Solving Supply Chain Issues with Additive - Webinar

07/25/2023

Arizona Tech Leadership Golf Tournament

07/24/2023

Arizona Tech CEO Leadership Retreat

07/19/2023

System Automation & Optimization Updates in Ansys 2023 R1 - Webinar

07/13/2023

2023 AEROSPACE, AVIATION, DEFENSE AND MANUFACTURING CONFERENCE

07/12/2023

Materials Updates in Ansys Granta 2023 R1 - Webinar

06/30/2023

Turbo Expo 2023

06/29/2023

Turbo Expo 2023

06/28/2023

Turbo Expo 2023

06/28/2023

Revolutionize Packaging Design with Additive - Webinar

06/27/2023

Turbo Expo 2023

06/27/2023

2023 E-MOBILITY AND CLEAN ENERGY SUMMIT

06/26/2023

Turbo Expo 2023

06/21/2023

Optics Updates in Ansys 2023 R1 - Webinar

06/07/2023

LS-DYNA Updates in Ansys 2023 R1 - Webinar

05/31/2023

Driving Automotive Innovation with Additive - Webinar

05/24/2023

Hill Air Force Base Tech Expo

05/24/2023

Structural Updates in Ansys 2023 R1 (3) – Structural Optimization & Ex

05/23/2023

CROSSTALK 2023: Emerging Opportunities for Advanced Manufacturing Smal

05/10/2023

Signal & Power Integrity Updates in Ansys 2023 R1 - Webinar

04/26/2023

Additive Manufacturing Updates in Ansys 2023 R1 - Webinar

04/20/2023

38th Space Symposium Arizona Space Industry

More Info

04/19/2023

38th Space Symposium
Arizona Space Industry

04/19/2023

Additive Aids for Manufacturing - Webinar

04/18/2023

38th Space Symposium
Arizona Space Industry

04/17/2023

38th Space Symposium

04/13/2023

Venture Madness 2023

04/12/2023

Fluid Meshing & GPU-Solver Updates in Ansys 2023 R1 - Webinar

03/29/2023

8th Thermal and Fluids Engineering Conference

03/29/2023

Structural Updates in Ansys 2023 R1 - Composites, Fracture & MAPDL

03/28/2023

8th Thermal and Fluids Engineering Conference

03/27/2023

8th Thermal and Fluids Engineering Conference

03/26/2023

8TH Thermal and Fluids Engineering Conference

03/24/2023

Arizona BioPreneur Conference | Spring 2023

03/22/2023

2023 Arizona MedTech Conference

03/22/2023

Optimize Jigs & Fixtures with Additive - Webinar

03/15/2023

3D Design Updates in Ansys 2023 R1 - Webinar

03/08/2023

Competitive Advantages of 1D/3D Coupled Simulation - Webinar

03/01/2023

High Frequency Updates in Ansys 2023 R1 - Webinar

02/22/2023

Additive Advantages in Aerospace - Webinar

02/15/2023

Structural Updates in Ansys 2023 R1 (1) - Webinar

02/09/2023

IME 2023: MD&M | WestPack | ATX | D&M | Plastek

02/08/2023

IME 2023 MD&M | WestPack | ATX | D&M | Plastek

02/07/2023

IME 2023 MD&M | WestPack | ATX | D&M | Plastek

01/27/2023

Arizona Photonics Days, 2023

01/26/2023

Arizona Photonics Days, 2023

01/26/2023

TIPE 3D Printing | 2023

01/26/2023

Venture Cafe Phoenix Talent Night - Job Fari

01/26/2023

VFS 2023 Autonomous/Electric VTOL Symposium

01/25/2023

Arizona Photonics Days, 2023

01/25/2023

Building A.M.- Utah: Kickoff!

01/25/2023

TIPE 3D Printing | 2023

01/25/2023

VFS 2023 Autonomous/Electric VTOL Symposium

01/24/2023

VFS 2023 Autonomous/Electric VTOL Symposium

01/24/2023

TIPE 3D Printing | 2023

01/18/2023

2023 AZ Tech Council Golf Tournament

12/21/2022

Simulation Best Practices for 5G Technology - Webinar

12/14/2022

Digital Twins Updates in Ansys 2022 R2 - Webinar

12/08/2022

Tech the Halls - AZ Tech Council Holiday Mixer

12/07/2022

Electric Vehicle and Other Infrastructure Update Panel

11/30/2022

SPEOS Updates in Ansys 2022 R2 - Webinar

11/23/2022

Simulation Best Practices for Electronics Reliability - Webinar

11/16/2022

Discovery Updates in Ansys 2022 R2

11/10/2022

VentureCafe Phoenix Panel: Venture Capital in AZ

11/08/2022

2022 GOVERNOR’S CELEBRATION OF INNOVATION AWARDS + TECH SHOWCASE

11/03/2022

VentureCafe Phoenix Panel: Angel Investment in AZ

11/02/2022

High & Low Frequency Electromagnetics Updates in Ansys 2022 R2

10/26/2022

Simulation Best Practices For Chip-Package-System Design & Development

10/20/2022

Nerdtoberfest 2022

10/19/2022

2022 Southern Arizona Tech + Business Expo

10/19/2022

LS-DYNA Updates in Ansys 2022 R2 - Webinar

Search in PADT site

Contact Us

Most of our customers receive their support over the phone or via email. Customers who are close by can also set up a face-to-face appointment with one of our engineers.

For most locations, simply contact us: