• Skip to main content
  • Skip to search
  • Skip to footer
Cadence Home
  • This search text may be transcribed, used, stored, or accessed by our third-party service providers per our Cookie Policy and Privacy Policy.

  1. Community Forums
  2. Simufact
  3. Help New Workstation

Following Cadence Design Systems’ acquisition of the Design & Engineering (D&E) business, the D&E Community Forum on the Nexus Community Center has been migrated in the Cadence Physical System Simulation Community. For more details and if you have any questions, please refer to the FAQ.

Stats

  • State Not Answered
  • Replies 1
  • Subscribers 2
  • Views 14
  • Members are here 0
More Content

Help New Workstation

Vjekoslav Keckes
Vjekoslav Keckes 6 months ago

I need assistance selecting a new high‑performance workstation for running multiple warm‑forming simulations in parallel.

I can't find any informations in this.


My current system (Intel i9‑9960X, 64 GB RAM, Nvidia Quadro P4000) is becoming too slow.

I typically run up to three simulations at the same time, each using 120,000–200,000 surface‑mesh elements with 1 mm size. Parallelization is enabled, but I am not fully aware of its actual performance impact.

For the new workstation, I want to maximize performance and need guidance on:

  • CPU choice: Intel 285K vs. AMD Threadripper – which is better for my workloads?
  • Single‑core vs. multi‑core performance: Which one is more important for my simulation sizes?
  • Platform bandwidth: Is a CPU with 2 lanes sufficient, or should I choose a workstation-class platform with 4 lanes (more memory channels, faster SSDs, multi‑GPU options)?
  • GPU relevance: Does the graphics card significantly influence simulation speed, or mainly visualization?
  • Memory requirements: Should I use 64 GB or 128 GB RAM for running several simulations in parallel?
  • Intel vPro: Do I need Intel vPro features for my use case?

My goal is to get maximum performance for current and future simulation workloads.

Is it possible to estimate how much faster the system can become?
  • Sign in to reply
  • Cancel
  • abdullah.kzzo
    0 abdullah.kzzo 6 months ago

    Hello Vjekoslav Keckes,

    In the release notes, you can find detailed information about the supported hardware. However, I would like to highlight a few key points regarding your questions.

    • Simufact Forming is certified for both Intel and AMD processors (a list of certified CPUs is provided in the release notes). Therefore, both the Intel 285K and AMD Threadripper are strong options. Just for your information: the Intel 285K has only 8 performance cores and 16 efficient cores. When running 2 to 3 simulations with parallelization, that becomes limiting quite quickly. However, its frequency is very high, and single‑core performance is important. I have no idea how many performance cores the AMD Threadripper has.
    • Since your workload involves running multiple simulations in parallel, multi-core performance is highly recommended. The number of cores required depends on your typical usage. For example, if you usually run four simulations simultaneously with eight cores each, a system with at least 32 cores is recommended. Additionally, it is advisable to reserve one or two extra cores for the operating system.
    • According to the release notes, a minimum of 32 GB of RAM is recommended for industrial use. However, based on your workload, 64–128 GB would be more appropriate. You can start with 64 GB, but ensure that the system has available slots for future expansion to 128 GB or more. It is especially important to monitor RAM usage in Task Manager while running representative simulations, as this will help you choose a configuration that provides sufficient headroom.
    • Regarding your question about 2 or 4 lanes: I don’t really have a definite answer. More lanes are certainly better, but it’s unclear how much this will actually affect performance. I think it would mainly influence remeshing performance, since the solver itself runs on the CPU and RAM. I would expect the manufacturer to choose a suitable number of lanes for the system.
    • GPU selection mainly affects visualization, as the solver itself does not utilize the GPU.
    • Faster SSDs can help reduce:
      • Import/export times
      • Writing large result files
      • Loading geometries
    However, they do not significantly impact solver performance, since computations are performed in CPU and RAM.
    • Intel vPro features are generally relevant for IT management and security and do not provide direct performance benefits for simulation workloads.

    At this stage, we cannot reliably estimate the exact performance improvement, as it strongly depends on the specific simulation models and configurations.

    Best Regards
    Abdullah Kzzo

    • Cancel
    • Vote Up 0 Vote Down
    • Sign in to reply
    • Verify Answer
    • Cancel
Cadence Guidelines

Community Guidelines

The Cadence Design Communities support Cadence users and technologists interacting to exchange ideas, news, technical information, and best practices to solve problems and get the most from Cadence technology. The community is open to everyone, and to provide the most value, we require participants to follow our Community Guidelines that facilitate a quality exchange of ideas and information. By accessing, contributing, using or downloading any materials from the site, you agree to be bound by the full Community Guidelines.

© 2026 Cadence Design Systems, Inc. All Rights Reserved.

  • Terms of Use
  • Privacy
  • Cookie Policy
  • US Trademarks
  • Do Not Sell or Share My Personal Information