F5F Stay Refreshed Hardware Desktop Required processor for CFD workstation

Required processor for CFD workstation

Required processor for CFD workstation

P
pafrickstump
Member
62
06-10-2025, 06:47 AM
#1
I'm planning to purchase a new workstation within the next year when prices stabilize slightly. My goal is to perform CFD simulations using openFoam. Comparing Epic and Threadripper, what benefits do you see? Will adding two CPUs double your RAM capacity? Are there comparable options from Intel in this area? It's generally advised to allocate 5-6GB of RAM per CPU core. At my current setup, I run tasks on a high-performance computing cluster with hundreds of cores, which usually takes 12-24 hours. Now I'm aiming for something more affordable, around $10k, and want to understand what performance is achievable in that budget.
P
pafrickstump
06-10-2025, 06:47 AM #1

I'm planning to purchase a new workstation within the next year when prices stabilize slightly. My goal is to perform CFD simulations using openFoam. Comparing Epic and Threadripper, what benefits do you see? Will adding two CPUs double your RAM capacity? Are there comparable options from Intel in this area? It's generally advised to allocate 5-6GB of RAM per CPU core. At my current setup, I run tasks on a high-performance computing cluster with hundreds of cores, which usually takes 12-24 hours. Now I'm aiming for something more affordable, around $10k, and want to understand what performance is achievable in that budget.

I
ItzLeiaMoshi
Member
121
06-10-2025, 07:24 AM
#2
I realize this is now an older (just short of 6 months) thread, but for the sake of search ability, you're currently best off maximizing using external accelerated solvers such as the PETSC framework and it's solvers. it supports a much wider set of solvers, and those solvers are available for cuda, Hip, Sycl etc. They also tend to push updated code for performance uplifts multiple time per quarter. Even without GPU I've seen net uplifts of over 2x in total compute time for the same solver types (and matching results) just by using the PETSC AVX2, AVX512 and intel KML plugins.
I
ItzLeiaMoshi
06-10-2025, 07:24 AM #2

I realize this is now an older (just short of 6 months) thread, but for the sake of search ability, you're currently best off maximizing using external accelerated solvers such as the PETSC framework and it's solvers. it supports a much wider set of solvers, and those solvers are available for cuda, Hip, Sycl etc. They also tend to push updated code for performance uplifts multiple time per quarter. Even without GPU I've seen net uplifts of over 2x in total compute time for the same solver types (and matching results) just by using the PETSC AVX2, AVX512 and intel KML plugins.