Laptop hardware for faster optistruct in HW 11 and 12

Rahul_P1

Hi all,

I am planning to buy a new laptop with a max budget of ~1500€ (with renew hardware if needed).

Have you got any recommendations/benchmarks for hardware inside this small budget to obtain the best speed with optistruct (HyperWorks 12 and 11)?
How to balance the hardware characteristics (CPU speed, RAM, graphic board)?

I had a look on the recommended graphic card list for HyperWorks 11. Like for other CAD/CAE softwares, AMD FirePro or NVIDIA Quadro are recommended/certified.
I read about the new trend for GPU computing to accelerate simulations, however is that a good choice in my case, should I better invest in a gaming laptop with a better CPU but weaker graphic card (gaming graphic card)?

For example, my first choice at the upper limit of my budget was a DELL Precision M4700:
- Intel Core i7-3520M 3rd generation (2,90 GHz Turbo, 4 MB)
- AMD FirePro M4000 Mobility Pro (1 GB GDDR5)
- RAM 16GB 1600MHz DDR3
But now, I wonder if a gaming laptop with a better CPU (with only a GeForce GPU) wouldn't be a better choice.

Any recommendation would be much appreciated.

Thank you,
Kind Regards,
Marc

Rahul_P1

Hi Marc,

In short DELL Precision M4700 is the laptop I use and would recommend you go for it 

Some details that may help you-

Motherboards and Front Side Bus (FSB) speeds and the RAM memory speeds and types supported are important since this will determine overall performance and bypass any bottlenecks you may face with applications.

A good solver machine would benefit from a 1066MHz/1333MHz FSB+DDR2/3 ram speeds (currently topping out at ~1600MHz) and top Intel/AMD chipsets and memory. Having the clock timings equal to CPU clock speeds will have better performance (no delay in CPU and memory cycles).

I would recommend at the very least 4GB of RAM memory with 8GB-32GB to be a better choice (4GB or 6GB per CPU is a rule of thumb) to be able to run applications in core (memory) instead of having the system utilize virtualization memory management and/or swap space memory which is much slower. Optistruct\Radioss\MotionSolve\etc. jobs will run better in core than on swap or virtual memory.

For graphics, if it is necessary (which solvers machines do not require since graphic intensive jobs arent utilized) Ì would recommend NVIDIA Quadro FX series cards or the ATI FireGL/FirePro series. (256MB or 512MB -> whichever is more affordable).

The recommended card should have 1GB or more dedicated memory onboard and at higher speeds (DDR4/5). These cards have a GPU running with workstation specific drivers for CAE/CAD specific applications which should handle the graphics in more of a efficient manner. The need for GPU and on board ram is also recommended

As for the hard drives, the bigger and higher rpm speeds the better. A SATA II RAID 0 (performance mode) with a swap file at least 1.5 times the size of system RAM (example, 4GB RAM = 6 GB swap file). This should give a high burst rate and will run Optistruct\Radioss and MotionSolve jobs better and general graphics information throughput faster as well. There is also the formatting of the drives in particular cases that will definitely influence performance, example, transferring of usually larger data chucks may result in better performance if the hard disk is formatted in larger data clusters than the usual smaller size (less I/O calls to transfer data).
There are newer Solid State Drives (SSD) with excellent throughput speeds for I/O but at the expense of cost and disk space size.

Rahul

Rahul_P1

Hello Rahul,

Thank you very much for your fast and detailed answer, it helps me a lot.

Can I ask you the details of your hardware inside your DELL Precision M4700? And some examples (if you have) of optimizations with optistruct (size/complexity of the model and run time the optimization took)?

Last question but maybe of lesser importance, did you try the gaming performance of the laptop? (flight simulations like X-plane for example  ) Feedback (graphics settings + FPS) on any game/simulation would be perfect.

Thanks again,
Kind Regards,
Marc

Rahul_P1

Marc,

The hardware configuration you specify is the same as mine, except I use the intel graphics, so you are looking at better graphics.

a 136 kb tutorial model runs within a second.

a 24mb modal transient analysis with below

MEMORY ESTIMATION INFORMATION :
-------------------------------
Solver Type is: Sparse-Matrix Solver
Direct Method
Block Lanczos Eigenvalue Extraction

Current Memory (RAM) : 753 MB
Estimated Minimum Memory (RAM) for Minimum Core Solution: 753 MB
Recommended Memory (RAM) for Minimum Core Solution : 753 MB
Estimated Minimum Memory (RAM) for Out of Core Solution : 1526 MB
Recommended Memory (RAM) for Out of Core Solution : 1713 MB
Recommended Memory (RAM) for In-Core Solution : 5848 MB
Recommended Number of Nodes for OS SPMD Parallel Run : 0
(Note: Minimum Core Solution Process is Activated.)
(Note: The Minimum Memory Requirement is limited by Output Calculation.)

DISK SPACE ESTIMATION INFORMATION :
-----------------------------------
Estimated Disk Space for Output Data Files : 638 MB
Estimated Scratch Disk Space for In-Core Solution : 16012 MB
Estimated Scratch Disk Space for Out of Core Solution : 20600 MB
Estimated Scratch Disk Space for Minimum Core Solution : 21560 MB

takes 10 minutes

MEMORY ESTIMATION INFORMATION :
-------------------------------
Solver Type is: Sparse-Matrix Solver
Direct Method
Block Lanczos Eigenvalue Extraction

Current Memory (RAM) : 1713 MB
Estimated Minimum Memory (RAM) for Out of Core Solution : 1526 MB
Recommended Memory (RAM) for Out of Core Solution : 1713 MB
Recommended Memory (RAM) for In-Core Solution : 5848 MB
Recommended Number of Nodes for OS SPMD Parallel Run : 0

DISK SPACE ESTIMATION INFORMATION :
-----------------------------------
Estimated Disk Space for Output Data Files : 638 MB
Estimated Scratch Disk Space for In-Core Solution : 15961 MB
Estimated Scratch Disk Space for Out of Core Solution : 20549 MB

takes 7 minutes

MEMORY ESTIMATION INFORMATION :
-------------------------------
Solver Type is: Sparse-Matrix Solver
Direct Method
Block Lanczos Eigenvalue Extraction

Current Memory (RAM) : 5848 MB
Estimated Minimum Memory (RAM) for Out of Core Solution : 1526 MB
Recommended Memory (RAM) for Out of Core Solution : 1713 MB
Recommended Memory (RAM) for In-Core Solution : 5848 MB
Recommended Number of Nodes for OS SPMD Parallel Run : 0

DISK SPACE ESTIMATION INFORMATION :
-----------------------------------
Estimated Disk Space for Output Data Files : 638 MB
Estimated Scratch Disk Space for In-Core Solution : 15961 MB
Estimated Scratch Disk Space for Out of Core Solution : 20549 MB

Takes 4 minutes (this one is –ncpu 2 i.e. 2 processors)

Rahul_P1

Thank you Rahul for the time you have taken to provide me those precious informations.

Best Regards,
Marc