Relatively quiet i7-4790k or i7-5820k for FEA and Engineerin

[cycleback]

Relatively quiet i7-4790k or i7-5820k for FEA and Engineering Analysis

I need some help trying to put together another system beyond my current machine for primarily performing finite element optimization type tasks and other engineering analysis. I haven’t built a system for long time but I would like it to be relatively quiet. Eventually the machine will become my day to day desktop (currently i7-860). I also need to buy a NAS or a storage server but I think that should be a separate box.

Primary Intended Usage:
==================
- Small 2D electromagnetic and thermal finite element simulations (generally < 20,000 elements) as part of an evolutionary optimization algorithm. For each generation of the optimization algorithm tens to a hundred independent designs are evaluated making the simulations extremely parallelizable favoring a large number of cores. I am not going to be running these all the time but currently when I do they generally take ½ day to 2 days to complete.

- Matlab simulations

- Solidworks: Relatively simple assemblies

- Rarely some larger scale 3D finite element simulations (generally < 250,000 elements). Maybe very rarely some CFD simulations.

-Eventually the machine will become my day to day desktop as my current machine is a i7-860 2.8 GHz, 8 Gb of RAM, ATI Radeon HD 5700 Series

-I don’t intend to over-clock the machine or play games on it.

The two systems I am thinking about are:
==============================
i7-4790k; $250
ASUS Z97-AR; $90
16 GB (2 x 8 GB) DDR3 1600; $160
Total: $500

i7-5820k; $300
ASUS X99-A; $235
16 GB (4 x 4 GB) DDR4 2400; $200
Video Card: Passive or semi-passive with Display Port and DVI outputs; $150
Total: $885

Components I have Already Purchased:
============================
Power Supply: Seasonic
Case: Fractal Design R5
CPU Cooler: Coolermaster Hyper 212 Evo
Storage: Crucial MX 100 512 GB SSD (Thinking about exchanging this)

Pluses for the i7-4790k:
Higher base (4 Gz) and turbo (4.4 GHz) CPU frequency than i7-5820k
Relatively in expensive through Microcenter (CPU: $250, MB: $90)
Built in graphics hardware
Low power draw on load ad idle compared to the i7-5820k

Pluses for the i7-5820k:
Two additional cores though they are slower
Twice the memory bandwidth
Maybe more future proof

Questions:
========
Which processor and platform is likely to be faster. The i7-4790k has quite a clock frequency advantage while the i7-5820k has two additional cores and twice the memory bandwidth. I know generally for large CFD type simulations a high memory bandwidth is highly recommended. I am not sure memory bandwidth matters much for small finite element simulations though.

Can the memory bandwidth of the i7-4790k and Z-97 be increased substantially by using a higher rated frequency memory and with reduced timings?

Is the additional cost of the i7-5820k and X-99 platform worth it?

I have been toying with the idea of trying to use an Intel Xeon Phi for parallelizing my small simulations further is it likely to work in a ASUS X99-A motherboard in the x16 slot?

What is the likely longevity of the Z-97 and X-99 platforms? I tend to keep computers for a very long time.

Is DDR3 likely to be phased out soon?

While DDR4 while theoretically more future proof I assume the timings and frequency are going to increase rapidly?

Is there a go to low cost video card that is passive or semi-passive with display port and DVI outputs?

Is the built in video card of the i7-4790k, HD 4600, okay for basic CAD work including Solidworks?

Any other thoughts or recommendations on what to purchase?

[boost]

Relatively quiet i7-4790k or i7-5820k for FEA and Engineering Analysis

I need some help trying to put together another system beyond my current machine for primarily performing finite element optimization type tasks and other engineering analysis. I haven’t built a system for long time but I would like it to be relatively quiet. Eventually the machine will become my day to day desktop (currently i7-860). I also need to buy a NAS or a storage server but I think that should be a separate box.

Primary Intended Usage:
==================
- Small 2D electromagnetic and thermal finite element simulations (generally < 20,000 elements) as part of an evolutionary optimization algorithm. For each generation of the optimization algorithm tens to a hundred independent designs are evaluated making the simulations extremely parallelizable favoring a large number of cores. I am not going to be running these all the time but currently when I do they generally take ½ day to 2 days to complete.

- Matlab simulations

- Solidworks: Relatively simple assemblies

- Rarely some larger scale 3D finite element simulations (generally < 250,000 elements). Maybe very rarely some CFD simulations.

-Eventually the machine will become my day to day desktop as my current machine is a i7-860 2.8 GHz, 8 Gb of RAM, ATI Radeon HD 5700 Series

-I don’t intend to over-clock the machine or play games on it.

The two systems I am thinking about are:
==============================
i7-4790k; $250
ASUS Z97-AR; $90
16 GB (2 x 8 GB) DDR3 1600; $160
Total: $500

i7-5820k; $300
ASUS X99-A; $235
16 GB (4 x 4 GB) DDR4 2400; $200
Video Card: Passive or semi-passive with Display Port and DVI outputs; $150
Total: $885

Components I have Already Purchased:
============================
Power Supply: Seasonic
Case: Fractal Design R5
CPU Cooler: Coolermaster Hyper 212 Evo
Storage: Crucial MX 100 512 GB SSD (Thinking about exchanging this)

Pluses for the i7-4790k:
Higher base (4 Gz) and turbo (4.4 GHz) CPU frequency than i7-5820k
Relatively in expensive through Microcenter (CPU: $250, MB: $90)
Built in graphics hardware
Low power draw on load ad idle compared to the i7-5820k

Pluses for the i7-5820k:
Two additional cores though they are slower
Twice the memory bandwidth
Maybe more future proof

Questions:
========
Which processor and platform is likely to be faster. The i7-4790k has quite a clock frequency advantage while the i7-5820k has two additional cores and twice the memory bandwidth. I know generally for large CFD type simulations a high memory bandwidth is highly recommended. I am not sure memory bandwidth matters much for small finite element simulations though.

Can the memory bandwidth of the i7-4790k and Z-97 be increased substantially by using a higher rated frequency memory and with reduced timings?

Is the additional cost of the i7-5820k and X-99 platform worth it?

I have been toying with the idea of trying to use an Intel Xeon Phi for parallelizing my small simulations further is it likely to work in a ASUS X99-A motherboard in the x16 slot?

What is the likely longevity of the Z-97 and X-99 platforms? I tend to keep computers for a very long time.

Is DDR3 likely to be phased out soon?

While DDR4 while theoretically more future proof I assume the timings and frequency are going to increase rapidly?

Is there a go to low cost video card that is passive or semi-passive with display port and DVI outputs?

Is the built in video card of the i7-4790k, HD 4600, okay for basic CAD work including Solidworks?

Any other thoughts or recommendations on what to purchase?

Yes bandwidth can be increased in the Z97 boards, with looser timings. 2400MHz DDR3 will give you 50% increase in bandwidth over the advertised number. DDR3 faster than 2400MHz is quite expensive.

Finite element analysis seems to me like one of the areas where parallelization and bandwidth are key.
I would go with the X99 - Socket 2011-3 system.

I think a Xeon Phi should work.
Did you investigate GPUs as (co-)processors for this kind of task?

DDR3 will be used in Intel next CPU generation (4790K successor) along with DDR4. AMD will use DDR4 in 2016.

DDR4 speeds are likely to increase as it goes mainstream.

There are several, both AMD and Nvidia, probably around 50$.

The graphics card in the i5 and i7 CPUs might work. The same graphics in the Xeon Version of the CPUs (i.e. Intel Xeon E3-1271 v3) have CAD certified drivers. The CPU should work in most Z97 boards and all C22X workstation boards. The Intel Xeon E3-1271 v3 tops out at 3.7GHz.

In the Socket 2011-3 system you can upgrade to a Xeon CPU with up to 18 cores, at considerable cost. The next Generation of Intel's high end CPUs should support socket 2011-3 X99 system.

[CA_Steve]

My first suggestion would be to see if your s/w benefits from GPU acceleration. If they do, then it might reduce your analysis time by 10x. Then, consider whether it's worth the buy-in costs, both for the hardware and the extra programming pain. Some programs only work with CUDA, others don't. There may be canned routines that'll set up the GPGPU horsepower, or there might not.

Also, look for graphics driver compatibilities with this s/w - will it work with the Haswell video driver or do they require a workstation level card?

Here's a comparison of the i7-4790K vs i7-5820K. The 3D Particle Movement: MultiThreaded benchmark is probably the closest to your apps. Your current i7-860 would probably come in around 410, vs 804 and 923 for the 4790K and 5820K, respectively. No matter what, you are doubling your performance.

Intel and memory speed: Performance improvement tends to be pretty inelastic with Intel memory controllers. Here's a CPU computing benchmark for the Haswell Z87 kit. This should hold true for the Haswell refresh Z97. My guess is the X99 platform will be similar. Rather than going overboard on RAM speed, you'd get a bigger benefit from a light overclock of an unlocked CPU.

Is the additional cost of the i7-5820k and X-99 platform worth it?

If your simulation currently takes 48 hours, and moving to the 4790K drops this to ~24.5 hours..does reducing this to 21.3 hours provide a significant benefit? (again, I suggest looking into GPU acceleration).

Z97 platform will also support Broadwell when it comes out in 2015. X99 will support Broadwell-E . Skylake and Skylake-E will have new chipsets/sockets...and Skylake will also be seen in 2015. X99 and Haswell-E supports DDR4. The consumer side will see DDR4 with Skylake.

Xeon Phi: dunno. Not sure this is faster or cheaper than gpgpu.

other stuff. You will need a better CPU cooler. Look at the Scythe Kotetsu review on the site. The Crucial SSD is fine unless your simulations require insane amounts of read/writes during the run....programs like Adobe benefit from multiple drives, where one runs the OS and apps and another is used for a scratch disk.

[Abula]

Skylake will also be seen in 2015. X99 and Haswell-E supports DDR4. The consumer side will see DDR4 with Skylake.

I dont think we will see skylake in 2015, specially into no desktop broadwell cpu were released, personally im confused as there are some mobile that are out.... even a nuk is coming in janauary with broadwell. I kinda think we will see desktop broadwell cpus around the same time as we saw Haswell refersh, and i expect to to see skylake around the same time in 2016.

[CA_Steve]

Saw an updated roadmap a few weeks ago showing Skylake intro in the 2H of 2015. However, if they do a Broadwell-like intro, then the std desktop stuff won't be seen until 2016.