I am thinking of buying a new system to run with Pinnacle Edition 6 Pro and am not sure how much of a performance gain there will be going for a dual 3.0 Xeon system over a single p4 3.6, does anyone have any experience?

Also is it worth waiting for 64 Bit Windows and editing software to come in?

Thanks

hi
I recently assembled my new video workstation and was on the same doubt as you are.
what I concluded (for me...not working full-time on video) was that dual processing was overkill.
my research told me that for working with video the disk arrangement is far more important than most informatic applications. I got myself a dual disk RAID0 with two 10,000rpm Raptor's for the system and plan on getting 3 regular 200Gb SATA's also in RAID0 for the footage. I still can´t make it not do realtime in Canopus Edius or Premiere (although i think i'm stiking with premiere for the better media management and more user-friendly interface).
I also spent a bit more on RAM (2Gb) and I think it was worth it.
Of course, if you buy a dual xeon it will boost your rendering times. It's just up to you to balance the budget/benefits ratio. (with this setup I can make less than 0.50 encoding of mpeg2...making a 2 pass encoding faster than realtime...good enough for me)

in the end it all depends on your needs...I wish I had enough money for a dual xeon setup! :)


edit: for what I can see 64bit software is going to take a lot to come...but if you go with the 6xx Intel CPU's you'll get 2Mb cache...compared to 1Mb on the regular 5xx series. that alone could speed up the whole system.
don't go with AMD for video...they have better CPU's for pure calculation (games, folding, etc.) but don't manage the multimedia instructions so well (SSE, MMX, etc.)

I would guess that a dual will get about 20-25% more performance on some CPU tasks, but not everything.

Do not ignore the GPU. An ATI X800 with 256MB can do wonders while editing for quickly rendering tranistions and effects.

I'm going to be in a boat similiar to this in the future. I edit on a Dual 1.8GHz G5 at work, but want to work PC at home with Vegas 6. I already use Vegas Audio and decided to give the video side of it a shot. As far as I'm concerned if it holds up to FCP in performance and easy of use then it will be perfect for me.

My only thing is that I want to get into compositing and intend to buy Discreet Combustion 4 soon. I need a computer that can handle that, but I don't want to spend an arm and a leg. I currently have a 2Ghz P4 with 1G of RAM and a crappy NVidia GeForce 2 card. My question is about real-time graphics processing. Does a dual-processor machine handle real-time graphics processing better than a single-processor machine? Also, how much of a distinguishable effect does a good video/graphics card have in that respect?

Liquid 6 is already hyperthreaded, so theres no need for a Xeon unit.. it really wont speed up any processing as its all done in the background anyway..

personally if using L6 (which i no longer do at my own studio as i despise the databasing "Posess your machine and files like the exorcist and its minions attitude" id save the cash and invest in the HD BoB.. THAT little unit is brilliant.. just make sure u have thr right chipset and its connected straight to the Mobos USB2 ports

Liquid 6 is already hyperthreaded, so theres no need for a Xeon unit.. it really wont speed up any processing as its all done in the background anyway..

LE is threaded. Dual CPUs do speed it up. Even in backgroup, you will get better conversion for full real-time playback (a dynamic timewarp will render in the background, but if you want to play it immediately, you need to wait for the first pass of rendering to complete - you can still keep editing without interruption).

Remember that HT is not a second processor, it is a better usage of the wait states and scheduling of idle threads while others are waiting for I/O. A dual will outperform a HT processor. But, it is not double. On some tasks, it gains about 20% over a HT of the same caliber. The AMD A64 dual core should be slightly faster than the dual Xeon (no one has one yet that I have seen in the Liquid forum.)

A P4 3.6 might be as fast as or even a little faster than a dual 3.06 Xeon. No one has had the two side-by-side and shared the results.

Well, IMO, I would have to say that you should wait especially right now. 64-bit computing is just around the corner and so are dual cores. My biggest question is whether Windows 64 will be able to take advantage of say, dual processor dual cores (meaning 4-way core processing) and even quad processor dual cores (8-way!). That would be....the best. =)

Also, the single 3.6ghz P4 would be about the same as the dual 3ghz Xeons. What would be better would be the dual 3.6ghz Xeons ;). Still, wait for awhile and when you do go next gen, try to keep it in the same style as my specs (particularly the 2x 10,000RPM drives, the 2x big storage drives and the 2gb+ of RAM).

My take is that if you have any interest in working with HD/HDV footage than you should get dual processors, or wait a few weeks for dual-core systems to become more widely available. Today's single-core processors are fine for most standard-definition video work, but as soon as you start working with HD you're pushing the limits of what a single CPU can support. As for 64-bit processing, it can't hurt to buy a processor which supports that, but there is currently very little optimized software or drivers. I'd put more emphasis on dual processors / dual cores for any editing system being built today.

I would look at how much your time is worth to you, and how much you edit.

If video is just a hobby thing for you, then I would probably get a single processor system (3.4ghz or so). Single processor systems have a much, much better price/performance ratio than dual processor systems. Generally in computers:
A- You pay exponentially more for small performance increases. Dual processors speed up performance from around -5% to 90% compared to a single processor of the same clock speed (this is HIGHLY dependent on the program in question- look at benchmarks for that particular program). Yes, they can be slower!
Edition benchmarks may be scarce.
However, doesn't background rendering mean you rarely have to wait on rendering?
B- Computers lose money to obsolescence very quickly, so if you overbuy then you lose a lot of money on your "investment". If you underbuy, it won't cost you that much for an upgrade (which gets cheaper as time goes on). About half value every two years.
C- Computers are always getting faster, so most of the time it doesn't make sense to wait for faster computers.

don't go with AMD for video...they have better CPU's for pure calculation (games, folding, etc.) but don't manage the multimedia instructions so well (SSE, MMX, etc.)
Dual Opterons will outperform dual Xeons in demanding applications (like video editing) mostly because of their memory management. Each proc has its own RAM bank and speeds up times immensely. At least, this is our experience when using Premiere Pro as well as our software.
For single Proc, HT is a huge help. A RAID array for capture is almost a must, and 1GB RAM is minimum (go for RAM with aggressive timing too! all PC3200 chips are not equal!)
Look out for the new dual-core CPUs as well. Intel's even releasing some dual-core CPUs w/ HT. They should fly.

Dual Opterons will outperform dual Xeons in demanding applications (like video editing) mostly because of their memory management.
Dual Opterons do not get a significant memory advantage over Xeons until you get past 2 processors.

Tim,
Have you run benchmarks to validate your statements?

Some of them I doubt:
Aggressive timings: I have tested this with Vegas and the sad truth is memory timings does nothing for Vegas.
http://www.dvinfo.net/conf/showthread.php?s=&threadid=18841

It may make a difference for MPEG2 encoding? At best, it would be a few percent. In any case, low latency memory is not worth paying money for. Brand name or the cheapest RAM you can find will work. You may want to test RAM with memtest to account for poorer quality control among cheaper RAM.

Some of your claims may be right, may be wrong:
Dual Opterons are faster than dual Xeons at Premiere Pro. I'd be interested to see benchmarks for this. Opteron definitely does scale up better than Xeons. It also depends if the OS is NUMA-aware (winXP is not).

However, that affects memory bandwidth... and it may not be all that important for video when you are dealing with complicated/long renders. Again, see
http://www.dvinfo.net/conf/showthread.php?s=&threadid=18841

(results for Vegas unfortunately)

Large (i.e. 30%) differences in memory bandwidth only translate to a few percent difference in render performance.

A RAID array for capture is almost a must
For DV, a RAID is unnecessary and may hurt performance (or not help it at all). Non-RAID is a faster configuration if you read off one drive and write to the other. In many scenarios for *DV*, hard drive speed is not an issue.
In special cases it is: i.e. laptops getting dropped frames, drives that are running out of space and/or are fragmented

I have yet to see the Pinnacle guys jump up and down over Opterons yet either. They still lean towards dual Xeons. The new dual cores may change that, but that will be after they get some in Germany and CT to test and verify with.

In my humble opinion you should get the highest performance your budget will allow. You can never have too much horsepower, memory, or disk space. If you have large projects with huges amounts of files, soundtracks, footage, etc -after a while in larger projects you'll notice a slowdown on lower end systems. This happens on nicer systems too, only not nearly as noticeably.

I don't use Pinnacle but I assume that it allows the use of multi-cpus. If it doesn't there is no point in getting 2. Fast drives and Fast RAM (and lots of it) will really make the difference. Have you thought about any of the P4EE versions?


I agree on the RAID issue too, I ran RAID for about a year and now have the drives separate and dedicated (one for raw DV files, one for sound, one for previews, one for OS and NLE) and I have not noticed a difference in rendering or speed.

Awesome thread. I wish someone would do a comparison test on a couple different editing set ups to see where the chips really fall in the realtime/rendering arena.

This is what I would like to see compared:

3.2-8 GHZ P4 HT
3.2 and up GHZ P4 Extreme Edition
3.2 and up GHZ XEON
3.2 GHZ dual core Pentium D
3.2 GHZ dual core Pentium Extreme Edition
Dual 3.2 and up GHZ XEON

Do a series of tests in Premiere, After Effects, Avid, etc and see just what kind of performance increase you're paying for with the fancier chips. The only benchmarking I've seen has been for piddly little mundane tasks like mp3 encoding. I want to know how long it will take each set up to render a half hour video segment chock full of color correction, film look, etc.

So Intel, if you're reading this, email me and I'll give you my address for where to send the systems and I'll be glad to post the results.

Thank you,

Eddie

Eddie: if you look around the internet at various user reports, it becomes apparent that dual Xeons are very effective for things like rendering when used with software which is dual processor savvy. People with good dual processor computers report being able to do two-pass MPEG2 encoding in faster than real time (i.e. less than one hour to encode an hour of video). With dual core processors you may be able to get close to a similar level of performance without having to spend so much on a fancy workstation motherboard, and perhaps with less heat generated than with two single-core Xeons. And eventually we'll have the option to use two dual-core processors, which should accelerate things even further.

Tim,
Have you run benchmarks to validate your statements?

Absolutely. Sandra alone has shown higher performance (memory bandwidth) on dual opterons versus my 3.2E P4 and even the new Dual-Core Smithfield Extreme Edition (that's a dual-core, hyper-threaded 3.2GHz, 800MHz FSB)


Some of them I doubt:
Aggressive timings: I have tested this with Vegas and the sad truth is memory timings does nothing for Vegas.
http://www.dvinfo.net/conf/showthread.php?s=&threadid=18841

It may make a difference for MPEG2 encoding? At best, it would be a few percent. In any case, low latency memory is not worth paying money for. Brand name or the cheapest RAM you can find will work. You may want to test RAM with memtest to account for poorer quality control among cheaper RAM.


The above mentioned Smithfield system has 1 GB (2x512) DDR2, 667 in dual-channel configuration. My personal 3.2E has PC4000 OCZ Gold Rev. 2 RAM with very aggressive timings. Sandra shows a 5.7GB/s bandwidth on my machine versus that of merely 4.7GB/s on the P4D system. My board's an 875i chipset, and I believe the Dual-Core EE is on a 955, but I'm not 100% sure. Our dual opteron systems are consistently over 6GB (using PC3200 ECC).


For DV, a RAID is unnecessary and may hurt performance (or not help it at all). Non-RAID is a faster configuration if you read off one drive and write to the other. In many scenarios for *DV*, hard drive speed is not an issue.
In special cases it is: i.e. laptops getting dropped frames, drives that are running out of space and/or are fragmented

DV requires nowhere near the bandwidth as HDV, especially when you're dealing with 1080. We have a number of testing sytsems, and systems with RAID arrays far outperform those with standalone drives. When you're trying to play three streams at once, one drive can't handle it.

DV and HDV are different ballgames, and a few percent here or there is an improvement, gets your rendering done faster, and makes real-time playback even smoother.

We've tested a number of systems over and over again -- Athlon 64 systems, P4 HT systems, Dual Xeons, and Dual Opterons -- and for the most demanding HDV projects, the Dual Opterons just perform better. The tests that we've run involve our software with PPro, and Sandra.

EDIT: Obviously, if you are sticking with DV most of this doesn't apply as the improvement gained by more sophisticated hardware is minimal compared to when dealing with HDV. Remember though, you generally pay for what you get.

Hi Tim,
If you look in my link:
http://www.dvinfo.net/conf/showthread.php?s=&threadid=18841
You'll see I have run my own benchmarks to measure things. A ~50% change in memory timings or memory bandwidth make less than a few percent difference in render performance. It's so small that it's hard to measure, but nonetheless less than a few percent.
*Memory bandwidth was measured using memtest86. It gives very similar results to one of the Sandra memory tests... the unbuffered ones I believe.

I think my benchmark is a much closer approximation to real world results than Sandra. You may see on many hardware review sites (xbitlabs.com, anandtech.com, etc.) that memory bandwidth correlates extremely weakly to actual performance because it typically is not the bottleneck. Memory bandwidth may have been a bottleneck in the RAMBUS days, where it may have made a meaningful difference in performance.


The above mentioned Smithfield system has 1 GB (2x512) DDR2, 667 in dual-channel configuration. My personal 3.2E has PC4000 OCZ Gold Rev. 2 RAM with very aggressive timings. Sandra shows a 5.7GB/s bandwidth on my machine versus that of merely 4.7GB/s on the P4D system. My board's an 875i chipset, and I believe the Dual-Core EE is on a 955, but I'm not 100% sure. Our dual opteron systems are consistently over 6GB (using PC3200 ECC).

You can change the memory timings on your RAM if you go inside the BIOS (*warning: making your RAM run faster, by lowering the timings, may/will cause instability). You will likely find that they make, at best, a few percent difference on performance and a milk (<~10%) difference to memory bandwidth.
I have run my own benchmarks, which you can see in the link above.
Hardware review sites also report similar things:
http://www.xbitlabs.com/articles/memory/display/p4-mem.html

2- Memory bandwidth is only one factor is determine why one processor is faster than another. Quick way of checking this is to drastically alter memory bandwidth (i.e. changing the FSB/RAM divider)- my own tests show less than a few percent difference in performance.
There are a large number of factors which affect processor performance- two of them for example are pipeline length [which explains why Prescott core Pentiums are usually slower than Northwood cores, even though Prescotts have more cache and look better on paper], and floating point performance [a major reason why AMD is very good at DAW performance]. Because of these factors there is a wide variation in performance. In my opinion, the best thing you can do is to find benchmarks for your specific scenario (main factors are program you run, and which processors you can afford).

We've tested a number of systems over and over again -- Athlon 64 systems, P4 HT systems, Dual Xeons, and Dual Opterons -- and for the most demanding HDV projects, the Dual Opterons just perform better. The tests that we've run involve our software with PPro, and Sandra.
You might be right there. I have no way of telling whether that's true because I don't have those systems to play with, and there are few relevant benchmarks.

Vegas may be a little different than Premiere. rendertest.veg results for Vegas shows Intel and AMD processors running neck to neck (Intel perhaps a little faster by a few-several percent). Those results are old though.

Results I've seen for Premiere Pro show AMD processors ~20% faster than an "equivalent" Pentium.

Again, remember we are talking about Pinnacle Liquid Edition 6 here. Pinnacle does not list AMD processors on the recommended or minimum list, although they have tested some of them. For 5.x, they did list various nForce2/3 boards as compatible, and I do not expect any issues with any AMD products. I do know that SSE2 compatibility is assumed on 5.x and you had to turn it off on AMDs that did not have it. 6.x seems to have gotten a lot less picky about hardware, but does like TI IEEE 1394 and ASIO2 support. Do get a M-Audio or Creative Labs Audigy 2 ZS or 4 card instead of using onboard Realtek chips. Onboard has been a source of OOS issues.

They are a couple of guys building X2 and 275 systems. But, since they did not have duals to compare to, and we do not have a standard benchmark, there really is not a way to compare.

Also, learn towards ATI for a Pinnacle system. nVidia is more often prone to driver issues with LE. LE prefers DX9 performance over OpenGL performance. Memory is king for HDV. I would recommend a X800 with 256MB for better seamless video. Not sure an 850 would buy much more. But boy, I sure want to try the new R520 boards.