Intel Core i7 3820 Review: $285 Quad-Core Sandy Bridge E
by Anand Lal Shimpi on December 29, 2011 2:28 AM EST- Posted in
- CPUs
- Intel
- Sandy Bridge
- Sandy Bridge E
Windows 7 Application Performance
3dsmax 9
Today's desktop processors are more than fast enough to do professional level 3D rendering at home. To look at performance under 3dsmax we ran the SPECapc 3dsmax 8 benchmark (only the CPU rendering tests) under 3dsmax 9 SP1. The results reported are the rendering composite scores.
Cinebench 11.5
Created by the Cinema 4D folks we have Cinebench, a popular 3D rendering benchmark that gives us both single and multi-threaded 3D rendering results.
With only a 100MHz clock speed advantage over a 2600K when running in single core turbo mode, the 3820 isn't much faster than the 2600K in our single threaded Cinebench test. The additional L3 cache doesn't have much of an impact here, although I suspect that has more to do with this particular workload rather than a general statement about the 3820. Let's look at multithreaded perf:
The performance gap increases to 5% once we ramp up thread count. The extra performance is mostly due to clock speed here, although you'll see later on that there are some applications that definitely appreciate the larger L3 cache.
7-Zip Benchmark
While Cinebench shows us multithreaded floating point performance, the 7-zip benchmark gives us an indication of multithreaded integer performance:
The 7-zip benchmark gives us a good example of what the SNB-E platform can offer given the right workload. Here we see an 8.6% performance advantage, despite a much smaller clock speed advantage. The added L3 cache helps out a bit here, although obviously there's a huge gap between the 3820 and its hexa-core brethren.
PAR2 Benchmark
Par2 is an application used for reconstructing downloaded archives. It can generate parity data from a given archive and later use it to recover the archive
Chuchusoft took the source code of par2cmdline 0.4 and parallelized it using Intel’s Threading Building Blocks 2.1. The result is a version of par2cmdline that can spawn multiple threads to repair par2 archives. For this test we took a 708MB archive, corrupted nearly 60MB of it, and used the multithreaded par2cmdline to recover it. The scores reported are the repair and recover time in seconds.
In tests that have more of an IO influence the difference between the 3820 and the 2600K is negligible, it will take higher clock speeds and more cores to really separate SNB-E from the vanilla SNB systems.
TrueCrypt Benchmark
TrueCrypt is a very popular encryption package that offers full AES-NI support. The application also features a built-in encryption benchmark that we can use to measure CPU performance:
Encryption speed once again scales with core count and clock speeds, the additional L3 cache doesn't do much in this benchmark.
x264 HD 3.03 Benchmark
Graysky's x264 HD test uses x264 to encode a 4Mbps 720p MPEG-2 source. The focus here is on quality rather than speed, thus the benchmark uses a 2-pass encode and reports the average frame rate in each pass.
We see a slight advantage over the 2600K in our x264 HD benchmark, however video transcoding doesn't benefit all that much from the small gains the 3820 offers. Most client users would be better off with the Quick Sync enabled 2600K, and the serious video professionals will want to invest in a six-core 3930K at the minimum.
Compile Chromium Test
You guys asked for it and finally I have something I feel is a good software build test. Using Visual Studio 2008 I'm compiling Chromium. It's a pretty huge project that takes over forty minutes to compile from the command line on the Core i3 2100. But the results are repeatable and the compile process will stress all 12 threads at 100% for almost the entire time on a 980X so it works for me.
Again we see a step function improvement when moving from four to six cores in our compile test, but no change between the 2600K and 3820. If you're building a dev workstation you're going to either want to save money and grab a 2600K or move to six cores for better performance. It is worth mentioning however that if you need eight DIMM slots the 3820 might be a better option than the 2600K, allowing you to outfit your workstation with insane amounts of memory.
Excel Monte Carlo
Our Monte Carlo simulation test is CPU bound but the 3820 shows a marginal improvement over the 2600K.
SYSMark 2007 & 2012
Although not the best indication of overall system performance, the SYSMark suites do give us a good idea of lighter workloads than we're used to testing. SYSMark 2007 is a better indication of low thread count performance, although 2012 isn't tremendously better in that regard.
In 2007 we see mild gains over the 2600K, although 2012 shows a much bigger gap between the 3820 and the 2500K due to the former's support for 8 threads vs. 4.
Facebook
Twitter
RSS
84 Comments
View All Comments
Roland00Address - Friday, December 30, 2011 - link
Yes the memory is cheaper (about $160). It is not "much much cheaper" (your words) anymore.An i7 2600k is $299 at amazon.com and newegg with free shipping and no tax in many states. That is a difference of +15 compared to the speculated price of 285 for the core i7 3820 (so a total of +175 for memory and cpu)
x79 motherboards cost between $215 to $470 on newegg. Cheapest board with 8 ram slots is $280
p67 motherboards cost between $95 to $310 on newegg
z68 motherboards cost between $90 to $340 on newegg
So you may save $175 on cpu and memory but you are going to spend another $100 ish on the motherboard making your savings less than a 100 dollars. A hundred dollars is not a small amount but we are probably talking all said and done talking about a computer that is going to cost between $1000 and $1500 to build, thus a 100 dollars is between 6 to 10% of the computer price.
There is a reason to get the x79 chipset, but if you are getting it due to memory, please do it so you can use you 64 GBs of memory instead of a mere 32. Do it for that reason or do it for the 6 core cpus, the pci-e . Do not get a x79 chipset just so you can go cheap on the memory and only get 32 GBs.
Do not wait another 3 months so you can save a small amount on memory.
Ammaross - Thursday, December 29, 2011 - link
Article: "If you're seriously considering anything in the SNB-E family, the latter [Ivy Bridge] isn't going to matter and the former will be of arguable value"piroroadkill: "Anyone who wanted a system of this performance already bought a 2500 or 2600K and overclocked the balls off it..."
With tri-gate, die-shrink, and small bump in performance, IVB will be a nice setup due to being highly overclockable (I hope!). If SNB can OC to ~4.5 on air (running 4.4 on my rig), IVB with die shrink would hopefully manage something approaching 5ghz (remember, tri-gate does a better job with power flow and reception at lower voltage or higher speeds...). And the pricing lineup has already been leaked and shows fairly similar pricing to SNB launch, so I'm just sitting on my hands until April.
p05esto - Thursday, December 29, 2011 - link
I've got an i7 940 system and skipped SB and SB-E, but Ivy is my upgrade plan at the moment. SB-E let me down, so I'm waiting till April now. And even then, my i7 940 on SSD does everything I need it to do and FAST..... it's just an upgrade itch that needs to be scratched every couple years (we're suckers perhaps).Coup27 - Thursday, December 29, 2011 - link
On the chipset block diagram, it says PCI Express 2.0 is branching off the CPU and also the chipset? Shouldn't that be 3?darckhart - Thursday, December 29, 2011 - link
Yes that confused me a bit as well. Or is that pcie v3.0 only off the cpu and v2.0 off the x79?deruberhanyok - Thursday, December 29, 2011 - link
Every time I see the "i7 3xxx" number I get excited and think someone got an early Ivy Bridge sample.Then I remember that Intel couldn't even stick to their own naming convention for two generations of the Core iX series. :(
p05esto - Thursday, December 29, 2011 - link
No kidding, that crap pisses me off. Why is so damn hard to come up with a simple naming convention that is intuitive and can be used for decades? Doesn't have to be fancy, they could prefix the convention with some silly name like Pentium, Core i7 or whatever but then give the freaking thing some letter/number designation that clearly shows what is what. I could come up with 10 different numbering schemes without even trying!descendency - Thursday, December 29, 2011 - link
Yeah. I don't get why they can't just name things likei3s...2100,2150,2200,2250
i5s... 2300, 2350, 2400, 2450
i7 (1155)...2500, 2550, 2600, 2650
i7 (2011)... 2700, 2750, 2800, 2850
with Extreme chips being 2900 X...
add in K, X, S and whatever other letters you want at the end
Then, when Ivy Bridge comes out, change those 2s to 3s... Oh. and when Haswell comes out... make those 3s into 4s... maybe even have an i3 2270 when you want to sell the better binned chips at a higher price.
dj christian - Thursday, January 5, 2012 - link
I don't get it, why would you sell the i3 2270 at a higher price? The SB is in it's way out..descendency - Thursday, December 29, 2011 - link
I know it would be expensive, but it would be nice occassionally to get a review of an entire platform and what is possible on it.For example, what FPS could you get in 6 monitor setups with 4x GPUs on SNB-E vs SNB. (or something like that)
How much does extra ram really benefit in those kinds of applications.
It just doesn't make sense to review all CPUs on even planes because all CPUs are not designed to do what some CPUs are and that's why they are 500-1000 dollars each.