Moving up the stack, today we are taking a look at the Intel Xeon E3-1270 V2, which is a new Ivy Bridge Xeon E3 series CPU built on Intel’s new 22nm process. Like last year where most of the original E3-1200 series was reviewed, we will be reviewing the vast majority of Intel’s Xeon E3 V2 lineup. The Xeon E3-1270 V2 holds a small performance advantage over the previously reviewed Intel Xeon E3-1230 V2 and Intel Xeon E3-1240 V2. Moving to the next 100MHz step up, the E3-1280 V2, which involves a similar 100MHz clock speed jump, currently costs another $280 over the Intel Xeon E3-1270 V2, or which is getting close to double the cost ($349 v. $629) for a relatively small 100MHz speed bump. Intel has upgraded this generation with a few new features, a power sipping 22nm tri-gate manufacturing process, PCIe 3.0, 1600MHz DDR3 unbuffered ECC memory support and a 100MHz speed bump over the Sandy Bridge generation. For those wondering, here is the Intel ARK comparison of the Sandy Bridge v. Ivy Bridge generations of the Intel Xeon E3-1280 (V2). Note: Intel’s ARK lists this as the Xeon E3-1280V2 with no space. What is interesting is that the Intel Xeon E3-1280 V2 at 3.6GHz base and 4.0GHz Turbo is actually faster than the enthusiast counterpart, the Core i7-3770K at 3.5GHz base and 3.9GHz Turbo (much like the Xeon E3-128 0V1) except that the Intel Core i7-3770K has the ability to overclock (the Xeon loses the ability to overclock for additional features such as ECC support and VT-d however) substantially. Let’s take a closer look at what this faster variant of the Xeon E3-1200 series has to offer!
Supermicro upgraded its X9SCx series to support the Ivy Bridge Xeon E3 family so I decided to use one of the most popular Xeon E3 LGA 1155 motherboards, the Supermicro X9SCM-F for the Ivy Bridge Xeon E3 reviews.
- CPU: Intel Xeon E3-1280 V2
- Motherboard: Supermicro X9SCM-F
- Memory: 16GB Kingston ECC 1600 CL11 DDR3 4x 4GB UDIMMs
- OS Drive: OCZ Vertex 4 256GB
- Enclosure: Norco RPC-4224
- Power Supply: Corsair AX750 750w 80Plus Gold PSU and PicoPSU 150XT with 150w power brick for power consumption testing.
- OS: Windows 7 Professional SP1 64-bit
As one may recall, the Intel C204 chipset does not allow one to use the integrated graphics of the Intel E3-12×5 (V1/V2) series CPUs so it is best to pair the X9SCM-F with a Xeon E3-12×0 series CPU. The older C206 or newer C216 chipsets are better pairings for the E3-12×5 series CPUs with onboard GPUs. Just to note, the configuration above was calibrated to within 1w at idle and load of the previous generation’s Tyan platform. I spent many hours getting this to be as close as possible, but for release support reasons I needed to switch to the Supermicro X9SCM-F platform for this round of Xeon E3-1200 V2 series reviews.
I will start off this section by saying that the standard test suite was built to test 1-8 thread single CPU systems such as the Sandy Bridge and Ivy Bridge Intel Xeon CPUs. With platforms like this one, I have been slowly altering the mix. Clearly, one would expect a different workload between the Xeon E5-2687W CPU and something found in a low-end, low-power server like a Pentium G630. Moving to the 16-64 core realm where the Xeon E5 series will play, that is becoming the norm today, I think that it will become ever more important to develop a second test suite.
I have been using Cinebench benchmarks for years but have held off using them on ServeTheHome.com because the primary focus of the site until the past few months has been predominantly storage servers. With the expansion of the site’s scope, Cinebench has been added to the test suite because it does represent a valuable benchmark of multi-threaded performance. I have had quite a few readers contact me about this type of performance for things like servers that are Adobe CS6 compute nodes and similar applications. Cinebench R11.5 is something that anyone can run on their Windows machines to get a relative idea of performance and both Ivy Bridge, Sandy Bridge and Sandy Bridge-EP systems run it well.
Here we see another nice improvement over the previous generation Intel Xeon E3-1280. We do see the performance is notably better than the E3-1270 V2 and Core i7-3770K. I put the E3-1280 V2 next to the E3-1270 V2 in these charts to make things a bit easier to read.
7-Zip Compression Benchmark
7-Zip is an immensely popular compression application with an easy to use benchmark.
Again, the Intel Xeon E3-1280 V2 puts out a bit more performance than the Xeon E3-1270 V2 and enjoys a nice advantage over the Xeon E3-1280 V1. Again, remember there is a $280 price premium over the $350 Xeon E3-1270 V2 for that small improvement.
TrueCrypt Encryption Benchmarks
With Intel’s focus on its AES-NI features TrueCrypt can look a bit skewed. Unlike some dubious drivers over the years that were optimized for benchmarks over real world application, Intel’s AES-NI feature does encompass the addition of specialized hardware. This specialized hardware has many practical uses and is becoming more supported. For example, users of Solaris 11 can utilize the AES-NI features to see much higher throughput on encrypted volumes. AMD has started offering AES-NI with their Bulldozer CPUs, and I will have those results added to future pieces. Let’s see how Intel does here.
Slightly better performance but a smaller jump than we saw with the E3-1240 V2 to the E3-1270 V2 which had the same 100MHz jump. The E3-1280 V2 ties the Intel Core i7-3770K here but that is most likely because the Core i7 is using non-ECC memory and realistically, the 100MHz difference is not that big of a jump.
Handbrake 0.9.5 x264 Encoding Benchmarks
I am still using Handbrake v0.9.5 simply because the Handbrake team does do some nice tweaking between annual versions and all of the other CPUs have been tested with v0.9.5. We will begin to collect data on v0.9.6 and start using that once we have critical mass. Either way, Handbrake is an extremely popular x264 encoding and transcoding application as it is very common practice these days to encode video for various tablets, phones and other devices. These transcodes also take a fair amount of time so having faster CPUs is important.
One big note here is that Handbrake is getting updated for GPU compute, and Intel has Quick Sync on its Intel Core i7 generation processors, such as the Core i7-3770K. For media encoding, if ECC is not an issue, the Core i7-3770K is still a better bet as that would allow one to overclock.
Intel’s move to 22nm is something hearlded as a new era in lower power consumption, especially with tri-gate technology and future process improvements that will increase that number. Using an Extech 380803 True RMS power analyzer which is a really nice unit that even records usage over time.
Overall, this is about what we would expect from an Ivy Bridge Xeon E3 CPU. I think the min-max numbers are my favorite to look at because it does help one see what a difference from idle would be in a datacenter. Still, it does look like it would be easy to keep a Xeon E3-1280 V2 server below 1 amp at 120v in a datacenter.
Here is the deal, the Intel Xeon E3-1280 V2 is certainly one of the fastest Ivy Bridge CPUs around at stock clocks. At $629 for the E3-1280 V2 you can get an Intel Xeon E5-2630 CPU with six cores and the additional memory and PCIe bandwidth that has to offer. Of course the E5-2630 is a 95w CPU while the E3-1280 V2 is a 69w part, but it is amazing that the chips are priced that similarly. Frankly, I think Intel needs to do a pricing reality check here and push the price down a bit. At $400-420 I think that would be “relatively” reasonable, but at over $600the Intel Xeon E3-1280 V2 is hard to justify unless you are in an ultra-dense rack and are trying to get as much performance as possible, but not in ways the Xeon E5 is better.