Disclaimer: As with our recent Core i7-4960X preview, the following story is based on an early engineering sample Xeon E5-2697 V2. Intel was not involved in the story, and was not asked for comment prior to its publication.
It’s in vogue to rag on the desktop market and point to analyst data that shows tablet and smartphone shipments accelerating. So begins another race to the bottom, where form factors shrink and ASPs drop.
Yeah, sure, those small touch-oriented devices are great for a lot of the tasks that used to require a PC. But they don’t replace PCs. And despite the financial services companies responsible for prophesying the continued contraction of desktop computing (or perhaps because of them), enthusiasts want assurance that they’ll always have high-end hardware options.
The problem is that enthusiast-class gear represents a sliver of what companies like Intel, AMD, and Nvidia sell, even if the technologies that go into those components filter down into higher-volume products. Every manufacturer, including Intel, claims that it's still looking out for the small but elite group of power users. To say otherwise is blasphemous. But my early look at the enthusiast-oriented Ivy Bridge-E configuration (Intel Core i7-4960X Preview: Ivy Bridge-E, Benchmarked) turned up a distinct lack of progress in this upcoming generation.
In the company’s defense, it’s simultaneously fighting higher-stakes battles on other fronts that require financial resources and engineering talent, which have to come from somewhere. Silvermont (Intel Silvermont Architecture: Does This Atom Change It All?) has the makings of an ARM-killer, and that’s where Intel is focusing its attention.
That’s not to explain away two successive desktop launches that left enthusiasts feeling a little underwhelmed, or to recommend that you buy a new system when your coming-up-on-three-year-old Sandy Bridge-based box is still plenty fast. Ivy Bridge and Haswell were both decidedly mobile-focused. So, in light of IDC's forecast that that tablet shipments will outpace desktops and laptops combined by 2015, it's really no wonder that Intel's emphasis is on low power and new form factors.
Simply, that’s where most of the innovation is happening right now. From Intel’s work with power to Nvidia’s computational photography, and Qualcomm’s emphasis on tightly integrating a broad portfolio of IP, there’s still a ton of differentiation going on. Meanwhile, what is keeping power users at their desks and buying high-end hardware? Gaming, largely. The recent Worldwide PC Gaming Hardware Market report from Jon Peddie Research confirms this. Occasionally I’ll get to write something like Next-Gen Video Encoding: x265 Tackles HEVC/H.265, where we catch a glimpse of an upcoming workload that’s going to make you want faster hardware. But even then, a relative few need powerful workstations for encoding 3840x2160 video.
Whatcha Got There, Mac Pro?
Intel introduced its Sandy Bridge-E architecture almost two years ago to much enthusiast excitement. The platform wasn’t for everyone—after all, the least-expensive LGA 2011-compatible chip sold for more than $300. But if you bought one, it held you over through the mainstream Ivy Bridge and Haswell launches.
The company plans to launch Ivy Bridge-E at this year’s IDF in September. But don’t hold your breath for the same magnitude of fanfare. While our aforementioned Core i7-4960X preview turned up some really cool efficiency data, minor performance improvements won’t compel you to upgrade. And if you held off onSandy Bridge-E altogether, you can look forward to building a new PC with X79 Express—a chipset that even lacks native USB 3.0 support. What’s more, we can’t even blame the lack of enthusiast appeal on Intel’s new phone and tablet focus. The fact that its top-end Ivy Bridge-E chip is a six-core processor with 15 MB of shared L3 cache, just like Sandy Bridge-E, is really a marketing call.
Sandy Bridge-EP featured as many as eight cores and 20 MB of L3 (we tested it in Core i7-3970X Extreme Review: Can It Stomp An Eight-Core Xeon?). But with the Xeon E5-2687W selling for $2000, Intel was under no pressure to introduce an equivalent Core i7. Soon we’re going to start seeing 12-core Ivy Bridge-EP CPUs (at lower 130 W TDPs, no less), but those are likewise turning into server- and workstation-oriented Xeon E5s.
Source: apple.com
Rather than turning its next Mac Pro into a big dual-socket affair, Apple is capitalizing on the fact that Ivy Bridge-EP will ship in 12-core configurations, and it’s consolidating the platform into a 9.9-inch-tall cylinder with up to one Xeon E5-2697 V2 CPU. Regardless of whether you love or hate the “wastebasket” design, the system’s specs are very impressive for the volume of space it occupies.
Pre-Production Benchmark Data Isn’t Always What It Seems
There were probably some bummed-out professionals, then, when a Geekbench result was recently uploaded to Primate Labs’ online browser showing that 12-core Xeon E5 around nine percent faster than last generation’s dual six-core Mac Pro, based on Westmere-EP.
Source: Geekbench Browser, Primate Labs
Those scores require a bit of context, though. The 32-bit build of Geekbench uses x87 code, for starters, so it isn’t optimized for any of the other instruction set extensions that Westmere-EP or Ivy Bridge-EP support. Getting close to Apple’s claim of doubled floating-point performance requires software compiled with the AVX flag. John Poole, the founder of Geekbench, posted several other reasons why the next-gen and previous-gen Mac Pros might be separated by such a narrow margin.
The leaked result was run using the free 32-bit build of Geekbench on a pre-release build of OS X Mavericks. Switching over to the paid 64-bit build of the benchmark adds SSE support, though that’s still a pre-Pentium 4 extension. Tab between the 32- and 64-bit runs on Xeon X5675-based systems and you’ll find that the SSE-capable build averages 14%-better performance.
Curious as to how the very same 12-core Xeon E5-2687 V2 compared in Windows, I ran my own test on a 64-bit build of Geekbench and scored in excess of 30,000 points—more than 25% faster than the leaked number. The individual sub-tests showed both Xeon E5-based platforms trading blows in the integer and floating-point components, but clearly a more real-world comparison was needed in order to establish the new Xeon’s performance in a workstation environment. Fortunately, I have the upcoming Xeon E5-2697 V2, the upcoming Core i7-4960X, an existing eight-core Xeon E5-2687W, and a Core i7-3970X.
Meet The Xeon E5-2697 V2
Intel's original Xeon E5 family was based on the Sandy Bridge architecture. Launched more than a year ago, they spanned thermal ceilings from 50 to 150 W, core counts between two and eight, and price points between $188 and $3620 (for the highest-end quad-socket-capable models). Truly, this was a processor line-up with something for everyone. Entry-level small business servers, powerful workstations, rack-mounted virtualization and cloud boxes, and storage appliances are all driven by carefully picked Xeon E5s.
A transition to the Ivy Bridge architecture sees Intel increment its nomenclature to the Xeon E5-16xx/24xx/26xx/46xx V2 series. A corresponding shrink to 22 nm manufacturing lets the company add more cores and L3 cache without violating the thermal limits imposed last generation. Expect to see 10-core models rated for as little as 70 W, 12-core models that hit 130 W, and a number of TDPs in between. All the while, Intel maintains 256 KB of L2 cache and a 2.5 MB slice of shared L3 per core.
Most of the Xeon E5-2697 V2's specifications are consequently pretty easy to guess. It's a 12-core processor with 3 MB total on-die L2 cache and 30 MB of shared L3. A base clock rate of 2.7 GHz jumps as high as 3.5 GHz with Turbo Boost enabled and just one core active. With two utilized, the clock rate tops out at 3.4 GHz. Frequency drops to 3.3 GHz with three cores active and 3.2 GHz with four. So long as thermals allow, spinning five cores up drops you to 3.1 GHz. From six to 12 active cores, the Xeon E5-2697 V2 tops out at 3 GHz.
As with the Ivy Bridge-E-based Core i7-4960X we previewed, Intel facilitates DDR3 data rates of up to 1866 MT/s. Basic RAS modes and ECC are enabled. You'll see QPI transfer rates of 6.4, 7.2, and 8 GT/s up and down the V2 line-up, but the -2697 V2 specifically sports a pair of links at that top specification.
| Test Hardware | |
|---|---|
| Processors | Intel Xeon E5-2697 V2 (Ivy Bridge-EP) 2.7 GHz (27 x 100 MHz), LGA 2011, 30 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled |
| Intel Xeon E5-2687W (Sandy Bridge-EP) 3.1 GHz (31 x 100 MHz), LGA 2011, 20 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-4960X (Ivy Bridge-E) 3.6 GHz (36 * 100 MHz), LGA 2011, 15 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-4770K (Haswell) 3.5 GHz (35 * 100 MHz), LGA 1150, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-3770K (Ivy Bridge) 3.5 GHz (35 * 100 MHz), LGA 1155, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-2700K (Sandy Bridge) 3.5 GHz (35 * 100 MHz), LGA 1155, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-3970X (Sandy Bridge-E) 3.5 GHz (35 * 100 MHz), LGA 2011, 15 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| Intel Core i7-3930K (Sandy Bridge-E) 3.2 GHz (32 * 100 MHz), LGA 2011, 12 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
| AMD FX-8350 (Vishera) 4.0 GHz (20 * 200 MHz), Socket AM3+, 8 MB Shared L3, Turbo Core enabled, Power-savings enabled | |
| AMD A10-5800K (Trinity) 3.8 GHz (19 * 200 MHz), Socket FM2, 4 MB Total L2 Cache, Turbo Core enabled, Power-savings enabled | |
| Motherboard | MSI Z87 Mpower Max (LGA 1150) Intel Z87 Express, BIOS 1.2B1 |
| MSI Z77 Mpower (LGA 1155) Intel Z77 Express, BIOS 17.8 | |
| MSI X79A-GD45 Plus (LGA 2011) Intel X79 Express, BIOS 17.2 | |
| MSI 990FXA-GD80 (Socket AM3+) AMD 990FX/SB950, BIOS 13.2 | |
| MSI FM2-A85XA-G65 (Socket FM2) AMD A85X, BIOS 2.0 | |
| Memory | G.Skill 16 GB (4 x 4 GB) DDR3-1600, F3-12800CL9Q2-32GBZL @ DDR3-1600 at 1.5 V |
| Hard Drive | Samsung 840 Pro 256 GB, SATA 6 Gb/s |
| Graphics | Nvidia GeForce GTX Titan 6 GB |
| Power Supply | Corsair AX860i, 80 PLUS Platinum, 860 W |
| System Software And Drivers | |
| Operating System | Windows 8 Professional x64 |
| DirectX | DirectX 11 |
| Graphics Driver | Nvidia GeForce Release 320.18 |
The Xeon E5-2697 V2 is still pre-production, so existing LGA 2011-based server and workstation platforms require a firmware update to support the processor. We had to seek this out specifically, but cannot say which platform was used for benchmarking the Ivy Bridge-EP-based CPU.
| Benchmark Configuration | |
|---|---|
| Adobe Creative Suite | |
| Adobe After Effects CS6 | Version 11.0.0.378 x64: Create Video which includes three Streams, 210 Frames, Render Multiple Frames Simultaneosly |
| Adobe Photoshop CS6 | Version 13 x64: Filter 15.7 MB TIF Image: Radial Blur, Shape Blur, Median, Polar Coordinates |
| Adobe Premeire Pro CS6 | Version 6.0.0.0, 6.61 GB MXF Project to H.264 to H.264 Blu-ray, Output 1920x1080, Maximum Quality |
| Audio/Video Encoding | |
| iTunes | Version 10.4.1.10 x64: Audio CD (Terminator II SE), 53 minutes, default AAC format |
| Lame MP3 | Version 3.98.3: Audio CD "Terminator II SE", 53 min, convert WAV to MP3 audio format, Command: -b 160 --nores (160 Kb/s) |
| HandBrake CLI | Version: 0.98: Video from Canon Eos 7D (1920x1080, 25 FPS) 1 Minutes 22 Seconds Audio: PCM-S16, 48,000 Hz, Two-Channel, to Video: AVC1 Audio: AAC (High Profile) |
| TotalCode Studio 2.5 | Version: 2.5.0.10677: MPEG-2 to H.264, MainConcept H.264/AVC Codec, 28 sec HDTV 1920x1080 (MPEG-2), Audio: MPEG-2 (44.1 kHz, 2 Channel, 16-Bit, 224 Kb/s), Codec: H.264 Pro, Mode: PAL 50i (25 FPS), Profile: H.264 BD HDMV |
| Productivity | |
| ABBYY FineReader | Version 10.0.102.95: Read PDF save to Doc, Source: Political Economy (J. Broadhurst 1842) 111 Pages |
| Adobe Acrobat X | Version 10.0.0.396: Print PDF from 115 Page PowerPoint, 128-bit RC4 Encryption |
| Autodesk 3ds Max 2012 and 2013 | Version 14.0 x64: Space Flyby Mentalray, 248 Frames, 1440x1080 |
| Blender | Version: 2.64a, Cycles Engine, Syntax blender -b thg.blend -f 1, 1920x1080, 8x Anti-Aliasing, Render THG.blend frame 1 |
| Visual Studio 2010 | Version 10.0, Compile Google Chrome, Scripted |
| File Compression | |
| WinZip | Version 17.0 Pro: THG-Workload (1.3 GB) to ZIP, command line switches "-a -ez -p -r" |
| WinRAR | Version 4.2: THG-Workload (1.3 GB) to RAR, command line switches "winrar a -r -m3" |
| 7-Zip | Version 9.28: THG-Workload (1.3 GB) to .7z, command line switches "a -t7z -r -m0=LZMA2 -mx=5" |
| Synthetic Benchmarks and Settings | |
| 3DMark 11 | Version: 1.0.1.0, Benchmark Only |
| SiSoftware Sandra 2013 | Version 2013.01.19.11, CPU Test = CPU Arithmetic / Multimedia / Cryptography / Memory Bandwidth / Cache Bandwidth |

It goes without saying that a 12-core CPU isn’t necessary for gaming. Indeed, when it comes to 3DMark’s Graphics component, the quad-core Sandy Bridge, Ivy Bridge, and Haswell processors are all faster than Intel’s upcoming Xeon E5.
However, the physics test spawns threads for physical and logical cores. Despite its lower clock rate and thermal ceiling, the Xeon E5-2697 V2 pulls down the highest Physics score.

The Core i7-4960X sports the same core configuration as its predecessor. Moreover, the Ivy Bridge architecture didn’t incorporate any instruction set extensions beyond Sandy Bridge’s design. Consequently, the -4960X doesn’t demonstrate any more alacrity in Sandra’s Arithmetic module. The eight-core Sandy Bridge-EP and 12-core Ivy Bridge-EP processors, on the other hand, are quite a bit faster in this synthetic metric.

The same applies to Sandra’s Multimedia test. Intel’s Haswell architecture fares well in the integer component thanks to its AVX2 support, even outperforming Core i7-4960X. However, more on-die resources give Intel’s eight- and 12-core CPUs an advantage. The floating-point tests are outright rocked by both of the Xeon processors.

As with Ivy Bridge-E, Ivy Bridge-EP supports four channels of DDR3-1866 memory. There’s a bit of difference between the quad-channel configurations. But, in essence, you’re seeing the high-end platforms doubling the dual-channel mainstream systems.

Intel’s Core i7-4770K came close, but we now have our first L1 data cache bandwidth result in excess of 1 TB/s. Of course, the Haswell architecture achieves its result through a doubling of L1 throughput compared to Ivy Bridge (this checks out; compare the Core i7-3770K).
The eight-core Sandy Bridge-EP-based Xeon E5-2687W comes close to matching Core i7-4770K by leveraging twice as many cores in this aggregate metric. Ivy Bridge-EP surpasses it with another four cores. Just imagine what a Haswell-based implementation could do!
L2 cache bandwidth aggregates as well, which is why Sandra measures almost 800 GB/s across all 12 cores. L3 is of course shared between the cores, though additional stops on the ring bus contribute to greater throughput in this case, too.

The Photoshop results are interesting, and we’re actively looking into why the results fall the way they do.
To be specific, the CPU-oriented Photoshop test that we run is well-optimized for threading, and you can clearly see performance scaling from the Ivy Bridge-based Core i7-3770K at 1:13 to the Ivy Bridge-EP-based Xeon E5-2697 V2 at :33, using eight additional cores to cut the workload time in more than half.
Our OpenCL-accelerated workload, which should leverage Nvidia’s GeForce GTX Titan, behaves less predictably. As we add processing power on the host side, performance actually gets worse. Quad-core Haswell finishes first, followed by Ivy Bridge. Ivy Bridge-E takes third with Sandy Bridge-E behind. The eight-core and 12-core Xeon E5s are trailed only by AMD’s FX-8350.

We’re working to replace our Premiere Pro workload with something more taxing. This project renders a custom sequence to H.264, but does not reward the addition of cores as much as it does maximum core clock rate. After all, the faster Ivy Bridge-E-based Core i7-4960X outmaneuvers the Xeon E5 we’re focusing on today.

In much the same way, our After Effects demonstrates sensitivity to IPC, clock rate, and available system memory per core due to the Quick Time component invoked in our workload.
Alright, so the Adobe CS 6 testing didn’t really demonstrate Intel’s upcoming Xeon E5-2697 V2 to be a big step forward compared to some of the company’s other processors with higher clock rates and lower core counts. That might sound like an issue for design professionals interested in running Adobe’s software on the upcoming Mac Pro.
However, it’s important to remember that one workload in any given application is not going to completely encapsulate that software’s performance. We know that scrubbing the Quick Time component from our After Effects test completely changes its behavior. And as Photoshop shows us, filters heavily optimized for multi-core CPUs really fly on a 12-core CPU, while those not threaded or tuned for OpenCL don’t see any benefit.

In both 3ds Max 2012 and 2013, Intel’s 12-core Xeon E5-2697 V2 is smoking-fast, slipping right past the eight-core Xeon E5-2687W and upcoming Ivy Bridge-E-based Core i7-4960X. The desktop-oriented CPUs are a ways behind.

This is the greatest victory yet for Intel’s upcoming Xeon E5-2697 V2. It flies past the eight-core Xeon E5-2687W, finishing our Blender workload in less than half the time of a Core i7-4770K. It’s looking like 3D modelers are going to seriously benefit from the potential that Ivy Bridge-EP offers to Apple’s Mac Pro, even in a single-socket configuration.

Based on Maxon’s Cinema 4D software, our scripted Cinebench test measures single- and multi-core processor performance.
In order to fit its 12 Ivy Bridge-based cores into a 130 W thermal design power, the Xeon E5-2697 V2 employs a 2.7 GHz base clock rate. With Turbo Boost enabled, a single core ramps up to 3.5 GHz. That’s slower than the rest of our test platforms in Cinebench’s single-core metric.
The threaded component takes off though, despite a maximum 12-core clock rate of 3 GHz. Intel’s eight-core Xeon E5-2687W is the next-closest comparison point. It spins up to 3.4 GHz with Turbo Boost enabled and all of its cores utilized, but still doesn’t come anywhere close to the Ivy Bridge-EP-based part.

Fully-threaded optical character recognition software FineReader fully utilizes the Xeon E5-2697 V2, finishing our benchmark workload in close to half the time of a Core i7-4770K. It’s even able to shave off 20% of the time from Intel’s 150 W eight-core Xeon E5-2687W. Impressive, indeed.

The decisive victories come to a screeching halt once we fire up PowerPoint and print a document to PDF. This single-threaded test only runs at 3.5 GHz on one Ivy Bridge-EP core. Even last generation’s Core i7-3770K can run this workload at 3.9 GHz.

If you’re in the market for a 12-core processor, there’s a good chance you already know whether your workloads benefit from multiple cores, though. In a compile job like Google’s Chrome Web browser (in Visual Studio), the Xeon E5-2697 V2 cuts big chunks out of the time you spend waiting for this task to finish.

Ivy Bridge-EP sits at the top of our Fritz benchmark, though it’s worth noting that only 16 of the E5-2697 V2’s 24 threads are active. As such, the new Xeon is 66% utilized.

A failure to scale meaningfully tells us little in WinRAR. It’s tempting to point to IPC and clock rate as the primary influencers on performance, except that the Sandy Bridge-E-based Core i7-3930K is in first place.

More so than WinRAR, 7-Zip appears to leverage at least eight cores, perhaps leveraging higher IPC throughput to compensate for lower frequency, and almost tying the Sandy Bridge-EP-based Xeon E5. Both server/workstation-oriented CPUs trounce the more enthusiast-centric models, though.

This chart is sorted according to the most taxing workload, triggered with the –ez command line switch. Almost inexplicably, the Xeon E5-2697 V2 finishes this test in just 35 seconds, which is unbelievably faster than the second-place Core i7-4960X. I ran and re-ran the test, and watched it complete in the same amount of time, plus or minus one second.
The OpenCL-accelerated test interestingly seems to mirror what we saw from Photoshop—that is, the quad-core CPUs with the most modern architectures fare best, while the most complex eight- and 12-core configurations perform worst. There’s definitely something to this…

TotalCode Studio (formerly MainConcept) doesn’t seem to fully utilize the Xeon E5-2697 V2. The Ivy Bridge-EP-based chip is on par with the previous-gen Xeon E5-2687W.

Scaling is pretty minor in our HandBrake transcode as well.

We could have guessed the outcome in iTunes based on our Adobe Acrobat file creation test in PowerPoint. This high-end Xeon necessarily runs at lower clock rates, so in a single-threaded benchmark, it’s at a severe disadvantage compared to more mainstream CPUs.

The same story applies to LAME. In choosing the Xeon E5-2697 V2, you’re accepting lower performance in apps not optimized for threading, assuming that they’re not particularly taxing in the first place, and, in return, getting a massive boost in software able to utilize the processor’s 12 Hyper-Threaded cores.
The biggest news in my Core i7-4960X preview was that, although Ivy Bridge-E didn’t impress in our benchmarks, it absolutely floored us with its efficiency. After multiplying performance by average power consumption, we discovered that the high-end -4960X was actually more efficient than a Core i7-2700K.
Intel’s upcoming Xeon E5-2697 V2 will also be a 130 W part. But because it sports twice as many cores, we’re expecting its power consumption throughout our suite to be measurably higher (particularly in the threaded tests).
We’re still logging power through the entire Tom’s Hardware benchmark suite every two seconds, and we continue adding a half-hour of idle time to the end of the test, bringing down average power on purpose to better-reflect a real-world usage model. However, I discovered something that required re-running my power data.
SiSoftware Sandra gets run alongside the other benchmarks. This diagnostic’s cache module tests the L1 data and instruction caches with 13 data points for every core. On a six-core processor, that’s 468 tests. On a 12-core processor that’s 936 tests. As a result, this isn’t a faster-is-better benchmark, so it throws off the performance-oriented efficiency result. The solution was to rem out Sandra from the power run and re-run those numbers. Unfortunately, I don’t have the Core i7-4960X anymore, so we have to leave that data point out for now…

None of the CPUs in this comparison can come close to Core i7-4770K’s amazingly-low idle power numbers. In fact, the 12-core Xeon E5 idles pretty high compared to the Core i7-3970X and Xeon E5-2687W. But it’s also the fastest—you can see the red line ending first in our chart.

Sure enough, the Haswell-based Core i7-4770K turns in the lowest average power number. Not surprisingly, the 130 W Xeon E5-2697 V2 follows, with the 150 W Sandy Bridge-EP- and Sandy Bridge-E-based chips behind.

Despite high idle power use, a number of single-threaded benchmarks that penalize it, and lots of artificially-injected idle time that favors the rest of the field, Intel’s upcoming 12-core Xeon E5-2697 V2 turns in the second-best efficiency rating.
The outcome isn’t as impressive as our look at Ivy Bridge-E. Then again, this page isn’t ever going to favor the most complex hardware configurations. Most exciting is that Intel has a 12-core processor with 30 MB of shared L3 cache that not only works with the previous-generation ecosystem, but also offers more performance than the eight-core Sandy Bridge-EP CPUs it succeeds, while cutting TDP by 20 W. That’s more performance, less power, and, as we can see, better efficiency.
Based on Intel’s exhaustive roadmap, it’s pretty clear how this year and next year are going to go down.
Ivy Bridge-E is coming up next. We know from Intel Core i7-4960X Preview: Ivy Bridge-E, Benchmarked that there’s not a whole lot to excite enthusiasts. Incremental performance gains and impressive efficiency won’t justify upgrading, and the X79 platform isn’t going to get anyone excited about building a new box.
Then we’re going to start seeing Haswell-based Core i3 and Pentium processors, followed by soldered-down Bay Trail-D Pentiums in Q4’13. That’ll be exciting, if only because the mainstream stack will consist of Haswell and Silvermont (I’m personally really looking forward to that architecture).
Next year we’ll get a “Haswell refresh,” along with the 9-series chipsets. And that’ll be followed by Haswell-E, which breaks processor interface compatibility with X79. If all goes according to plan, expect to see the first eight-core high-end desktop CPUs in the second half of next year.
Until then, enthusiasts have to look to the server and workstation space for evidence that Intel is still very much active beyond its aspirations to counter ARM’s momentum in the low-power space. Upcoming Ivy Bridge-EP-based Xeon E5s will operate within the same thermal envelopes as Intel’s LGA 2011-based Core i7s, but in four-, six-, eight-, 10-, and 12-core configurations. Most will drop into dual-socket platforms, though single- and quad-interface models are planned, too.
Of course we’d all love to see Intel pull out the stops and get enthusiasts excited with an eight-, 10-, or 12-core high-end desktop chip. But there’s just no business case to eat into sales of Xeon E5s.
Apple is going to have them in its next-gen Mac Pro workstations, and it’ll be interesting to see how much a 12-core Xeon E5 adds to the small cylinder’s price tag. Given a number of motherboard vendors that added Xeon E5 support to their X79 platforms, you should be able to build your own 12-core workstation running Windows. But if you thought that $1000 for an Extreme Edition CPU was nuts, just wait till you hear what a Xeon E5-2697 V2 will run you.