Page 1:Preface: Where's The Innovation In High-End Desktops?
Page 2:Intel's Xeon E5-2697 V2 And Leaked Benchmarks
Page 3:Test Setup And Benchmarks
Page 4:Results: Synthetics
Page 5:Results: Adobe CS6
Page 6:Results: Content Creation
Page 7:Results: Productivity
Page 8:Results: Compression Apps
Page 9:Results: Media Encoding
Page 10:Power Consumption: Does Ivy Bridge-EP Impress?
Page 11:Xeon E5-2600 V2: The Real Innovation Happens Up Top
Power Consumption: Does Ivy Bridge-EP Impress?
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.
- Preface: Where's The Innovation In High-End Desktops?
- Intel's Xeon E5-2697 V2 And Leaked Benchmarks
- Test Setup And Benchmarks
- Results: Synthetics
- Results: Adobe CS6
- Results: Content Creation
- Results: Productivity
- Results: Compression Apps
- Results: Media Encoding
- Power Consumption: Does Ivy Bridge-EP Impress?
- Xeon E5-2600 V2: The Real Innovation Happens Up Top