Table of Contents
Table of Contents
Typically, a new CPUs is faster than it's predecessor – it is just a question of whether is it by a little or a lot. The new Intel 5960X, however, is not typical because it sacrifices clock speed in order to add more cores. More cores is definitely better from a forward-thinking standpoint, but currently there is a lot of software that is not coded very well for multithreading so the drop in clock speed may cause a drop in performance.
The Intel Core i7 5960X is an eight core 3.0GHz CPU that has a maximum turbo boost of 3.5GHz. This means that while it has two more cores than the Core i7 4960X, it also has a .5-.6GHz drop in clock speed.
|Max Turbo Boost||3.5GHz||3.7GHz||4.0GHz|
|L2 Cache||8 x 256KB||6 x 256KB||6 x 256KB|
|PCI-E Lanes||40 PCI-E 3.0||40 PCI-E 3.0||40 PCI-E 3.0|
In this article we want to run a wide variety of benchmarks to find out what applications benefit from the additional cores and which suffer from the drop in clock speed. In order to provide another point of comparison, we will also be including the new Intel Core i7 5930K in our testing. It doesn't have quite as high of a clock speed as the 4960X, but it is high enough that with the other improvements in Haswell-E and X99 it may actually outperform the 4960X.
It's worth pointing out that while we are primarily focusing on the CPU, Haswell-E uses the new X99 chipset which includes many improvements including DDR4 support. So in addition to the CPU itself, the chipset and DDR4 RAM may very well affect our benchmarks. For more information on what is new in Haswell-E and X99 we recommend reading our X79 vs X99: What is new in X99 and Haswell-E article.
To benchmark these CPUs, we used the following hardware:
|Motherboard:||Asus X99 Deluxe||Asus P9X79 Deluxe|
Intel Core i7 5960X 3.0GHz Eight Core
Intel Core i7 5930K 3.5GHz Six Core
|Intel Core i7 4960X 3.6GHz Six Core|
|RAM:||4x Crucial DDR4-2133 CL15 4GB||4x Kingston DDR3-1600 CL9 4GB|
|GPU:||Asus GeForce GTX 780 Ti 3GB DirectCU II OC|
|Hard Drive:||Samsung 850 Pro 128GB SATA 6Gb/s SSD|
|OS:||Windows 8.1 Pro 64-bit|
|PSU:||Antec HCP Platinum 850W|
|Chassis:||Fractal Design Arc Midi R2|
Corsair Hydro Series H60 CPU Cooler (Rev. 2)
w/ Cooljag Everflow 120mm PWM fan
|System Cooling:||2x front Fractal 140mm intake, 1x top Fractal 140mm exhaust, 1x side Fractal 120mm intake @ 5v|
For the majority of our testing, we used two systems to expedite our testing. For the thermal and power draw portions, however, we used the exact same CPU cooler, chassis, and power supply to remove as many variables as possible. For the duration of our testing, the CPU fan was set to the standard QFan profile and the chassis fans were run at 5v.
All Windows, driver, and software updates were applied prior to testing.
Synthetic & Scientific Benchmarks
Starting with the single core portion of GeekBench 3, we see the first evidence of performance issues with the 5960X. Since it only has a clock speed of 3.0-3.5 GHz, it has a lower GeekBench score than either the 5930K or 4960X. What is interesting is that the 5930K outperforms the 4960X even though it's maximum turbo frequency is .4 GHz lower. This is a good sign for the Haswell-E architecture as a whole and suggests that the 5930K may outperform both the 5960X and 4960X in single-threaded applications.
One thing we want to point out is the low memory score on both the 5960X and 5930K. These CPUs use the new DDR4 memory running at 2133MHz versus the DDR3 memory running at 1600MHz we used with the 4960X. One benchmark is obviously not conclusive, but this does suggest that DDR4 memory might not have much of a performance advantage over DDR3 quite yet.
Moving on to the multi core portion of GeekBench 3, we see where the 5960X really shines. With eight cores, it easily outperforms both the 5930K and 4960X. Interestingly, the 5930K performs about the same as the 4960X in this test even though its single core performance was better.
Unlike the single core benchmark results, the memory score with DDR4 on the Haswell-E CPUs is actually higher than the 4960X.
CineBench R15 is a great rendering benchmark based on MAXON's CINEMA 4D software that measures single and multi core performance as well as OpenGL graphics performance. In this benchmark, all three CPUs get effectively the same score on the single core portion of the benchmark, but the 5960X really pulls ahead in the multi core portion.
The OpenGL portion of CineBench is supposed to measure the performance of the GPU so we didn't expect to see much difference between the three CPUs. Oddly, both of the Haswell-E CPUs outperformed the 4960X by a healthy margin. This may just be an aberration, or it may be an indicator that GPU intensive tasks might see a benefit when using a Haswell-E CPU.
Linpack is a standard benchmark in the scientific community that measures a system's floating point computing power. This benchmark can take advantage of the AVX2 instruction set that is included in Haswell-E which is clearly shown by the large increase in performance. The 5930K is anywhere from 27-75% faster than the 4960X and the 5960X is anywhere from 45-114% faster depending on the problem size.
This is amazing for the scientific community, but we want to be clear that for the average user this is not really an indicator that Haswell-E will double your performance. To find out how much of a performance increase you could expect in a variety of situations, lets move on to some real-world benchmarks.
To benchmark the performance of Photoshop, we applied a number of effects to both a 110MB and 1GB image and recorded how long it took for each effect to finish. These effects include CMYK Color Conversion, RGB Color Conversion, Ink Outlines, Dust and Scratches, Watercolor, Stained Glass, Lighting Effects, Mosaic Tiles, Extrude, Smart Blur, UnderPainting, Palette Knife, and Sponge.
The 110MB image shows roughly a 5% drop in performance with the Haswell-E CPUs compared to the 4960X. The 1GB image also shows a drop in performance, but the 5960X is a bit better than the 5930K. What this means is that if you use Photoshop a lot and already have a 4960X CPU, you probably should not upgrade to a Haswell-E CPU.
Unlike Photoshop, Premiere Pro appears to like the new Haswell-E CPUs. The parts of the benchmark that uses GPU acceleration doesn't show much difference between the three CPUs, but the portion that is CPU only shows almost a 30% performance increase with the 5960X compared the the 4960X. The 5930K is also better than the 4960X, but only by about 5%.
The Cadalyst benchmark for AutoCAD 2015 is interesting because it shows a slight performance increase with Haswell-E on the CPU and 2D Graphics tests, but a larger performance increase in the 3D Graphics portion. This increase in 3D performance is reminiscent of the OpenGL performance in CineBench we saw earlier and is something we did not expect to see.
Handbrake is an open source video transcoder that reports performance in the number of frames it is able to process per second. As you can see, the 5930K is almost identical in performance to the 4960X. The additional cores on the 5960X, on the other hand, give it a nice ~10% performance boost over the 4960X.
Unlike Handbrake, Lame is not multithreaded so the number of CPU cores you have does not affect performance. Because of this, both the 5930K and 5960X (both of which have a lower frequency than the 4960X) show about a 6-9% drop in relative performance.
In our three gaming benchmarks, the 5930K performs almost identically to the 4960X. The 5960X, however, sees a very slight drop in performance of about 1%. This is a really small performance variance, so at least for these titles and settings it appears that Haswell-E (and consequently DDR4) does not offer any performance advantage for gaming right now.
Temperature & Power Draw
Haswell-E CPUs have a TDP of 140W so we expected them to run hotter than Ivy Bridge-E which has a TDP of only 130W. Interestingly, however, both the 5960X and 5930K ran cooler than the 4960X both at idle, high CPU load, and high CPU+GPU load.
Our test systems are using QFan, however, so it is possible that the fan ramping is simply more aggressive on X99 than it is on X79:
At idle the CPU fan is running slower on Haswell-E so at least at that point Haswell-E is definitely cooler than Ivy Bridge-E. When running Prime95, the CPU fan is running a bit faster on the 5960X compared to the 4960X, but 55 RPM is nowhere near enough to account for the 5 °C reduction in temperature.
Prime95 + Furmark is about as heavy a load you can put on a system, and interestingly the X99 system ended up ramping up the CPU fan about 200 RPM faster than the X79 system. This indicates that our X99 motherboard has a bit more aggressive fan profile than our X79 board, but is once again not enough to account for the 6-7 °C drop in temperature.
In other words, even though Haswell-E has a higher TDP than Ivy Bridge-E, it appears that it actually runs cooler both at idle and load.
The total system power draw also surprised us a bit. We expected lower idle wattage since Haswell-E and X99 introduces a number of low power improvements (including DDR4), but the 30-40 watt drop in power draw under load is not something we expected.
Since Haswell-E sacrifices clock speed in exchange for more CPU cores, our benchmarks show two very different stories. Applications like Premiere Pro, AutoCAD, and HandBrake showed the benefits of the 8 cores on the 5960X, but others like Photoshop and Lame showed the downsides to the lower frequency found on Haswell-E. At the same time, our gaming benchmarks really didn't seem to care what CPU we used since the GPU is by far a bigger factor in those games.
In addition, there are a couple of benchmarks that show the benefits of using the latest generation of CPU regardless of the frequency or core count. For example, Linpack clearly shows the potential performance benefit of using the latest instruction sets. 350 GFlops is a very impressive Linpack score that until Haswell-E launched was frankly not possible with a single CPU system. In addition, the increased 3D performance in CineBench and AutoCAD is something we did not expect to see and is certainly due to something new in either the CPU, chipset, or possibly even from the new DDR4 memory.
While Haswell-E might not perform better than Ivy Bridge-E in all applications, the one area it is definitely better is in temperature and power draw. With the higher TDP we expected Haswell-E to run hotter than Ivy Bridge-E, so a 5-7 °C drop in temperature is a very nice unexpected surprise. The lower system power draw was expected to a degree, but we only expected a 10-20 watt drop, not the 30-40 watt drop we actually recorded.
Overall, Haswell-E and X99 feel to us like a platform of the future. It may not outperform Ivy Bridge in all applications, but the eight cores on the 5960X and DDR4 support makes it a much more future-proof platform than Ivy Bridge-E. In addition, the X99 chipset with native USB 3.0, ten SATA 6Gb/s, and M.2 support also leads itself to being a very forward-thinking platform. If you need the absolute best possible performance today, we highly recommend finding a benchmark for your specific application before deciding to use Haswell-E or Ivy Bridge-E. However, if you want a system that will last much longer and take advantage of future software improvements, Haswell-E is a much better choice in our opinion.