Puget Systems print logo


Read this article at https://www.pugetsystems.com/guides/588

Game Benchmarks

Haswell-E 5960X 5930K 4960X benchmark - Gaming

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 5960X 5930K 4960X CPU Temperature

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:

Haswell-E 5960X 5930K 4960X CPU Fan Speed

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.

Haswell-E 5960X 5930K 4960X Power Draw

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.


Asus X99 DeluxeSince 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.

< Previous
Tags: X99, Haswell-E, X79, Ivy Bridge-E, 5960X, 5930K, 4960X, Benchmark

A processor with 8 cores is good enough for most of people. So hopefully next gen will boost its clock to improve single core performance instead adding more cores.

Posted on 2015-07-03 19:12:56
John Og Elisabeth Andersen

I am pretty sure that the way it will go is more cores slower speeds for multiple reasons. One of the main reasons being, that we can make transistor smaller.

Visit my build here: http://computer.bazoom.com/dk/...

Posted on 2015-10-17 10:27:58
Daniel Padia

they did the exact opposite of what you said, lol. 6950x

Posted on 2016-06-01 23:41:54

Well to be fair they DID improve single core IPC performance by roughly 10%. A 4.4ghz i7 6800K is easily equal to a 4.7ghz i7 5820K. I've seen some people on overclock.net saying their ~4.3ghz i7 6900K 8 cores are as fast as their golden silicon lottery winning i7 5960X running at 4.7ghz. That's a "400mhz increase" in performance so to speak. (i.e. The broadwell-e gives identical performance to the haswell-e despite running roughly 400mhz lower max clock speed) And since, for example, the i7 6900K runs at a stock speed of 3.7ghz we can find out that my 10% estimate is pretty accurate, for example, 10% of 3700mhz/3.7ghz = 370mhz. If we add 370mhz to 3700mhz we get 4070mhz or 4.07ghz. That's DAMN close to the actual "400mhz" performance difference i just said people are seeing with Broadwell-E (technically its 10.8%, but that's close enough. i did say ROUGHLY lol)

So if we combine that knowledge of 10.8% increased performance on Broadwell-E and then factor in that the 8 core i7 6900K runs 200mhz faster than 5960X (3.7ghz boost clock speed compared to the 3.5ghz boost on 5960X) we can actually see the difference of what a "stock" 6900K would have over a stock 5960X.

3700mhz * 110.8% = Speed that a 5960X would have to run at to be as fast as a stock 6900K

3700mhz * 110.8% = 4099mhz, (i.e. 4.1ghz)

This means that a stock 3.7ghz 6900K is as fast as a 4100mhz or 4.1ghz 5960X. And since most Broadwell-E chips overclock to 4.3ghz or 4.4ghz if you push voltage (good samples can reach 4.4ghz at safe ~1.3v ranges sometimes) we can compare overclocked too

4300mhz * 110.8% = Speed that an overclocked 5960X would have to run at to be as fast as an overclocked 6900K

4300mhz * 110.8% = 4764mhz (i.e. 4.764ghz) That's a 476mhz increase!

So lets round the number and just say that a 4.3ghz Broadwell-E 6900K is as fast as a 4.75ghz 5960X!!

That's not a bad performance increase frankly, at least considering Intel's slow crawl of CPU gains lately. If you think about it, this is BROADwell, NOT SKYLAKE! But Broadwell-E is having as big of a performance increase over Haswell-E as we got moving from Haswell 4790K to Skylake 6700K!!

And if you can get a "gold silicon lottery" chip you're in an even BETTER situation comparing Broadwell-E to Haswell-E. Let's try a 4.4ghz which we know is possible at just over 1.3v on "good lottery chips", and then since HWBot has already shown a record of 4.6ghz on a 6800K we can assume 4.5ghz is possible at ~1.4v which is still "relatively" safe, so we'll use that too.

4.4ghz Broadwell-E * 110.8% = 4,875mhz!!! So a 4.4ghz Broadwell-E 6900K is equal to a whopping 4.875ghz 5960X!!! I don't think i've seen a SINGLE 5960X hit over 4.7ghz even on water cooling, only with phase change or liquid nitrogen!

Now, the finale. The "golden lottery winner" 4.5ghz ~1.4v chip

4.5ghz Broadwell-E * 110.8% = 4,986mhz!!!!! So a 4.5ghz Broadwell-E 6900K is equal to a fucking MASSIVE ~5GHZ 5960X!!!!!

Posted on 2016-06-20 09:00:05

Ok, now I feel bad about the used 5960x I just bought, thanks. :D

Posted on 2016-07-20 09:22:22

Which one of these benchmarks is most like calculating formulas in a massive Excel 2010 32-bit spreadsheet? If I had to guess, many upgrade taking place in the work place are inspired by the frustration of watching a slow calculation every time you open, make changes to or save a massive spreadsheet.

Posted on 2015-07-08 16:28:08

A good review with interesting results, Thanks.
It would of been nice to see some overclocking data too though. :)

Posted on 2015-07-22 11:55:37