CPU Real World Performance

A small note on real world testing against synthetic testing – due to the way that DRAM affects a system, there can be a large disconnect between what we can observe in synthetic tests against real world testing. Synthetic tests are designed to exploit various feature XYZ, usually in an unrealistic scenario, such as pure memory read speeds or bandwidth numbers. While these are good for exploring the peak potential of a system, they often to not translate as well as CPU speed does if we invoke some common prosumer real world task. So while spending 10x on memory might show a large improvement in peak bandwidth numbers, users will have to weigh up the real world benefits in order to find the day-to-day difference when going for expensive hardware. Typically a limiting factor might be something else in the system, such as the size of a cache, so with all the will in the world a faster read speed won’t make much difference. As a result, we tend to stick to real world tests for almost all of our testing (with a couple of minor suggestions). Our benchmarks are either derived from areas such as transcoding a film or come from a regular software format such as molecular dynamics running a consistent scene.

Handbrake v0.9.9

For HandBrake, we take two videos (a 2h20 640x266 DVD rip and a 10min double UHD 3840x4320 animation short) and convert them to x264 format in an MP4 container.  Results are given in terms of the frames per second processed, and HandBrake uses as many threads as possible.

HandBrake v0.9.9 LQ Film

HandBrake v0.9.9 HQ Film

The low quality conversion is more reliant on CPU cycles available, while the high resolution conversion seems to have a very slight ~3% benefit moving up to DDR4-3000 memory.

WinRAR 5.01

Our WinRAR test from 2013 is updated to the latest version of WinRAR at the start of 2014. We compress a set of 2867 files across 320 folders totaling 1.52 GB in size – 95% of these files are small typical website files, and the rest (90% of the size) are small 30 second 720p videos.

WinRAR 5.01

The biggest difference showed a 5% gain over DDR4-2133 C15, although this seemed at random.

FastStone Image Viewer 4.9

FastStone Image Viewer is a free piece of software I have been using for quite a few years now. It allows quick viewing of flat images, as well as resizing, changing color depth, adding simple text or simple filters. It also has a bulk image conversion tool, which we use here. The software currently operates only in single-thread mode, which should change in later versions of the software. For this test, we convert a series of 170 files, of various resolutions, dimensions and types (of a total size of 163MB), all to the .gif format of 640x480 dimensions. Results shown are in seconds, lower is better.

FastStone Image Viewer 4.9

No difference between the memory speeds in FastStone.

x264 HD 3.0 Benchmark

The x264 HD Benchmark uses a common HD encoding tool to process an HD MPEG2 source at 1280x720 at 3963 Kbps. This test represents a standardized result which can be compared across other reviews, and is dependent on both CPU power and memory speed. The benchmark performs a 2-pass encode, and the results shown are the average frame rate of each pass performed four times. Higher is better this time around.

x264 HD 3.0, 1st Pass

x264 HD 3.0, 2nd Pass

The faster memory showed a 2.5% gain on the first pass, but less than a 1% gain in the second pass.

7-Zip 9.2

As an open source compression tool, 7-Zip is a popular tool for making sets of files easier to handle and transfer. The software offers up its own benchmark, to which we report the result.

7-Zip 9.2

At most a 2% gain was shown by 3000+ memory.

Mozilla Kraken 1.1

One of the more popular web benchmarks that stresses various codes, we run this benchmark in Chrome 35.

Mozilla Kraken 1.1

Kraken seemed to prefer the fast 1.2V memory, giving a 4.8% gain at DDR4-2800 C16, although this did not translate into the faster memory.

WebXPRT

A more in-depth web test featuring stock price rendering, image manipulation and face recognition algorithms, also run in Chrome 35.

WebXPRT

The DDR4-3200 gave an 11% gain over the base JEDEC memory, although this seemed to be more of a step than a slow rise.

Enabling XMP Memory Scaling on Haswell: Professional Performance
POST A COMMENT

120 Comments

View All Comments

  • Flunk - Thursday, February 5, 2015 - link

    "There is one other group of individuals where super-high frequency memory on Haswell-E makes sense – the sub-zero overclockers."

    Yeah, I'm sure the 200 people on the planet who care about that are a real big market...

    Nice article overall though. I don't know why, but I was expecting more from DDR4. It looks like there is little reason to upgrade right now. Although I expect we'll all end up being forced into it by Intel.
    Reply
  • Antronman - Thursday, February 5, 2015 - link

    There's a lot of consumers who want high clocked memory just because they want it.

    And there's more than 200 extreme overclockers on the planet.
    Reply
  • galta - Thursday, February 5, 2015 - link

    The reason to upgrade today is not DDR4 per se, but 5xxx CPUs, and you might want these CPUs because of the extra cores, extra pci lanes, both, or just because you want it and can pay for it.
    These discussions over RAM get me tired. Rocks on the streets know that:
    a) fast memory makes close to no difference in real world, especially today with overclocking being so much more friendly than it was in the past
    b) whenever a new standard is introduced, it performs poorly when compared to previous standard. It was like this with DDR3 back in 2008 and it's the same today, but today you probably have less than 200 people saying they miss DDR2.
    Let's discuss more interesting and reasonable subjects.
    Reply
  • Murloc - Thursday, February 5, 2015 - link

    200? You're severely underestimating the number of people who do that.

    Also why do car companies make cars that are going to be driven by just a few sheiks?

    With rams it's probably even easier given that you just have to bin chips and there are people who buy them just because they want the best. That's why they put increasingly cooler heatsinks and packages on the more pricey sticks. Not because they really need additional cooling in non-extreme use cases.
    Reply
  • FlushedBubblyJock - Sunday, February 15, 2015 - link

    Because the elite cater to the elite, and the clique' is small and expensive, and leeches off the masses for the advantage and opulent and greedy lifestyle and media hype and self aggrandizement.
    They can fly each other around the world for huge parties and giveaway gatherings called global contests and spend enormous sums and feel very important.
    Reply
  • imaheadcase - Thursday, February 5, 2015 - link

    Wait a tick, DDR2 is 800+mhz. That is what its default to on both my systems. Reply
  • imaheadcase - Thursday, February 5, 2015 - link

    You put 200-533 MHz. My is actually at 936mhz for the overclock to. Reply
  • ZeDestructor - Thursday, February 5, 2015 - link

    DDR = Double Data Rate, i.e: two operations are done per clock cycle. Thus the frequency is 400, but the effective frequency is 800. Same applies for DDR1-DDR4.

    GDDR5 is crazier: 4 operations per clock cycle, so 1750MHz works out to 7000MHz effective.
    Reply
  • Murloc - Thursday, February 5, 2015 - link

    so basically what we knew all along: many enthusiasts are just wasting their money. The same goes for size although few people who build PCs are that stupid when it comes to this, it's mostly gamers who buy pre-built PCs who fall into this trap (it's not like they have much of a choice anyway, everybody is selling computers with lots of RAM and a pricey CPU bottlenecked by a weak GPU because it makes them money). Reply
  • fredv78 - Thursday, February 5, 2015 - link

    seems to me most benchmarks are within the error margin (which is usually up to 3% and ideally should be quoted) Reply

Log in

Don't have an account? Sign up now