Professional Performance: Windows

Agisoft Photoscan – 2D to 3D Image Manipulation: link

Agisoft Photoscan creates 3D models from 2D images, a process which is very computationally expensive. The algorithm is split into four distinct phases, and different phases of the model reconstruction require either fast memory, fast IPC, more cores, or even OpenCL compute devices to hand. Agisoft supplied us with a special version of the software to script the process, where we take 50 images of a stately home and convert it into a medium quality model. This benchmark typically takes around 15-20 minutes on a high end PC on the CPU alone, with GPUs reducing the time.

Agisoft PhotoScan Benchmark - Total Time

The variable workload of Agisoft means there are parts where the code path is single threaded and others where multithreading is near perfect. As a result we see the overclocked i3 march past almost all the AMD parts but not up to the Core i5s.

Cinebench R15

Cinebench is a benchmark based around Cinema 4D, and is fairly well known among enthusiasts for stressing the CPU for a provided workload. Results are given as a score, where higher is better.

Cinebench R15 - Single Threaded

Cinebench R15 - Multi-Threaded

HandBrake v0.9.9: link

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 2x4K

At double 4K, Handbrake requires enough cache and buffers to keep supplying frames. The Core i3 line has a reduced L3 compared to the Core i5s, but also has to share it between threads (1.5MB/thread compared to 2MB per core) which can cause bottlenecks.

Core i3-6100TE Office and Web Performance Core i3-6100TE Professional Performance: Linux
Comments Locked

62 Comments

View All Comments

  • nathanddrews - Thursday, March 17, 2016 - link

    Predicating the value of i3 overclocking as a whole on the 6100TE is absurd, don't you think? The 35% OC of the 6100TE is still slower than the base clock speed of the vanilla 6100 (3.7GHz), which when OCed over 4.2GHz offers a tremendous value. For the same price - why on earth would you buy the much slower 35W variant if your goal is overclocking?

    http://ark.intel.com/compare/90729,88181

    From the standpoint of motherboard/BIOS SKYOC availability alone I would agree that the case is now somewhat moot, but I think the case that has already been made months ago by DigitalFoundry and others is that the SKYOC i3 (normal i3 CPUs that you can buy) makes a very strong value. It's a shame that mobo vendors caved so quickly.
  • dualsmp - Thursday, March 17, 2016 - link

    I suspect politics is a work here. Also, the conclusion would be more clear cut with the 6100 rather than a bit nebulous with the 6100TE.

    Remember how fast Intel shutdown overclocking after the Clarkdale i3? When the Clarkdale i3 was overclocked it was nipping at the heels of Intel's more expensive parts at the time. The Clarkdale i3 offered too much value for the money when overclocked, so Intel had to shut it down.
  • ImSpartacus - Thursday, March 17, 2016 - link

    You're probably right about the politics. It's a shame, but Anandtech is probably under Intel's finger.
  • alistair.brogan - Thursday, March 17, 2016 - link

    Is there hope for an AMD Zen dual core that will overclock? That's all I'd recommend for people :)
  • ImSpartacus - Friday, March 18, 2016 - link

    If zen is only 40% better ipc than excavator, then it won't be leading Intel and amd will still need high clocks compete. So I would bet that the stock zen parts might be using up a fair bit of that overclocking headroom.
  • alistair.brogan - Thursday, March 17, 2016 - link

    I think a properly overclockable i3 would hit 4.5ghz, just like an i5 can, so imagine the results in that case. It wouldn't "maybe" be worth it, it would absolutely by awesome. Which is why Intel doesn't allow it..... don't want people buying 4.5ghz i3's and saying good bye to the expensive i5s
  • dragosmp - Thursday, March 17, 2016 - link

    Thanks for the review, it's a good reference point.

    I thought at some point the lowest end Xeon v5 (4C/8T) was quite a bit cheaper than the 6700K and much more available. If that could be OCed, and I think some motherboards like Gigabyte's Cxxx say they could, that would have been the fastest CPU while keeping some money in the pocket.

    Agreed with getting older and putting a higher value on our time, but if my kid decides to leave me alone for a while I still like to tinker with OCing
  • Samus - Friday, March 18, 2016 - link

    It's true Xeon's are usually priced between the i-series and i-series k equivalents (there are i5 and i7 based Xeon's) so it would be cheaper than a "k" part while giving you ECC and full vPro support, not to mention Xeon's appear to have soldered heatspreaders when starting with Ivy Bridge, everything but Xeon's were shipped with pretty subpar TIM/paste. That only slightly improved with Devils Canyon...they still weren't fused lid-to-die like a Xeon.

    There are a few theories why Intel uses solder on Xeon CPU's. One is obviously temperature and 24/7 consistency. The most plausible reason, though, is the weight and pressure of server cooling solutions (compared to most OEM PC coolers and water blocks. I weighed a tiny 1U Xeon cooler once. This thing was like 20mm tall, and it still weighed 870 grams. That's 2 lbs! Pure block of copper fins. Tightened down to 25Nm and exposed to the pressure, vibration and temperatures of a 1U environment for years, you can take a guess why Intel makes the Xeon lids more durable.
  • extide - Thursday, March 17, 2016 - link

    Please do that future piece, anyone who is seriously considering doing this will definitely not be sing the T or TE series chips, and as you mentioned you can't even really get them in the retail market. I would really like to see what a 4.4-4.6Ghz i3 can do.
  • LostWander - Thursday, March 17, 2016 - link

    The idea is to show how close to i5 performance you can get while paying the price of an i3. Although it would be interesting to see how well the i5 overclocks too so we can see how close to K performance we can get for a non-k price.

Log in

Don't have an account? Sign up now