The Intel Core i5-7600K (91W) Review: The More Amenable Mainstream Performerby Ian Cutress on January 3, 2017 12:01 PM EST
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.
Here we report the overall time to complete the test – sub-test results can be found in Bench.
The Core i5-7600K does well in the sub-tests that are more IPC dependent, but there are more sub-tests that revolve around threads and frequency and pure single-core grunt. As a result the i5-7600K pretty much matches the i5-6600K for performance.
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.
All the Kaby Lake processors seem to do well in CB15 single threaded performance, given that all the K-processors can reach 4.2 GHz or higher one way or another. This puts the i5-7600K on par with Devil’s Canyon when we factor in the IPC change as well.
Common consensus is that CB15 scales with threads, however the Core i5-7600K sits above the Core i7-2600K thanks to frequency and IPC gains over the years.
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.
Both the HandBrake tests essentially mirror what we saw in CB15 – the Core i5-7600K is there or thereabouts when frequency is the main factor, and when we stick a register-heavy threaded situation in the path, the effect from not having hyperthreading compared to the Core i7-7700K is relatively muted – in this case the i7 is only +20% performance over the i5, despite costing nearly 50% more.
Hybrid is a new benchmark, where we take a 4K 1500 frame video and convert it into an x265 format without audio. Results are given in frames per second.
Our Hybrid test is somewhat similar to the HandBrake HQ test, showing the fact that heavy threads reduce the efficacy of hyperthreads.