AMD Carrizo Part 2: A Generational Deep Dive into the Athlon X4 845 at $70by Ian Cutress on July 14, 2016 9:00 AM EST
Office Performance at 3 GHz
All of our benchmark results can also be found in our benchmark engine, Bench.
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.
Looking at the subtests for Photoscan, Carrizo's biggest hiccup was in the first stage which loads images into memory and attempts to identify and compare similar points in the photograph and its location relative to the object. This requires a significant amount of memory management, and Carrizo loses 17% in the first stage to Kaveri. Stage 4 gets a bump with Carrizo over Kaveri, enough to bring it back over Trinity and Richland, but overall the Carrizo part is still 6% down.
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.
Similar to Dolphin and 3DPMv2, Carrizo's microarchitectural changes help with CineBench 15 as well. Kaveri appearing on the same level as Trinity/Richland for single threaded is as expected, with the better multithreading handling coming through in the second test.
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.
Typically we expect something like video conversion to be memory intensive, especially with codec decone/encode, however the base microarchitecture gives Carrizo an 8% lead and a 9% lead over Kaveri in our low quality and double UHD tests.
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.
However, with x265. both Kaveri and Carrizo perform similarly.
Post Your CommentPlease log in or sign up to comment.
View All Comments
artk2219 - Thursday, July 14, 2016 - linkThey had too many parts that weren't hitting their mobile TDP's, or they just bakes too many chips than was needed on the mobile side. Either way, why let them sit in a warehouse or toss them at a loss, when for a very smalla mount you can just throw them into your standard desktop package and make some extra sales.
TheinsanegamerN - Thursday, July 14, 2016 - linkCarrizo and kaveri did not use hypertransport. They would have to re-engineer their chip to work on AM3+, and to be frank, the AM3+ market is just too small to justify the tiny margins they would get.
That money is better spent on getting zen out of the door.
neblogai - Thursday, July 14, 2016 - linkWhy invest into upgrading bad product, when you can sell the same Bulldozer cores till Zen comes? And this Carriso Athlon is just a by-product of a mobile part and can only be sold for desktop. It all makes sense financially. By the way, new Bristol Ridge AMD 15W APUs are really nice and competitive, but laptop manufacturers are failing again- for example, HP Envy x360 comes with FX-9800P APU- again in single channel memory memory configuration, also with HDD installed and without possibility to use SSD. https://hardforum.com/threads/unboxing-1st-impress...
TheinsanegamerN - Friday, July 15, 2016 - linkAMD doesnt take the mobile market seriously. If they did, they would be partnering up with the likes of MSI or clevo to produce a good laptop line for their APUs, or at the very least make dual channel a strict requirement.
The_Countess - Tuesday, July 19, 2016 - linkAMD unfortunately can't demand much of anything from OEM's currently.
and as intel still has a defacto monopoly no OEM wants to piss of intel by making a better AMD laptop.
nathanddrews - Thursday, July 14, 2016 - linkSo... will there ever be a desktop Carrizo w/IGP? Much of the hype around Carrizo was focused on its very low power video playback, including H.265 hardware encode/decode.
stardude82 - Thursday, July 14, 2016 - linkIsn't that what Bristol Ridge is? But on the new AM3 socket.
Arnulf - Thursday, July 14, 2016 - linkAM4.
Pissedoffyouth - Thursday, July 14, 2016 - linkWhy not bang 8 of these cores into a 125w TDP and make it for FM2+ or AM3+? Finally an upgrade for Piledriver on AM3
KAlmquist - Friday, July 15, 2016 - linkIf you compare the Athlon 845 with the FX-4350 (link below), the Athlon wins on some benchmarks and loses on others. The Athlon has better IPC, but the FX has a faster clock and a 3rd level cache, leaving no clear-cut winner. If we added an L3 cache to the Athlon chip, that would speed it up, but not by a lot. In other words, Excavator is a big improvement over Piledriver in terms of performance per watt, but not much in terms of absolute performance. An Excavator based FX chip (by which I mean a chip with 8 Excavator cores and 8 MB of L3 cache) would probably be a very marginal improvement over the existing FX lineup at stock frequency, and would have less overclocking potential. I can see why AMD decided not to spend the resources to develop such a chip.