Testing AMD Ryzen and Intel Kaby Lake For Business Use

The nigh interesting processor proclamation of the yr has been AMD's Ryzen desktop processors, based on the company's new Zen architecture. I've been looking forward to AMD getting more competitive in this market for some time, and now that I've had the hazard to run some real benchmarks, I've institute some interesting differences, with AMD looking nifty in some tests, but lagging in other areas.

AMD has historically been Intel's main competitor in desktop and laptops chips, but has lagged appreciably over the past few years, so much and then that it hasn't really been worth trying to compare the two. Just Ryzen is much more competitive—indeed, the acme-of-the-line Ryzen 1800X, based on the company's Summit Ridge platform, offers eight cores and 16 threads, with a nominal clock speed of 3.6 GHz and turbo speeds of upward to 4.0 GHz. It's manufactured on GlobalFoundries' 14nm procedure, sells for $499, and AMD has more often than not been comparison information technology to Intel'southward Core i7-6900K (Broadwell-E), which has a similar number of threads at more than twice the toll.

Over the past several weeks, I've seen a lot of benchmarks comparing the ii Ryzen 7 8-cadre chips to the 6900K. The fastest of the newest Intel fries, the 4-core, viii-thread Cadre i7-7700K (based on the Kaby Lake platform), has a nominal clock speed of 4.two GHz and a turbo speed of 4.5 GHz, and a listing price of $350.

This includes reviews from sites such as Anandtech, Tech Report, our sister publications, ExtremeTech, and Calculator Shopper.

Most of these reviews have focused on general purpose applications, and in general, Ryzen looks pretty good; in gaming, Ryzen does well on 4K tests but somehow seems to lag a scrap in a number of 1080p benchmarks.

But my principal interest is business calculating, and high-end business concern applications in particular. I sympathize why AMD would want to compare Ryzen seven to Broadwell-E, since AMD gives you the same number of cores for less coin, simply I don't meet much for Broadwell-East in business organisation (although I suppose it could take an application in things like video encoding.) Broadwell-E has mainly been pushed for very high-end enthusiast and professional person gaming desktops, and is an older part that's likely to exist replaced soon. Instead, I wanted to look at the latest and greatest from each company, and so I focused on comparing the Ryzen 7 1800X to the Kaby Lake Core i7-7700K.

I thought this would exist peculiarly interesting because AMD's Ryzen 7 has more cores and threads (eight/16 compared to four/eight for the Cadre i7-7700K), just the Core processor has a faster clock (four.2 – four.5 GHz vs. Ryzen'due south 3.six- iv.0 GHz.) Notation though that in that location are other differences, including (notably) that the current Ryzen bit supports only 128-scrap wide AVX (SIMD) instructions, versus 256-chip support on Kaby Lake.

(All tests were run in systems with peak-end MSI Xpower Gaming motherboards, 16 GB of Corsair Vengeance DDR4 retention, a 240 GB Kingston Digital SSD V300 SATA 3 SSD, and an eVGA Nvidia GeForce GTX 1080 graphics board.)

Full general Business concern Tests

CPU-Z sheds light on the raw horsepower of the systems, simply not specifically on business concern functioning. Hither Ryzen vii has a clear atomic number 82, even on the single-threaded examination, which shows the company has made significant progress with its Zen core blueprint. Just information technology really shines on the multi-threaded exam – reflecting its 16 threads compared to the Core i7's eight.

We tested the complete version of this criterion, which runs a serial of scenarios in common business applications. Kaby Lake wins here—in both the conventional and OpenCL-accelerated versions of the test, but Ryzen looks quite good. In the real earth, I'm non sure yous'd observe much departure because—permit's confront information technology—well-nigh typically are now fast enough on only about whatever machine on the market.

While TrueCrypt isn't used equally much as information technology in one case was, information technology remains an interesting benchmark for encryption. Both fries back up AES encryption natively, and simply having more cores made the Ryzen shine on this examination.

seven-Zip is a popular compression/decompression programme for Zip files. Hither the results are very interesting, with Kaby Lake much faster at pinch and Ryzen much faster at decompression. Most of u.s. decompress files a lot more often that nosotros compress them, so this is probably a proficient tradeoff for AMD.

Overall, for typical business use, yous'd be quite happy with either selection.

Scientific Computing

For scientific computing, we used the Stars Euler 3D computational fluid dynamics exam. This seems to be very much dependent on memory bandwidth equally well equally core count, and here the Kaby Lake processor does a bit better, but non much. Other testers suggest the Broadwell-Due east would really exist much faster on this exam.

Another examination that may be applicable for scientific calculating is Y-Cruncher, a program that tin can compute PI to an arbitrary number of digits. Information technology has been optimized for many different processors, including a recent optimization for AMD'due south Zen compages.

Nosotros tested for computing Pi to two.v billion digits, and found it took Ryzen 303 seconds of ciphering time using the Zen optimization (compared to 337 seconds without), vs. 280 seconds for Kaby Lake. Kaby Lake was significantly faster, likely because of the superior AVX2 back up in the Intel processor.

In general, scientific computing is probably a case where spending more than for the biggest processor yous tin notice makes sense. Kaby Lake beat Ryzen here, but the real selection would probably exist the Broadwell-E, or fifty-fifty a 12-core, 24-thread Xeon-E5 2600W v4 processor. Graphics and Video

Based on Maxon's Movie house 4D software, Cinebench has go a standard criterion for 3D animation, and AMD actually pushed the multi-threaded version of this exam during its introduction of the Ryzen 7 processor. The CPU examination renders a scene using but the CPU cores, and while the Kaby Lake was faster on a single-threaded run, having more than cores conspicuously gave Ryzen a big do good in the multi-threaded run. Interestingly, on the OpenGL exam, which is supposed to mostly test the GPU, the Kaby Lake system was able to render scenes much more than quickly, which is a scenario that more than reflects real globe employ.

Here we took a high-quality x-minute 4K video encoded in H.264 MPEG4 at fifty frames per second and converted it into a 1080p H.265 HEVC video at 30 frames per second using Handbrake and the X.265 open up-source encoder. This examination seemed to scale very nicely with all 16 threads at 100% the entire time, and equally a consequence, the Ryzen seven significantly outpaced the Kaby Lake.

Compilation

Nigh mid-sized organizations and enterprises accept developers who spend a lot of their time edifice, updating, and integrating corporate applications. For developers, we used the Visual C++ 2022 to compile the LLVM compiler and tools and Clang front-end. (Yep, nosotros are compiling a compiler.) This seems to use a mix of series and parallel code, and Kaby Lake's performance was notably better.

Fiscal Applications

Finally, nosotros go to the kind of applications that affair most to me: those that deal with the simulation of large financial applications.

I started with a portfolio simulation application in Matlab, a numerical computing environment that has been widely used in financial firms for creating complex models. In this exam, the Ryzen 7 came out slightly faster, probably every bit a event of the additional cores.

I hadn't run Matlab on loftier-finish desktops in a while, but both did notably better than an overclocked (three.9 GHz) Core i7-4770K (Haswell) I tested a few years ago, http://forwardthinking.pcmag.com/computing/314776-how-fast-is-a-haswell which completed the test in 36 minutes.

I next turned to Excel, and started with a new, larger version of a basic Monte Carlo simulation I've been running for a long time (previous versions of the test are now as well brusk). I had idea that Ryzen 7 would do ameliorate on this examination, because it seems to fully saturate all the threads, but in fact information technology was the Cadre i7 that was notably better on this test.

I also tried a exam I've been running on many generations of desktop processors, involving a very large data table. Here again I had a much better score from the Intel system: the Kaby Lake took 46 minutes compared to the Ryzen's 59 minutes, and that's the kind of difference y'all would really notice in the existent globe.

1 interesting thing I observed was that on the Intel system, while it mostly used 1 thread, it would occasionally spin off tasks on other threads, while on the AMD system, it exclusively used a single thread (which of course works confronting the Ryzen). It's unclear to me whether this is related to the processor, or whether there is something in Excel 2022 that schedules tasks more than efficiently with the Intel processor.

I tin't even say I was particularly impressed by the Intel organization on this test, though. It actually came in slightly slower than the overclocked Ivy Bridge and Haswell systems from iii-4 years ago, despite the aforementioned number of cores and a higher clock rate. (With the Haswell systems, I did the tests with Excel 2022 and Windows 8; this fourth dimension I'g using Excel 2022 and Windows ten, so that may have some effect.) Dorsum so, Intel systems were almost twice the speed of AMD versions on this examination. Zen shows AMD has made great strides since then, while Intel'due south results do not indicate the aforementioned.

Conclusion

Overall, the results are mixed. In some cases, such equally True Crypt encryption and HEVC encoding, Ryzen was conspicuously faster, which is probably a reflection of the additional threads. In other cases – such equally for scientific calculating (tested in the Stars Euler examination and Y-Cruncher) and Excel, Kaby Lake did much better, which may be attributed to the higher clock speed and 256-bit AVX back up. Either would work well for nearly business cases.

That itself is a big win for AMD. It'southward been a long time since the company has had a competitive desktop production for demanding business users, and Ryzen certainly fills that need. While I nonetheless wait Intel to dominate the corporate desktop market—in part because of the inherent conservatism of those buyers—it'south cracking to have another option.