What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

AMD Ryzen 7 1700X Review; Testing SMT

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Now that the initial excitement surrounding AMD’s Ryzen processors has settled down and the screams of joy turned down to a muted buzz, it isn’t time to take a breather quite yet. While our original review covered the $500 Ryzen 7 1800X there’s still two more very similar processors to cover; one of which is the less expensive 1700X.

By this point about a week ago I was well into testing that 1800X and for my initial impressions, I felt it wasn’t a great fit for gamers but it would be an awesome purchase for massively parallel processing tasks. Creative professionals, folks running virtual clients or those who needed home servers could all benefit in some way from what AMD was offering. But was it really necessary to buy into the “full monty” chip or would the 1700X provide a perfect gateway drug into the world that Ryzen was endeavoring to create? I wanted to find out.

RYZEN-1700X-30.jpg

Even though our launch-day review of the Ryzen series covered the ins and outs of the entire product stack, let’s dive back in to get an idea about what the 1700X brings to the table. For those of you interested the initial review also took a deep dive into the Zen architecture and AMD’s new AM4 platform so if this is your first introduction to Ryzen, I’d recommend reading that article first.

For its part the Ryzen 7 1700X retains the 8-core, 16-thread architecture of the 1800X with the only real difference being its achievable frequencies. Both the Base and Precision Boost speeds come in at an even 200MHz lower while TDP remains a very reasonable 95W. As with all X-series Ryzen CPU’s it also features an additional 100MHz of headroom through XFR. Essentially performance will likely be between 5-10% lower than the flagship X1800 but its $400 price is 20% less. That could be a pretty compelling story in its own right.

Another thing to take into account is that the Ryzen 7 1700X requires less input voltage and when you couple that with lower clock speeds, it will produce less heat than the X1800 and thus be easier to keep cool. As such it will achieve the temperature threshold needed for XFR much easier. With that in mind it isn’t hard to understand why I think this may be the darling of AMD’s current lineup.

RYZEN-1700X-1.jpg

Right before I published the Ryzen 7 1800X review, I received several emails from AMD’s PR team discussing how to improve in-game performance of their current architecture. Reviewers weren’t achieving framerate levels which aligned with expectations and our results reflected that. Now the word “expectations” here is key since I think they were overblown to begin with. As I said about a week ago, be it Intel or AMD those large eight-core, 16-thread processors are poor companions for a desktop system that focuses solely on gaming and light workloads. They can’t achieve the clock speeds necessary to be competitive on a price / performance level in lightly threaded scenarios.

One suggestion from AMD involved turning off SMT within the BIOS in an effort to improve performance in certain instances. My gut reaction to that email isn’t fit for these pages but let me explain nonetheless. In Ryzen’s case simultaneous multithreading essentially allows a processor design with eight physical cores to produce sixteen threads. This is hugely beneficial in programs that can scale across that many concurrent threads, but it can also lead to issues where the necessary optimizations aren’t in place.

Not only would toggling SMT be a completely unrealistic expectation for end users, but it’s been long known that simultaneous multithreading isn’t the end-all argument for CPU performance. Physical cores and the threads they produce often trump “virtual” ones. This is why AMD’s Piledriver cores were able to achieve impressive (for the time) results against Intel within certain situations; some games and applications simply don’t play nice with SMT-based designs, be it Intel’s Hyper-Threading or Ryzen’s paralleling technology.

RYZEN-1700X-2.jpg

At the time, I didn’t have time to humor AMD’s recommendation since it came with less than 48 hours before the NDA lifted. However, I decided to give the whole “let’s turn off SMT” directive a shot in this particular review... but with a bit of a twist to level the playing field. Not only did I turn off SMT for the Ryzen 7 1700X, but I also disabled Hyper-Threading on the i7-6900K to insure that this remains a true apples to apples comparison. Hopefully, this will also highlight application support rather than just claiming that any inherent “issues” are AMD-specific.

Now before heading directly into the benchmarks, one thing I noticed is that the behavior of Intel’s Broadwell-E is slightly more nuanced than Ryzen when there’s no multithreading involved. With all eight cores evenly loaded the Ryzen 7 1700X’s frequency remained at 3.5GHz, which is 100MHz higher than its stated Base Clock. The i7-6900K on the other hand took full advantage of Intel’s Turbo Boost Max technology and leveled out at 3.7GHz, which is a good 400MHz higher than its Base Clock.

With that being said, I’m not taking overall non-SMT performance into account within this particular article. Rather, I want to see how the Ryzen 7 1700X natively performs and if any of its SMT benefits / pitfalls are mirrored on Intel’s side of the fence. It should be an interesting one…..
 
Last edited by a moderator:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Test Setups & Methodology

Test Setups & Methodology


For this review, we have prepared a number of different test setups, representing many of the popular platforms at the moment. As much as possible, the test setups feature identical components, memory timings, drivers, etc. Aside from manually selecting memory frequencies and timings, every option in the BIOS was at its default setting.

RYZEN7-1800X-62.jpg

For all of the benchmarks, appropriate lengths are taken to ensure an equal comparison through methodical setup, installation, and testing. The following outlines our testing methodology:

A) Windows is installed using a full format.

B) Chipset drivers and accessory hardware drivers (audio, network, GPU) are installed.

C)To ensure consistent results, a few tweaks are applied to Windows 10 and the NVIDIA control panel:
  • UAC – Disabled
  • Indexing – Disabled
  • Superfetch – Disabled
  • System Protection/Restore – Disabled
  • Problem & Error Reporting – Disabled
  • Remote Desktop/Assistance - Disabled
  • Windows Security Center Alerts – Disabled
  • Windows Defender – Disabled
  • Screensaver – Disabled
  • Power Plan – High Performance
  • V-Sync – Off
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
System Benchmarks: AIDA64

AIDA64 Extreme Edition


AIDA64 uses a suite of benchmarks to determine general performance and has quickly become one of the de facto standards among end users for component comparisons. While it may include a great many tests, we used it for general CPU testing (CPU ZLib / CPU Hash) and floating point benchmarks (FPU VP8 / FPU SinJulia).


CPU PhotoWorxx Benchmark
This benchmark performs different common tasks used during digital photo processing. It performs a number of modification tasks on a very large RGB image:

This benchmark stresses the SIMD integer arithmetic execution units of the CPU and also the memory subsystem. CPU PhotoWorxx test uses the appropriate x87, MMX, MMX+, 3DNow!, 3DNow!+, SSE, SSE2, SSSE3, SSE4.1, SSE4A, AVX, AVX2, and XOP instruction set extension and it is NUMA, HyperThreading, multi-processor (SMP) and multi-core (CMP) aware.


RYZEN-1700X-31.jpg



CPU ZLib Benchmark

This integer benchmark measures combined CPU and memory subsystem performance through the public ZLib compression library. CPU ZLib test uses only the basic x86 instructions but is nonetheless a good indicator of general system performance.

RYZEN-1700X-32.jpg



CPU AES Benchmark

This benchmark measures CPU performance using AES (Advanced Encryption Standard) data encryption. In cryptography AES is a symmetric-key encryption standard. AES is used in several compression tools today, like 7z, RAR, WinZip, and also in disk encryption solutions like BitLocker, FileVault (Mac OS X), TrueCrypt. CPU AES test uses the appropriate x86, MMX and SSE4.1 instructions, and it's hardware accelerated on Intel AES-NI instruction set extension capable processors. The test is HyperThreading, multi-processor (SMP) and multi-core (CMP) aware.

RYZEN-1700X-33.jpg



CPU Hash Benchmark

This benchmark measures CPU performance using the SHA1 hashing algorithm defined in the Federal Information Processing Standards Publication 180-3. The code behind this benchmark method is written in Assembly. More importantly, it uses MMX, MMX+/SSE, SSE2, SSSE3, AVX instruction sets, allowing for increased performance on supporting processors.

RYZEN-1700X-34.jpg



FPU VP8 / SinJulia Benchmarks

AIDA’s FPU VP8 benchmark measures video compression performance using the Google VP8 (WebM) video codec Version 0.9.5 and stresses the floating point unit. The test encodes 1280x720 resolution video frames in 1-pass mode at a bitrate of 8192 kbps with best quality settings. The content of the frames are then generated by the FPU Julia fractal module. The code behind this benchmark method utilizes MMX, SSE2 or SSSE3 instruction set extensions.

Meanwhile, SinJulia measures the extended precision (also known as 80-bit) floating-point performance through the computation of a single frame of a modified "Julia" fractal. The code behind this benchmark method is written in Assembly, and utilizes trigonometric and exponential x87 instructions.


RYZEN-1700X-35.jpg

Personally I love the varying results that AIDA spits out across its various tests. They really give a good snapshot as to where performance is well rounded and where it is lacking.

Here the Ryzen 7 1700X performs as expected given its frequencies; within spitting distance of the 1800X. At times it is within 10% but others shows it less than 3% behind.

Testing with and without HT / SMT showed an extremely interesting byplay. Most tests showed Broadwell-E and Ryzen benefitting from their own version of simultaneous multithreading…except the PhotoWorxx and VP8 benchmarks, neither of which represent lightly threaded workloads. In those the Ryzen 7 1700X posted significantly better results when it was operating as a simple 8-core processor. Intel’s results meanwhile exceeded even my most wild expectations; in the right situation that i7-6900K can absolutely fly when Hyper Threading is turned off. The conclusion here is pretty simple: when one architecture benefits from a lack of SMT ops, so does its competitor.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
System Benchmarks: Cinebench / PCMark 8 / WPrime

CineBench R15 64-bit


The latest benchmark from MAXON, Cinebench R15 makes use of all your system's processing power to render a photorealistic 3D scene using various different algorithms to stress all available processor cores. The test scene contains approximately 2,000 objects containing more than 300,000 total polygons and uses sharp and blurred reflections, area lights and shadows, procedural shaders, antialiasing, and much more. This particular benchmarking can measure systems with up to 64 processor threads. The result is given in points (pts). The higher the number, the faster your processor.

RYZEN-1700X-38.jpg


PCMark 8


PCMark 8 is the latest iteration of Futuremark’s system benchmark franchise. It generates an overall score based upon system performance with all components being stressed in one way or another. The result is posted as a generalized score. In this case, we didn’t use the Accelerated benchmark but rather just used the standard Computational results which cut out OpenCL from the equation.

RYZEN-1700X-40.jpg

RYZEN-1700X-41.jpg



WPrime


wPrime is a leading multithreaded benchmark for x86 processors that tests your processor performance by calculating square roots with a recursive call of Newton's method for estimating functions, with f(x)=x2-k, where k is the number we're squaring, until Sgn(f(x)/f'(x)) does not equal that of the previous iteration, starting with an estimation of k/2. It then uses an iterative calling of the estimation method a set amount of times to increase the accuracy of the results. It then confirms that n(k)2=k to ensure the calculation was correct. It repeats this for all numbers from 1 to the requested maximum. This is a highly multi-threaded workload. Below are the scores for the 1024M benchmark.

RYZEN-1700X-42.jpg

All of these tests once again show the R7 1700X performing strongly against both the 1800X and Intel’s own very expensive i7-6900K.

As for the SMT question, nothing is really answered here. Cinebench and WPrime are both heavily multithreaded programs so they benefit from more active threads whereas the PCMark results focus in on overall system performance and aren’t entirely dependent on the number of threads being processed.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Productivity Benchmarks: 7-Zip / Adobe Premier Pro

7-Zip


At face value, 7-Zip is a simple compression/decompresion tool like popular applications like WinZip and WinRAR but it also has numerous additional functions that can allow encryption, decryption and other options. For this test, we use the standard built-in benchmark which focuses on raw multi-threaded throughput.

RYZEN-1700X-44.jpg



Adobe Premier Pro CC


Adobe Premier Pro CC is one of the most recognizable video editing programs on the market today as it is used by videography professionals and YouTubers alike. In this test we take elements of a 60-second 4K video file and render them out into a cohesive MP4 video via Adobe’s Media Encoder. Note that GPU acceleration is turned on.

RYZEN-1700X-51.jpg

Here we have a bit of an interesting situation. 7-Zip sees huge benefits with multithreading enabled but Adobe Premier Pro CC’s Media Encoder doesn’t. The reason for this is pretty simple: 7-Zip’s benchmark is very much multi thread aware and CPU dependent while Adobe’s output is affected by secondary components like the GPU’s acceleration algorithm and memory bandwidth.

As for the Ryzen 7 1700X itself, I couldn’t be more impressed with how well it does given its relative cost to the 1800X. Despite lower frequencies it does extremely well.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Productivity Benchmarks: Blender / 3ds MAX Corona

Blender


Blender is a free-to-use 3D content creation program that also features an extremely robust rendering back-end. It boasts extremely good multi core scaling and even incorporates a good amount of GPU acceleration for various higher level tasks. In this benchmark we take a custom 1440P 3D image and render it out using the built-in tool. The results you see below list how long it took each processor to complete the test.

RYZEN-1700X-45.jpg



3ds MAX Corona Renderer


Autodesk’s 3ds MAX is currently one of the most-used 3D modeling, animation and rendering programs on the market, providing a creative platform for architects to industrial designers alike. Unfortunately its rendering algorithms leave much to be desired and third party rendering add-ons are quite popular. One of the newest ones is called Corona.

In this test we take a custom 3D scene of a room with global illumination enabled and render it out in 720P using Corona’s built-in renderer.


RYZEN-1700X-46.jpg

AMD has a productivity winner on their hands with the 1700X. For a mere $400 you can have an 8-core, 16-thread processor that will cut into rendering times like no one’s business.

Say hello to why we have simultaneous multithreading. In rendering programs such as these it makes a tangible difference. One thing to notice is that the performance uplift for AMD’s SMT technology is slightly higher than Intel’s Hyper Threading. That leads me to the assumption that Ryzen’s implementation is slightly more efficient and Broadwell-E’s. Once the 4-core Ryzen parts arrive it will be interesting to see how AMD’s technology stacks up against Kaby Lake in this respect.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Productivity Benchmarks: GIMP / Handbrake

GIMP


While it may be open source, GIMP is actually one of the most popular free photo editors available right now. It uses both CPU and GPU acceleration for certain tasks. In this test we use an 8K image and use a script to run eight different filters in succession. This is considered a lightly threaded workload since the memory, CPU and storage drive can all play a role in performance.

RYZEN-1700X-47.jpg



Handbrake


Video conversion from one format to another is a stressful task for any processor and speed is paramount. Handbrake is one of the more popular transcoders on the market since it is free, has a long feature list, supports GPU acceleration and has an easy-to-understand interface. In this test we take a 6GB 4K MP4 and convert it to a 1080P MKV file with a H.264 container format. GPU acceleration has been disabled. The results posted indicate how long it took for the conversion to complete.

RYZEN-1700X-48.jpg

There’s nothing unexpected here in regards to the Ryzen 7 1700X’s performance; it remains very close to the 1800X and hands down trumps the i7-6900K from a price / performance perspective.

Since these are two lightly threaded workloads there isn’t much (or any) benefit when SMT is enabled. Handbrake is slightly better in this respect but again, other system components get in the way of delivering a CPU-focused result.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Productivity Benchmarks: POV Ray / WinRAR

POV Ray 3.7


POV Ray is a complex yet simple to use freeware ray tracing program which has the ability to efficiently use multiple CPU cores in order to speed up rendering output. For this test, we use its built-in benchmark feature which renders a high definition scene. The rendering time to completion is logged and then listed below.

RYZEN-1700X-49.jpg


WinRAR


WinRAR is one of those free tools that everyone seems to use. Its compression and decompression algorithms are fully multi-core aware which allows for a significant speedup when processing files. In this test we compress a 3GB folder of various files and add a 256-bit encryption key. Once again the number listed is the time to completion.

RYZEN-1700X-50.jpg

No surprises here either for the 1700X. Performance has been strong throughout.

POV Ray shows us a situation wherein AMD’s SMT implementation is obviously more efficient than Intel’s. I was actually quite shocked at how little the additional threads benefitted both of these architectures in a key rendering benchmark. With that being said, Intel’s higher clock rates with HT off obviously benefit it more within WinRAR.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Single Thread Performance / Memory Bandwidth

Single Thread Performance


Even though most modern applications have the capability to utilize more than one CPU thread, single threaded performance is still a cornerstone of modern CPU IPC improvements. In this section, we take a number of synthetic applications and run them in single thread mode.

RYZEN-1700X-39.jpg
RYZEN-1700X-43.jpg

I wasn’t expecting single thread performance to be any different with or without SMT and these results prove that assumption correct. There’s a slight uptick on the Cinebench numbers for the 1700X but that is likely just a factor of the way our averages are calculated rather than an actual benefit.

Here it is hard to critique the Zen architecture; it has obviously allowed AMD to substantially increase their single core performance, something that was seriously lacking with Bulldozer’s derivatives.



Memory Bandwidth


If you actually managed to read page 5 of this review, my inclusion of this section should come as no surprise. If you haven’t read it, do so now. Simply put, the Zen architecture has some very serious memory limitations that will certainly affect the way people buy their modules and adds confusion to an otherwise straightforward launch. With those specific characteristics in mind, I wanted to see how Ryzen handled memory-specific workloads and the fact I’m using identical DDR4 memory on every platform in this review (minus 990FX of course) allowed me to test in a controlled environment.

RYZEN-1700X-37.jpg
RYZEN-1700X-36.jpg

Memory bandwidth remains very consistent when going from one Ryzen CPU to the next. Meanwhile, enabling or disabling SMT on Broadwell-E and Zen has very little to no effect upon these results. There’s a small uptick in Intel’s results but they are well within the margin of error.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,841
Location
Montreal
Gaming Performance (Synthetic)

3DMark Fire Strike (DX11)


RYZEN-1700X-52.jpg

I’m sure that most of you skipped to this section, so let’s start it out with some light synthetic tests which should set the stage for the next few pages of real-world testing. When using DX11 Ryzen suffers which is likely due to the benchmark’s focus on dual to quad thread workloads; an area where AMD’s new architecture has trouble keeping up with Intel.


3DMark Time Spy (DX12)


RYZEN-1700X-53.jpg
RYZEN-1700X-54.jpg

It is extremely hard to find fault with the 1700X when compared against its immediate Broadwell-E competition. With that being said, none of the 8-core processors perform particularly well in gaming-centric applications.

Now we start to get into an area that’s supposed to see some notable improvements for SMT but there really isn’t much to see here. The only exception to this is 3DMark’s Time Spy CPU test which is heavily multi threaded.
 

Latest posts

Twitter

Top