ASRock Z270 Extreme4 Motherboard Review: Page 6 of 8
Posted by Damon Bailey on Tuesday, January 3, 2017 - 12:30pm
Performance & Testing
Stock Performance Testing
All performance testing was done with the i7 6700K and default clocks with Turbo Boost left enabled for up to 4.2Ghz boost speeds. The Galax 1070 HOF was clocked at stock speeds, reaching a core boost speed of 2025Mhz and an effective memory speed of 8008MHz. The Geil EvoX ram was set to XMP Profile 1 (3000Mhz, 15-17-17-38 2T)
Games where ran at a resolution of 1920 x 1080px with to maximum graphical settings applied with V-sync and MSAA always turned off.
PassMark Performance Test 9
Fast, easy to use, PC speed testing and benchmarking. PassMark Performance Test allows you to objectively benchmark a PC using a variety of different speed tests and compare the results to other computers.
Find out if your PC is performing at its best.
Compare the performance of your machine to similar machines.
Measure the effect of configuration changes and upgrades.
Avoid paying big bucks for poor performance.
Make objective independent measurements on which to base your purchasing decision.
Use the advanced tests to create you own benchmark scenarios.
Thirty two standard benchmark tests are available in five test suites plus there are eight advanced testing windows for custom benchmarking. In addition to the standard tests, there are 5 summary results plus the overall "PassMark Rating" result. The benchmark results are presented as easy to read charts so that you don't need to spend hours studying the number to know the result.
A major advantage is the support for built-in baseline results which allows you to compare computer systems (a baseline is a standard set of results from another computer). These baseline results can be used to determine how fast your computer is in comparison with other computer systems.
We can see this system is a beast, even at stock clocks, surpassing 99%+ of the rest of the systems tested.
Novabench is a freeware benchmark test for Windows and macOS. It quickly tests your computer's capabilities (CPU, Graphics, RAM, and Storage). Novabench has been trusted by millions since 2007. NovaBench tests the main components of your computer quickly. Testing only takes a few minutes, and produces detailed information and an overall system score.
Floating Point - Tests CPU's floating point arithmetic speed
Integer - Tests CPU's integer arithmetic speed
MD5 Hashing - General CPU test
3D Graphics - Tests GPU with a heavily shader dependent 3D scene
RAM Speed - Tests RAM read and write speed
Disk Write Speed - Test write speed of primary or selected storage device
NovaBench is quick, and produces a baseline score that is a sum of each individual section. This score works well to give you a quick black and white picture of what a system change or hardware upgrade has done to you, but since it does not provide a weighted score, it is hard to compare to other systems if they are not an exactly identical configuration.
Again, you can only really compare scores on NovaBench to similar systems, but this combination of hardware actually managed a higher overall score than our recent MSI X99A Tomahawk review with a Intel Core i7-5960X. The test systems had same GPU and SSD, even with 4 fewer cores. The difference here is mostly the 25% higher base clock speed. It also scored a significantly higher GPU 3D score with the same card at the same clocks.
CPU Performance Testing
CINEBENCH is a real-world cross platform test suite that evaluates your computer's performance capabilities. CINEBENCH is based on MAXON's award-winning animation software CINEMA 4D, which is used extensively by studios and production houses worldwide for 3D content creation. MAXON software has been used in blockbuster movies such as Iron Man 3, Oblivion, Life of Pi or Prometheus and many more.
CINEBENCH is the perfect tool to compare CPU and graphics performance across various systems and platforms (Windows and OS X). And best of all: It's completely free."
A score of 867 cb is pretty typical of the 6700K and just edges out is prior generation counter parts.
The benchmark shows a rating in MIPS (million instructions per second). The rating value is calculated from the measured speed, and it is normalized with results of Intel Core 2 CPU with multi-threading option switched off. So if you have modern CPU from Intel or AMD, rating values in single-thread mode must be close to real CPU frequency. There are two tests, compression with LZMA method and decompression with LZMA method. Once the total passes reaches 20, the score is taken.
The i7-6700K scored a total rating of 26,665 Million Instructions per Second on the 7-Zip testing after 20 runs.
Written by Alexander J. Lee “From a high-school project that went a little too far...” y-cruncher, (y for gamma) is a number crunching program that can compute various mathematical constants.
It was originally a small program specialized for computing the Euler-Mascheroni Constant. (Which uses gamma as its symbol, hence the name). It has since gained the ability to compute other constants.
It is the first of its kind that is multi-threaded and scalable to multi-core systems. Ever since its launch in 2009, it has become a common benchmarking and stress-testing application for overclockers and hardware enthusiasts.
We tested using the built in benchmarks to compute Pi to 1 Billion Digits.
Our i7-6700K calculated 1 Billion digits of Pi in 98.701 Seconds using all 4 cores.
Memory Performance Testing
AIDA64 Extreme Edition
AIDA64 implements a set of 64-bit benchmarks to measure how fast the computer performs various data processing tasks and mathematical calculations. Multi-threaded memory and cache benchmarks are available to analyze system RAM bandwidth and latency. Benchmark pages of AIDA64 Extreme provide several methods to measure system performance. These benchmarks are synthetic, so their results show only the theoretical (maximum) performance of the system.
CPU and FPU benchmarks of AIDA64 Extreme are built on the multi-threaded AIDA64 Benchmark Engine that supports up to 32 simultaneous processing threads. It also supports multi-processor, multi-core and Hyper Threading enabled systems.
Memory bandwidth benchmarks (Memory Read, Memory Write, and Memory Copy) measure the maximum achievable memory data transfer bandwidth. The code behind these benchmark methods are written in Assembly and they are extremely optimized for every popular AMD, Intel and VIA processor core variants by utilizing the appropriate x86/x64, x87, MMX, MMX+, 3DNow!, SSE, SSE2, SSE4.1, AVX, and AVX2 instruction set extension.
The Memory Latency benchmark measures the typical delay when the CPU reads data from system memory. Memory latency time means the penalty measured from the issuing of the read command until the data arrives to the integer registers of the CPU.
The Geil EvoX 3000Mhz ram scored nearly 42GB/s reads, 44GB/s writes, and 40GB/s copy speeds with a 50.1ns latency which is pretty good. Here you can also see the Internal Cache speeds and Latency of the CPU as well.
3DMark - Firestrike
"The new 3DMark includes everything you need to benchmark your hardware. With three all new tests you can bench everything from smartphones and tablets, to notebooks and home PCs, to the latest high-end, multi-GPU gaming desktops. And it's not just for Windows. With 3DMark you can compare your scores with Android and iOS devices too. It's the most powerful and flexible 3DMark we've ever created.
Fire Strike is a showcase DirectX 11 benchmark designed for today's high-performance gaming PCs. It is our most ambitious and technical benchmark ever, featuring real-time graphics rendered with detail and complexity far beyond what is found in other benchmarks and games today"
Our tests setup scored 19,064 Graphics, 13,632 Physics score, and 7,534 points combined for an overall score of 15,718. This shows strong performance that is on the upper end of average for systems near this configuration, and should prove capable of playing any current games with maximum settings around the 1440p mark up to medium settings at 4K.
Metro: Last Light
"It Is the Year 2034. Beneath the ruins of post-apocalyptic Moscow, in the tunnels of the Metro, the remnants of mankind are besieged by deadly threats from outside – and within. Mutants stalk the catacombs beneath the desolate surface, and hunt a midst the poisoned skies above."
Developed by 4A games and published by Deepsilver, Metro: Last Light uses the 4A game engine. At its highest settings, the 4A game engine is capable of bringing all but the most extreme gaming systems to their knees.
3 Runs of the Metro: Last Light built in benchmark with the above settings. The results of the benchmark run are as follows:
- Average Framerate: 118.68
- Max. Framerate: 209.03
- Min. Framerate: 29.99
"Garrett, the Master Thief, steps out of the shadows into the City. In this treacherous place, where the Baron’s Watch spreads a rising tide of fear and oppression, his skills are the only things he can trust. Even the most cautious citizens and their best-guarded possessions are not safe from his reach."
Thief was developed by Eidos-Montréal and published by SQUARE ENIX, Eidos Interactive. The newest game in our benchmark suite, Thief is also one of the most demanding and has the highest recommended system requirements. Those heavy requirements allow it to use the Unreal 3 game engine to great effect. It also features AMD's Mantle API, as well as Microsoft's common DirectX 11 API.
With a minimum FPS of nearly 100, this system has no issues holding a solid frame rate at 1080p, but the goal here was to test for bottlenecks rather than the capabilities of the GPU.
Middle Earth: Shadow of Mordor
Middle-Earth: Shadow of Mordor is an open world action-adventure video game set within Tolkien's legendarium, developed by Monolith Productions and published by Warner Bros. Interactive Entertainment. Officially announced in November 2013, it was released a year later in November 2014.
Here again in another title that can be rather demanding we see a minimum FPS of 93 while topping out at nearly 200 FPS.
CrystalDiskMark is designed to quickly test the performance of your hard drives. Currently, the program allows to measure sequential and random read/write speeds."
We’ll start out with testing the M.2 Slots on the board with our Plextor M8Pe 128GB drive. CrystalDisk Info reports the drive connected at PCIe 3.0 x4 in both slots, and scored 1.3GB/s reads and nearly 500MB/s writes which is the maximum capabilities of this particular drive in both slots. The CrystalDiskMark test show here is from the Lower slot, but the top one scored the exact same within a margin of error. We did not have two identical drives on hand to test M.2 RAID unfortunately.
ATTO Disk Benchmark
“As the industry's leading provider of high-performance storage & network connectivity products, ATTO has created a widely-accepted Disk Benchmark freeware utility to help measure storage system performance. As one of the top tools utilized in the industry, Disk Benchmark identifies performance in hard drives, solid state drives, RAID arrays as well as connections to storage. Top drive manufacturers, like Hitachi, build and test every drive using the ATTO Disk Benchmark"
Our Plextor M8Pe drive scores nearly the exact same in ATTO. A peak read speed of about 1.3GB/s and about 500MB/s write speeds. With 32Gbps maximum bandwidth available on each M.2 Slot, the ASRock Z270 Extreme4 can handle drives much faster than this.
Next Up is USB Storage Testing. The Fastest drive we have on hand is Corsair’s Flash Voyager GTX 128GB UASP enabled USB SSD. Fully capable of saturating a 5Gbps USB 3.0 port, It is one of the fastest drives on the market at present.
ASRock uses the newer ASMedia 2142 USB 3.1 Gen 2 controller to feed the two 10gbps ports on the board. We see very slightly faster speeds via this controller over the Intel Chipset Provided USB 3.0 ports also on the rear I/O but the writes are slightly less stable. Our Corsair drive has slight bug causing a huge dip in read performance at the 64KB test block size, this is the drives fault and no indication of USB port issues.
Last but certainly not least: testing the storage performance of the Onboard SATA Ports. Using Intel Rapid Storage, we tested a single Corsair Force GT 240GB SSD and in RAID-0 with two, three and four drives. Rather surprisingly, we see nearly perfect scaling up to 4 drives and landing right at the 2GB/s read speeds while a single drive scores about 550MB/s. Former Intel chipsets, including the most recent 100 Series usually top out at around 1.3 to 1.6GB/s or about 2.5 to 3x the speed of a single drive.
We see very similar scaling on the write side as well which also scales well to around the 1.95GB/s mark. Out of curiosity, we did dig out a fifth matching drive, but it turned in nearly the same results as 4 drives. 2GB a second out of an Intel Chipset RAID controller is spectacular! This is a VERY welcome surprise as a quartet of SATA SSD’s is still cheaper than many NVMe drives and can turn in similar sequential speeds.