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!

Intel Skylake i5-6500, i5-6400 & i3-6100 Review

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
When Intel first launched their Skylake processors, buyers’ choices were essentially limited to a pair of options: the i7 6700K and later the i5 6600K. Both boasted features enthusiasts looked for like unlocked multipliers and fast out-of-box performance but they were also priced accordingly. These remained the only two possibilities for Skylake-bound buyers until late last year when Intel finally rolled out a top-to-bottom lineup.

The way Intel has approached Skylake’s cadence into lower price points has been drastically different from previous generations. Instead of offering a broad range of products from day one, additional i5, i3 and Pentium-class CPUs became available in fits and spurts, sometimes months after their initial “launch” dates. Much of this odd rollout seems to have been dictated by challenges brought about by Intel’s advanced 14nm manufacturing process, one which has effectively broken the ground rules set out by Moore’s Law. Simply put, Intel can’t produce Skylake processors fast enough to satisfy the market’s demand.

While this situation could eventually play into AMD’s hands provided their Zen microarchitecture meets expectations, for the time being this isn’t negatively impact Intel’s commanding market share. It has however contributed to prices remaining high which has pushed potential customers to lower price points. Many have asked themselves whether or not those unlocked multipliers that distinguish K-series processors are really worth the investment.

Enthusiasts who really want to push their systems will always gravitate towards overclocking. However, some of these more affordable alternatives could be an excellent option if a user believes the money saved versus something like the i7 6700K would be better invested in a motherboard with a huge feature set or a better graphics card.


This all brings us to the three processors in today’s review, namely the i5-6500, i5-6400 and i3-6100. All of these have been chosen for their price points above all else but there is a notable absence: the i3-6300. Unfortunately, since we purchased all of these processors it was the only one which wasn’t available but, on paper at least, it really doesn’t offer that much more than the i3-6100.

The $192USD i5-6500 is a processor many have considered to be a fitting replacement for the significantly higher priced i5-6600K. It offers Base and Boost frequencies that are within a mere 10% of Intel’s lowest-priced unlocked Skylake CPU while still incorporating four native processor cores, a 6MB cache and a 26W lower TDP. Unfortunately the 3.6GHz max Turbo speed is a far cry away from the 8-threaded i7-6700K’s 4.2GHz but the i5-6500 costs nearly $150 less.

Judging from the response on various online forums, the i5-6400 is considered by many to be the black sheep of Intel’s lineup. While it still includes four native processor cores and a quartet of threads, its base clock (typically what the processor will run at under heavily multithreaded workloads) and graphics clock are much lower than the 6500’s despite a slim $15 cost savings. TDP also remains identical to its more expensive sibling at 65W.

The benefits of a native quad core processor in today’s workloads can’t be overlooked. Hence, regardless of how efficient Intel’s Hyperthreading technology is, a dual core CPU like the i3-6100 which can process up to four threads will typically fall behind its more expensive quad core siblings. Nonetheless, this inexpensive sub-$120 processor can still tackle multi-threaded workloads with aplomb and its “virtual” threads will become transparent to certain applications. There’s also the potential to see performance pushed well ahead of previous-generation Haswell processors since Skylake’s HyperThreading algorithms have been improved.

Past its obvious efficiency advantage there’s a lot to differentiate the i3-6100 from the other processors in this review. It goes about its business without Turbo Boost functionality so instead of dynamically increasing clock speeds when the chip’s TDP allows, 3.7GHz is the constant running frequency. That’s actually quite impressive given the i5-6500 tops out at 3.6GHz. However, while clock speeds seem to be well aligned with higher end alternatives, the i3-6100’s meager 3MB of unified cache will likely hold back performance in some applications.


Added to our i7-6700K, we now have the potential to get a good snapshot of the Skylake lineup at several different price points. While every buyer loves to see how enthusiast level products handle themselves, the reality is that very few actually end up buying those expensive leading-edge wares. Our intent is to see how these less popular family members line up. Many will end up looking towards the i5 and i3 product stacks for their upgrade or new system needs; at the high end (the i5-6600K) they offer unlocked multipliers while something like the i3-6100 could allow someone to maximize the money invested in other components. Honestly, few require overclocking and even fewer games make use of anything more than four threads so any one of these three processors we’re about to cover could be an excellent choice.

Typically our introduction would end here and the benchmarks would start rolling but overclocking does need to be mentioned since it’s recently become something of a hot potato issue. While the locked nature of non-K processors effectively eliminates straightforward overclocking by simply increasing the multiplier, motherboard manufacturers had begun rolling out BIOSes which allowed Base Clock (BCLK) increases. This was significant since the CPU’s running frequency is derived from the base clock (typically 100MHz) and multiplier so with the latter being locked down, higher clock speeds could be realized by manually increasing the BCLK.

With Skylake’s BCLK infinitely more tractable than previous generations, budget-minded overclockers could suddenly buy a less expensive processor that could be overclocked to a point where it competed against much more expensive K-series chips. For example, we saw i5-6400’s easily reaching 4.1GHz with a Base Clock of 125MHz. Actually achieving those overclocks was more challenging than multiplier-based overclocking but it was still possible…..until last week.

We won’t delve into all the speculation surrounding this but for whatever reason, the non-K overclocking BIOSes which motherboard manufacturers were so quick to market suddenly started disappearing. All of them are still available on archive sites but key microcode and platform fixes which were rolled out in the last few weeks aren’t included on those earlier files. They’re essentially a dead end and no longer even supported by the manufacturers who originally released them.

Taking this into account, we’ve actually cut out overclocking from this review but the lack of any possible performance boost through higher than reference frequencies shouldn't dissuade you in any way. All of these CPUs offer some pretty impressive results straight out of the box.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
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.


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 8.1 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

D) Windows updates are then completed installing all available updates

E) All programs are installed and then updated.

F) Benchmarks are each run three to eight times, and unless otherwise stated, the results are then averaged.

G) All processors had their energy saving options / c-states enabled
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
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.




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.



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.



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.



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.



The first round of benchmarks shows an interesting melting pot of results, particularly for the i3-6100. On one hand the optimizations build into Skylake for Photoworxx’s workloads (particularly for AVX2) allow it to pull ahead of even the fastest processors of the Haswell generation while still maintaining a relatively consistent 15% loss to the i5-6400 in the FPU tests. Moving beyond those situations, the i3-6100 really suffers in some of these tests due to its lack of AES-256 decryption acceleration, lower L3 cache allocation and –despite a consistently high Hyperthreading frequency- its two physical cores.

As their specifications would lead you to believe, the i5-6400 and i5-6500 perform within spitting distance of one another and they actually end up competing quite well against the i5-4670K. What we aren’t seeing is any appreciable performance improvement against Haswell in the vast majority of benchmarks.

One of the main issues here is that Intel is competing against themselves rather than AMD since all of APUs are pushed so far down the charts that they are bordering on irrelevant. Hopefully this will change soon.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
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.




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.




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.


Now we come into some interesting results, particularly for that inexpensive little i3-6100. Since Cinebench is Hyperthreading-aware, you would expect the i3 to perform quite well and it does, particularly when compared against i3-series Haswell processors. However, without those four physical cores and the cache bandwidth available to higher end i5 CPU’s it falls behind in heavily threaded rendering workloads.

As for the i5 Skylake-S processors, they fill the gap between expensive i7-6700K and the i3-series perfectly but the $20 extra you pay for the 6500 doesn’t lead to particularly better results in Cinebench.

Moving on to PCMark and the situation becomes drastically different. Here we can see the results are more platform-specific with the three Skylake-S CPUs clustered around the same area. However, since this benchmark puts emphasis on additional single core workloads alongside multi-core tests, the i3-6100’s higher frequency allows it to vault right into the thick of things. Once again, AMD’s APU’s show their weakness and are clustered towards the bottom of the charts.

Finally there’s WPrime which shows results for all three processors that are very much in line with Cinebench. This leads to the i3-6100 falling behind since, despite not including Turbo Boost, it still downclocks to a lower level when its two cores are fully loaded.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
Productivity Benchmarks: 7-Zip / Blender / Handbrake

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.




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.



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.



In 7Zip, Blender and Handbrake there’s a continuation of the results we’ve seen on previous pages: the i5 processors put down very good results due to their quad core nature, the inclusion of more cache and Turbo Boost. Meanwhile, the i3-6100’s lack of AES acceleration puts its results back in 7Zip but it still manages to stay comfortably ahead of the i3-4370. That’s a pretty impressive metric given the fact the 4370 was almost $40 more expensive when it was fist launched about 16 months ago.

One small surprise here is the relative performance of AMD’s APU in Blender despite their massive losses in all other benchmarks.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
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.



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.



Once again the i5-6500 and i5-6400’s results are very strong given their relative price points and we can totally see budget-conscious buyers looking towards them if overclocking isn’t on the radar.

The i3-6100 presented us with a yin and yang situation since its performance in WinRAR was right in line with expectations and once again extremely competitive. Unfortunately, for some reason things fell apart in POV Ray where its results plunged into the gutter. It looks increasingly like its cache becomes saturated and clock speeds tank which leads to lower than expected performance. Luckily we can’t see many using an i3 series processor for continual rendering tasks but this is nonetheless something to take into account if you are looking for a value-focused CPU for a workstation.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
Single Thread Performance

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. The only addition to our normal benchmarks is Dolphin which uses a simple Nintendo GameCube emulation test on a single core.



As a single thread workhorse, the i3-6100 is an absolute beast due to its high single thread frequency. This bodes extremely well for its performance in games, many of which still struggle to take advantage of more than two threads.

Since these are purely frequency-based results (ie: the high speed will always win) the i5 processors fall behind their little i3 brother. However, the applications which are not multi-thread aware are becoming exceedingly hard to find so this section may just be a red herring for most users.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
Accelerated Graphics Performance

Accelerated Graphics Performance


With many CPUs using integrated graphics processors, parallel co-processing has become a hot topic of conversation for the last few years. While many were hoping the see a revolution in this field, thus far OpenCL and DirectCompute have failed to gain all that much traction in the development community. However, there are still a few programs that put GPU computing to good use.

In this section, we will be benchmarking a number of applications which support (or claim to support) GPU compute in an effort to highlight the performance benefits which come with this technology. All of these tests are conducted on a system WITHOUT a discrete GPU installed.



AIDA64 GPGPU Benchmark


AIDA64’s integrated graphics benchmark runs the integrated GPU through a number of different tests. In this benchmark we focus on the simple 32-bit and 64-bit integer processing which stresses both the graphics engine and its associated memory.




PCMark 8 - Accelerated


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. In this test the Accelerated OpenCL path was used.




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. GPU acceleration was enabled.




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 enabled in this case. The results posted indicate how long it took for the conversion to complete.


The i3-6100 once again shows some real strength due to its higher iGPU frequency and the i5-6500 and i5-6400 aren’t slouches either. With that being said, GPGPU support is spotty at best with Intel’s Quick Sync Video helping push Handbrake performance to some extremely high levels but in other applications like Blender, there’s a lack of recognition.

One thing that we need to highlight is how much Skylake’s baseline GPU performance has improved versus Haswell. If this trend is any indication, we may see Intel catch AMD within a processor generation.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
Gaming Benchmarks (720P) – Discrete GPU

Gaming Benchmarks (720P) – Discrete GPU






The gaming results are likely when many of you came here for and once again the i3-6100 is this show’s shining star. While it does bring up the rear among the Skylake-S processors in Grand Theft Auto and The Witcher 3 (games that are impressively multi-threaded) it competes right alongside significantly more expensive alternatives in four of our six testing scenarios. Even when it falls behind, that $120 processor remains less than 10% behind the i5-6500 and i5-6400.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,410
Location
Montreal
Gaming Benchmarks (1080P) – Discrete GPU

Gaming Benchmarks (1080P) – Discrete GPU






By putting the onus on the GPU we can see the top half of our charts tightening up even further and the onscreen framerate differences between the respective Skylake processors become infinitesimal. This situation will become even closer as resolution moves up a notch to 1440P and 4K respectively. Will DX12’s change this as it puts more onus on multi-threading? Likely not initially since much of the asynchronous processing can be done at a local level on the GPU itself though there is certainly a possibility Microsoft’s next generation API could utilize a huge number of threads for things like AI and simply feeding the GPU with additional information.
 

Twitter

Top