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 i7-4960X Ivy Bridge-E Review

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
In the world of high end processors, Intel’s Extreme editions have always been at the enthusiast market’s forefront. From Gulftown to Sandy Bridge E, the last few generations have gradually moved the yardsticks forward with better performance and increased instructions per clock. Now, Intel’s Ivy Bridge Extreme is looking to pick up the mantle from its predecessors by introducing Intel’s flagship CPUs to a 22nm 3D Tri gate manufacturing process.

While the mainstream product segment has moved on to the Haswell microarchitecture alongside Z87 motherboards, the extreme family has been lagging behind in some respects. The outgoing SB-E processors have been around for nearly two years now which may not seem like a long time but that’s an eternity in the world of processor lifespans.


Some have blamed this stately progression on the near-complete lack of viable competition from AMD while those with a mind towards conspiracy theories tend to point a finger at Intel purposely holding back technologies from the high end in order to milk their current offerings for all they’re worth. The actual reasoning behind this out-of-sync approach likely isn’t quite so dramatic.

Like its predecessor, the Ivy Bridge Extreme processors are based on Intel’s Xeon E-series server / workstation CPUs, though in this case the IVB-EP architecture is being used. As we have seen in every processor generation, the extreme and EP series progression marches to the beat of a different drummer while still maintaining Intel’s valued Tick / Tock strategy. So, it shouldn’t come as any surprise that these new processors are being released after Haswell made its debut not that long ago.


Since Ivy Bridge is essentially a 22nm die-shrink of Sandy Bridge, there really aren’t many base architectural differences. The memory controller is integrated onto the die, as it has been for the last few generations while the Queue, Uncore and primary I/O functions haven’t experienced any major changes in the move away from Sandy Bridge. The memory controller has been slightly revised with official support for DDR3-1866 memory but for enthusiasts that isn’t much of a change since Sandy Bridge-E CPUs had no problem reaching that frequency anyways. In addition, all processors now have native support for PCI-E 3.0.

The move to 22nm Tri-Gate 3D transistor technology is a particularly important one for these large 265mm² CPU dies. It essentially stacks transistors across the die’s z-axis in order to save room and increase processing efficiency which has significant effect upon power consumption and heat output. In most instances, these new processors will consume less power, allowing system builders some additional PSU overhead.

Since the Tri-Gate 3D technology essentially stacks the processor’s hottest-running elements across a more concentrated area, Ivy Bridge processors typically run hotter than their predecessor but Intel has revised their IHS design in an effort to alleviate this issue.

While the standard desktop Ivy Bridge variants retained four physical cores and up to eight threads, the Extreme die ups the ante with six cores and 15MB of L3 cache that‘s shared between the processor cores and other architectural functions. Unfortunately, for the time being, we won’t see any eight, ten or twelve core desktop CPUs (with up to 24 threads) as those have been reserved for the Ivy Bridge EP lineup.


Much like the move between the mainstream desktop versions of Sandy Bridge and Ivy Bridge, these new Ivy Bridge Exreme processors represent a simple incremental performance increase over Sandy Bridge-E. The focus for IVB-E has been put squarely upon moderate IPC boosts and some serious on-die efficiency improvements. Sadly, this means the actual performance difference between it and comparable processors from the SB-E era will be minimal in most instances.

Headlining Intel’s new product stack is the i7-4960X, a 6-core, 12-thread fully unlocked processor that has nearly the same specifications as the outgoing i7-3970X and one-ups the older i7-3960X by a significant margin. There is a small 100MHz Base Clock increase and a lower TDP but everything else remains the same, even the stratospheric $999 price point.


Moving slightly further down the lineup we have the i7-4930K and i7-4820K which replace the i7-3930K and i7-3820 respectively. Both of these look like worthy replacements for their forefathers for a number of different reasons. The i7-4930K still features twelve threads and a TDP of 130W but makes due with slightly less L3 cache than its $450 more expensive sibling while operating at frequencies that equal the i7-3960X. That represents an impressive speed boost over the 3930K. TDP remains at 130W but with less L3 cache, expect power needs to be further reduced.

In our opinion, the most interesting processor in this lineup is the i7-4820K due to the limitations of the processor it replaces. While the i7-3820 had its multiplier capped at 45X, this new CPU has a max multi of 63X so hitting ultra high frequencies won’t require changes to the Base Clock or gear ratio (two items which could hold back overclocks in some instances). The 4820K also features the highest Base Clock of any IVB-E processor and represents a very good competitor to the slightly more expensive Haswell i7-4770K. This could quickly become the darling of Intel’s Ivy Bridge Extreme lineup.


So with all of this information being thrown into a melting pot, what does IVB-E offer over SB-E on the performance front? Not all that much but enough to keep it relevant in today’s marketplace. Games and general tasks won’t be accomplished with noticeably more speed but Ivy Bridge’s IPC improvements will translate into improved speed within processing-intensive environments.

In many ways, these new processors aren’t meant as an upgrade path for Sandy Bridge-E users even though they are a simple drop-in upgrade for X79 motherboards (a BIOS update may be necessary though). The addition of official PCI-E 3.0 support and more overclocking features on lower-end SKUs will certainly be tempting but it is Gulftown, Bloomfield and AMD Thuban users who should really be paying attention here. For them, the performance increases and expanded feature set will likely be worthwhile.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
Intel's X79 Express Chipset; Redux

Intel's X79 Express Chipset; Redux


While some were hoping that the advent of Ivy Bridge-E processors would bring about a revision to Intel’s enthusiast platform, that didn’t happen. That means their newest processors will be paired up with the two year old X79 (code named Patsburg) PCH, dashing any hope that the Z77’s expanded feature set would make its presence felt.



As with Sandy Bridge-E, an Integrated Memory Controller acts as a backbone for up to four high speed DDR3 memory channels, each rated at 14.9 GB/s while a separate on-die controller takes care of the PCI-E lanes. This represents an improvement over the previous generation which could only handle 12.8 GB/s though a DDR3-1600 interface.

The new Ivy Bridge Extreme processors support up to 40 PCI-E 3.0 lanes which can be configured in a variety of different layouts depending on the number of slots Intel’s motherboard partners implement on their boards. There will be at least two x16 PCI-E 3.0 slots for full speed 16x / 16x Crossfire or SLI, which is a vast improvement over the 8x / 8x supported by the Haswell platform’s Z87 boards. There is also the option of having a third or fourth graphics slot (running at 8x bandwidth) for triple and quad GPU setups. PCI-E 3.0 is something that SB-E never “officially” supported.

The X79 Express Chipset incorporates the motherboard’s I/O functions and its features haven’t changed. It includes support for up to 14 USB 2.0 and six SATA ports, though only two of those can be used for SATA 6Gbps. That’s a serious limitation for anyone building a larger RAID array with modern SSDs, especially when you consider Haswell’s PCH allows for up to six such high speed ports.

Many will be disappointed with the omission of integrated USB 3.0 and Thunderbolt support considering, once again, Haswell and even the mainstream Ivy Bridge platforms have included both since day one. Nonetheless, there is an additional 8 PCI-E 2.0 lanes that can be used for more slots or add on-controllers so boards can include USB 3.0 and other non natively supported features.


Connecting the processor to the PCH is a second generation Direct Media Interface along with an optional SCSI Controller Unit. The Direct Media Interface (DMI) hasn’t changed either. When necessary, it can function with the same peak bandwidth as four PCI-E 2.0 lanes or 5 GT/s (20Gb/s) but most of the time it will be operating at lower speeds ensure optimal efficiency.

One thing that we didn’t see on previous chipsets is the SCU Uplink allows for a dedicated path between the PCH and processor in order to speed up storage performance and decrease latency. The only downside to using the SCU function is its need for a portion of the CPU’s PCI-E lanes (in this case four) which in essence limits the secondary PCI-E function to a x4 link down from x8 and eliminates the possibility for native 3-way GPU compatibility.


In an effort to refresh their X79 lineups despite Intel’s insistence that the current PCH is good enough, motherboard manufacturers will be forging ahead with a number of initiatives. Take ASUS’s new X79 Deluxe for example. It includes support for SSD Caching (at least ASUS’ take on the technology) and six additional SATA 6Gbps ports via a pair of third party controllers. USB 3.0 has even been included through the addition of three ASMedia hubs.

ASUS has basically thrown the option book at the Deluxe since it also packs Wireless AC support with a secondary module, Bluetooth v4.0, support for 3-Way SLI or triple Crossfire and Dolby DTS certification. Add to that ASUS’ intuitive software stack and you have one of the premier X79 motherboards which goes above and beyond to offer features Intel didn’t build into their X79 PCH. Expect our review in the coming weeks.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
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 7 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
12,857
Location
Montreal
System Benchmarks: AIDA64 / Cinebench r11.5

System Benchmarks


In this section, we will be using a combination of synthetic benchmarks which stress the CPU and system in a number of different domains. Most of these tests are easy to acquire or are completely free to use so anyone reading this article can easily repeat our tests on their own systems.

To vary the results as much as possible, we have chosen a selection of benchmarks which focus upon varied instruction sets (SSE, SSE3, 3DNow!, AVX, etc.) and different internal CPU components like the floating point units and general processing stages.


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 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 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.


RESULTS: The first set of benchmarks shows a slightly mixed bag for the i7-4960X as it gets beaten cleanly by AMD’s FX-9590 in the CPU Hash benchmark but redeems itself by a large amount in ZLib. This is likely due to AMD simply ignoring legacy instruction sets within their latest architectures while Intel has forged ahead with new support without discarding previous iterations.



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.



RESULTS: VP8 and SinJulia play into Intel’s hands with the Ivy Bridge Extreme series significantly outperforming its predecessor. With that being said, Haswell, with its enhanced FP performance is able to surge ahead in the VP8 benchmark.



CineBench r11.5 64-bit


The latest benchmark from MAXON, Cinebench R11.5 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.


RESULTS: With a dozen threads working at nearly 4GHz, the i7-4960X demolishes the competition in high bandwidth rendering scenarios. Even the 3960X is left behind in its dust.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
System Benchmarks: Civ V / PCMark 7

System Benchmarks (pg.2)



Civilization V: Gods & Kings Unit Benchmark


Civilization V includes a number of benchmarks which run on the CPU, GPU or a combination thereof. The Unit Benchmark simulates thousands of units and actions being generated at the same time, stresses multi core CPUs, system memory and GPU We give the non-rendered score below as it is more pertinent to overall CPU performance within the application.


RESULTS: In a truly multi-threaded environment, nothing can touch Intel’s Ivy Bridge Extreme even though its performance here can’t be considered noticeably better than its predecessor. With that being said, it remains well ahead of AMD’s offerings and even leaves the i7-4770K behind.


PCMark 7


PCMark 7 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. We also give the Computation Suite score as it isolates the CPU and memory within a single test, without the influence of other components.



RESULTS: This is an interesting test for the i7-4960X since it highlights some potential platform limitations. As we can see, both quad core, eight thread Ivy Bridge and Sandy Bridge processors are able to remain ahead but in the CPU-centric computational benchmark, the new IVB-E processor surges to the forefront. This may point to anything from latency issues (though we are using the same memory for all platforms) to I/O bottlenecks but one thing is certain: the X79 PCH may be showing its age.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
System Benchmarks: 3DMark (CPU) / WPrime

System Benchmarks (pg.3)



3DMark06 CPU


While 3DMark06 may be a slightly older synthetic benchmark, its CPU test still allows for multi threaded performance evaluations within a gaming environment. It effectively removes the CPU from the equation, generating a CPU-centric score.



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 sqrting, 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 32M and 1024M benchmarks.



RESULTS: Once again we’re seeing Intel’s latest flagship CPU powering itself to the head of our charts, though the amount of light between it and the i7-3960X isn’t all that much. While performance is spectacular, all we’re seeing here is an incremental increase from one generation to another.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
System Benchmarks: Single Thread Performance

System Benchmarks: 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.




RESULTS: Single thread performance has long been a strong area for Intel’s processors and this one continues the tradition. Since the i7-4960X is able to hit 4GHz with regularity, it remains slightly ahead of the outgoing Sandy Bridge Extreme chips. However, due to its true architectural advances, the i7-4770K remains nearly impossible to beat in most scenarios.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
Productivity Benchmarks: 7-Zip / MediaCoder

Productivity Benchmarks


In this section, we will avoid generalized synthetic benchmarks and instead concentrate upon CPU performance within real-world applications and standard usage patterns. Every one of the programs included here has functions that many professionals and everyday users utilize in their day to day computing lives.


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 are avoiding its built-in benchmark and once again only focus upon real world testing by compressing a 2.6GB folder of various files and adding an AES-256 encryption layer for good measure. The test is timed until it is complete.


RESULTS: Compression and decompression programs like 7-Zip absolutely thrive when paired up with a massive number of threads and these results prove that. Once again, Ivy Bridge-E is able to flex its muscles here.


MediaCoder x64


Due to the varying compatibility of certain mobile devices, video transcoding performance has become something of a big deal. Transcoding allows one type of video / audio file to be converted into a different format and it typically takes up a huge amount of system resources. The MediaCoder application brings multi format transcoding to an accessible level with numerous options and acceleration for Intel’s QuickSync and NVIDIA’s CUDA technologies. In addition, its CPU support allows for full multi core utilization. In this test, we use the MediaCoder i-devices edition to convert a 600MB AVCHD file to an iPhone 4S friendly MPEG-4 format.


RESULTS: Transcoding performance is one of the cornerstones of IVB-E so naturally the i7-4960X leads the pack by a significant amount. It even comes close to matching the numbers posted by a CUDA-equipped GPU.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
Productivity Benchmarks: Photoshop CS6 / POV Ray 3.7

Productivity Benchmarks (pg.2)



Adobe Photoshop CS6


For the image editing portion of this section, we use Photoshop CS6 in coordination with a custom benchmark script. This script automates the application of 20 different image manipulation functions to a 120MB PNG image, acting as an excellent test of CPU power and memory bandwidth. For this test, we have disabled GPU acceleration so it won’t play a factor in the areas where it would typically be used. We use Photoshop’s built-in timing feature to provide a result at each test stage.


RESULTS: unfortunately, Photoshop (at least the version we are using) isn’t completely multi-core aware past eight threads so the performance of processors like the 12-thread i7-4960X suffers. It still posts excellent results but once again, the Haswell i7-4770K receives top honors.


POV Ray 3.7 RC6


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 multiple passes of a high definition scene. In order to get the most accurate results, the second pass of the first test is logged, resulting in a benchmark score showing the average amount of pixels rendered per second.


RESULTS: As we move back into an application that fully supports muti core processors, the IVB-E CPU simply demolishes everything else. When its clock speeds are paired up with 15MB of L3 cache and high bandwidth quad channel memory, the numbers it posts become unassailable.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
12,857
Location
Montreal
Productivity Benchmarks: TrueCrypt 7.1 / x264HD

Productivity Benchmarks (pg. 3)



TrueCrypt 7.1


Truecrypt is another freeware gem which allows for on-the-fly disk encryption. More importantly, it fully supports AES-256 encryption methods and multi core processors. For this test, we used the built-in benchmark tool are logged the data throughput for TrueCrypt’s AES-256 encryption method.


RESULTS: TrueCrypt echoes the results we saw in previous tests: if an application can take full advantage of its resources, the i7-4960X can really stretch its legs.


x264HD Benchmark


x264 is quickly becoming the new codec of choice for encoding a growing number of H.264/MPEG-4 AVC videos. Think of it as the new Divx of HD and you can understand why we felt it critical to include. Tech Arp's recent development of the x264 HD Benchmark takes a 30 second HD video clip and encodes it into the x264 codec with the intention of little to no quality loss. The test is measured using the average frames per second achieved during encoding, which scales with processor speed and efficiency. The benchmark also allows the use of multi-core processors so it gives a very accurate depiction of what to expect when using encoding application on a typical full length video. We use the second pass of the first test for this benchmark as it fully loads all multi core processors.


RESULTS: The final test in our productivity suite plays on the multi threaded strengths of this architecture. It shouldn’t come as any surprise that the i7-4960X excels here.
 

Latest posts

Twitter

Top