This article provides a small comparison of i3 i5 i7 processors. Typical tasks for all Core series processors will also be briefly described. The names of processors from Intel vary so much that the average user will not understand at all what one or the other processor name means. Of course, in itself it carries its own meaning, but at first glance, this is a confusion of abbreviations and numbers.
Before buying a new processor from Intel, a reasonable question will arise, what is the difference between i3 i5 i7 processors. To understand all this, we can divide all the names of Core processors into two groups. The first, the most interesting for us, is the line (i3 / i5 / i7). We will focus our attention on it. The rest of the name, including numbers and letters, shows us distinctive features one or another processor, which we will consider below.
There are a couple of main features in the Core series. The socket (socket for installing the processor) in the same generation will always be the same. You won't need another motherboard for the same Core i3 as you would with an i5 or i7. All processors have a built-in graphics core. The sixth generation of Skylake we are reviewing uses 1151 sockets and integrated HD530 graphics.
Core i3
Although i3 processors are the least powerful among the Core processor series, they are an excellent choice for everyday tasks. They have two physical cores, but Hyper-Threading technology makes up for this. Hyper-Threading doubles the available CPU threads by emulating 4 "virtual" cores. The L3 cache size reaches 3-4 MB, depending on the specific model, and the frequencies range from 2.7 to 3.9 GHz. You can buy a processor for 110-140 US dollars.
He can do a little of everything, but he can do nothing perfectly. The performance of these processors is enough for the responsiveness of the system, but heavy tasks like rendering or video editing on them will be flour. They are fast enough to unleash a modern graphics card, so they can be used in entry-level gaming systems with a mid-range graphics card.
Core i5
Sitting right in the middle between the i3 and i7 lines, the i5 line has many of the latest features with pretty good power efficiency. This series does not have Hyper-Threading technology, but has 4 physical cores, Turbo Boost, and processor models with an unlocked multiplier for overclocking. The amount of L3 cache reaches 6 MB (in i5 desktop models).
Turbo Boost allows the processor to temporarily increase the frequency of one or more cores under load, at the cost of increased power consumption and reduced processing power of other cores. In fact, this technology is a kind of overclocking of the physical core. Sixth generation i5 frequencies range from 2.2 to 3.5 GHz and prices range from $180 to $220
Core i7
At the top are the i7 processors. They have four logical cores, as in the i5 line. Hyper-Threading is also present, already creating as many as 8 threads on 4 physical cores. These processors have the highest frequencies, reaching 4 GHz by default and 4.2 GHz with Turbo Boost. The i7 comes with 8MB of L3 cache, and the processors in this line can be purchased for prices ranging from $300 to $340.
Although these processors are endowed with the highest performance, this is clearly more than enough for the average user. It is the processors of this line that will allow you to see by eye how the i3 i5 i7 processors differ. i7 processors are great for programs that can take full advantage of all 8 threads. Despite this, many games still use only 4 cores to this day. Even Photoshop only wins with more than 2 cores when using special filters and operations. If you do not work in Maya and Autodesk on a regular basis, you will hardly see an increase, how and how the i3 i5 i7 differ in simple tasks.
Index values
A processor from any manufacturer has its own indexes, which are in the rest of the name after the manufacturer and product number. The larger the product ID, the more powerful the processor is usually. Letters T, U And Y denote processors designed for low power consumption. The letter K at the end denote processors with overclocking potential, and P indicates the presence of a less powerful graphics core. If you want a more detailed description of the indexes, take a look at the Intel website.
What to buy?
Without delving into all these designations, we can say that Core processors make it easy to determine which one is best for you. This can be seen even by one character in the name of the line. The difference between the i3 i5 i7 lies in the processing power. Another difference between the i3 i5 i7 processors lies in the graphics core. In i5 and i7 it is usually the same, but in i3 it is weaker. Unfortunately, not all users think about the difference between i3 i5 i7 and take a processor whose capabilities are simply not used, or vice versa.
For most users, the i5 will suffice, which provides good attitude prices and capacities. i3 will still be a great choice for budget builds, it a good option for their money. If you are confident that heavy tasks like rendering or editing large video files or modeling will fall on the shoulders of your processor, then the capabilities of the Core i7 will completely satisfy you.
I think that this article has clarified how the i3 i5 i7 processors differ. I hope this information will play a role in choosing one or another processor when buying.
On June 2, Intel announced ten new 14nm 5th Gen Intel Core family (codenamed Broadwell-C) 14nm desktop and mobile processors and five new 14nm Intel Xeon E3-1200 v4 family processors.
Of the ten new 5th Generation (Broadwell-C) desktop and mobile Intel Core processors, only two desktop-oriented processors feature an LGA 1150 socket: the quad-core Intel Core i7-5775C and Core i5-5675C. All other 5th generation Intel Core processors are BGA-based and laptop-oriented. Brief characteristics new Broadwell-C processors are presented in the table.
| connector | Number of cores/threads | L3 cache size, MB | TDP, W | Graphics core | ||
| Core i7-5950HQ | BGA | 4/8 | 6 | 2,9/3,7 | 47 | Iris Pro Graphics 6200 |
| Core i7-5850HQ | BGA | 4/8 | 6 | 2,7/3,6 | 47 | Iris Pro Graphics 6200 |
| Core i7-5750HQ | BGA | 4/8 | 6 | 2,5/3,4 | 47 | Iris Pro Graphics 6200 |
| Core i7-5700HQ | BGA | 4/8 | 6 | 2,7/3,5 | 47 | Intel HD Graphics 5600 |
| Core i5-5350H | BGA | 2/4 | 4 | 3,1/3,5 | 47 | Iris Pro Graphics 6200 |
| Core i7-5775R | BGA | 4/8 | 6 | 3,3/3,8 | 65 | Iris Pro Graphics 6200 |
| Core i5-5675R | BGA | 4/4 | 4 | 3,1/3,6 | 65 | Iris Pro Graphics 6200 |
| Core i5-5575R | BGA | 4/4 | 4 | 2,8/3,3 | 65 | Iris Pro Graphics 6200 |
| Core i7-5775C | LGA 1150 | 4/8 | 6 | 3,3/3,7 | 65 | Iris Pro Graphics 6200 |
| Core i5-5675C | LGA 1150 | 4/4 | 4 | 3,1/3,6 | 65 | Iris Pro Graphics 6200 |
Of the five new processors of the Intel Xeon E3-1200 v4 family, only three models (Xeon E3-1285 v4, Xeon E3-1285L v4, Xeon E3-1265L v4) have an LGA 1150 socket, and two more models are made in a BGA package and are not designed for self-installation on the motherboard. Brief characteristics of the new processors of the Intel Xeon E3-1200 v4 family are presented in the table.
| connector | Number of cores/threads | L3 cache size, MB | Frequency nominal / maximum, GHz | TDP, W | Graphics core | |
| Xeon E3-1285 v4 | LGA 1150 | 4/8 | 6 | 3,5/3,8 | 95 | Iris Pro Graphics P6300 |
| Xeon E3-1285L v4 | LGA 1150 | 4/8 | 6 | 3,4/3,8 | 65 | Iris Pro Graphics P6300 |
| Xeon E3-1265Lv4 | LGA 1150 | 4/8 | 6 | 2,3/3,3 | 35 | Iris Pro Graphics P6300 |
| Xeon E3-1278L v4 | BGA | 4/8 | 6 | 2,0/3,3 | 47 | Iris Pro Graphics P6300 |
| Xeon E3-1258L v4 | BGA | 2/4 | 6 | 1,8/3,2 | 47 | Intel HD Graphics P5700 |
Thus, out of 15 new Intel processors, only five models have an LGA 1150 socket and are aimed at desktop systems. For users, of course, the choice is small, especially considering that the Intel Xeon E3-1200 v4 family of processors is focused on servers, and not on user PCs.
In the following, we will focus on the new 14nm processors with LGA 1150 socket.
So, the main features of the new fifth-generation Intel Core processors and the Intel Xeon E3-1200 v4 family of processors are a new 14-nanometer core microarchitecture with code name Broadwell. In principle, there is no fundamental difference between the processors of the Intel Xeon E3-1200 v4 family and the fifth generation Intel Core processors for desktop systems, so in the future we will refer to all these processors as Broadwell.
In general, it should be noted that the Broadwell microarchitecture is not just Haswell in 14nm. Rather, it is a slightly improved Haswell microarchitecture. However, Intel always does this: when switching to a new manufacturing process, changes are made to the microarchitecture itself. In the case of Broadwell, we are talking about cosmetic improvements. In particular, the volumes of internal buffers have been increased, there are changes in the execution units of the processor core (the scheme for performing floating-point multiplication and division operations has been changed).
We will not consider in detail all the features of the Broadwell microarchitecture (this is a topic for a separate article), but we emphasize once again that we are talking only about cosmetic changes in the Haswell microarchitecture, and therefore, one should not expect that Broadwell processors will be more productive than Haswell processors. Of course, the transition to a new process technology allowed to reduce the power consumption of processors (at the same clock frequency), but we should not expect any significant performance gains.
Perhaps the most significant difference between the new Broadwell processors and Haswell lies in the fourth level cache (L4 cache) Crystalwell. Let us clarify that such an L4 cache was present in Haswell processors, but only in top models of mobile processors, while Haswell processors for desktop PCs with an LGA 1150 socket did not have it.
Recall that in some top models of Haswell mobile processors, the Iris Pro graphics core was implemented with additional eDRAM (embedded DRAM) memory, which made it possible to solve the problem with insufficient memory bandwidth used for the GPU. eDRAM memory was a separate chip, which was located on the same substrate as the processor chip. This crystal was codenamed Crystalwell.
The eDRAM memory was 128 MB in size and was manufactured using a 22-nanometer process technology. But the most important thing is that this eDRAM memory was used not only for the needs of the GPU, but also for the computing cores of the processor itself. That is, in fact, Crystalwell was an L4 cache shared between the GPU and the processor cores.
All new Broadwell processors also feature a separate 128MB eDRAM die that acts as an L4 cache and can be used by the processor's graphics and compute cores. Moreover, we note that the eDRAM memory in the 14-nanometer Broadwell processors is exactly the same as in the top Haswell mobile processors, that is, it is performed according to the 22-nanometer process technology.
The next feature of the new Broadwell processors is the new graphics core codenamed Broadwell GT3e. For desktop and mobile processors (Intel Core i5/i7), this is Iris Pro Graphics 6200, and for Intel Xeon E3-1200 v4 family processors, this is Iris Pro Graphics P6300 (excluding Xeon E3-1258L v4). We will not delve into the specifics of the architecture of the Broadwell GT3e graphics cores (this is a topic for a separate article) and will only briefly consider its main features.
Recall that the Iris Pro graphics core was previously present only in Haswell mobile processors (Iris Pro Graphics 5100 and 5200). Moreover, in the graphics cores of Iris Pro Graphics 5100 and 5200 there are 40 execution units (EU) each. The new graphics cores Iris Pro Graphics 6200 and Iris Pro Graphics P6300 are already equipped with 48 EU, and the EU organization system has also changed. Each individual GPU unit contains 8 EUs, and the graphics module combines three graphics units. That is, one graphics module contains 24 EU, and in the Iris Pro Graphics 6200 or Iris Pro Graphics P6300 GPU itself, two modules are combined, that is, in total we get 48 EU.
As for the difference between the Iris Pro Graphics 6200 and Iris Pro Graphics P6300 graphics cores, at the hardware level they are the same (Broadwell GT3e), but they have different drivers. In the Iris Pro Graphics P6300 variant, the drivers are optimized for tasks specific to servers and graphics stations.
Before moving on to a detailed examination of the results of Broadwell testing, let's talk about a few more features of the new processors.
First of all, the new Broadwell processors (including the Xeon E3-1200 v4) are compatible with motherboards based on Intel 9-series chipsets. We can't say that any board based on the Intel 9-series chipset will support these new Broadwell processors, but most boards do. True, for this you will have to update the BIOS on the board, and the BIOS must support new processors. For example, for testing, we used the ASRock Z97 OC Formula board, and without a BIOS update, the system worked only with a discrete video card, and image output through the graphics core of Broadwell processors was not possible.
The next feature of the new Broadwell processors is that the Core i7-5775C and Core i5-5675C models have an unlocked multiplier, that is, they are focused on overclocking. In the Haswell processor family, such processors with an unlocked multiplier made up the K-series, and in the Broadwell family, the letter "C" is used instead of the letter "K". But the Xeon E3-1200 v4 processors do not support overclocking (they cannot increase the multiplier).
Now let's take a closer look at the processors that came to us for testing. These are models , and . In fact, of the five new models with the LGA 1150 socket, only the Xeon E3-1285L v4 processor is missing, which differs from the Xeon E3-1285 v4 model only in lower power consumption (65 W instead of 95 W) and the fact that the nominal clock frequency of the cores slightly lower (3.4 GHz instead of 3.5 GHz). In addition, for comparison, we also added the Intel Core i7-4790K, which is the top processor in the Haswell family.
The characteristics of all tested processors are presented in the table:
| Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i7-5775C | Core i5-5675С | Core i7-4790K | |
| Process technology, nm | 14 | 14 | 14 | 14 | 22 |
| connector | LGA 1150 | LGA 1150 | LGA 1150 | LGA 1150 | LGA 1150 |
| Number of Cores | 4 | 4 | 4 | 4 | 4 |
| Number of threads | 8 | 8 | 8 | 4 | 8 |
| L3 cache, MB | 6 | 6 | 6 | 4 | 8 |
| L4 cache (eDRAM), MB | 128 | 128 | 128 | 128 | N/A |
| Rated frequency, GHz | 3,5 | 2,3 | 3,3 | 3,1 | 4,0 |
| Maximum frequency, GHz | 3,8 | 3,3 | 3,7 | 3,6 | 4,4 |
| TDP, W | 95 | 35 | 65 | 65 | 88 |
| Memory type | DDR3-1333/1600/1866 | DDR3-1333/1600 | |||
| Graphics core | Iris Pro Graphics P6300 | Iris Pro Graphics P6300 | Iris Pro Graphics 6200 | Iris Pro Graphics 6200 | HD Graphics 4600 |
| Number of GPU execution units | 48 (Broadwell GT3e) | 48 (Broadwell GT3e) | 48 (Broadwell GT3e) | 48 (Broadwell GT3e) | 20 (Haswell GT2) |
| Nominal GPU frequency, MHz | 300 | 300 | 300 | 300 | 350 |
| Maximum GPU frequency, GHz | 1,15 | 1,05 | 1,15 | 1,1 | 1,25 |
| vpro technology | + | + | − | − | − |
| VT-x technology | + | + | + | + | + |
| VT-d technology | + | + | + | + | + |
| Cost, $ | 556 | 417 | 366 | 276 | 339 |
And now, after our express review of the new Broadwell processors, let's move on to testing the new products.
test stand
To test the processors, we used the bench with the following configuration:
Test Methodology
Processors were tested using our scripted benchmarks , and . To be more precise, we took the workstation testing methodology as a basis, but expanded it by adding tests from the iXBT Application Benchmark 2015 package and iXBT Game Benchmark 2015 gaming tests.
Thus, the following applications and benchmarks were used to test the processors:
- MediaCoder x64 0.8.33.5680
- SVPmark 3.0
- Adobe Premiere Pro CC 2014.1 (Build 8.1.0)
- Adobe after effects CC 2014.1.1 (Version 13.1.1.3)
- Photodex ProShow Producer 6.0.3410
- Adobe Photoshop CC 2014.2.1
- ACDSee Pro 8
- Adobe Illustrator CC 2014.1.1
- Adobe Audition CC 2014.2
- Abbyy Fine Reader 12
- WinRAR 5.11
- Dassault SolidWorks 2014 SP3 (Flow Simulation Package)
- SPCapc for 3ds max 2015
- SPECapc for Maya 2012
- POV Ray 3.7
- Maxon Cinebench R15
- SPECviewperf v.12.0.2
- SPECwpc 1.2
In addition, games and gaming benchmarks from the iXBT Game Benchmark 2015 package were used for testing. Testing in games was carried out at a resolution of 1920x1080.
In addition, we measured the power consumption of processors in idle and stressful loading modes. For this, a specialized software and hardware complex was used, connected to the break in the power supply circuits of the motherboard, that is, between the power supply and the motherboard.
We used the AIDA64 utility (Stress FPU and Stress GPU tests) to create a CPU stress load.
Test results
Processor Power Consumption
So, let's start with the results of testing processors for power consumption. The test results are presented in the diagram.
The most voracious in terms of power consumption, as expected, was the Intel Core i7-4790K processor with a declared TDP of 88 watts. Its real power consumption in stress mode was 119 watts. At the same time, the temperature of the processor cores was 95 °C and throttling was observed.
Next in terms of power consumption was the Intel Core i7-5775C processor with a claimed TDP of 65W. For this processor, power consumption in stress mode was 72.5 watts. The temperature of the processor cores reached 90 °C, but no throttling was observed.
The third place in terms of power consumption was taken by the Intel Xeon E3-1285 v4 processor with a TDP of 95 watts. Its power consumption in stress mode was 71 W, and the temperature of the processor cores was 78 °C
And the most economical in terms of power consumption was the Intel Xeon E3-1265L v4 processor with a TDP of 35 watts. In stress mode, the power consumption of this processor did not exceed 39 W, and the temperature of the processor cores was only 56 °C.
Well, if we focus on the power consumption of processors, then we must state that Broadwell has a significantly lower power consumption compared to Haswell.
Tests from iXBT Application Benchmark 2015
Let's start with the tests included in the iXBT Application Benchmark 2015. Note that we calculated the integral performance result as the geometric mean of the results in logical groups of tests (video conversion and video processing, video content creation, etc.). To calculate the results in logical groups of tests, the same reference system was used as in the iXBT Application Benchmark 2015.
The full test results are shown in the table. In addition, we present the results of testing for logical groups of tests on diagrams in a normalized form. The result of the Core i7-4790K processor is taken as a reference.
| Logical group of tests | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| Video conversion and video processing, points | 364,3 | 316,7 | 272,6 | 280,5 | 314,0 |
| MediaCoder x64 0.8.33.5680, seconds | 125,4 | 144,8 | 170,7 | 155,4 | 132,3 |
| SVPmark 3.0 points | 3349,6 | 2924,6 | 2552,7 | 2462,2 | 2627,3 |
| Creation of video content, points | 302,6 | 264,4 | 273,3 | 264,5 | 290,9 |
| Adobe Premiere Pro CC 2014.1, seconds | 503,0 | 579,0 | 634,6 | 612,0 | 556,9 |
| Adobe After Effects CC 2014.1.1 (Test #1), seconds | 666,8 | 768,0 | 802,0 | 758,8 | 695,3 |
| Adobe After Effects CC 2014.1.1 (Test #2), seconds | 330,0 | 372,2 | 327,3 | 372,4 | 342,0 |
| Photodex ProShow Producer 6.0.3410, seconds | 436,2 | 500,4 | 435,1 | 477,7 | 426,7 |
| Digital photo processing, points | 295,2 | 258,5 | 254,1 | 288,1 | 287.0 |
| Adobe Photoshop CC 2014.2.1, seconds | 677,5 | 770,9 | 789,4 | 695,4 | 765,0 |
| ACDSee Pro 8, seconds | 289,1 | 331,4 | 334,8 | 295,8 | 271,0 |
| Vector graphics, scores | 150,6 | 130,7 | 140,6 | 147,2 | 177,7 |
| Adobe Illustrator CC 2014.1.1, seconds | 341,9 | 394,0 | 366,3 | 349,9 | 289,8 |
| Audio processing, points | 231,3 | 203,7 | 202,3 | 228,2 | 260,9 |
| Adobe Audition CC 2014.2, seconds | 452,6 | 514,0 | 517,6 | 458,8 | 401,3 |
| Text recognition, points | 302,4 | 263,6 | 205,8 | 269,9 | 310,6 |
| Abbyy FineReader 12 seconds | 181,4 | 208,1 | 266,6 | 203,3 | 176,6 |
| Archiving and unarchiving data, points | 228,4 | 203,0 | 178,6 | 220,7 | 228,9 |
| WinRAR 5.11 archiving, seconds | 105,6 | 120,7 | 154,8 | 112,6 | 110,5 |
| WinRAR 5.11 unzipping, seconds | 7,3 | 8,1 | 8,29 | 7,4 | 7,0 |
| Integral performance result, points | 259,1 | 226,8 | 212,8 | 237,6 | 262,7 |
So, as you can see from the test results, the integrated performance of the Intel Xeon E3-1285 v4 processor practically does not differ from the Intel Core i7-4790K processor. However, this is an integral result for the totality of all applications used in the benchmark.
However, there are a number of applications that benefit from the Intel Xeon E3-1285 v4 processor. These applications are MediaCoder x64 0.8.33.5680 and SVPmark 3.0 (video conversion and processing), Adobe Premiere Pro CC 2014.1 and Adobe After Effects CC 2014.1.1 (video content creation), Adobe Photoshop CC 2014.2.1 and ACDSee Pro 8 (digital photos). In these applications, the higher clock speed of the Intel Core i7-4790K processor does not give it an advantage over the Intel Xeon processor E3-1285 v4.
But in applications such as Adobe Illustrator CC 2014.1.1 (vector graphics), Adobe Audition CC 2014.2 (audio processing), Abbyy FineReader 12 (text recognition), the advantage is on the side of the higher-frequency Intel Xeon E3-1285 v4 processor. It is interesting to note here that tests based on Adobe Illustrator CC 2014.1.1 and Adobe Audition CC 2014.2 applications load the processor cores to a lesser extent (in comparison with other applications).
And of course, there are tests in which the Intel Xeon E3-1285 v4 and Intel Core i7-4790K processors demonstrate the same performance. For example, this is a test based on the WinRAR 5.11 application.
In general, it should be noted that the Intel Core i7-4790K processor demonstrates higher performance (compared to the Intel Xeon E3-1285 v4 processor) precisely in those applications in which not all processor cores are involved or the core load is not full. At the same time, in tests where all processor cores are 100% loaded, the leadership is on the side of the Intel Xeon E3-1285 v4 processor.
Calculations in Dassault SolidWorks 2014 SP3 (Flow Simulation)
The test based on the Dassault SolidWorks 2014 SP3 application with the optional Flow Simulation package was taken separately, since this test does not use a reference system, as in the tests of the iXBT Application Benchmark 2015 benchmark.
Recall that in this test we are talking about hydro / aerodynamic and thermal calculations. A total of six different models are calculated, and the results of each subtest are the calculation time in seconds.
Detailed test results are presented in the table.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| conjugate heat transfer, seconds | 353.7 | 402.0 | 382.3 | 328.7 | 415.7 |
| textile machine, seconds | 399.3 | 449.3 | 441.0 | 415.0 | 510.0 |
| rotating impeller, seconds | 247.0 | 278.7 | 271.3 | 246.3 | 318.7 |
| cpu cooler, seconds | 710.3 | 795.3 | 784.7 | 678.7 | 814.3 |
| halogen floodlight, seconds | 322.3 | 373.3 | 352.7 | 331.3 | 366.3 |
| electronic components, seconds | 510.0 | 583.7 | 559.3 | 448.7 | 602.0 |
| Total calculation time, seconds | 2542,7 | 2882,3 | 2791,3 | 2448,7 | 3027,0 |
In addition, we also give the normalized result of the calculation speed (the reciprocal of the total calculation time). The result of the Core i7-4790K processor is taken as a reference.
As can be seen from the test results, in these specific calculations, the leadership is on the side of Broadwell processors. All four Broadwell processors demonstrate higher computational speed compared to the Core i7-4790K processor. Apparently, these specific calculations are affected by the improvements in the execution units that were implemented in the Broadwell microarchitecture.
SPCapc for 3ds max 2015
Next, consider the results of the SPECapc for 3ds max 2015 test for an Autodesk 3ds max 2015 SP1 application. The detailed results of this test are presented in the table, and the normalized results for the CPU Composite Score and GPU Composite Score are shown in the charts. The result of the Core i7-4790K processor is taken as a reference.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| CPU Composite Score | 4,52 | 3,97 | 4,09 | 4,51 | 4,54 |
| GPU Composite Score | 2,36 | 2,16 | 2,35 | 2,37 | 1,39 |
| Large Model Composite Score | 1,75 | 1,59 | 1,68 | 1,73 | 1,21 |
| Large Model CPU | 2,62 | 2,32 | 2,50 | 2,56 | 2,79 |
| Large Model GPU | 1,17 | 1,08 | 1,13 | 1,17 | 0,52 |
| Interactive Graphics | 2,45 | 2,22 | 2,49 | 2,46 | 1,61 |
| Advanced Visual Styles | 2,29 | 2,08 | 2,23 | 2,25 | 1,19 |
| Modeling | 1,96 | 1,80 | 1,94 | 1,98 | 1,12 |
| CPU Computing | 3,38 | 3,04 | 3,15 | 3,37 | 3,35 |
| CPU Rendering | 5,99 | 5,18 | 5,29 | 6,01 | 5,99 |
| GPU Rendering | 3,13 | 2,86 | 3,07 | 3,16 | 1,74 |
In the SPECapc 3ds for max 2015 test, Broadwell processors are in the lead. Moreover, if in the subtests that depend on the performance of the CPU (CPU Composite Score), the Core i7-4790K and Xeon E3-1285 v4 processors demonstrate equal performance, then in the subtests that depend on the performance of the graphics core (GPU Composite Score), all Broadwell processors significantly ahead of the Core i7-4790K processor.
SPECapc for Maya 2012
Now let's look at the result of another 3D modeling test - SPECapc for Maya 2012. Recall that this benchmark was launched in tandem with the Autodesk Maya 2015 package.
The results of this test are presented in the table, and the normalized results are in the charts. The result of the Core i7-4790K processor is taken as a reference.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| GFX Score | 1,96 | 1,75 | 1,87 | 1,91 | 1,67 |
| CPU Score | 5,47 | 4,79 | 4,76 | 5,41 | 5,35 |
In this test, the Xeon E3-1285 v4 processor shows a slightly higher performance compared to the Core i7-4790K processor, however, the difference is not as significant as in the SPECapc 3ds for max 2015 package.
POV Ray 3.7
In the POV-Ray 3.7 test (3D rendering), the leader is the Core i7-4790K processor. In this case, a higher clock speed (with an equal number of cores) gives an advantage to the processor.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| Render average, PPS | 1568,18 | 1348,81 | 1396,3 | 1560.6 | 1754,48 |
Cinebench R15
In the Cinebench R15 benchmark, the result was mixed. In the OpenGL test, all Broadwell processors significantly outperform the Core i7-4790K processor, which is natural, since they integrate a more powerful graphics core. But in the processor test, on the contrary, the Core i7-4790K processor turns out to be more productive.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| opengl fps | 71,88 | 66,4 | 72,57 | 73 | 33,5 |
| CPU, cb | 774 | 667 | 572 | 771 | 850 |
SPECviewperf v.12.0.2
In the tests of the SPECviewperf v.12.0.2 package, the results are determined mainly by the performance of the graphics core of the processor and, moreover, by the optimization of the video driver for certain applications. Therefore, in these tests, the Core i7-4790K processor is significantly behind the Broadwell processors.
The test results are presented in the table, as well as in a normalized form in the diagrams. The result of the Core i7-4790K processor is taken as a reference.
| Test | Xeon E3-1285 v4 | Xeon E3-1265Lv4 | Core i5-5675C | Core i7-5775C | Core i7-4790K |
| catia-04 | 20,55 | 18,94 | 20,10 | 20,91 | 12,75 |
| creo-01 | 16,56 | 15,52 | 15,33 | 15,55 | 9,53 |
| energy-01 | 0,11 | 0,10 | 0,10 | 0,10 | 0,08 |
| maya-04 | 19,47 | 18,31 | 19,87 | 20,32 | 2,83 |
| medical-01 | 2,16 | 1,98 | 2,06 | 2,15 | 1,60 |
| showcase-01 | 10,46 | 9,96 | 10,17 | 10,39 | 5,64 |
| snx-02 | 12,72 | 11,92 | 3,51 | 3,55 | 3,71 |
| sw-03 | 31,32 | 28,47 | 28,93 | 29,60 | 22,63 |
It cannot be said that everything is unambiguous in this test. In some scenarios (Media and Entertainment, Product Development, Life Sciences), Broadwell processors show better results. There are scenarios (Financial Services, Energy, General Operation) where the advantage is on the side of the Core i7-4790K processor or the results are approximately the same.
Game tests
And in conclusion, let's look at the results of testing processors in gaming tests. Recall that for testing we used the following games and gaming benchmarks:
- Aliens vs Predators
- World of Tanks 0.9.5
- Grid 2
- Metro: LL Redux
- Metro: 2033 Redux
- Hitman: Absolution
- Thief
- tomb raider
- Sleeping Dogs
- Sniper Elite V2
Testing was carried out at a screen resolution of 1920×1080 and in two settings: maximum and minimum quality. The test results are presented in the diagrams. In this case, the results are not normalized.
In gaming tests, the results are as follows: all Broadwell processors show very close results, which is natural, since they use the same Broadwell GT3e graphics core. And most importantly, with settings for the minimum quality, Broadwell processors allow you to comfortably play (at FPS over 40) most games (at a resolution of 1920x1080).
On the other hand, if the system uses a discrete graphics card, then there is simply no point in the new Broadwell processors. That is, it makes no sense to change Haswell to Broadwell. And the price of Broadwells is not so very attractive. For example, the Intel Core i7-5775C costs more than the Intel Core i7-4790K.
However, Intel does not seem to be betting on Broadwell desktop processors. The range of models is extremely modest, and Skylake processors are on the way, so it is unlikely that the Intel Core i7-5775C and Core i5-5675C processors will be in special demand.
Server processors of the Xeon E3-1200 v4 family are a separate market segment. For most ordinary home users, such processors are not of interest, but in the corporate sector of the market, these processors may be in demand.
One of the conditions for the speed of a computer is a processor, of course, in games it is still necessary to take into account the speed of the video card, but for work not related to graphics, the video card is not critical and the main role is played by which processor is used.
Processors from Intel have been improved to reduce power consumption and increase performance, the thickness of the deposition layers has decreased, and work is underway to release processes using 10nm technologies.
4 types of processors are available
- For desktop computers.
- For mobile devices, tablets, laptops.
- For servers
- Embedded processors
The characteristics of the processors are similar for different types, processors for servers are slightly different, they are subject to higher requirements for reliability and speed, for example, they have an internal cache of more than 10mv and the price is higher.
Table of evolution of processor cores from Intel
In general, the characteristics of processors are similar for different types of devices.
The main differences in the Core i3, i5, i7, i9 processors from 1 to 9 generations.
- Core i3- the cheapest processors, these processors have 2 physical cores, technology is used to increase performance. This technology creates 2 more virtual cores from 2 physical cores and operating system determines that the processor has 4 cores. Memory cache 3-4MB.
- Core i5- mid-range processors, as a rule, these processors have 4 physical cores, only some models have only 2 physical cores + 2 virtual ones. The memory cache is typically 6MB but some models may have 4 or 8MB. Higher performance is achieved by the presence of 4 physical cores and an increased amount of cache memory.
- Core i7- processors have from 4 to 8 physical cores with the obligatory use of technology INTEL® HYPER THREADING TECHNOLOGY. Memory cache from 8MB to 20MB latest models processors. The performance is increased by virtual cores and a large amount of cache memory. Processors for mobile devices can have 2 physical cores.
- Core i9- 6 - 8 physical cores, memory cache from 10Mb, the i9 series was conceived as a competitor to gaming processors from AMD. Core i9 began to be released in 2018. More cores, more speed, but not by much. Since i9 is slightly better than i7, there is practically no point in developing this line of processors. Only a few core i9 processor models were released.
Generations of Intel i3, i5, i7, i9 processors
In total, as of the beginning of 2019, 9 generations of processors have been released.
- 1st generation - manufactured using 45nm technology in 2010 using 32nm technology, developed in 2008-2010, without integrated graphics.
- 2nd generation - 32nm technology, intel 2000, 3000 graphics, 2011 release.
- 3rd generation - 32-22nm technology, Intel 4000 graphics, release 2011-2012.
- 4th generation - 22nm technology, Intel graphics 4600-5200 release 2013.
- 5th generation - 14nm and 22nm technology, Intel 6200 graphics release 2014-2015.
- 6th generation - 14nm technology, Intel graphics 530-580, release 2015-2016.
- 7th generation - 14nm technology, Intel graphics 610-620, release 2016-2017.
- 8th generation - 14nm technology, Intel 615-655 graphics, there are various graphics modifications with support for HD and UHD screen resolutions, release 2017-2018
- 9 generation- 14nm technology, Intel UHD 630 graphics, release 2018-2019. Technologies are used in various combinations depending on the type of processor.
- Intel® Turbo Boost Technology 2.0
- Intel® Hyper-Threading Technology
- Intel® Smart Cache Technology
- Integrated memory controller
- Intel® UHD Graphics
- Intel® Quick Sync Video Technology
- Overclocking of processor cores, memory and graphics
- PCI Express* 3.0 interface
- Support for Intel® Optane™ Memory Intel® Power Optimizer
For the first time, desktop 6-core processors appeared eight years ago at a price of $600. But the Socket LGA1366 platform itself was quite expensive, and only wealthy enthusiasts could afford it. Although perhaps main reason, due to which such solutions could not become popular, we can consider the lack of wide distribution software able to take full advantage of the opportunities that were new at that time. Of course, there was specialized software, but only in certain narrow niches. In order for multi-core processors to become mainstream, it was necessary to prepare the ground, which Intel did.
To do this, starting with the mainstream platform Socket LGA1156 and subsequent, a hierarchy was introduced that remained almost unchanged until the seventh generation of Intel Core. So, at the very bottom there are 2-core Intel Celeron and Intel Pentium chips (a 4-thread "hyperstump" and the like stand out from the general row). The models of the Intel Core i3 line go one step higher, which also have 2 cores, but thanks to the support of Intel Hyper-Threading logical multithreading technology, they are able to process 4 threads. At the very top are Intel Core i5 / i7 processors: they have 4 full cores (the exception is 2-core 4-thread models of the Intel Core i5-6xx family), and in the latter case, twice the number of threads. This approach allowed the microprocessor giant to cover all the needs for building a wide range of home, educational or office computers. And all subsequent years, engineers from Santa Clara were engaged in improving the quality of their products and expanding their functionality.
At the same time, HEDT platforms were also developing, which in their composition offer multi-core “pebbles” for creating uncompromising gaming or workstations. It is noteworthy that with the release of Socket LGA2011-v3, the recommended price tag for 6-core processors dropped below $400, and 8-core 16-thread models, and then 10-core 20-thread models, leaked into the desktop segment for the first time.
What about AMD? I must say that after the appearance of the Intel Core 2 Duo on the scene, the “reds” were in the role of catching up. The company tried to take the quantity by offering more cores than the competitor. We are talking about 6-core AMD Phenom II X6 and newer 8-core AMD FX. But at the dawn of their appearance, game engines used only 1-2 threads, and due to faster cores, Intel solutions looked preferable. However, this does not mean that these processors turned out to be unsuccessful, just then their time has not yet come. As evidence, we can recall a lot of modern tests of "fufiks", which even now look very good, especially after proper overclocking. Separately, it is worth mentioning that AMD managed to firmly register in consoles thanks to its 8-core Jaguar CPUs, which prompted game developers to parallelize code.
It would seem that nothing can break this hegemony and everyone has already come to terms with a slight (5-10%) increase in computing power during the transition of the CPU from generation to generation, which was confirmed by the release of the line , which is essentially just a slightly modified version of . But with the debut of the long-awaited processors, the company from Sunnyvale managed to impose an active struggle against Intel in the price segments from $100 and above. And AMD has remained true to its principles - "more opportunities for less money." As a result, in every price range, Ryzen outperforms the competitor in the number of cores or threads. In fairness, it should be noted that this does not always result in an unconditional advantage in performance, but from a purely psychological and marketing point of view, the blow was tangible. Naturally, the Blues had to make an accelerated response to such a daring attack from their eternal opponent. First of all, plans for the release of the platform were adjusted and the line of Intel Core X chips was significantly expanded, including a real monster - the 18-core 36-thread Intel Core i9-7980XE.
But much more excitement was caused by the debut of the 8th generation Intel Core processors. This is due to the fact that the new Intel Coffee Lake family for the first time in many years received a proportional increase in the number of cores / threads and cache memory. That is, now in the Intel Core i5 / i7 CPU series, solutions are offered with six computing cores, which are characterized by the presence / absence of support for Intel Hyper-Threading technology and L3 cache 9 / 12 MB, and Intel Core i3 have acquired four full-fledged cores, without HT, but with an L3 cache increased to 6 MB. In practice, this resulted in a significant increase in productivity, which was confirmed by our practical acquaintance with and . By the way, a couple of our experiments showed that it bypasses not only its 2-core predecessor in the face of the Core i3-7100, but also the younger 4-core Core i5 of previous generations. It is curious, but it can also compete on equal terms with the more expensive one. And this suggests that the new Core i5 look very attractive options for building a modern gaming computer.
Now in the Intel lineup there is the most affordable 6-core. Just a minute, according to the official price list Intel Core i5-8400 is $187 in quantities of 1,000 or more, making it a very tasty purchase. But the real picture is slightly different. At the time of writing these lines, its average cost reached $250 in the domestic market, while a direct competitor in person can be found for $220. Given the temporary lack of available motherboards for Coffee Lake, when assembling real systems on Socket AM4 you can additionally save about $60 or even more. But what to choose in this case? And you will find out by reading this material.
Specification
|
Processor socket |
|
|
Base / dynamic clock frequency, GHz |
|
|
base multiplier |
|
|
Base system bus frequency, MHz |
|
|
Number of cores / threads |
|
|
L1 cache size, KB |
6 x 32 (data memory) |
|
L2 cache size, KB |
|
|
L3 cache size, MB |
|
|
microarchitecture |
Intel Coffee Lake |
|
codename |
Intel Coffee Lake-S |
|
Maximum design power (TDP), W |
|
|
Process technology, nm |
|
|
Critical temperature (T junction), °C |
|
|
Support for instructions and technologies |
Intel Turbo Boost 2.0, Intel Optane Memory, Intel vPro, Intel VT-x, Intel VT-d, Intel VT-x EPT, Intel TSX-NI, Intel 64, Execute Disable Bit, Intel AEX-NI, MMX, SSE, SSE2 , SSE3, SSSE3, SSE4.1, SSE4.2, EM64T, AES, AVX, AVX 2.0, FMA3, Enhanced Intel SpeedStep, Thermal Monitoring, Intel Identity Protection, Intel Stable Image Platform Program (SIPP) |
|
Built-in memory controller |
|
|
Memory type |
|
|
Supported frequency, MHz |
|
|
Number of channels |
|
|
Maximum memory, GB |
|
|
Integrated Intel UHD Graphics 630 |
|
|
Number of execution units (EU) |
|
|
Base / dynamic frequency, MHz |
|
|
Maximum video memory (allocated from RAM), GB |
|
|
Maximum screen resolution at 60 Hz |
|
|
Maximum supported displays |
|
|
Supported technologies and APIs |
DirectX 12, OpenGL 4.5, Intel Quick Sync Video, Intel InTru 3D, Intel Clear Video HD, Intel Clear Video |
|
Products webpage |
|
|
Processor page |
|
|
Purchase page |
|
Packaging, scope of delivery and appearance
The processor was kindly provided for testing by the company BRAIN Computers. In the company store, it is available in the BOX version (BX80684I58400) with a simple cooler. He came to us in the OEM version (CM8068403358811) without a cooling system. The price difference is about $15-20, which will allow the user to choose a more efficient cooler, but instead of a three-year warranty, you will have to limit yourself to only one.
The marking on the heat spreader cover of the Intel Core i5-8400 says that our sample was manufactured in Malaysia on the 37th week of 2017, that is, between September 11 and 17. Considering the use of the same Socket LGA1151 processor socket, there are practically no visual differences from its predecessors.
But it is worth recalling that for any Intel Coffee Lake processor to work, you will need a motherboard based on Intel 300 series chipsets. Although, at your own peril and risk, you can use and either endow a model based on Intel 100- / 200-series chipsets with the ability to work with new CPUs, or, at best, lose time (and at worst, turn it into a museum piece).
At the moment, only models based on the overclocker chipset are available for the updated platform. Naturally, if you are the owner of a chip with an unlocked multiplier, then this is a completely justified choice, but owners of models without the “K” index will have to pay a fair amount for the functionality they do not need. The cheapest boards based on it will cost around $120-130, which is approximately 2.5 times more expensive than budget solutions based on Intel H110 for Intel Skylake/Kaby Lake. We expect the debut of available options on lower chipsets (Intel H310, H370 and B360) since January, but so far they have not appeared on open sale.
Analysis of technical characteristics
As already mentioned, the Intel Core i5-8400 is a 6-core processor that is manufactured using a 14nm process technology. At the microarchitectural level, Intel Coffee Lake has a minimum of differences from, that is, with a single-threaded load and at the same frequency, they are equal. But the new chips use a modified manufacturing process, which the manufacturer himself refers to as 14 ++ nm (recall that Intel began using 14 nm back in 2015 in Intel Broadwell processors). This technology makes it possible to produce multi-core solutions with relatively low heat release, increases the yield of suitable chips and reduces their cost. As an example, our test subject has a TDP of 65 watts. Of course, its base frequency is quite modest and is only 2.8 GHz, but thanks to Intel Turbo Boost 2.0 technology given value can go up to 4 GHz.
We conducted practical tests on a motherboard with an inexpensive cooler Vinga CL-2001B, which is suitable for 65-watt processors from AMD and Intel. Its design consists of an aluminum radiator and a 120mm hydrodynamic bearing fan with blue LED illumination.
In the AIDA64 stress test, the maximum temperature of the cores did not exceed 72 ° C with a critical indicator of 100 ° C, and their clock frequency was at 3.8 GHz. The chip can also operate at a frequency of 3.9 GHz in the case of a load of 2-4 cores, or accelerate to 4 GHz in single-threaded mode. The cooler speed did not exceed 1400 rpm, although the specification says 1600 rpm. The background noise was absolutely comfortable.
For comparison, we recall that the predecessor in the face with a smaller number of cores and the same thermal package can operate at maximum load only at a frequency of 3.3 GHz, and when it decreases, you can see a value of 3.5 GHz. In turn, the older brother, when loaded on all cores, it operates at a frequency of 4.1 GHz, when using 2-4 cores, this figure increases to 4.2 GHz, and in a single thread it should be 4.3 GHz.
We are grateful to the companyBRAIN Computers for the processor provided for testing.
Article read 37166 times
| Subscribe to our channels | |||||
We examine models of the mass segment in comparison with processors three years ago
Quad-core processors of the Ivy Bridge family are firmly registered on the shelves of all computer stores, so it's time to expand our knowledge about them, hitherto limited to only two top overclocking models Core i5 and i7. Moreover, younger models are of greater practical interest for two reasons. Firstly, they are cheaper, and sometimes noticeable: the savings can be 1000-1500 rubles, which is quite comparable, for example, with the price difference between the Radeon HD 6670 and HD 7750 or HD 7770 and HD 6930, that is, this difference is very relevant for an economical gamer (let's digress for now from the question of the need to purchase a Core i5 and higher in this case - a person can also have interests other than games in parallel). Secondly, the usefulness of buying a representative of the 3x70K line greatly reduces the increased heat flux (due to a decrease in the crystal area). Thus, overclockers, quite possibly, will continue to look more closely at the “oldies” Core i5-2500K and i7-2600K, whose “air” overclocking is somewhat easier, and there is no need for everyone else to pay extra for unlocked multipliers. On the other hand, there is no longer any incentive to purchase “regular” Sandy Bridges: the younger Ivy Bridges cost about the same, but in normal mode they consume less energy and work somewhat faster at the same formal frequencies due to improvements in Turbo Boost technology. Even if you plan to overclock a little (and purchase a board on a chipset that allows it), you should not forget that the so-called. The "Limited Unlocked Core" in the third generation of Core has not gone away, i.e. "throw" +400 MHz on lower models of processors, but it is difficult to get ≈5 GHz due to degraded heat dissipation on older ones.
In general, summing up, the younger Core i5 and i7 models do not claim to be the most massive processors, since they are somewhat expensive from the point of view of a “regular” user (usually limited to processors priced up to $ 200), however, of course, they are doomed to greater popularity than their top counterparts. Therefore, the need for their testing is obvious, and that is what we will deal with today.
Test stand configuration
| CPU | Core i5-3450 | Core i5-3550 | Core i5-3570K | Core i7-3770 | Core i7-3770K |
| Kernel name | Ivy Bridge QC | Ivy Bridge QC | Ivy Bridge QC | Ivy Bridge QC | Ivy Bridge QC |
| Production technology | 22 nm | 22 nm | 22 nm | 22 nm | 22 nm |
| Core frequency (std/max), GHz | 3,1/3,5 | 3,3/3,7 | 3,4/3,8 | 3,4/3,9 | 3,5/3,9 |
| 31 | 33 | 34 | 34 | 35 | |
| How Turbo Boost works | 4-4-3-2 | 4-4-3-2 | 4-4-3-2 | 5-5-4-3 | 4-4-3-2 |
| 4/4 | 4/4 | 4/4 | 4/8 | 4/8 | |
| L1 cache, I/D, KB | 32/32 | 32/32 | 32/32 | 32/32 | 32/32 |
| L2 cache, KB | 4×256 | 4×256 | 4×256 | 4×256 | 4×256 |
| L3 cache, MiB | 6 | 6 | 6 | 8 | 8 |
| UnCore frequency, GHz | 3,1 | 3,3 | 3,4 | 3,4 | 3,5 |
| RAM | 2×DDR3-1600 | 2×DDR3-1600 | 2×DDR3-1600 | 2×DDR3-1600 | 2×DDR3-1600 |
| video core | GMA HD 2500 | GMA HD 2500 | GMA HD 4000 | GMA HD 4000 | GMA HD 4000 |
| socket | LGA1155 | LGA1155 | LGA1155 | LGA1155 | LGA1155 |
| TDP | 77 W | 77 W | 77 W | 77 W | 77 W |
| Price | N/A() | $250() | $284() | $368() | $431() |
This is how the entire Ivy Bridge line looks today, with the exception of energy-efficient models. There are more of the latter than before, but the number of conventional processors has slightly decreased: at the start of the Core i5-2000 there were four such processors, and three remained in the 3000 line. Over time, their number will certainly grow, but it is unlikely to be equal to the Sandy Bridge assortment. There, we recall, over the past year and a half, 9 Core i5 and 3 Core i7 have already accumulated, to which the new line responds with three and two models, respectively. On the other hand, there were a few more S- and T-modifications from the very beginning, i.e. the trend is clearly visible: since Intel now manages to “cram” even the Core i7 into 45 W, it would be strange not to use it. Moreover, the S-variants are now distinguished from the "regular" models not by 30, but by only 12 watts. In general, the bet on profitability.
The most curious, perhaps, will be the results of 3770 and 3770K. As you can see, the leadership of the second processor in terms of the nominal clock frequency does not mean anything - in reality, these devices will most likely operate at equal frequencies at the same time points. If this assumption is confirmed, this will be the final nail in the coffin of the idea of buying a 3770K for normal operation. Here in the last generation, things were a little different: the Core i7-2700K had the highest clock speeds in the family. Another argument against the older "regular" Core i7-2600 was the GMA HD 2000 video core, not 3000 (as in 2600K and 2700K). And now in normal mode there should be no differences between the 3770 and 3770K, and absolutely all desktop Core i7 received the GMA HD 4000. That is, the formal additional 100 MHz of the nominal frequency is just a beautiful bow (to make it more pleasant for buyers of the top model), and the same number for both processors is not without reason. But on the floor below, everything is the same: the Core i5-3570K really has a slightly higher frequency than the 3550, and even the GMA HD 4000 is the only one (at the moment) among all the desktop Core i5, so here it’s just a little justified different numbers.
| CPU | Core 2 Duo E8600 | Core 2 Quad Q9650 | Core i5-750 | Core i7-860 | Core i7-920 |
| Kernel name | wolfdale | Yorkfield | Lynnfield | Lynnfield | Bloomfield |
| Production technology | 45 nm | 45 nm | 45 nm | 45 nm | 45 nm |
| Core frequency (std/max), GHz | 3,33 | 3,0 | 2,66/3,2 | 2,8/3,46 | 2,66/2,93 |
| Starting multiplication factor | 10 | 9 | 20 | 21 | 20 |
| How Turbo Boost works | - | - | 4-4-1-1 | 5-4-1-1 | 2-1-1-1 |
| Number of cores/threads of calculation | 2/2 | 4/4 | 4/4 | 4/8 | 4/8 |
| L1 cache, I/D, KB | 32/32 | 32/32 | 32/32 | 32/32 | 32/32 |
| L2 cache, KB | 6144 | 2×6144 | 4×256 | 4×256 | 4×256 |
| L3 cache, MiB | - | - | 8 | 8 | 8 |
| UnCore frequency, GHz | - | - | 2,66 | 2,8 | 2,13 |
| RAM | - | - | 2×DDR3-1333 | 2×DDR3-1333 | 3×DDR3-1066 |
| socket | LGA775 | LGA775 | LGA1156 | LGA1156 | LGA1366 |
| TDP | 65 W | 95 W | 95 W | 95 W | 130 W |
| Price | N/A() | N/A() | N/A() | N/A() | N/A() |
Who are the processors to compare? For simplicity, we decided to arrange a kind of express testing, since the K-family was compared with other competitors of a similar level last time. But we will still go a little beyond the Ivy Bridge family, taking five “oldies” for comparison. Core 2 Duo E8600 and Core 2 Quad Q9650 are the best processors for the LGA775 platform (excluding extreme models), which remained the most popular until 2009-2010. Core i5-750 and Core i7-860 are the two most interesting models for LGA1156 in the second half of 2009 (in 2010 they were actually replaced by 760 and 870, but the difference in performance between them and their predecessors is small). And the "folk" solution for the early LGA1366, as well as the first massively (relatively) affordable Core i7 - 920. Again - later, for the same money, Intel offered faster solutions, but this started already in 2010. And we are more interested in just the period 2008-2009 for one simple reason: about three years have passed since then, so the "then" computers may already be tempted to change. Naturally, the most impatient enthusiasts may have already done this some time ago, but they are a minority among users. And those who were in no hurry to replace the old Core 2 Quad with Sandy Bridge, very likely, will just now consider the transition to Ivy Bridge as a potentially useful event. So let's evaluate how useful it is in practice. For those who fundamentally disagree with our approach, we traditionally recommend using a pivot table and comparing anything with anything :)
| Motherboard | RAM | |
| LGA1155 | Biostar TH67XE (H67) | |
| LGA1366 | Intel DX58SO2 (X58) | 12 GB 3×1066; 8-8-8-19 |
| LGA775 | ASUS Maximus Extreme (X38) | Corsair Vengeance CMZ8GX3M2A1600C9B (2×1333; 9-9-9-24) |
| LGA1156 | ASUS P7H55-M Pro (H55) | Corsair Vengeance CMZ8GX3M2A1600C9B (2×1333; 9-9-9-24) |
Testing
Traditionally, we divide all tests into a number of groups and show the average result for a group of tests/applications on the diagrams (for details on the testing methodology, see a separate article). The results in the diagrams are given in points, for 100 points the performance of the reference test system, the site of the sample of 2011, is taken. It is based on the AMD Athlon II X4 620 processor, but the amount of memory (8 GB) and video card () are standard for all tests of the “main line” and can only be changed as part of special studies. For those who are more interested detailed information, again, it is traditionally offered to download a table in Microsoft Excel format, in which all the results are given both in converted into points and in "natural" form.
Interactive work in 3D packages
As you can see, the efficiency of all 45nm Intel processors is approximately equal, so some differences can only arise due to extensive improvements, such as frequency or cache memory capacity. But Sandy Bridge raised the bar by 20-25 percent, and Ivy Bridge did not lose this advantage - with the ensuing result. However, according to the results, it is obvious that for interactive work, it may very well make sense to purchase one of the dual-core Core i3 for LGA1155 (or wait a bit for similar models on Ivy Bridge), since additional computation threads are unnecessary here - a couple will definitely suffice. But the money is not superfluous :)
Final rendering of 3D scenes
What is the most interesting here? The fact that the younger modern Core i5-3450 turned out to be slightly faster than the Core i7 of three or four years ago. Yes, already old processors, but generally speaking, they belong to a higher class (and more expensive, in particular). And this is despite a significant increase from Hyper-Threading technology, which allows the Core i7 to always overtake the Core i5 of the same generation! The progress since the days of Core2 is also very indicative - the 3770/3770K is almost twice as fast as the Q9650. At the time of the announcement in August 2008, the latter, by the way, cost $530 in bulk, i.e. much more expensive than any current processor for LGA1155 (and in general, six-core Core i7 have been “registered” in a close price range for almost a year and a half). As for the results of the E8600, there is no point in commenting on it - it seems to us that those who really need high performance in multi-threaded applications have parted ways with the Core 2 Duo a long time ago.
Packing and unpacking
But in archiving tests, the benefits of multithreading are not very great, the reason for which has already been voiced more than once: only one test out of four can use it fully, and for two, one thread is enough. Therefore, the entire increase can be obtained only by improving the architecture and extensive methods. Of course, it is, but not nearly as impressive as in the previous or subsequent cases.
Audio encoding
A similar situation with rendering, with one small exception: the Core i5-3450 managed to overtake only the Core i7-920, but not faster models. However, given the love of this test to increase multithreading in any way, and this should be assessed as a very good result. The first (albeit modernized) Intel quad-cores, of course, are not competitors to modern ones, even if the latest ones do not have NT. And in the presence - again, almost a two-fold difference.
Compilation
As we have already said, Intel's decision to reduce the cache memory capacity in the second generation Core i5 severely clipped their wings in the compiler tests. This also applies to the third generation, so only the best of the modern Core i5 managed to only catch up with the worst of the Core i7 of all time. But at least he caught up with him. But the Core i7 retained their 8 MiB of cache memory, so they easily went ahead, and they again outperformed one of the best Core 2 Quad almost twice.
Mathematical and engineering calculations
And again, a low-flow group, although the architectural improvements of both "bridges" affect it for the second year in a row. Accordingly, even the Core i5-3450 significantly outperformed all the oldies, which is good. And what is bad is that there is no question of any two-fold increase under such a load in any pair of “old-new” processors.
Raster graphics
Again, a mixed group, where there is an increase both from an increase in the number of nuclei and from NT, but in both cases it is unprincipled. The architecture has a stronger influence, so again, on the one hand, the new processors are noticeably faster than the old ones, and on the other hand, the advantage nowhere reaches a twofold.
Vector graphics
Half the dose of Core 2 Duo is enough here, and something can be improved only architecturally - or by higher frequencies. Ivy Bridge has both, which allows them to be the fastest. But not as fast as in multi-threaded tests - here, at best, one and a half times superiority is observed.
Video encoding
But in video processing, it again begins to tend to double (if we discard the Core 2 Duo, however, as it seems to us, no one has had illusions about dual-core processors under such a load for five years already). Another thing is more curious - the already noted tendency for the efficiency of Hyper-Threading to decrease as the Core architecture improves: if in the first generation the i7 outperformed the similar i5 by about 10%, now the difference has halved. Which, in general, is understandable: the “dense” the available resources are loaded by one thread, the more difficult it is to allocate them for the second.
Office software
What is curious is that the seemingly very conservative office group accelerated just as fast as the others (and even better compared to some programs). As we have already said, there is no great sense in this when comparing processors of the class under consideration, but all the same - a trifle, but nice.
Java
Again a multi-threaded group, and again an almost twofold advantage of the new Core i7 over the old Core 2 Quad. Well, the fact that the new Core i5 is able to overtake the old Core i7 is also no longer a secret. In general, progress has not gone anywhere - the whole question is in assessing its pace.
Games
But in games, as it has already been said a hundred times, processor performance is not a determining factor, since the video system is in the first place. But, as we can see, we should not neglect the processor either - even the cheapest of modern Core i5 is almost one and a half times faster than the best Core 2 Duo and is 25% superior to the best Core 2 Quad. In general, it makes sense for a gamer to think about switching from LGA775 at the same time as acquiring a new card - far from the worst idea. The main thing is not to spoil it with the desire to purchase the fastest processor for LGA1155 - this is not too justified. And for those who over the past years managed to migrate to LGA1366 or LGA1156, as it seems to us, they can not fuss, because it will not pay off.
Total
The first thing you should pay attention to: except for overclocking, the Core i7-3770K is no longer needed for anything. The difference in the nominal frequency, however, somehow affects, but +0.5% performance is not at all something worth paying more than 10% of the price for. Whether it is worth paying extra for Core i7 at all is also an interesting question. As you can see, the difference between the i7 and i5 families is really gradually decreasing (following the decrease in the relative efficiency of Hyper-Threading), which was not prevented even by the reduction in cache memory in the latter last year. But here already everyone chooses according to their capabilities and needs: in some classes of problems the difference between these families is still great, in others (also - as before) it is not worth paying attention to it.
Is it worth switching to a new platform from one of the old ones? No less complex and dependent on many factors issues. It is clear that those who have enough power of the used computer are not affected by it - they will use it until it burns out. Or - until there is an irresistible desire to buy something new, but here already the calculations and calculations do not make sense :) In other cases, options are possible. As you can see, in general, even the slowest processor of the new Core i5 family is about one and a half times faster than the best one for LGA775. Together with other advantages of new motherboards, this leads us to the unequivocal conclusion that an upgrade within the LGA775 is less justified than a transition to a new platform. For LGA1156 and LGA1366, everything is not so clear - after all, we considered junior processors for these platforms, which are still only a maximum of one and a half times behind the quad-core Ivy Bridge, and there are also older ones. So if you have such a processor, then you can not rush until the next cardinal update of the Intel microarchitecture (or until some AMD miracle). If not, then it will most likely be possible to purchase an old platform for reasonable money only in the secondary market - to buy a new Core i7-960 at the price of a set of Core i5-3550 and a good board (and somewhere such a ratio is observed in those stores where where the "old men" are still on the shelves) certainly not worth it. Well, or, of course, you can always indulge in overclocking, since the old platforms are more loyal to this than the new ones.
In general, in this case, everything depends on what point of view the potential buyer (if, we repeat, he is a potential buyer) adheres to. Optimistic - new processors are slightly faster and more economical than old ones. Pessimistic - they are too A little faster, and money is not superfluous. The final choice, as usual, will depend on what outweighs :)
