[nextpage title=”Introduction”]
This month AMD released its second-generation of CPUs with integrated video, dubbed “Trinity.” The A8-5600K is a top mid-range model that runs at 3.6 GHz and costs USD 110, competing directly with the Pentium G2120 (3.1 GHz, USD 100) and the Core i3-2100 (3.1 GHz, USD 120).
It is interesting to see AMD starting to use the same letter as Intel to indicate its CPUs with an unlocked clock multiplier, “K.”
This new generation of AMD APUs, dubbed “Trinity,” uses a new CPU socket, called FM2, which is incompatible with the FM1 socket used by the previous generation of APUs (codenamed “llano”). They are physically different, so it is not possible to install an FM1 CPU into an FM2 socket or an FM2 CPU into an FM1 socket. The Pentium and Core i3 CPUs included in our review use the LGA1155 socket.
Figure 1: The AMD A8-5600K processor
In the tables below, we compare the main features of the CPUs included in our review. The second-generation APUs (“Trinity”) finally brings support for the SSE4 instruction set (both SSE4.1 and SSE4.2). It also supports the AVX instruction set. More importantly, it has a “turbo clock” technology, which was not available on the previous generation and is not available on Intel’s Pentium and Core i3 processor lines.
The AMD CPUs included in our review are quad-core models, while the Intel CPUs included are dual-core models. However, the Core i3 processors included support the Hyper-Threading (HT) technology, which simulates one additional core per CPU physical core. The operating system “sees” these CPUs as having four cores. This technology is not available on the Pentium CPU, which is one of the main differences between the Core i3 and the current Pentium processors.
It is important to understand that with the second-generation APUs from AMD, each pair of CPU cores share the same front-end engine (i.e., the fetch unit, the L1 instruction cache, and the instruction decoders). So, each pair of CPU cores is part of the same “module,” and the A8-5600K and the A10-5800K are comprised of two of these modules. This concept was introduced with the AMD “Bulldozer” architecture, used on AMD’s FX processor line, and adopted on the “Piledriver” architecture used by the second-generation APUs. With the other CPUs included in our review, each core is a complete CPU, each with its own front-end engine.
CPU | Cores | HT | SSE4 | AVX | IGP | Clock | Turbo Clock | Base Clock | Codename | Tech. | TDP | Socket | Price |
A8-3850 | 4 | No | No | No | Yes | 2.9 GHz | No | 100 MHz | Llano | 32 nm | 100 W | FM1 | USD 95 |
A8-3870K | 4 | No | No | No | Yes | 3.0 GHz | No | 100 MHz | Llano | 32 nm | 100 W | FM1 | USD 105 |
A8-5600K | 4 | No | Yes | Yes | Yes | 3.6 GHz | 3.9 GHz | 100 MHz | Trinity | 32 nm | 100 W | FM2 | USD 110 |
A10-5800K | 4 | No | Yes | Yes | Yes | 3.8 GHz | 4.2 GHz | 100 MHz | Trinity | 32 nm | 100 W | FM2 | USD 130 |
Pentium G2120 | 2 | No | Yes | No | Yes | 3.1 GHz | No | 100 MHz | Ivy Bridge | 22 nm | 55 W | LGA1155 | USD 100 |
Core i3-2100 | 2 | Yes | Yes | Yes | Yes | 3.1 GHz | No | 100 MHz | Sandy Bridge | 32 nm | 65 W | LGA1155 | USD 120 |
Core i3-2105 | 2 | Yes | Yes | Yes | Yes | 3.1 GHz | No | 100 MHz | Sandy Bridge | 32 nm | 65 W | LGA1155 | USD 135 |
Core i3-3220 | 2 | Yes | Yes | Yes | Yes | 3.3 GHz | No | 100 MHz | Ivy Bridge | 22 nm | 55 W | LGA1155 | USD 130 |
Prices were researched at Newegg.com on the day we published this review. TDP stands for Thermal Design Power and states the maximum amount of heat the CPU can dissipate. The CPU cooler must be capable of dissipating at least this amount of heat.
Below you can see the memory configuration for each CPU.
CPU | L1 Cache (I + D) | L2 Cache | L3 Cache | Memory Support | Memory Channels |
A8-3850 | 64 KB + 64 KB per core | 1 MB per core | No | Up to DDR3-1866 | Two |
A8-3870K | 64 KB + 64 KB per core | 1 MB per core | No | Up to DDR3-1866 | Two |
A8-5600K | 64 kB per module + 16 kB per core | 2 MB x 2 | No | Up to DDR3-1866 | Two |
A10-5800K | 64 kB per module + 16 kB per core | 2 MB x 2 | No | Up to DDR3-1866 | Two |
Pentium G2120 | 32 KB + 32 KB per core | 256 kB per core | 3 MB total | Up to DDR3-1600 | Two |
Core i3-2100 | 32 KB + 32 KB per core | 256 kB per core | 3 MB total | Up to DDR3-1333 | Two |
Core i3-2105 | 32 KB + 32 KB per core | 256 kB per core | 3 MB total | Up to DDR3-1333 | Two |
Core i3-3220 | 32 KB + 32 KB per core | 256 kB per core | 3 MB total | Up to DDR3-1333 | Two |
Below we have a quick comparison of the video engine of the CPUs.
CPU | Video Engine | DirectX | Clock | Cores |
A8-3850 | Radeon HD 6550D | 11 | 600 MHz | 400 |
A8-3870K | Radeon HD 6550D | 11 | 600 MHz | 400 |
A8-5600K | Radeon HD 7560D | 11 | 760 MHz | 256 |
A10-5800K | Radeon HD 7660D | 11 | 800 MHz | 384 |
Pentium G2120 | Intel HD Graphics | 11 | 650 MHz/1.05 GHz | 6 |
Core i3-2100 | Intel HD 2000 | 10.1 | 850 MHz/1.1 GHz | 6 |
Core i3-2105 | Intel HD 3000 | 10.1 | 850 MHz/1.1 GHz | 12 |
Core i3-3220 | Intel HD 2500 | 11 | 650 MHz/1.05 GHz | 6 |
[nextpage title=”How We Tested”]
During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions, the only variable device was the CPU being tested and the motherboard, which had to be replaced to match the different CPU sockets.
Hardware Configuration
- Motherboard (Socket FM2): MSI FM2-A85XA-G65 (1.1 BIOS)
- Motherboard (Socket FM1): Gigabyte GA-A75M-UD2H (F6c BIOS)
- Motherboard (Socket LGA1155): ASRock Z77 Extreme4-M (1.30 BIOS)
- CPU Cooler: Intel/AMD stock
- Memory: 8 GB DDR3-1600, two AMD Entertainment Edition (AE34G1609U2) 4 GB memory modules
- Hard Disk Drive: Hitachi Deskstar P7K500 500 GB (HDP725050GLA360)
- Video Card: Sparkle GeForce GT 440 1 GB (some tests only)
- Video Monitor: AOC e3343Fwk
- Power Supply: OCZ StealthXStream 400 W
Operating System Configuration
- Windows 7 Ultimate 64-bit
- NTFS
- Video resolution: 1920 x 1080 60 Hz
Driver Versions
- AMD video driver version: Catalyst 12.8
- NVIDIA video driver version: 306.97
- Intel video driver version: 15.26.12.64.2761
- Intel Inf chipset driver version: 9.3.0.1021
Software Used
- 3DMark 11 Professional 1.0.3
- Adobe After Effects CS4
- Adobe Photoshop CS5 Extended + Retouch Artist Speed Test 1.0
- Battlefield 3
- Cinebench 11.529
- Far Cry 2 – Patch 1.03
- iTunes 10.2
- Media Espresso 6.5
- PCMark 7 1.0.4
- Starcraft II: Wings of Liberty – Patch 1.5
- VirtualDub 1.9.5 + MPEG-2 Plugin 3.1 + DivX 6.9.2
- WinZip 16.5
Error Margin
We adopted a 3% error margin. Thus, differences below 3% cannot be considered relevant. In other words, products with a performance difference below 3% should be considered as having similar performance.
[nextpage title=”PCMark 7″]
PCMark 7 performs a series of tests and gives scores in the following categories: An overall score called PCMark; a Productivity score, which is the system performance when using applications such as web browsing and home office applications; a Creativity score, which is the system performance when viewing, editing, converting, and storing photos and videos; an Entertainment score, which is the system performance when recording, viewing, streaming, and converting TV shows and movies, importing, organizing, and browsing music, and gaming; and a Computation score, which indicates the processing performance of the system. Let’s analyze the results.
The A8-5600K achieved a higher score than both its main competitors, the Pentium G2120 (17%) and the Core i3-2100 (20%), and also a higher score than the first-generation APUs we included in this review, the A8-3870K (12%) and the A8-3850 (14%).
On the productivity benchmark, the A8-5600K achieved a score similar to the A10-5800K and the Core i3-3220, a bit higher than the Pentium G2120 (4%) and substantially higher than the Core i3-2100 (15%). The A8-5600K also achieved a better score than the first-generation APUs we included in this review, the A8-3870K (20%) and the A8-3850 (23%).
On the creativity benchmark, the A8-5600K achieved the same score level as the A10-5800K, which was 5% higher than the Core i3-2100 and the Pentium G2120, 10% higher than the A8-3870K, and 11% higher than the A8-3850.
On the entertainment benchmark, the A8-5600K achieved a score much higher than its competitors, the Pentium G2120 (39%) and the Core i3-2100 (32%). The A8-5600K also achieved a better result than the A8-3870K (4%) and the A8-3850 (6%).
On the computation benchmark, the A8-5600K achieved the same performance level as the Core i3-2100 and the Pentium G2120, with a score 12% higher than the A8-3870K and 15% higher than the A8-3850.
[nextpage title=”VirtualDub”]
With VirtualDub, we converted a full-length DVD movie to DivX format and saw how long it took for this conversion to be completed. DivX codec is capable of recognizing and using not only more than one CPU (i.e., more than one core) but also the SSE4 instruction set.
The movie we chose to convert was “Star Trek – The Motion Picture: Director’s Cut.” We copied the movie to our hard disk drive with no compression, so the final original file on our HDD was 6.79 GB. After compressing it with DivX, the final file was only 767.40 MB, which is quite remarkable.
The results below are given in seconds, so the lower the better.
On DivX encoding, the A8-5600K achieved the same performance level as the other APUs from AMD that we included in this review. It was 16% faster than the Core i3-2100 and 17% faster th
an the Pentium G2120.
[nextpage title=”Photoshop CS5″]
The best way to measure performance is by using real programs. The problem, though, is creating a methodology using real software that provides accurate results. For Photoshop CS5, we used a script called “Retouch Artist Speed Test,” which applies a series of filters to a sample image and gives us the time that Photoshop took to run all the filters. The results below are given in seconds, so the lower the number the better.
On Photoshop CS5, the A8-5600K was 10% faster than the Pentium G2120; however, the Core i3-2100 was 13% faster than this new APU. The A8-5600K was 5% faster than the A8-3870K and 7% faster than the A8-3850.
[nextpage title=”After Effects CS4″]
After Effects is a very well-known program for video post-production, to add animation and visual effects in videos. To evaluate the performance of each CPU running this program, we ran a workload consisting of a number of compositions that applied several filters and effects to a variety of input file types such as PSD (Photoshop), AI (Illustrator), EPS and TIF. After each filter was applied, the composition was rendered to an uncompressed AVI file with the same resolution as the input files. The results below are the times each CPU took to finish the whole batch, given in seconds, so the lower the number the better.
On After Effects CS4, the A8-5600K was 9% faster than the Pentium G2120, but the Core i3-2100 was 10% faster than this new APU from AMD. The A8-5600K achieved the same performance level as the A10-5800K and was 7% faster than the A8-3870K and 9% faster than the A8-3850.
[nextpage title=”Media Espresso 6.5″]
Media Espresso is a video conversion program that uses the graphics processing unit of the video card to speed up the conversion process. It is also capable of using Intel’s QuickSync technology available in the CPUs from this company. We converted a 449 MB, 1920x1080i, 18,884 kbps, MPG2 video file to a smaller 640×360, H.264, .MP4 file for viewing on a portable device such as an iPhone or iPod Touch.
Here the A8-5600K achieved the same performance level as the A10-5800K and the Pentium G2120, and was slightly faster than the Core i3-2100 (5%). The A8-5600K was 10% faster than the A8-3870K and 13% faster than the A8-3850.
[nextpage title=”WinZip”]
We used WinZip not only to measure compression time, but also decryption time. We measured the time each CPU took to decompress and decrypt 200 JPEG images, 125 of them at 10 megapixels and 75 of them at six megapixels. The total size of all the photos was around 830 MB. The results below are given in seconds, so the lower the number the better.
Decompressing and decrypting files, the A8-5600K was 19% faster than the Pentium G2120 and 21% faster than the Core i3-2100. It was also 19% faster than the A8-3870K and 24% faster than the A8-3850.
[nextpage title=”iTunes”]
We used iTunes to convert an uncompressed .wav file into a high-quality (160 Kbps) MP3 file, and checked how many seconds each CPU took to perform this operation. Therefore, the results below are given in seconds, so the lower the number the better.
Here the Core i3-2100 was 12% faster than the A8-5600K, which achieved the same performance level as the Pentium G2120, the A8-3850, and the A8-3870K.
[nextpage title=”Cinebench 11.5″]
Cinebench 11.5 is based on the 3D software Cinema 4D. It is very useful to measure the performance gain given by having more than one CPU installed on the system when rendering heavy 3D images. Rendering is one area in which having more than one CPU helps considerably, because usually, rendering software recognizes several CPUs. (Cinebench, for instance, can use up to 16 CPUs.)
Since we were interested in measuring the rendering performance, we ran the test called “Rendering x CPUs,” which renders a “heavy” sample image using all available CPUs or “cores” – either real or virtual – to speed up the process. (On CPUs with Hyper-Threading technology, each core is recognized as two cores by the operating system.)
Here the A8-5600K achieved the same performance level as the A8-3870K, and was 7% faster than the A8-3850, 26% faster than the Core i3-2100, and 28% faster than the Pentium G2120.
[nextpage title=”StarCraft II: Wings of Liberty”]
StarCraft II: Wings of Liberty is a very popular DirectX 9 game that was released in 2010. Though this game uses an old version of DirectX, the amount of textures that can be represented on one screen can push most of the top-end graphics cards to their limits. StarCraft II: Wings of Liberty uses its own physics engine that is bound to the CPU and thus does not benefit from PhysX.
We tested this game at 1920×1080, configuring all image quality settings at their lowest values. We then used FRAPS to collect the frame rate of a replay on the “Unit Testing” custom map. We used a battle between very large armies to stress the video cards.
The performance level of the A8-5600K’s integrated video was similar to that of a GeForce GT 440 with 1 GB, which is remarkable. Only the integrated video of the A10-5800K was faster than the integrated video of the A8-5600K (by 32%); the integrated video of the A8-5600K was 8% faster than the A8-3870K, 10% faster than the A8-3850, 143% faster than the Pentium G2120, and 207% faster than the Core i3-2100.
[nextpage title=”Far Cry 2″]
Released in 2008, Far Cry 2 is based on a game engine called Dunia, which is DirectX 10. We used the benchmarking utility that comes with this game at 1920×1080, configuring all image quality settings at their lowest values, and running the “Ranch Long” demo three times. The results below are expressed in frames per second and are an arithmetic average of the three results collected.
The performance level of the A8-5600K’s integrated video on this DirectX 10 game was also comparable to that of a GeForce GT 440 with 1 GB. Only the integrated video of the A10-5800K was faster than the integrated video of the A8-5600K (by 15%); the integrated video of the A8-5600K was 13% faster than the A8-3870K, 23% faster than the A8-3850, 202% faster than the Pentium G2120, and 342% faster than the Core i3-2100.
[nextpage title=”DiRT3″]
DiRT3 is a DirectX 11 game. We measured performance using this game by running a race and then playing it back using FRAPS. We tested this game at 1920×1080, configuring all image quality settings at their lowest values.
The performance level of the A8-5600K’s integrated video on DiRT3 was also comparable to that of a GeForce GT 440 with 1 GB. Only the integrated video of the A10-5800K was faster than the integrated video of the A8-5600K (by 28%); the integrated video of the A8-5600K was 8% faster than the A8-3870, 16% faster than the A8-3850, and 157% faster than the Pentium G2120. The Core i3-2100 can’t run this game, since its video engine is DirectX 10.1, not DirectX 11.
[nextpage title=”Battlefield 3″]
Battlefield 3 is the latest installment in the Battlefield franchise released in 2011. It is based on the Frostbite 2 engine, which is DirectX 11. In order to measure performance using this game, we walked our way through the first half of the “Operation Swordbreaker” mission, measuring the number of frames per second using FRAPS. We tested this game at 1920×1080, configuring all image quality settings at their lowest values.
Once again, the performance level of the A8-5600K’s integrated video was also comparable to that of a GeForce GT 440 with 1 GB. Only the integrated video of the A10-5800K was faster than the integrated video of the A8-5600K (by 25%); the integrated video of the A8-5600K was 5% faster than the A8-3870K, 15% faster than the A8-3850, and 159% faster than the Pentium G2120. The Core i3-2100 can’t run this game, since its video engine is DirectX 10.1, not DirectX 11.
[nextpage title=”Borderlands 2″]
Borderlands 2 is a very recent game, released in 2012, supporting NVIDIA’s PhysX technology. We used the in-game benchmarking utility at 1920×1080, disabling PhysX and configuring all image quality settings at their lowest values.
The performance level of the A8-5600K’s integrated video on Borderlands 2 was identical to that of a GeForce GT 440 with 1 GB. The integrated video of the A10-5800K was 27% faster than the integrated video of the A8-5600K. The integrated video of the A8-3870K was 14% faster than the integrated video of the A8-5600K on this game as well. The integrated video of the A8-5600K was 4% faster than the A8-3850, and 92% faster than the Pentium G2120. The Core i3-2100 can’t run this game, since its video engine is DirectX 10.1, not DirectX 11.
[nextpage title=”3DMark 11 Professional”]
3DMark 11 Professional measures Shader 5.0 (i.e., DirectX 11) performance. We ran this program at 1920×1080 using the “Entry” profile.
This program provides three different scores: graphics, physics and combined.
The Core i3-2100 is not able to run this program, since this CPU is not compatible with DirectX 11.
The graphics score of the A10-5800K was 25% higher than the A8-5600K, and the graphics score of a GeForce GT 440 with 1 GB was 7% higher than the A8-5600K, which achieved a performance level similar to the A8-3870K and the A8-3850. The score of the A8-5600K was 222% higher than the Pentium G2120.
The physics score measures exclusively the physics performance of the system, a process that is typically done on the CPU. Here the A8-5600K achieved the same performance level as the A8-3870K and the A8-3850, with a score 17% higher than the Pentium G2120.
The combined score shows a balance between the graphics and the physics performance achieved by each system being tested. Here the A8-3850 achieved a score 5% higher than the A8-5600K, which in turn achieved a score 4% higher than the A8-3870K and 72% higher than the Pentium G2120.
[nextpage title=”Overclocking”]
The A8-5600K is an unlocked CPU, meaning that you can change its clock multiplier. We could increase its clock multiplier to 37 from its default of 36. We were also able to increase its base clock from 100 MHz to 107 MHz. Above that, our system would crash. This overclocking made our A8-5600K run at 3,959 MHz, a 10% increase over its default clock rate of 3.6 GHz.
The above result was achieved using AMD’s stock cooler. By replacing the cooler with AMD’s liquid cooling solution, we were able to increase the clock multiplier to 38 and the base clock to 109 MHz, making our A8-5600K run at 4,142 MHz, a 15% increase over its default clock rate.
In order to achieve these numbers, we had to increase the CPU voltage to 1.5 V (from the default of 1.25 V) and the CPU-NB voltage to 1.4 V.
With time and patience, you may be able to achieve better results.
[nextpage title=”Conclusions”]
The new A8-5600K provides a far better cost/benefit ratio than the A10-5800K. The A10-5800K, as you can see in our review, has an excellent gaming performance for its class, but falls short on general processing power. Its competitor, the Core i3-3220, is a faster CPU for regular programs.
The A8-5600K, on the other hand, is priced just right. At USD 110, it competes with the Pentium G2120 (USD 100, which is based on Intel’s “Ivy Bridge” microarchitecture) and the Core i3-2100 (USD 120, which is based on Intel’s “Sandy Bridge” microarchitecture). The A8-5600K proved to be a superior CPU than these entry-level models from Intel for both general computing and gaming.
According to our tests, the integrated video of the A8-5600K has the same performance level as a GeForce GT 440 with 1 GB, which is terrific.
Therefore, we highly recommend the A8-5600K if you are building a mainstream PC. Even if you are not going to play games, the A8-5600K w
ill provide better general performance than its competitors.
Leave a Reply