AMD FX-7600P vs Intel Core i3-7020U vs Intel Core i7-7660U

AMD FX-7600P

The quad-core AMD FX-7600P is a mid-range processor based on the Kaveri architecture. It was revealed in June 2014 for notebooks and is manufactured by GlobalFoundries using a 28 nm SHP process. In addition to having two CPU modules for a total of four integer cores clocked at 2.7 - 3.6 GHz, the AMD chip also integrates a Radeon R7 GPU clocked at up to 686 MHz with 512 GCN shaders and a dual-channel DDR3-2133 memory controller. The FX-7600P was the fastest mobile Kaveri APU in 2014.

In addition to the CPU and GPU cores, the APU also integrates a dual-channel DDR3-2133 memory controller, UVD 4.0 video decoder, VCE 2.0 video encoder and TrueAudio audio processor.

Architecture 

Kaveri is the successor to the 2013 Richland architecture (e.g. A10-5750M). The revised CPU cores, codenamed Steamroller, represent the third generation of the module-based Bulldozer design. A number of major changes include modified decoders (now one per integer core), optimized branch prediction, and increased L1 I-cache from 64 KB to 96 KB per module. These revisions boost the performance per clock slightly over a similarly clocked Richland APU. For more details about the AMD Kaveri architecture, see our detailed analysis here:

Analysis of the AMD Kaveri Notebook Platform

Performance 

In our benchmarks with a demo laptop from AMD the performance of the processor cores was comparable to a Haswell Core i5-4210U. The single thread performance is the bottleneck of the CPU and only on a level of the previous A10-5750M (Richland) or Haswell Core i3-4030U.

Overall, the FX-7600P will be sufficient for multitasking daily workloads (Office, Internet browsing, multimedia) as well as more demanding programs.

Graphics

The Radeon R7 (Kaveri) GPU of the FX-7600P features a core clock of up to 686 MHz and 512 shader units. Since the GPU is based on AMD's GCN 1.1 architecture, both DirectX 11.2 "Tier 2" and Mantle are supported. Furthermore, the GPU can be used for general purpose computing in various applications, such as Adobe Photoshop via the OpenCL API. 

In terms of 3D performance, the GPU benefits from its high raw computational power and memory support up to DDR3-2133. Thus, the Radeon R7 is just slightly behind Intel's Iris Pro Graphics 5200 and roughly on par with a dedicated GeForce GT 730M. The integrated GPU in the Core i3 and i5 Haswell processors (like HD Graphics 4400) is left clearly behind.

As of Q2 2014, the Radeon R7 in the FX-7600P is one of the fastest integrated notebook graphics solutions that can handle many current games at low or medium settings at WXGA resolution.

Power Consumption

The power consumption of the entire APU is rated at 35 Watts, which is similar to other competing mid-range models. As a result, the FX-7600P is best suited for 14-inch notebooks or larger.

Intel Core i3-7020U

The Intel Core i3-7020U is a dual-core processor of the Kaby Lake architecture. It offers two CPU cores clocked at 2.3 GHz (without Turbo Boost) and integrates HyperThreading to work with up to 4 threads at once. The architectural differences are rather small compared to the Skylake generation, therefore the performance per MHz should be very similar. The SoC includes a dual channel DDR4 memory controller and Intel HD Graphics 620 graphics card (clocked at 300 - 1000 MHz). It is manufactured in an improved 14nm FinFET process at Intel. Compare to the old i3-7100U, the newer i3-7020U is clocked 100 MHz lower (CPU cores) and therefore the current entry level model for the Core i3 line. The similar Pentium Gold 4415U offers less Cache (2 versus 3 MB) and a slower GPU.

Architecture

Intel basically uses the same micro architecture compared to Skylake, so the per-MHz performance does not differ. The manufacturer only reworked the Speed Shift technology for faster dynamic adjustments of voltages and clocks, and the improved 14nm process allows much higher frequencies combined with better efficiency than before.

Intel Core i7-7660U

The Intel Core i7-7660U is a fast dual-core SoC for notebooks and Ultrabooks based on the Kaby Lake architecture and was announced in January 2017. The CPU has two processor cores clocked at 2.5-4 GHz (two cores up to 3.8 GHz). The processor can execute up to four threads simultaneously thanks to Hyper Threading. It is also equipped with an Intel Iris Plus Graphics 640 GPU with 64 MB eDRAm, a dual-channel memory controller (DDR4) as well as VP9 and H.265 video decoding as well as encoding. The chip is still manufactured in a 14nm process with FinFET transistors.

Compared to the Core i7-7600U, the 7660 does have a higher single-core Turbo of 4 GHz (+100 MHz), but a lower dual-core Turbo (-100 MHz) and a lower base frequency (-300 MHz). However, the CPU part can also use the 64 MB eDRAM as L5 cache.

Architecture

Intel basically uses the same micro architecture compared to Skylake, so the per-MHz performance does not differ. The manufacturer only reworked the Speed Shift technology for faster dynamic adjustments of voltages and clocks, and the improved 14nm process allows much higher frequencies combined with better efficiency than before.

Performance

At 2.5-4 GHz, the Core i7-7660U has a slightly lower frequency (except for the single-core Turbo) compared to the Core i7-7600U, but the CPU part can also use the 64 MB eDRAM, so the performance should be similar.

Graphics

The integrated Intel Iris Plus 640 Graphics is the GT3e model of the Kaby Lake GPU (Intel Gen. 9.5). It has 48 Execution Units running at 300-1050 MHz and the performance is comparable to a GeForce 920MX thanks to fast eDRAM cache. However, there aren't any significant improvements compared to the old Iris Pro 540, so modern games can often not be played smoothly or only at the lowest or medium settings, respectively.

Contrary to Skylake, Kaby lake now also supports H.265/HEVC Main 10 with a 10-bit color depth as well as Google's VP9 codec. The dual-core Kaby Lake processors announced in January should also support HDCP 2.2.

Power Consumption

The chip is manufactured in an improved 14nm process with FinFET transistors, which improves the efficiency even further. Intel still specifies the TDP with 15 Watts, which is typical for ULV chips. Depending on the usage scenario, the TDP can vary between 7.5 (cTDP Down) and 25 Watts.