Radeon HD 8670D vs GeForce GTX 660 OEM

Place in performance ranking	697	965
Place by popularity	not in top-100	not in top-100
Value for money	0.08	0.06
Architecture	Kepler (2012−2018)	Terascale 3 (2010−2013)
GPU code name	GK104	Richland
Market segment	Desktop	Desktop
Release date	22 August 2012 (11 years old)	4 June 2013 (10 years old)
Current price	$481	$89

Value for money

Performance to price ratio. The higher, the better.

GTX 660 OEM has 33% better value for money than HD 8670D.

Technical specs

General performance parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. These parameters indirectly speak of performance, but for precise assessment you have to consider their benchmark and gaming test results. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	1152	384
Core clock speed	823 MHz	844 MHz
Boost clock speed	888 MHz	no data
Number of transistors	3,540 million	1,303 million
Manufacturing process technology	28 nm	32 nm
Power consumption (TDP)	130 Watt	100 Watt
Texture fill rate	85.25	22.80
Floating-point performance	2,046 gflops	no data

Size and compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 3.0 x16	IGP
Length	241 mm	no data
Width	2-slot	IGP
Supplementary power connectors	1x 6-pin	no data

Memory

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR5	no data
Maximum RAM amount	2 GB	System Shared
Memory bus width	256 Bit	no data
Memory clock speed	5600 MHz	no data
Memory bandwidth	179.2 GB/s	no data
Shared memory	no data	+

Video outputs and ports

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors	2x DVI, 1x HDMI, 1x DisplayPort	No outputs
HDMI	+	no data

API support

List of supported graphics and general-purpose computing APIs, including their specific versions.

DirectX	12 (11_0)	11.2 (11_0)
Shader Model	5.1	5.0
OpenGL	4.6	4.4
OpenCL	1.2	1.2
Vulkan	1.1.126	N/A
CUDA	3.0	no data

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Average FPS across all PC games

Here are the average frames per second in a large set of popular games across different resolutions:

Full HD

40−45
+122%

−122%

Advantages and disadvantages

Performance score	3.34	1.37
Recency	22 August 2012	4 June 2013
Maximum RAM amount	2 GB	System Shared
Chip lithography	28 nm	32 nm
Power consumption (TDP)	130 Watt	100 Watt