NVIDIA GeForce 820M vs ATI Radeon HD 4670

Comparative analysis of NVIDIA GeForce 820M and ATI Radeon HD 4670 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

NVIDIA GeForce 820M

ATI Radeon HD 4670

Differences

Reasons to consider the NVIDIA GeForce 820M

Videocard is newer: launch date 6 year(s) 6 month(s) later
Around 8% higher core clock speed: 810 MHz vs 750 MHz
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 55 nm
Around 31% lower typical power consumption: 45 Watt vs 59 Watt
2x more maximum memory size: 1 GB vs 512 MB
Around 13% higher memory clock speed: 1802 MHz vs 1600 MHz
Around 28% better performance in PassMark - G3D Mark: 491 vs 383
3.2x better performance in PassMark - G2D Mark: 114 vs 36
Around 2% better performance in GFXBench 4.0 - T-Rex (Frames): 3349 vs 3285
Around 2% better performance in GFXBench 4.0 - T-Rex (Fps): 3349 vs 3285

Specifications (specs)
Launch date	21 March 2015 vs 10 September 2008
Core clock speed	810 MHz vs 750 MHz
Manufacturing process technology	28 nm vs 55 nm
Thermal Design Power (TDP)	45 Watt vs 59 Watt
Maximum memory size	1 GB vs 512 MB
Memory clock speed	1802 MHz vs 1600 MHz
Benchmarks
PassMark - G3D Mark	491 vs 383
PassMark - G2D Mark	114 vs 36
GFXBench 4.0 - T-Rex (Frames)	3349 vs 3285
GFXBench 4.0 - T-Rex (Fps)	3349 vs 3285

Reasons to consider the ATI Radeon HD 4670

2.4x more texture fill rate: 24 GTexel / s vs 10 GTexel / s
3.3x more pipelines: 320 vs 96
2x better floating-point performance: 480.0 gflops vs 240.0 gflops

Texture fill rate	24 GTexel / s vs 10 GTexel / s
Pipelines	320 vs 96
Floating-point performance	480.0 gflops vs 240.0 gflops

Compare benchmarks

GPU 1: NVIDIA GeForce 820M
GPU 2: ATI Radeon HD 4670

PassMark - G3D Mark

GPU 1

GPU 2

491

383

PassMark - G2D Mark

GPU 1

GPU 2

114

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3349

3285

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3349

3285

Name	NVIDIA GeForce 820M	ATI Radeon HD 4670
PassMark - G3D Mark	491	383
PassMark - G2D Mark	114	36
Geekbench - OpenCL	2789
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	7.765
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	161.305
CompuBench 1.5 Desktop - T-Rex (Frames/s)	0.686
CompuBench 1.5 Desktop - Video Composition (Frames/s)	14.257
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	22.768
GFXBench 4.0 - Car Chase Offscreen (Frames)	1195
GFXBench 4.0 - Manhattan (Frames)	1447
GFXBench 4.0 - T-Rex (Frames)	3349	3285
GFXBench 4.0 - Car Chase Offscreen (Fps)	1195
GFXBench 4.0 - Manhattan (Fps)	1447
GFXBench 4.0 - T-Rex (Fps)	3349	3285
3DMark Fire Strike - Graphics Score	847

Compare specifications (specs)

	NVIDIA GeForce 820M	ATI Radeon HD 4670
Essentials
Architecture	Kepler	TeraScale
Code name	GK107	RV730
Launch date	21 March 2015	10 September 2008
Place in performance rating	1460	1457
Type	Laptop	Desktop
Launch price (MSRP)		$67
Technical info
Core clock speed	810 MHz	750 MHz
Floating-point performance	240.0 gflops	480.0 gflops
Manufacturing process technology	28 nm	55 nm
Pipelines	96	320
Texture fill rate	10 GTexel / s	24 GTexel / s
Thermal Design Power (TDP)	45 Watt	59 Watt
Transistor count	1,270 million	514 million
Video outputs and ports
Display Connectors	No outputs	2x DVI, 1x S-Video
Compatibility, dimensions and requirements
Bus support	PCI Express 2.0
Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length		193 mm
Supplementary power connectors		None
API support
DirectX	12.0 (11_0)	10.1
OpenGL	4.5	3.3
Memory
Maximum RAM amount	1 GB	512 MB
Memory bandwidth	14.4 GB / s	25.6 GB / s
Memory bus width	64 Bit	128 Bit
Memory clock speed	1802 MHz	1600 MHz
Memory type	DDR3	GDDR3
Shared memory	0
Technologies
CUDA
GameWorks
GPU Boost
Optimus
Verde Drivers