AMD Radeon HD 7970M vs NVIDIA GeForce 8800 Ultra

Comparative analysis of AMD Radeon HD 7970M and NVIDIA GeForce 8800 Ultra 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.

AMD Radeon HD 7970M

NVIDIA GeForce 8800 Ultra

Differences

Reasons to consider the AMD Radeon HD 7970M

Videocard is newer: launch date 4 year(s) 11 month(s) later
Around 39% higher core clock speed: 850 MHz vs 612 MHz
Around 73% higher texture fill rate: 68 GTexel / s vs 39.2 billion / sec
10x more pipelines: 1280 vs 128
5.6x better floating-point performance: 2,176 gflops vs 387.1 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 90 nm
Around 71% lower typical power consumption: 100 Watt vs 171 Watt
4x more maximum memory size: 2 GB vs 512 MB
4.4x more memory clock speed: 4800 MHz vs 1080 MHz
5.5x better performance in PassMark - G3D Mark: 3529 vs 643
2x better performance in PassMark - G2D Mark: 506 vs 252

Specifications (specs)
Launch date	24 April 2012 vs 2 May 2007
Core clock speed	850 MHz vs 612 MHz
Texture fill rate	68 GTexel / s vs 39.2 billion / sec
Pipelines	1280 vs 128
Floating-point performance	2,176 gflops vs 387.1 gflops
Manufacturing process technology	28 nm vs 90 nm
Thermal Design Power (TDP)	100 Watt vs 171 Watt
Maximum memory size	2 GB vs 512 MB
Memory clock speed	4800 MHz vs 1080 MHz
Benchmarks
PassMark - G3D Mark	3529 vs 643
PassMark - G2D Mark	506 vs 252

Compare benchmarks

GPU 1: AMD Radeon HD 7970M
GPU 2: NVIDIA GeForce 8800 Ultra

PassMark - G3D Mark

GPU 1

GPU 2

3529

643

PassMark - G2D Mark

GPU 1

GPU 2

506

252

Name	AMD Radeon HD 7970M	NVIDIA GeForce 8800 Ultra
PassMark - G3D Mark	3529	643
PassMark - G2D Mark	506	252
Geekbench - OpenCL	17210
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	51.181
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1121.002
CompuBench 1.5 Desktop - T-Rex (Frames/s)	5.355
CompuBench 1.5 Desktop - Video Composition (Frames/s)	81.527
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	256.99
GFXBench 4.0 - Car Chase Offscreen (Frames)	5094
GFXBench 4.0 - Manhattan (Frames)	3692
GFXBench 4.0 - T-Rex (Frames)	3339
GFXBench 4.0 - Car Chase Offscreen (Fps)	5094
GFXBench 4.0 - Manhattan (Fps)	3692
GFXBench 4.0 - T-Rex (Fps)	3339
3DMark Fire Strike - Graphics Score	0

Compare specifications (specs)

	AMD Radeon HD 7970M	NVIDIA GeForce 8800 Ultra
Essentials
Architecture	GCN 1.0	Tesla
Code name	Wimbledon	G80
Launch date	24 April 2012	2 May 2007
Place in performance rating	614	616
Type	Laptop	Desktop
Launch price (MSRP)		$829
Technical info
Core clock speed	850 MHz	612 MHz
Floating-point performance	2,176 gflops	387.1 gflops
Manufacturing process technology	28 nm	90 nm
Pipelines	1280	128
Texture fill rate	68 GTexel / s	39.2 billion / sec
Thermal Design Power (TDP)	100 Watt	171 Watt
Transistor count	2,800 million	681 million
CUDA cores		612
Video outputs and ports
Display Connectors	No outputs	2x DVI, 1x S-Video
Compatibility, dimensions and requirements
Interface	MXM-B (3.0)	PCIe 1.0 x16
Laptop size	large
Supplementary power connectors	None	2x 6-pin
Length		270 mm
API support
DirectX	12.0 (11_1)	10.0
OpenGL	4.5	3.3
Memory
Maximum RAM amount	2 GB	512 MB
Memory bandwidth	153.6 GB / s	103.7 GB / s
Memory bus width	256 Bit	384 Bit
Memory clock speed	4800 MHz	1080 MHz
Memory type	GDDR5	GDDR3
Shared memory	0
Technologies
SLI