NVIDIA P104-100 vs NVIDIA GeForce GTX 670

Comparative analysis of NVIDIA P104-100 and NVIDIA GeForce GTX 670 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: Geekbench - OpenCL, PassMark - G2D Mark, PassMark - G3D Mark, 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 P104-100

NVIDIA GeForce GTX 670

Differences

Reasons to consider the NVIDIA P104-100

Videocard is newer: launch date 5 year(s) 7 month(s) later
Around 64% higher core clock speed: 1607 MHz vs 980 MHz
Around 77% higher boost clock speed: 1733 MHz vs 980 MHz
2.7x more texture fill rate: 277.3 GTexel / s vs 102.5 billion / sec
Around 90% higher pipelines: 2560 vs 1344
3.6x better floating-point performance: 8,873 gflops vs 2,459.5 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 16 nm vs 28 nm
4x more maximum memory size: 8 GB vs 2 GB
1668x more memory clock speed: 10008 MHz vs 6.0 GB/s
3.3x better performance in Geekbench - OpenCL: 51497 vs 15494

Specifications (specs)
Launch date	12 December 2017 vs 10 May 2012
Core clock speed	1607 MHz vs 980 MHz
Boost clock speed	1733 MHz vs 980 MHz
Texture fill rate	277.3 GTexel / s vs 102.5 billion / sec
Pipelines	2560 vs 1344
Floating-point performance	8,873 gflops vs 2,459.5 gflops
Manufacturing process technology	16 nm vs 28 nm
Maximum memory size	8 GB vs 2 GB
Memory clock speed	10008 MHz vs 6.0 GB/s
Benchmarks
Geekbench - OpenCL	51497 vs 15494

Reasons to consider the NVIDIA GeForce GTX 670

4.4x better performance in PassMark - G2D Mark: 532 vs 120
Around 47% better performance in PassMark - G3D Mark: 5326 vs 3628

Benchmarks
PassMark - G2D Mark	532 vs 120
PassMark - G3D Mark	5326 vs 3628

Compare benchmarks

GPU 1: NVIDIA P104-100
GPU 2: NVIDIA GeForce GTX 670

Geekbench - OpenCL

GPU 1

GPU 2

51497

15494

PassMark - G2D Mark

GPU 1

GPU 2

120

532

PassMark - G3D Mark

GPU 1

GPU 2

3628

5326

Name	NVIDIA P104-100	NVIDIA GeForce GTX 670
Geekbench - OpenCL	51497	15494
PassMark - G2D Mark	120	532
PassMark - G3D Mark	3628	5326
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		41.613
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		971.208
CompuBench 1.5 Desktop - T-Rex (Frames/s)		4.281
CompuBench 1.5 Desktop - Video Composition (Frames/s)		40.404
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		86.208
GFXBench 4.0 - Car Chase Offscreen (Frames)		7038
GFXBench 4.0 - Manhattan (Frames)		3686
GFXBench 4.0 - T-Rex (Frames)		3361
GFXBench 4.0 - Car Chase Offscreen (Fps)		7038
GFXBench 4.0 - Manhattan (Fps)		3686
GFXBench 4.0 - T-Rex (Fps)		3361
3DMark Fire Strike - Graphics Score		1838

Compare specifications (specs)

	NVIDIA P104-100	NVIDIA GeForce GTX 670
Essentials
Architecture	Pascal	Kepler
Code name	GP104	GK104
Launch date	12 December 2017	10 May 2012
Place in performance rating	566	568
Type	Desktop	Desktop
Launch price (MSRP)		$399
Price now		$474.99
Value for money (0-100)		13.20
Technical info
Boost clock speed	1733 MHz	980 MHz
Core clock speed	1607 MHz	980 MHz
Floating-point performance	8,873 gflops	2,459.5 gflops
Manufacturing process technology	16 nm	28 nm
Pipelines	2560	1344
Texture fill rate	277.3 GTexel / s	102.5 billion / sec
Transistor count	7,200 million	3,540 million
CUDA cores		1344
Maximum GPU temperature		97 °C
Thermal Design Power (TDP)		170 Watt
Video outputs and ports
Display Connectors	No outputs	One Dual Link DVI-I, One Dual Link DVI-D, One HDMI..., 2x DVI, 1x HDMI, 1x DisplayPort
Audio input for HDMI		Internal
G-SYNC support
HDCP
HDMI
Maximum VGA resolution		2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm	9.5" (24.1 cm)
Supplementary power connectors	1x 8-pin	Two 6-pin
Bus support		PCI Express 3.0
Height		4.376" (11.1 cm)
SLI options		3-way
API support
DirectX	12.0 (12_1)	12.0 (11_0)
OpenGL	4.6	4.2
Memory
Maximum RAM amount	8 GB	2 GB
Memory bandwidth	320.3 GB / s	192.2 GB / s
Memory bus width	256 Bit	256-bit GDDR5
Memory clock speed	10008 MHz	6.0 GB/s
Memory type	GDDR5X	GDDR5
Technologies
3D Blu-Ray
3D Gaming
3D Vision
Adaptive VSync
CUDA
FXAA
GPU Boost
SLI
TXAA