NVIDIA Tesla K20Xm vs NVIDIA GeForce GTX 470

Comparative analysis of NVIDIA Tesla K20Xm and NVIDIA GeForce GTX 470 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 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), 3DMark Fire Strike - Graphics Score.

NVIDIA Tesla K20Xm

NVIDIA GeForce GTX 470

Differences

Reasons to consider the NVIDIA Tesla K20Xm

Videocard is newer: launch date 2 year(s) 7 month(s) later
4.8x more texture fill rate: 164.0 GTexel / s vs 34.0 billion / sec
6x more pipelines: 2688 vs 448
3.6x better floating-point performance: 3,935 gflops vs 1,088.6 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 40 nm
4.8x more maximum memory size: 6 GB vs 1280 MB
3.1x more memory clock speed: 5200 MHz vs 1674 MHz (3348 data rate)
Around 51% better performance in Geekbench - OpenCL: 16581 vs 10961
Around 77% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 49.455 vs 27.93
Around 70% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1666.354 vs 980.005
Around 79% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 5.836 vs 3.268
Around 95% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 92.472 vs 47.309
2.8x better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 275.229 vs 97.852
2.1x better performance in GFXBench 4.0 - T-Rex (Frames): 7038 vs 3317
2.1x better performance in GFXBench 4.0 - T-Rex (Fps): 7038 vs 3317

Specifications (specs)
Launch date	12 November 2012 vs 26 March 2010
Texture fill rate	164.0 GTexel / s vs 34.0 billion / sec
Pipelines	2688 vs 448
Floating-point performance	3,935 gflops vs 1,088.6 gflops
Manufacturing process technology	28 nm vs 40 nm
Maximum memory size	6 GB vs 1280 MB
Memory clock speed	5200 MHz vs 1674 MHz (3348 data rate)
Benchmarks
Geekbench - OpenCL	16581 vs 10961
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	49.455 vs 27.93
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1666.354 vs 980.005
CompuBench 1.5 Desktop - T-Rex (Frames/s)	5.836 vs 3.268
CompuBench 1.5 Desktop - Video Composition (Frames/s)	92.472 vs 47.309
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	275.229 vs 97.852
GFXBench 4.0 - T-Rex (Frames)	7038 vs 3317
GFXBench 4.0 - T-Rex (Fps)	7038 vs 3317

Reasons to consider the NVIDIA GeForce GTX 470

Around 66% higher core clock speed: 1215 MHz vs 732 MHz
Around 9% lower typical power consumption: 215 Watt vs 235 Watt
Around 6% better performance in PassMark - G3D Mark: 3107 vs 2918
2.4x better performance in PassMark - G2D Mark: 406 vs 172
3.5x better performance in GFXBench 4.0 - Manhattan (Frames): 3614 vs 1032
3.5x better performance in GFXBench 4.0 - Manhattan (Fps): 3614 vs 1032

Specifications (specs)
Core clock speed	1215 MHz vs 732 MHz
Thermal Design Power (TDP)	215 Watt vs 235 Watt
Benchmarks
PassMark - G3D Mark	3107 vs 2918
PassMark - G2D Mark	406 vs 172
GFXBench 4.0 - Manhattan (Frames)	3614 vs 1032
GFXBench 4.0 - Manhattan (Fps)	3614 vs 1032

Compare benchmarks

GPU 1: NVIDIA Tesla K20Xm
GPU 2: NVIDIA GeForce GTX 470

PassMark - G3D Mark

GPU 1

GPU 2

2918

3107

PassMark - G2D Mark

GPU 1

GPU 2

172

406

Geekbench - OpenCL

GPU 1

GPU 2

16581

10961

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

49.455

27.93

CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)

GPU 1

GPU 2

1666.354

980.005

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

5.836

3.268

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

92.472

47.309

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

275.229

97.852

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

1032

3614

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

7038

3317

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

1032

3614

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

7038

3317

Name	NVIDIA Tesla K20Xm	NVIDIA GeForce GTX 470
PassMark - G3D Mark	2918	3107
PassMark - G2D Mark	172	406
Geekbench - OpenCL	16581	10961
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	49.455	27.93
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1666.354	980.005
CompuBench 1.5 Desktop - T-Rex (Frames/s)	5.836	3.268
CompuBench 1.5 Desktop - Video Composition (Frames/s)	92.472	47.309
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	275.229	97.852
GFXBench 4.0 - Manhattan (Frames)	1032	3614
GFXBench 4.0 - T-Rex (Frames)	7038	3317
GFXBench 4.0 - Manhattan (Fps)	1032	3614
GFXBench 4.0 - T-Rex (Fps)	7038	3317
GFXBench 4.0 - Car Chase Offscreen (Frames)		3873
GFXBench 4.0 - Car Chase Offscreen (Fps)		3873
3DMark Fire Strike - Graphics Score		0

Compare specifications (specs)

	NVIDIA Tesla K20Xm	NVIDIA GeForce GTX 470
Essentials
Architecture	Kepler	Fermi
Code name	GK110	GF100
Launch date	12 November 2012	26 March 2010
Launch price (MSRP)	$7,699	$349
Place in performance rating	808	810
Type	Workstation	Desktop
Price now		$522.01
Value for money (0-100)		6.87
Technical info
Core clock speed	732 MHz	1215 MHz
Floating-point performance	3,935 gflops	1,088.6 gflops
Manufacturing process technology	28 nm	40 nm
Pipelines	2688	448
Texture fill rate	164.0 GTexel / s	34.0 billion / sec
Thermal Design Power (TDP)	235 Watt	215 Watt
Transistor count	7,080 million	3,100 million
CUDA cores		448
Maximum GPU temperature		105 °C
Video outputs and ports
Display Connectors	No outputs	2x DVI, 1x mini-HDMI, Two Dual Link DVIMini HDMI
Audio input for HDMI		Internal
HDMI
Maximum VGA resolution		2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length	267 mm	9.5" (241 mm) (24.1 cm)
Bus support		16x PCI-E 2.0
Height		4.376" (111 mm) (11.1 cm)
SLI options		2-way3-way
Supplementary power connectors		Two 6-pins
API support
DirectX	12.0 (11_0)	12.0 (11_0)
OpenGL	4.6	4.2
Memory
Maximum RAM amount	6 GB	1280 MB
Memory bandwidth	249.6 GB / s	133.9 GB / s
Memory bus width	384 Bit	320 Bit
Memory clock speed	5200 MHz	1674 MHz (3348 data rate)
Memory type	GDDR5	GDDR5
Shared memory		0
Technologies
3D Vision
CUDA
DSR
SLI
Surround