NVIDIA Tesla K20Xm vs ATI FireGL V3600

Comparative analysis of NVIDIA Tesla K20Xm and ATI FireGL V3600 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. 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).

NVIDIA Tesla K20Xm

ATI FireGL V3600

Differences

Reasons to consider the NVIDIA Tesla K20Xm

Videocard is newer: launch date 5 year(s) 4 month(s) later
Around 22% higher core clock speed: 732 MHz vs 600 MHz
34.2x more texture fill rate: 164.0 GTexel / s vs 4.8 GTexel / s
22.4x more pipelines: 2688 vs 120
27.3x better floating-point performance: 3,935 gflops vs 144 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 65 nm
24x more maximum memory size: 6 GB vs 256 MB
5.2x more memory clock speed: 5200 MHz vs 1000 MHz
24.5x better performance in PassMark - G3D Mark: 4403 vs 180
4x better performance in GFXBench 4.0 - T-Rex (Frames): 7038 vs 1755
4x better performance in GFXBench 4.0 - T-Rex (Fps): 7038 vs 1755

Specifications (specs)
Launch date	12 November 2012 vs 28 June 2007
Core clock speed	732 MHz vs 600 MHz
Texture fill rate	164.0 GTexel / s vs 4.8 GTexel / s
Pipelines	2688 vs 120
Floating-point performance	3,935 gflops vs 144 gflops
Manufacturing process technology	28 nm vs 65 nm
Maximum memory size	6 GB vs 256 MB
Memory clock speed	5200 MHz vs 1000 MHz
Benchmarks
PassMark - G3D Mark	4403 vs 180
GFXBench 4.0 - T-Rex (Frames)	7038 vs 1755
GFXBench 4.0 - T-Rex (Fps)	7038 vs 1755

Reasons to consider the ATI FireGL V3600

3.2x lower typical power consumption: 73 Watt vs 235 Watt
2x better performance in PassMark - G2D Mark: 399 vs 198

Specifications (specs)
Thermal Design Power (TDP)	73 Watt vs 235 Watt
Benchmarks
PassMark - G2D Mark	399 vs 198

Compare benchmarks

GPU 1: NVIDIA Tesla K20Xm
GPU 2: ATI FireGL V3600

PassMark - G3D Mark

GPU 1

GPU 2

4403

180

PassMark - G2D Mark

GPU 1

GPU 2

198

399

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

7038

1755

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

7038

1755

Name	NVIDIA Tesla K20Xm	ATI FireGL V3600
PassMark - G3D Mark	4403	180
PassMark - G2D Mark	198	399
Geekbench - OpenCL	16726
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	49.455
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1666.354
CompuBench 1.5 Desktop - T-Rex (Frames/s)	5.836
CompuBench 1.5 Desktop - Video Composition (Frames/s)	92.472
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	275.229
GFXBench 4.0 - Manhattan (Frames)	1032
GFXBench 4.0 - T-Rex (Frames)	7038	1755
GFXBench 4.0 - Manhattan (Fps)	1032
GFXBench 4.0 - T-Rex (Fps)	7038	1755

Compare specifications (specs)

	NVIDIA Tesla K20Xm	ATI FireGL V3600
Essentials
Architecture	Kepler	TeraScale
Code name	GK110	RV630
Launch date	12 November 2012	28 June 2007
Launch price (MSRP)	$7,699	$299
Place in performance rating	749	751
Type	Workstation	Workstation
Technical info
Core clock speed	732 MHz	600 MHz
Floating-point performance	3,935 gflops	144 gflops
Manufacturing process technology	28 nm	65 nm
Pipelines	2688	120
Texture fill rate	164.0 GTexel / s	4.8 GTexel / s
Thermal Design Power (TDP)	235 Watt	73 Watt
Transistor count	7,080 million	390 million
Video outputs and ports
Display Connectors	No outputs	No outputs
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 1.0 x16
Length	267 mm
Supplementary power connectors		None
API support
DirectX	12.0 (11_0)	10.0
OpenGL	4.6	3.3
Memory
Maximum RAM amount	6 GB	256 MB
Memory bandwidth	249.6 GB / s	16 GB / s
Memory bus width	384 Bit	128 Bit
Memory clock speed	5200 MHz	1000 MHz
Memory type	GDDR5	DDR2