NVIDIA Tesla K40m vs NVIDIA GeForce 8800 Ultra

Comparative analysis of NVIDIA Tesla K40m 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: 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), PassMark - G2D Mark, PassMark - G3D Mark.

NVIDIA Tesla K40m

NVIDIA GeForce 8800 Ultra

Differences

Reasons to consider the NVIDIA Tesla K40m

Videocard is newer: launch date 6 year(s) 6 month(s) later
Around 9% higher core clock speed: 667 MHz vs 612 MHz
4.6x more texture fill rate: 178.8 GTexel / s vs 39.2 billion / sec
22.5x more pipelines: 2880 vs 128
11.1x better floating-point performance: 4,291 gflops vs 387.1 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 90 nm
24x more maximum memory size: 12 GB vs 512 MB
5.6x more memory clock speed: 6008 MHz vs 1080 MHz
4.9x better performance in PassMark - G3D Mark: 3143 vs 643

Specifications (specs)
Launch date	22 November 2013 vs 2 May 2007
Core clock speed	667 MHz vs 612 MHz
Texture fill rate	178.8 GTexel / s vs 39.2 billion / sec
Pipelines	2880 vs 128
Floating-point performance	4,291 gflops vs 387.1 gflops
Manufacturing process technology	28 nm vs 90 nm
Maximum memory size	12 GB vs 512 MB
Memory clock speed	6008 MHz vs 1080 MHz
Benchmarks
PassMark - G3D Mark	3143 vs 643

Reasons to consider the NVIDIA GeForce 8800 Ultra

Around 43% lower typical power consumption: 171 Watt vs 245 Watt
Around 37% better performance in PassMark - G2D Mark: 252 vs 184

Specifications (specs)
Thermal Design Power (TDP)	171 Watt vs 245 Watt
Benchmarks
PassMark - G2D Mark	252 vs 184

Compare benchmarks

GPU 1: NVIDIA Tesla K40m
GPU 2: NVIDIA GeForce 8800 Ultra

PassMark - G2D Mark

GPU 1

GPU 2

184

252

PassMark - G3D Mark

GPU 1

GPU 2

3143

643

Name	NVIDIA Tesla K40m	NVIDIA GeForce 8800 Ultra
Geekbench - OpenCL	19542
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	68.519
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1884.11
CompuBench 1.5 Desktop - T-Rex (Frames/s)	6.358
CompuBench 1.5 Desktop - Video Composition (Frames/s)	117.253
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	310.472
PassMark - G2D Mark	184	252
PassMark - G3D Mark	3143	643

Compare specifications (specs)

	NVIDIA Tesla K40m	NVIDIA GeForce 8800 Ultra
Essentials
Architecture	Kepler	Tesla
Code name	GK110B	G80
Launch date	22 November 2013	2 May 2007
Launch price (MSRP)	$7,699	$829
Place in performance rating	613	616
Type	Workstation	Desktop
Technical info
Boost clock speed	745 MHz
Core clock speed	667 MHz	612 MHz
Floating-point performance	4,291 gflops	387.1 gflops
Manufacturing process technology	28 nm	90 nm
Pipelines	2880	128
Texture fill rate	178.8 GTexel / s	39.2 billion / sec
Thermal Design Power (TDP)	245 Watt	171 Watt
Transistor count	7,080 million	681 million
CUDA cores		612
Video outputs and ports
Display Connectors	No outputs	2x DVI, 1x S-Video
Compatibility, dimensions and requirements
Interface	PCIe 3.0 x16	PCIe 1.0 x16
Length	267 mm	270 mm
Supplementary power connectors		2x 6-pin
API support
DirectX	12.0 (11_1)	10.0
OpenGL	4.6	3.3
Memory
Maximum RAM amount	12 GB	512 MB
Memory bandwidth	288.4 GB / s	103.7 GB / s
Memory bus width	384 Bit	384 Bit
Memory clock speed	6008 MHz	1080 MHz
Memory type	GDDR5	GDDR3
Technologies
SLI