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.

 

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