NVIDIA Tesla K40m vs ATI Radeon HD 5970

Comparative analysis of NVIDIA Tesla K40m and ATI Radeon HD 5970 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, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), 3DMark Fire Strike - Graphics Score, GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the NVIDIA Tesla K40m

  • Videocard is newer: launch date 4 year(s) 0 month(s) later
  • Around 3% higher boost clock speed: 745 MHz vs 725 MHz
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 40 nm
  • Around 22% lower typical power consumption: 245 Watt vs 300 Watt
  • 6x more maximum memory size: 12 GB vs 2 GB
  • Around 50% higher memory clock speed: 6008 MHz vs 4000 MHz
  • Around 38% better performance in PassMark - G3D Mark: 3143 vs 2282
Specifications (specs)
Launch date 22 November 2013 vs 18 November 2009
Boost clock speed 745 MHz vs 725 MHz
Manufacturing process technology 28 nm vs 40 nm
Thermal Design Power (TDP) 245 Watt vs 300 Watt
Maximum memory size 12 GB vs 2 GB
Memory clock speed 6008 MHz vs 4000 MHz
Benchmarks
PassMark - G3D Mark 3143 vs 2282

Reasons to consider the ATI Radeon HD 5970

  • Around 9% higher core clock speed: 725 MHz vs 667 MHz
  • Around 44% higher texture fill rate: 2x 58.0 GTexel / s billion / sec vs 178.8 GTexel / s
  • Around 11% higher pipelines: 2x 1600 vs 2880
  • Around 8% better floating-point performance: 2x 2,320.0 gflops vs 4,291 gflops
  • 2.3x better performance in PassMark - G2D Mark: 418 vs 184
Specifications (specs)
Core clock speed 725 MHz vs 667 MHz
Texture fill rate 2x 58.0 GTexel / s billion / sec vs 178.8 GTexel / s
Pipelines 2x 1600 vs 2880
Floating-point performance 2x 2,320.0 gflops vs 4,291 gflops
Benchmarks
PassMark - G2D Mark 418 vs 184

Compare benchmarks

GPU 1: NVIDIA Tesla K40m
GPU 2: ATI Radeon HD 5970

PassMark - G2D Mark
GPU 1
GPU 2
184
418
PassMark - G3D Mark
GPU 1
GPU 2
3143
2282
Name NVIDIA Tesla K40m ATI Radeon HD 5970
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 184 418
PassMark - G3D Mark 3143 2282
GFXBench 4.0 - Car Chase Offscreen (Frames) 3977
GFXBench 4.0 - Car Chase Offscreen (Fps) 3977
3DMark Fire Strike - Graphics Score 0
GFXBench 4.0 - Manhattan (Frames) 3454
GFXBench 4.0 - Manhattan (Fps) 3454
GFXBench 4.0 - T-Rex (Frames) 3213
GFXBench 4.0 - T-Rex (Fps) 3213

Compare specifications (specs)

NVIDIA Tesla K40m ATI Radeon HD 5970

Essentials

Architecture Kepler TeraScale 2
Code name GK110B Hemlock
Launch date 22 November 2013 18 November 2009
Launch price (MSRP) $7,699 $699
Place in performance rating 613 615
Type Workstation Desktop
Design ATI Radeon HD 5000 Series

Technical info

Boost clock speed 745 MHz 725 MHz
Core clock speed 667 MHz 725 MHz
Floating-point performance 4,291 gflops 2x 2,320.0 gflops
Manufacturing process technology 28 nm 40 nm
Pipelines 2880 2x 1600
Texture fill rate 178.8 GTexel / s 2x 58.0 GTexel / s billion / sec
Thermal Design Power (TDP) 245 Watt 300 Watt
Transistor count 7,080 million 2,154 million

Video outputs and ports

Display Connectors No outputs 2x DVI, 1x mini-DisplayPort
DisplayPort support
Dual-link DVI support
VGA

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 2.0 x16
Length 267 mm 305 mm
Supplementary power connectors 1x 6-pin + 1x 8-pin

API support

DirectX 12.0 (11_1) 11
OpenGL 4.6 4.4

Memory

Maximum RAM amount 12 GB 2 GB
Memory bandwidth 288.4 GB / s 2x 128.0 GB / s
Memory bus width 384 Bit 2x 256 Bit
Memory clock speed 6008 MHz 4000 MHz
Memory type GDDR5 GDDR5

Technologies

AMD Eyefinity