NVIDIA Tesla T4 vs NVIDIA Tesla P40

Comparative analysis of NVIDIA Tesla T4 and NVIDIA Tesla P40 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 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps).

 

Differences

Reasons to consider the NVIDIA Tesla T4

  • Videocard is newer: launch date 2 year(s) 0 month(s) later
  • A newer manufacturing process allows for a more powerful, yet cooler running videocard: 12 nm vs 16 nm
  • 3.3x lower typical power consumption: 75 Watt vs 250 Watt
  • Around 35% better performance in PassMark - G2D Mark: 592 vs 439
  • Around 48% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 14076 vs 9538
  • Around 48% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 14076 vs 9538
Specifications (specs)
Launch date 13 September 2018 vs 13 September 2016
Manufacturing process technology 12 nm vs 16 nm
Thermal Design Power (TDP) 75 Watt vs 250 Watt
Benchmarks
PassMark - G2D Mark 592 vs 439
GFXBench 4.0 - Car Chase Offscreen (Frames) 14076 vs 9538
GFXBench 4.0 - Car Chase Offscreen (Fps) 14076 vs 9538

Reasons to consider the NVIDIA Tesla P40

  • Around 30% higher core clock speed: 1303 MHz vs 1005 MHz
  • Around 1% higher boost clock speed: 1531 MHz vs 1515 MHz
  • Around 16% better performance in PassMark - G3D Mark: 12267 vs 10616
  • Around 2% better performance in Geekbench - OpenCL: 62287 vs 61276
  • 2.4x better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 300.355 vs 127.622
  • Around 18% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 3559.383 vs 3026.812
  • Around 5% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 19.757 vs 18.798
  • Around 70% better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 204.32 vs 119.936
  • Around 33% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 1214.142 vs 910.721
  • Around 87% better performance in GFXBench 4.0 - Manhattan (Frames): 3699 vs 1976
  • Around 88% better performance in GFXBench 4.0 - T-Rex (Frames): 3340 vs 1781
  • Around 87% better performance in GFXBench 4.0 - Manhattan (Fps): 3699 vs 1976
  • Around 88% better performance in GFXBench 4.0 - T-Rex (Fps): 3340 vs 1781
Specifications (specs)
Core clock speed 1303 MHz vs 1005 MHz
Boost clock speed 1531 MHz vs 1515 MHz
Memory clock speed 10008 MHz vs 10000 MHz
Benchmarks
PassMark - G3D Mark 12267 vs 10616
Geekbench - OpenCL 62287 vs 61276
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 300.355 vs 127.622
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 3559.383 vs 3026.812
CompuBench 1.5 Desktop - T-Rex (Frames/s) 19.757 vs 18.798
CompuBench 1.5 Desktop - Video Composition (Frames/s) 204.32 vs 119.936
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 1214.142 vs 910.721
GFXBench 4.0 - Manhattan (Frames) 3699 vs 1976
GFXBench 4.0 - T-Rex (Frames) 3340 vs 1781
GFXBench 4.0 - Manhattan (Fps) 3699 vs 1976
GFXBench 4.0 - T-Rex (Fps) 3340 vs 1781

Compare benchmarks

GPU 1: NVIDIA Tesla T4
GPU 2: NVIDIA Tesla P40

PassMark - G3D Mark
GPU 1
GPU 2
10616
12267
PassMark - G2D Mark
GPU 1
GPU 2
592
439
Geekbench - OpenCL
GPU 1
GPU 2
61276
62287
CompuBench 1.5 Desktop - Face Detection (mPixels/s)
GPU 1
GPU 2
127.622
300.355
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)
GPU 1
GPU 2
3026.812
3559.383
CompuBench 1.5 Desktop - T-Rex (Frames/s)
GPU 1
GPU 2
18.798
19.757
CompuBench 1.5 Desktop - Video Composition (Frames/s)
GPU 1
GPU 2
119.936
204.32
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)
GPU 1
GPU 2
910.721
1214.142
GFXBench 4.0 - Car Chase Offscreen (Frames)
GPU 1
GPU 2
14076
9538
GFXBench 4.0 - Manhattan (Frames)
GPU 1
GPU 2
1976
3699
GFXBench 4.0 - T-Rex (Frames)
GPU 1
GPU 2
1781
3340
GFXBench 4.0 - Car Chase Offscreen (Fps)
GPU 1
GPU 2
14076
9538
GFXBench 4.0 - Manhattan (Fps)
GPU 1
GPU 2
1976
3699
GFXBench 4.0 - T-Rex (Fps)
GPU 1
GPU 2
1781
3340
Name NVIDIA Tesla T4 NVIDIA Tesla P40
PassMark - G3D Mark 10616 12267
PassMark - G2D Mark 592 439
Geekbench - OpenCL 61276 62287
CompuBench 1.5 Desktop - Face Detection (mPixels/s) 127.622 300.355
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s) 3026.812 3559.383
CompuBench 1.5 Desktop - T-Rex (Frames/s) 18.798 19.757
CompuBench 1.5 Desktop - Video Composition (Frames/s) 119.936 204.32
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s) 910.721 1214.142
GFXBench 4.0 - Car Chase Offscreen (Frames) 14076 9538
GFXBench 4.0 - Manhattan (Frames) 1976 3699
GFXBench 4.0 - T-Rex (Frames) 1781 3340
GFXBench 4.0 - Car Chase Offscreen (Fps) 14076 9538
GFXBench 4.0 - Manhattan (Fps) 1976 3699
GFXBench 4.0 - T-Rex (Fps) 1781 3340

Compare specifications (specs)

NVIDIA Tesla T4 NVIDIA Tesla P40

Essentials

Architecture Turing Pascal
Code name TU104 GP102
Launch date 13 September 2018 13 September 2016
Place in performance rating 270 234
Type Workstation Workstation
Launch price (MSRP) $5,699

Technical info

Boost clock speed 1515 MHz 1531 MHz
Core clock speed 1005 MHz 1303 MHz
Manufacturing process technology 12 nm 16 nm
Thermal Design Power (TDP) 75 Watt 250 Watt
Transistor count 13,600 million 11,800 million
Floating-point performance 11,758 gflops
Pipelines 3840
Texture fill rate 367.4 GTexel / s

Video outputs and ports

Display Connectors No outputs No outputs

Compatibility, dimensions and requirements

Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors None 1x 6-pin + 1x 8-pin
Length 267 mm

API support

DirectX 12.0 (12_1) 12.0 (12_1)
OpenGL 4.6 4.6

Memory

Memory clock speed 10000 MHz 10008 MHz
Maximum RAM amount 24 GB
Memory bandwidth 480.4 GB / s
Memory bus width 384 Bit
Memory type GDDR5X