NVIDIA Tesla K80 vs NVIDIA Tesla P100 PCIe 16 GB
Comparative analysis of NVIDIA Tesla K80 and NVIDIA Tesla P100 PCIe 16 GB 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 - G2D Mark, PassMark - G3D Mark, Geekbench - OpenCL, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), 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 K80
- 517x more texture fill rate: 171.4 GTexel/s vs 331.5 GTexel / s
Texture fill rate | 171.4 GTexel/s vs 331.5 GTexel / s |
Reasons to consider the NVIDIA Tesla P100 PCIe 16 GB
- Videocard is newer: launch date 1 year(s) 7 month(s) later
- 2.1x more core clock speed: 1190 MHz vs 562 MHz
- Around 61% higher boost clock speed: 1329 MHz vs 824 MHz
- Around 44% higher pipelines: 3584 vs 2496
- A newer manufacturing process allows for a more powerful, yet cooler running videocard: 16 nm vs 28 nm
- Around 20% lower typical power consumption: 250 Watt vs 300 Watt
- Around 33% higher maximum memory size: 16 GB vs 12 GB
- Around 14% higher memory clock speed: 1430 MHz vs 1253 MHz, 5 Gbps effective
- 2.2x better performance in PassMark - G2D Mark: 611 vs 280
- 2.5x better performance in PassMark - G3D Mark: 11814 vs 4680
Specifications (specs) | |
Launch date | 20 June 2016 vs 17 Nov 2014 |
Core clock speed | 1190 MHz vs 562 MHz |
Boost clock speed | 1329 MHz vs 824 MHz |
Pipelines | 3584 vs 2496 |
Manufacturing process technology | 16 nm vs 28 nm |
Thermal Design Power (TDP) | 250 Watt vs 300 Watt |
Maximum memory size | 16 GB vs 12 GB |
Memory clock speed | 1430 MHz vs 1253 MHz, 5 Gbps effective |
Benchmarks | |
PassMark - G2D Mark | 611 vs 280 |
PassMark - G3D Mark | 11814 vs 4680 |
Compare benchmarks
GPU 1: NVIDIA Tesla K80
GPU 2: NVIDIA Tesla P100 PCIe 16 GB
PassMark - G2D Mark |
|
|
||||
PassMark - G3D Mark |
|
|
Name | NVIDIA Tesla K80 | NVIDIA Tesla P100 PCIe 16 GB |
---|---|---|
PassMark - G2D Mark | 280 | 611 |
PassMark - G3D Mark | 4680 | 11814 |
Geekbench - OpenCL | 78188 | |
GFXBench 4.0 - Car Chase Offscreen (Frames) | 13720 | |
GFXBench 4.0 - Car Chase Offscreen (Fps) | 13720 | |
GFXBench 4.0 - Manhattan (Frames) | 6381 | |
GFXBench 4.0 - Manhattan (Fps) | 6381 | |
GFXBench 4.0 - T-Rex (Frames) | 8915 | |
GFXBench 4.0 - T-Rex (Fps) | 8915 |
Compare specifications (specs)
NVIDIA Tesla K80 | NVIDIA Tesla P100 PCIe 16 GB | |
---|---|---|
Essentials |
||
Architecture | Kepler 2.0 | Pascal |
Code name | GK210 | GP100 |
Launch date | 17 Nov 2014 | 20 June 2016 |
Place in performance rating | 374 | 176 |
Launch price (MSRP) | $5,699 | |
Type | Workstation | |
Technical info |
||
Boost clock speed | 824 MHz | 1329 MHz |
Core clock speed | 562 MHz | 1190 MHz |
Manufacturing process technology | 28 nm | 16 nm |
Peak Double Precision (FP64) Performance | 1,371 GFLOPS (1:3) | |
Peak Single Precision (FP32) Performance | 4.113 TFLOPS | |
Pipelines | 2496 | 3584 |
Pixel fill rate | 42.85 GPixel/s | |
Texture fill rate | 171.4 GTexel/s | 331.5 GTexel / s |
Thermal Design Power (TDP) | 300 Watt | 250 Watt |
Transistor count | 7100 million | 15,300 million |
Floating-point performance | 10,609 gflops | |
Video outputs and ports |
||
Display Connectors | No outputs | No outputs |
Compatibility, dimensions and requirements |
||
Form factor | Dual-slot | |
Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Length | 267 mm, 10.5 inches | 267 mm |
Recommended system power (PSU) | 700 Watt | |
Supplementary power connectors | 1x 8-pin | 1x 8-pin |
API support |
||
DirectX | 12 (11_1) | 12.0 (12_1) |
OpenCL | 3.0 | |
OpenGL | 4.6 | 4.6 |
Shader Model | 6.5 (5.1) | |
Vulkan | ||
Memory |
||
Maximum RAM amount | 12 GB | 16 GB |
Memory bandwidth | 240.6 GB/s | 720.9 GB / s |
Memory bus width | 384 bit | 4096 Bit |
Memory clock speed | 1253 MHz, 5 Gbps effective | 1430 MHz |
Memory type | GDDR5 | HBM2 |