NVIDIA P104 100 vs NVIDIA Tesla K20m

GPU · Specs Compare

Products
GPU NVIDIA P104 100 NVIDIA · 2017-12
GPU NVIDIA Tesla K20m NVIDIA · 2013-01
Graphics Card
Release Date
Dec 2017
Jan 2013
Generation
Mining GPUs
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 1.0 x4
PCIe 2.0 x16
Clock Speeds
Base Clock
1607 MHz
—
Boost Clock
1733 MHz
—
Memory Clock
1251 MHz
1300 MHz
Memory
Memory Size
4GB
5GB
Memory Type
GDDR5X
GDDR5
Memory Bus
256bit
320bit
Bandwidth
320.3GB/s
208.0GB/s
Render Config
SM Count
15
—
Shading Units
1920
2496
TMUs
120
208
ROPs
64
40
L1 Cache
48 KB (per SM)
16 KB (per SMX)
L2 Cache
2 MB
1280 KB
Theoretical Performance
Pixel Rate
110.9 GPixel/s
36.71 GPixel/s
Texture Rate
208.0 GTexel/s
146.8 GTexel/s
FP16 (half)
104.0 GFLOPS
—
FP32 (float)
6.655 TFLOPS
3.524 TFLOPS
FP64 (double)
208.0 GFLOPS
1175 GFLOPS
Graphics Processor
GPU Name
GP104
GK110
GPU Variant
GP104-100-A1
—
Architecture
Pascal
Kepler
Foundry
TSMC
TSMC
Process Size
16 nm
28 nm
Transistors
7.2 billion
7.08 billion
Die Size
314 mm²
561 mm²
Board Design
TDP
Unknown
225W
Suggested PSU
200 W
550 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 (12_1)
12 (11_0)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.1
CUDA
6.1
3.5
Shader Model
6.8
5.1
Benchmark
3DMark Time Spy
5,439
—
3DMark Time Spy Extreme
2,718
—
OctaneBench
124
—
Blender
701
—
▲ Specs Compare Data sourced from official specifications and benchmark tests.