NVIDIA Tesla K20s vs NVIDIA GRID RTX T10 8
GPU · Specs Compare
Graphics Card
Release Date
Feb 2013
Unknown
Generation
Tesla
GRID
Type
Professional
Professional
Bus Interface
PCIe 2.0 x16
PCIe 3.0 x16
Clock Speeds
Memory Clock
1300 MHz
1750 MHz
Base Clock
—
1065 MHz
Boost Clock
—
1395 MHz
Memory
Memory Size
5GB
8GB
Memory Type
GDDR5
GDDR6
Memory Bus
320bit
384bit
Bandwidth
208.0GB/s
672.0GB/s
Render Config
Shading Units
2496
3584
TMUs
208
224
ROPs
40
64
L1 Cache
16 KB (per SMX)
64 KB (per SM)
L2 Cache
1280 KB
6 MB
SM Count
—
56
Tensor Cores
—
448
RT Cores
—
56
Theoretical Performance
Pixel Rate
29.90 GPixel/s
89.28 GPixel/s
Texture Rate
119.6 GTexel/s
312.5 GTexel/s
FP32 (float)
2.870 TFLOPS
9.999 TFLOPS
FP64 (double)
956.8 GFLOPS
312.5 GFLOPS
FP16 (half)
—
20.00 TFLOPS
Graphics Processor
GPU Name
GK110
TU102
Architecture
Kepler
Turing
Foundry
TSMC
TSMC
Process Size
28 nm
12 nm
Transistors
7.08 billion
18.6 billion
Die Size
561 mm²
754 mm²
GPU Variant
—
TU102-875-A1
Board Design
TDP
225W
150W
Suggested PSU
550 W
450 W
Outputs
No outputs
No outputs
Power Connectors
—
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
1.3
CUDA
3.5
7.5
Shader Model
5.1
6.8
▲ Specs Compare
Data sourced from official specifications and benchmark tests.