NVIDIA Tesla K8 vs NVIDIA CMP 170HX
GPU Specs Compare
Graphics Card
Release Date
Sep 2014
Sep 2021
Generation
Tesla
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x4
Clock Speeds
Base Clock
693 MHz
1140 MHz
Boost Clock
811 MHz
1410 MHz
Memory Clock
1250 MHz
1458 MHz
Memory
Memory Size
8GB
16GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
4096bit
Bandwidth
160.0GB/s
1493GB/s
Render Config
Shading Units
1536
4480
TMUs
128
280
ROPs
32
128
L1 Cache
16 KB (per SMX)
192 KB (per SM)
L2 Cache
512 KB
8 MB
SM Count
-
70
Tensor Cores
-
280
Theoretical Performance
Pixel Rate
25.95 GPixel/s
180.5 GPixel/s
Texture Rate
103.8 GTexel/s
394.8 GTexel/s
FP32 (float)
2.491 TFLOPS
12.63 TFLOPS
FP64 (double)
103.8 GFLOPS
6.317 TFLOPS
FP16 (half)
-
50.53 TFLOPS
Graphics Processor
GPU Name
GK104
GA100
Architecture
Kepler
Ampere
Foundry
TSMC
TSMC
Process Size
28 nm
7 nm
Transistors
3.54 billion
54.2 billion
Die Size
294 mm²
826 mm²
GPU Variant
-
GA100-105F-A1
Board Design
TDP
100W
250W
Suggested PSU
300 W
600 W
Outputs
No outputs
No outputs
Power Connectors
1x 6-pin
2x 8-pin
Graphics Features
DirectX
12 (11_0)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.1
N/A
CUDA
3.0
8.0
Shader Model
5.1
N/A