NVIDIA Tesla K40st vs AMD Radeon 680M

GPU Specs Compare

G

NVIDIA Tesla K40st

NVIDIA 2013-11
G

AMD Radeon 680M

AMD 2022-01

Graphics Card

Release Date
Nov 2013
Jan 2022
Generation
Tesla
Navi II IGP
Type
Professional
Integrated
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x8

Clock Speeds

Memory Clock
1502 MHz
System Shared
Base Clock
-
2000 MHz
Boost Clock
-
2200 MHz

Memory

Memory Size
12GB
System Shared
Memory Type
GDDR5
System Shared
Memory Bus
384bit
System Shared
Bandwidth
288.4GB/s
System Dependent

Render Config

Shading Units
2880
768
TMUs
240
48
ROPs
48
32
L1 Cache
16 KB (per SMX)
128 KB per Array
L2 Cache
1536 KB
2 MB
Compute Units
-
12
RT Cores
-
12

Theoretical Performance

Pixel Rate
34.50 GPixel/s
70.40 GPixel/s
Texture Rate
138.0 GTexel/s
105.6 GTexel/s
FP32 (float)
3.312 TFLOPS
3.379 TFLOPS
FP64 (double)
1104 GFLOPS
211.2 GFLOPS
FP16 (half)
-
6.758 TFLOPS

Graphics Processor

GPU Name
GK110B
Rembrandt
Architecture
Kepler
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
28 nm
6 nm
Transistors
7.08 billion
13.1 billion
Die Size
561 mm²
208 mm²

Board Design

TDP
245W
50W
Suggested PSU
550 W
-
Outputs
No outputs
Portable Device Dependent
Power Connectors
-
None

Graphics Features

DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.0
Vulkan
1.1
1.3
CUDA
3.5
-
Shader Model
5.1
6.7