AMD Radeon 660M vs NVIDIA L40 CNX
GPU · Specs Compare
Graphics Card
Release Date
Jan 2022
Oct 2022
Generation
Rembrandt
Tesla Ada
Type
Integrated
Professional
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Clock Speeds
Base Clock
1500 MHz
1005 MHz
Boost Clock
1900 MHz
2475 MHz
Memory Clock
System Shared
2250 MHz
Memory
Memory Size
System Shared
24GB
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
384bit
Bandwidth
System Dependent
864.0GB/s
Render Config
Compute Units
6
—
Shading Units
384
18176
TMUs
24
568
ROPs
16
192
RT Cores
6
142
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
48 MB
SM Count
—
142
Tensor Cores
—
568
Theoretical Performance
Pixel Rate
30.40 GPixel/s
475.2 GPixel/s
Texture Rate
45.60 GTexel/s
1406 GTexel/s
FP16 (half)
2.918 TFLOPS
89.97 TFLOPS
FP32 (float)
1459 GFLOPS
89.97 TFLOPS
FP64 (double)
91.20 GFLOPS
1406 GFLOPS
Graphics Processor
GPU Name
Rembrandt
AD102
Architecture
RDNA 2.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
6 nm
4 nm
Transistors
13.1 billion
76.3 billion
Die Size
210 mm²
608 mm²
GPU Variant
—
AD102-???-A1
Board Design
TDP
15W
300W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
None
1x 16-pin
Suggested PSU
—
700 W
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.0
3.0
Vulkan
1.2
1.3
Shader Model
6.5
6.6
CUDA
—
8.9
Benchmark
3DMark Time Spy
1,537
—
3DMark Time Spy Extreme
701
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.