AMD Radeon Pro Duo vs NVIDIA L40
GPU · Specs Compare
Graphics Card
Release Date
Apr 2016
Oct 2022
Generation
Radeon Pro
Tesla Ada
Type
Desktop
Professional
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Memory Clock
500 MHz
2250 MHz
Base Clock
—
735 MHz
Boost Clock
—
2490 MHz
Memory
Memory Size
4GB
48GB
Memory Type
HBM
GDDR6
Memory Bus
4096bit
384bit
Bandwidth
512.0GB/s
864.0GB/s
Render Config
Compute Units
64
—
Shading Units
4096
18176
TMUs
256
568
ROPs
64
192
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
2 MB
96 MB
SM Count
—
142
Tensor Cores
—
568
RT Cores
—
142
Theoretical Performance
Pixel Rate
64.00 GPixel/s
478.1 GPixel/s
Texture Rate
256.0 GTexel/s
1414 GTexel/s
FP16 (half)
8.192 TFLOPS
90.52 TFLOPS
FP32 (float)
8.192 TFLOPS
90.52 TFLOPS
FP64 (double)
512.0 GFLOPS
1414 GFLOPS
Graphics Processor
GPU Name
Capsaicin
AD102
GPU Variant
Capsaicin XT
AD102-895-A1
Architecture
GCN 3.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
28 nm
4 nm
Transistors
8.9 billion
76.3 billion
Die Size
596 mm²
608 mm²
Board Design
TDP
350W
300W
Suggested PSU
750 W
700 W
Outputs
1x HDMI 1.4a3x DisplayPort 1.2
4x DisplayPort 1.4a
Power Connectors
3x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.0
3.0
Vulkan
1.2
1.3
Shader Model
6.0
6.6
CUDA
—
8.9
Benchmark
Blender
—
3,901
▲ Specs Compare
Data sourced from official specifications and benchmark tests.