AMD Radeon Pro W5700 vs NVIDIA L20
GPU · Specs Compare
Graphics Card
Release Date
Nov 2019
Nov 2023
Generation
Radeon Pro
Server Ada
Type
Desktop
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1400 MHz
1440 MHz
Boost Clock
1880 MHz
2520 MHz
Memory Clock
1750 MHz
2250 MHz
Memory
Memory Size
8GB
48GB
Memory Type
GDDR6
GDDR6
Memory Bus
256bit
384bit
Bandwidth
448.0GB/s
864.0GB/s
Render Config
Compute Units
36
—
Shading Units
2304
11776
TMUs
144
368
ROPs
64
128
L2 Cache
4 MB
96 MB
SM Count
—
92
Tensor Cores
—
368
RT Cores
—
92
L1 Cache
—
128 KB (per SM)
Theoretical Performance
Pixel Rate
120.3 GPixel/s
322.6 GPixel/s
Texture Rate
270.7 GTexel/s
927.4 GTexel/s
FP16 (half)
17.33 TFLOPS
59.35 TFLOPS
FP32 (float)
8.663 TFLOPS
59.35 TFLOPS
FP64 (double)
541.4 GFLOPS
927.4 GFLOPS
Graphics Processor
GPU Name
Navi 10
AD102
Architecture
RDNA 1.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
7 nm
5 nm
Transistors
10.3 billion
76.3 billion
Die Size
251 mm²
609 mm²
GPU Variant
—
AD102
Board Design
TDP
205W
275W
Suggested PSU
550 W
600 W
Outputs
5x mini-DisplayPort 1.4a1x USB Type-C
4x DisplayPort 1.4a
Power Connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.4
Shader Model
6.5
6.9
CUDA
—
8.9
Benchmark
3DMark Time Spy
8,549
—
3DMark Time Spy Extreme
4,103
—
Blender
964
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.