NVIDIA GeForce RTX 3080 vs AMD Radeon RX 550
We compared two Desktop platform GPUs: 10GB VRAM GeForce RTX 3080 and 2GB VRAM Radeon RX 550 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3080 's Advantages
Released 3 years and 5 months late
Boost Clock has increased by 45% (1710MHz vs 1183MHz)
More VRAM (10GB vs 2GB)
Larger VRAM bandwidth (760.3GB/s vs 112.0GB/s)
8192 additional rendering cores
AMD Radeon RX 550 's Advantages
Lower TDP (50W vs 320W)
Score
Benchmark
FP32 (float)
GeForce RTX 3080
+2358%
29.77 TFLOPS
Radeon RX 550
1.211 TFLOPS
3DMark Time Spy
GeForce RTX 3080
+1379%
17662
Radeon RX 550
1194
3DMark Time Spy Extreme
GeForce RTX 3080
+1526%
8879
Radeon RX 550
546
Shadow of the Tomb Raider 2160p
GeForce RTX 3080
+1216%
79
Radeon RX 550
6
Shadow of the Tomb Raider 1440p
GeForce RTX 3080
+1058%
139
Radeon RX 550
12
Shadow of the Tomb Raider 1080p
GeForce RTX 3080
+761%
181
Radeon RX 550
21
Battlefield 5 2160p
GeForce RTX 3080
+1428%
107
Radeon RX 550
7
Battlefield 5 1440p
GeForce RTX 3080
+1057%
162
Radeon RX 550
14
Battlefield 5 1080p
GeForce RTX 3080
+850%
190
Radeon RX 550
20
GTA 5 1080p
GeForce RTX 3080
+104%
172
Radeon RX 550
84
Graphics Card
Sep 2020
Release Date
Apr 2017
GeForce 30
Generation
Polaris
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x8
Clock Speeds
1440 MHz
Base Clock
1100 MHz
1710 MHz
Boost Clock
1183 MHz
1188 MHz
Memory Clock
1750 MHz
Memory
10GB
Memory Size
2GB
GDDR6X
Memory Type
GDDR5
320bit
Memory Bus
128bit
760.3GB/s
Bandwidth
112.0GB/s
Render Config
-
Compute Units
8
68
SM Count
-
8704
Shading Units
512
272
TMUs
32
96
ROPs
16
272
Tensor Cores
-
68
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
5 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
164.2 GPixel/s
Pixel Rate
18.93 GPixel/s
465.1 GTexel/s
Texture Rate
37.86 GTexel/s
29.77 TFLOPS
FP16 (half)
1211 GFLOPS
29.77 TFLOPS
FP32 (float)
1211 GFLOPS
465.1 GFLOPS
FP64 (double)
75.71 GFLOPS
Board Design
320W
TDP
50W
700 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0b
1x DisplayPort 1.4a
1x 12-pin
Power Connectors
None
Graphics Processor
GA102
GPU Name
Lexa
GA102-200-KD-A1
GPU Variant
Lexa PRO
(215-0904018)
Ampere
Architecture
GCN 4.0
Samsung
Foundry
GlobalFoundries
8 nm
Process Size
14 nm
28.3 billion
Transistors
2.2 billion
628 mm²
Die Size
103 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
8.6
CUDA
-
6.6
Shader Model
6.4
