AMD Radeon Instinct MI50 vs NVIDIA GeForce RTX 3080 Ti Mobile

GPU · Specs Compare

Products
GPU AMD Radeon Instinct MI50 AMD · 2018-11
GPU NVIDIA GeForce RTX 3080 Ti Mobile NVIDIA · 2022-01
Graphics Card
Release Date
Nov 2018
Jan 2022
Generation
Radeon Instinct
GeForce 30 Mobile
Type
Professional
Mobile
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1200 MHz
810 MHz
Boost Clock
1746 MHz
1260 MHz
Memory Clock
1000 MHz
2000 MHz
Memory
Memory Size
16GB
16GB
Memory Type
HBM2
GDDR6
Memory Bus
4096bit
256bit
Bandwidth
1.02TB/s
512.0GB/s
Render Config
Compute Units
60
—
Shading Units
3840
7424
TMUs
240
232
ROPs
64
96
RT Cores
32
58
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
4 MB
4 MB
L3 Cache
32 MB
—
SM Count
—
58
Tensor Cores
—
232
Theoretical Performance
Pixel Rate
111.7 GPixel/s
121.0 GPixel/s
Texture Rate
419.0 GTexel/s
292.3 GTexel/s
FP16 (half)
26.82 TFLOPS
18.71 TFLOPS
FP32 (float)
13.41 TFLOPS
18.71 TFLOPS
FP64 (double)
6.705 TFLOPS
292.3 GFLOPS
Graphics Processor
GPU Name
Vega 20
GA103S
GPU Variant
Vega 20 GLXT
GN20-E8-A1
Architecture
GCN 5.1
Ampere
Foundry
TSMC
Samsung
Process Size
7 nm
8 nm
Transistors
13.23 billion
Unknown
Die Size
331 mm²
496 mm²
Board Design
TDP
300W
115W
Suggested PSU
700 W
—
Outputs
1x mini-DisplayPort 1.4a
No outputs
Power Connectors
2x 8-pin
None
Graphics Features
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.1
3.0
Vulkan
1.3
1.3
Shader Model
6.7
6.5
CUDA
—
8.6
Benchmark
3DMark Time Spy
—
12,905
3DMark Time Spy Extreme
—
6,164
▲ Specs Compare Data sourced from official specifications and benchmark tests.