Intel Data Center GPU Flex 170 vs AMD Radeon Instinct MI50
We compared two Professional market GPUs: 16GB VRAM Data Center GPU Flex 170 and 8GB VRAM Radeon Instinct MI50 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Flex 170 's Advantages
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (512.0GB/s vs 322.3GB/s)
2048 additional rendering cores
AMD Radeon Instinct MI50 's Advantages
Released 2 years and 9 months late
Boost Clock has increased by 58% (3230MHz vs 2050MHz)
Score
Benchmark
FP32 (float)
Data Center GPU Flex 170
16.79 TFLOPS
Radeon Instinct MI50
+57%
26.46 TFLOPS
Graphics Card
Aug 2022
Release Date
May 2025
Data Center GPU
Generation
Navi IV
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x8
Clock Speeds
1950 MHz
Base Clock
2220 MHz
2050 MHz
Boost Clock
3230 MHz
2000 MHz
Memory Clock
2518 MHz
Memory
16GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
128bit
512.0GB/s
Bandwidth
322.3GB/s
Render Config
-
Compute Units
32
-
-
-
4096
Shading Units
2048
256
TMUs
128
128
ROPs
64
-
-
-
32
RT Cores
32
-
L1 Cache
16 KB (per CU)
16 MB
L2 Cache
4 MB
-
L3 Cache
32 MB
Theoretical Performance
262.4 GPixel/s
Pixel Rate
206.7 GPixel/s
524.8 GTexel/s
Texture Rate
413.4 GTexel/s
33.59 TFLOPS
FP16 (half)
52.92 TFLOPS
16.79 TFLOPS
FP32 (float)
26.46 TFLOPS
-
FP64 (double)
826.9 GFLOPS
Board Design
150W
TDP
150W
450 W
Suggested PSU
450 W
1x HDMI 2.1
3x DisplayPort 2.0
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1a
1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
DG2-512
GPU Name
Navi 44
ACM-G10
GPU Variant
Navi 44 XT
Generation 12.7
Architecture
RDNA 4.0
TSMC
Foundry
TSMC
6 nm
Process Size
4 nm
21.7 billion
Transistors
Unknown
406 mm²
Die Size
153 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
2.2
1.3
Vulkan
1.3
-
-
-
6.6
Shader Model
6.8
