Radeon Pro Duo Polaris vs H200 NVL
We compared two Desktop platform GPUs: 16GB VRAM Radeon Pro Duo Polaris and 141GB VRAM H200 NVL to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon Pro Duo Polaris 's Advantages
Lower TDP (250W vs 600W)
H200 NVL 's Advantages
Released 7 years and 7 months late
Boost Clock1785MHz
More VRAM (141GB vs 16GB)
Larger VRAM bandwidth (4.89TB/s vs 224.0GB/s)
14592 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Pro Duo Polaris
5728
H200 NVL
+953%
60320
Graphics Card
Apr 2017
Release Date
Nov 2024
Radeon Pro GCN
Generation
Server Hopper
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
-
Base Clock
1365 MHz
-
Boost Clock
1785 MHz
1750 MHz
Memory Clock
1593 MHz
Memory
16GB
Memory Size
141GB
GDDR5
Memory Type
HBM3e
256bit
Memory Bus
6144bit
224.0GB/s
Bandwidth
4.89TB/s
Render Config
36
Compute Units
-
-
SM Count
132
2304
Shading Units
16896
144
TMUs
528
32
ROPs
24
-
Tensor Cores
528
16 KB (per CU)
L1 Cache
256 KB (per SM)
2 MB
L2 Cache
50 MB
Theoretical Performance
39.78 GPixel/s
Pixel Rate
42.84 GPixel/s
179.0 GTexel/s
Texture Rate
942.5 GTexel/s
5.728 TFLOPS
FP16 (half)
241.3 TFLOPS
5.728 TFLOPS
FP32 (float)
60.32 TFLOPS
358.0 GFLOPS
FP64 (double)
30.16 TFLOPS
Board Design
250W
TDP
600W
600 W
Suggested PSU
1000 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
Ellesmere
GPU Name
GH100
Ellesmere Gemini GL
GPU Variant
-
GCN 4.0
Architecture
Hopper
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
5 nm
5.7 billion
Transistors
80 billion
232 mm²
Die Size
814 mm²
Graphics Features
12 (12_0)
DirectX
N/A
4.6
OpenGL
N/A
2.1
OpenCL
3.0
1.3
Vulkan
N/A
-
CUDA
9.0
6.7
Shader Model
N/A
