AMD Radeon Pro Vega II Duo vs NVIDIA H100 SXM5 94 GB
We compared two Desktop platform GPUs: 32GB VRAM Radeon Pro Vega II Duo and 94GB VRAM H100 SXM5 94 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Pro Vega II Duo 's Advantages
Lower TDP (475W vs 700W)
NVIDIA H100 SXM5 94 GB 's Advantages
Released 3 years and 9 months late
Boost Clock has increased by 15% (1980MHz vs 1720MHz)
More VRAM (94GB vs 32GB)
Larger VRAM bandwidth (3.36TB/s vs 1020GB/s)
12800 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Pro Vega II Duo
14.09 TFLOPS
H100 SXM5 94 GB
+374%
66.91 TFLOPS
Graphics Card
Jun 2019
Release Date
Mar 2023
Radeon Pro Mac
Generation
Server Hopper
Desktop
Type
Desktop
Apple MPX
Bus Interface
PCIe 5.0 x16
Clock Speeds
1400 MHz
Base Clock
1350 MHz
1720 MHz
Boost Clock
1980 MHz
1000 MHz
Memory Clock
1313 MHz
Memory
32GB
Memory Size
94GB
HBM2
Memory Type
HBM3
4096bit
Memory Bus
5120bit
1020GB/s
Bandwidth
3.36TB/s
Render Config
64
Compute Units
-
-
SM Count
132
4096
Shading Units
16896
256
TMUs
528
64
ROPs
24
-
Tensor Cores
528
-
-
-
16 KB (per CU)
L1 Cache
256 KB (per SM)
4 MB
L2 Cache
50 MB
-
-
-
Theoretical Performance
110.1 GPixel/s
Pixel Rate
47.52 GPixel/s
440.3 GTexel/s
Texture Rate
1045 GTexel/s
28.18 TFLOPS
FP16 (half)
267.6 TFLOPS
14.09 TFLOPS
FP32 (float)
66.91 TFLOPS
7.045 TFLOPS
FP64 (double)
33.45 TFLOPS
Board Design
475W
TDP
700W
850 W
Suggested PSU
1100 W
1x HDMI 2.0b
4x Thunderbolt
Outputs
No outputs
None
Power Connectors
8-pin EPS
Graphics Processor
Vega 20
GPU Name
GH100
Vega 20 XT
GPU Variant
-
GCN 5.1
Architecture
Hopper
TSMC
Foundry
TSMC
7 nm
Process Size
5 nm
13.23 billion
Transistors
80 billion
331 mm²
Die Size
814 mm²
Graphics Features
12 (12_1)
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
