NVIDIA H100 PCIe vs AMD Radeon Pro WX Vega M GL
GPU · Specs Compare
Graphics Card
Release Date
Mar 2022
Apr 2018
Generation
Tesla Hopper
Vega
Type
AI GPU
Mobile
Bus Interface
PCIe 5.0 x16
IGP
Clock Speeds
Base Clock
1095 MHz
931 MHz
Boost Clock
1755 MHz
1011 MHz
Memory Clock
1593 MHz
700 MHz
Memory
Memory Size
80GB
4GB
Memory Type
HBM2e
HBM2
Memory Bus
5120bit
1024bit
Bandwidth
2039GB/s
179.2GB/s
Render Config
SM Count
114
—
Shading Units
14592
1280
TMUs
456
80
ROPs
24
32
Tensor Cores
456
—
L1 Cache
256 KB (per SM)
16 KB (per CU)
L2 Cache
50 MB
1024 KB
Compute Units
—
20
Theoretical Performance
Pixel Rate
42.12 GPixel/s
32.35 GPixel/s
Texture Rate
800.3 GTexel/s
80.88 GTexel/s
FP16 (half)
204.9 TFLOPS
2.588 TFLOPS
FP32 (float)
51.22 TFLOPS
2.588 TFLOPS
FP64 (double)
25.61 TFLOPS
161.8 GFLOPS
Graphics Processor
GPU Name
GH100
Polaris 22
Architecture
Hopper
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
4 nm
14 nm
Transistors
80 billion
5 billion
Die Size
814 mm²
208 mm²
GPU Variant
—
VegaM MGL XL
Board Design
TDP
350W
65W
Suggested PSU
750 W
—
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
N/A
12 (12_0)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
9.0
—
Shader Model
N/A
6.4
▲ Specs Compare
Data sourced from official specifications and benchmark tests.