AMD Radeon Vega 11 Embedded vs NVIDIA H100 CNX
GPU · Specs Compare
Graphics Card
Release Date
Feb 2018
Mar 2023
Generation
Great Horned Owl
Tesla Hopper
Type
Integrated
AI GPU
Bus Interface
IGP
PCIe 5.0 x16
Clock Speeds
Base Clock
300 MHz
690 MHz
Boost Clock
1301 MHz
1845 MHz
Memory Clock
System Shared
1593 MHz
Memory
Memory Size
System Shared
80GB
Memory Type
System Shared
HBM2e
Memory Bus
System Shared
5120bit
Bandwidth
System Dependent
2039GB/s
Render Config
Compute Units
11
—
Shading Units
704
14592
TMUs
44
456
ROPs
8
24
SM Count
—
114
Tensor Cores
—
456
L1 Cache
—
256 KB (per SM)
L2 Cache
—
50 MB
Theoretical Performance
Pixel Rate
10.41 GPixel/s
44.28 GPixel/s
Texture Rate
57.24 GTexel/s
841.3 GTexel/s
FP16 (half)
3.664 TFLOPS
215.4 TFLOPS
FP32 (float)
1.832 TFLOPS
53.84 TFLOPS
FP64 (double)
114.5 GFLOPS
26.92 TFLOPS
Graphics Processor
GPU Name
Raven
GH100
Architecture
GCN 5.0
Hopper
Foundry
GlobalFoundries
TSMC
Process Size
14 nm
4 nm
Transistors
4.94 billion
80 billion
Die Size
210 mm²
814 mm²
Board Design
TDP
35W
350W
Outputs
No outputs
No outputs
Power Connectors
None
8-pin EPS
Suggested PSU
—
750 W
Graphics Features
DirectX
12 (12_1)
N/A
OpenGL
4.6
N/A
OpenCL
2.1
3.0
Vulkan
1.2
N/A
Shader Model
6.4
N/A
CUDA
—
9.0
▲ Specs Compare
Data sourced from official specifications and benchmark tests.