NVIDIA H100 CNX vs AMD Radeon Vega 11 Embedded

GPU Specs Compare

Graphics Card

Release Date
Mar 2023
Feb 2018
Generation
Tesla Hopper
Great Horned Owl
Type
AI GPU
Integrated
Bus Interface
PCIe 5.0 x16
IGP

Clock Speeds

Base Clock
690 MHz
300 MHz
Boost Clock
1845 MHz
1301 MHz
Memory Clock
1593 MHz
System Shared

Memory

Memory Size
80GB
System Shared
Memory Type
HBM2e
System Shared
Memory Bus
5120bit
System Shared
Bandwidth
2039GB/s
System Dependent

Render Config

SM Count
114
-
Shading Units
14592
704
TMUs
456
44
ROPs
24
8
Tensor Cores
456
-
L1 Cache
256 KB (per SM)
-
L2 Cache
50 MB
-
Compute Units
-
11

Theoretical Performance

Pixel Rate
44.28 GPixel/s
10.41 GPixel/s
Texture Rate
841.3 GTexel/s
57.24 GTexel/s
FP16 (half)
215.4 TFLOPS
3.664 TFLOPS
FP32 (float)
53.84 TFLOPS
1.832 TFLOPS
FP64 (double)
26.92 TFLOPS
114.5 GFLOPS

Graphics Processor

GPU Name
GH100
Raven
Architecture
Hopper
GCN 5.0
Foundry
TSMC
GlobalFoundries
Process Size
4 nm
14 nm
Transistors
80 billion
4.94 billion
Die Size
814 mm²
210 mm²

Board Design

TDP
350W
35W
Suggested PSU
750 W
-
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
None

Graphics Features

DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
9.0
-
Shader Model
N/A
6.4