NVIDIA H100 PCIe 80 GB vs AMD Radeon 680M
GPU · Specs Compare
Graphics Card
Release Date
Oct 2022
Jan 2022
Generation
Server Hopper
Navi II IGP
Type
AI GPU
Integrated
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x8
Clock Speeds
Base Clock
1095 MHz
2000 MHz
Boost Clock
1755 MHz
2200 MHz
Memory Clock
1593 MHz
System Shared
Memory
Memory Size
80GB
System Shared
Memory Type
HBM2e
System Shared
Memory Bus
5120bit
System Shared
Bandwidth
2.04TB/s
System Dependent
Render Config
SM Count
114
—
Shading Units
14592
768
TMUs
456
48
ROPs
24
32
Tensor Cores
456
—
L1 Cache
256 KB (per SM)
128 KB per Array
L2 Cache
50 MB
2 MB
Compute Units
—
12
RT Cores
—
12
Theoretical Performance
Pixel Rate
42.12 GPixel/s
70.40 GPixel/s
Texture Rate
800.3 GTexel/s
105.6 GTexel/s
FP16 (half)
204.9 TFLOPS
6.758 TFLOPS
FP32 (float)
51.22 TFLOPS
3.379 TFLOPS
FP64 (double)
25.61 TFLOPS
211.2 GFLOPS
Graphics Processor
GPU Name
GH100
Rembrandt
Architecture
Hopper
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
6 nm
Transistors
80 billion
13.1 billion
Die Size
814 mm²
208 mm²
Board Design
TDP
350W
50W
Suggested PSU
750 W
—
Outputs
No outputs
Portable Device Dependent
Power Connectors
1x 16-pin
None
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
2.0
Vulkan
N/A
1.3
CUDA
9.0
—
Shader Model
N/A
6.7
▲ Specs Compare
Data sourced from official specifications and benchmark tests.