NVIDIA H100 PCIe vs Intel Data Center GPU Max 1550
GPU · Specs Compare
Graphics Card
Release Date
Mar 2022
Jan 2023
Generation
Tesla Hopper
Data Center GPU
Type
AI GPU
Professional
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1095 MHz
900 MHz
Boost Clock
1755 MHz
1600 MHz
Memory Clock
1593 MHz
1600 MHz
Memory
Memory Size
80GB
128GB
Memory Type
HBM2e
HBM2e
Memory Bus
5120bit
8192bit
Bandwidth
2039GB/s
3.28TB/s
Render Config
SM Count
114
—
Shading Units
14592
16384
TMUs
456
1024
ROPs
24
0
Tensor Cores
456
1024
L1 Cache
256 KB (per SM)
64 KB (per EU)
L2 Cache
50 MB
408 MB
RT Cores
—
128
Theoretical Performance
Pixel Rate
42.12 GPixel/s
0 MPixel/s
Texture Rate
800.3 GTexel/s
1638.4 GTexel/s
FP16 (half)
204.9 TFLOPS
52.43 TFLOPS
FP32 (float)
51.22 TFLOPS
52.43 TFLOPS
FP64 (double)
25.61 TFLOPS
52.43 TFLOPS
Graphics Processor
GPU Name
GH100
Ponte Vecchio
Architecture
Hopper
Generation 12.5
Foundry
TSMC
Intel
Process Size
4 nm
10 nm
Transistors
80 billion
100 billion
Die Size
814 mm²
1280 mm²
Board Design
TDP
350W
600W
Suggested PSU
750 W
1000 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
9.0
—
Shader Model
N/A
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.