Intel Data Center GPU Max 1350 vs NVIDIA H100 CNX
GPU Specs Compare
Graphics Card
Release Date
Jan 2023
Mar 2023
Generation
Data Center GPU
Tesla Hopper
Type
Professional
AI GPU
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
750 MHz
690 MHz
Boost Clock
1550 MHz
1845 MHz
Memory Clock
1200 MHz
1593 MHz
Memory
Memory Size
96GB
80GB
Memory Type
HBM2e
HBM2e
Memory Bus
8192bit
5120bit
Bandwidth
2458GB/s
2039GB/s
Render Config
Shading Units
14336
14592
TMUs
896
456
ROPs
0
24
Tensor Cores
896
456
RT Cores
112
-
L1 Cache
64 KB (per EU)
256 KB (per SM)
L2 Cache
408 MB
50 MB
SM Count
-
114
Theoretical Performance
Pixel Rate
0 MPixel/s
44.28 GPixel/s
Texture Rate
1389 GTexel/s
841.3 GTexel/s
FP16 (half)
44.44 TFLOPS
215.4 TFLOPS
FP32 (float)
44.44 TFLOPS
53.84 TFLOPS
FP64 (double)
44.44 TFLOPS
26.92 TFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
GH100
Architecture
Generation 12.5
Hopper
Foundry
Intel
TSMC
Process Size
10 nm
4 nm
Transistors
100 billion
80 billion
Die Size
1280 mm²
814 mm²
Board Design
TDP
450W
350W
Suggested PSU
850 W
750 W
Outputs
No outputs
No outputs
Power Connectors
-
8-pin EPS
Graphics Features
DirectX
12 (12_1)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
Shader Model
6.6
N/A
CUDA
-
9.0