Intel Data Center GPU Max 1100 vs H200 SXM

GPU · Specs Compare

Products
GPU Intel Data Center GPU Max 1100 Intel · 2023-01
GPU H200 SXM · 2023-11
Graphics Card
Release Date
Jan 2023
Nov 2023
Generation
Data Center GPU
Hopper
Type
Professional
AI GPU
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1000 MHz
1590 MHz
Boost Clock
1550 MHz
1980 MHz
Memory Clock
600 MHz
1313 MHz
Memory
Memory Size
48GB
141GB
Memory Type
HBM2e
HBM3e
Memory Bus
8192bit
5120bit
Bandwidth
1229GB/s
4800GB/s
Render Config
Shading Units
7168
16896
TMUs
448
528
ROPs
0
24
Tensor Cores
448
528
RT Cores
56
—
L1 Cache
64 KB (per EU)
256 KB (per SM)
L2 Cache
204 MB
50 MB
SM Count
—
132
Theoretical Performance
Pixel Rate
0 MPixel/s
47.52 GPixel/s
Texture Rate
694.4 GTexel/s
1045 GTexel/s
FP16 (half)
22.22 TFLOPS
1979 TFLOPS
FP32 (float)
22.22 TFLOPS
67 TFLOPS
FP64 (double)
22.22 TFLOPS
34 TFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
GH200
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
300W
700W
Suggested PSU
700 W
1100 W
Outputs
No outputs
No outputs
Power Connectors
1x 12-pin
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
▲ Specs Compare Data sourced from official specifications and benchmark tests.