Intel Data Center GPU Max 1350 vs NVIDIA A100 PCIe 80 GB
We compared two Professional market GPUs: 96GB VRAM Data Center GPU Max 1350 and 80GB VRAM A100 PCIe 80 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Max 1350 's Advantages
Released 1 years and 7 months late
Boost Clock has increased by 10% (1550MHz vs 1410MHz)
More VRAM (96GB vs 80GB)
Larger VRAM bandwidth (2458GB/s vs 1.94TB/s)
7424 additional rendering cores
NVIDIA A100 PCIe 80 GB 's Advantages
Lower TDP (300W vs 450W)
Score
Benchmark
FP32 (float)
Data Center GPU Max 1350
+128%
44.44 TFLOPS
A100 PCIe 80 GB
19.49 TFLOPS
Graphics Card
Jan 2023
Release Date
Jun 2021
Data Center GPU
Generation
Tesla Ampere(Axx)
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
750 MHz
Base Clock
1065 MHz
1550 MHz
Boost Clock
1410 MHz
1200 MHz
Memory Clock
1512 MHz
Memory
96GB
Memory Size
80GB
HBM2e
Memory Type
HBM2e
8192bit
Memory Bus
5120bit
2458GB/s
Bandwidth
1.94TB/s
Render Config
-
-
-
-
SM Count
108
14336
Shading Units
6912
896
TMUs
432
0
ROPs
160
896
Tensor Cores
432
112
RT Cores
-
64 KB (per EU)
L1 Cache
192 KB (per SM)
408 MB
L2 Cache
80 MB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
225.6 GPixel/s
1389 GTexel/s
Texture Rate
609.1 GTexel/s
44.44 TFLOPS
FP16 (half)
77.97 TFLOPS
44.44 TFLOPS
FP32 (float)
19.49 TFLOPS
44.44 TFLOPS
FP64 (double)
9.746 TFLOPS
Board Design
450W
TDP
300W
850 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
-
Power Connectors
8-pin EPS
Graphics Processor
Ponte Vecchio
GPU Name
GA100
-
-
-
Generation 12.5
Architecture
Ampere
Intel
Foundry
TSMC
10 nm
Process Size
7 nm
100 billion
Transistors
54.2 billion
1280 mm²
Die Size
826 mm²
Graphics Features
12 (12_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
N/A
Vulkan
N/A
-
CUDA
8.0
6.6
Shader Model
N/A
