NVIDIA A100 SXM4 40 GB vs Intel Data Center GPU Max 1350

GPU Specs Compare

Graphics Card

Release Date
May 2020
Jan 2023
Generation
Tesla Ampere
Data Center GPU
Type
AI GPU
Professional
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16

Clock Speeds

Base Clock
1095 MHz
750 MHz
Boost Clock
1410 MHz
1550 MHz
Memory Clock
1215 MHz
1200 MHz

Memory

Memory Size
40GB
96GB
Memory Type
HBM2e
HBM2e
Memory Bus
5120bit
8192bit
Bandwidth
1555GB/s
2458GB/s

Render Config

SM Count
108
-
Shading Units
6912
14336
TMUs
432
896
ROPs
160
0
Tensor Cores
432
896
L1 Cache
192 KB (per SM)
64 KB (per EU)
L2 Cache
40 MB
408 MB
RT Cores
-
112

Theoretical Performance

Pixel Rate
225.6 GPixel/s
0 MPixel/s
Texture Rate
609.1 GTexel/s
1389 GTexel/s
FP16 (half)
77.97 TFLOPS
44.44 TFLOPS
FP32 (float)
19.49 TFLOPS
44.44 TFLOPS
FP64 (double)
9.746 TFLOPS
44.44 TFLOPS

Graphics Processor

GPU Name
GA100
Ponte Vecchio
Architecture
Ampere
Generation 12.5
Foundry
TSMC
Intel
Process Size
7 nm
10 nm
Transistors
54.2 billion
100 billion
Die Size
826 mm²
1280 mm²

Board Design

TDP
400W
450W
Suggested PSU
800 W
850 W
Outputs
No outputs
No outputs
Power Connectors
None
-

Graphics Features

DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
8.0
-
Shader Model
N/A
6.6

📊 Benchmark

Blender
2,186
-