NVIDIA A10G vs Intel Data Center GPU Max 1550
GPU · Specs Compare
Graphics Card
Release Date
Apr 2021
Jan 2023
Generation
Tesla
Data Center GPU
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1320 MHz
900 MHz
Boost Clock
1710 MHz
1600 MHz
Memory Clock
1563 MHz
1600 MHz
Memory
Memory Size
12GB
128GB
Memory Type
GDDR6
HBM2e
Memory Bus
384bit
8192bit
Bandwidth
600.2GB/s
3.28TB/s
Render Config
SM Count
72
—
Shading Units
9216
16384
TMUs
288
1024
ROPs
96
0
Tensor Cores
288
1024
RT Cores
72
128
L1 Cache
128 KB (per SM)
64 KB (per EU)
L2 Cache
6 MB
408 MB
Theoretical Performance
Pixel Rate
164.2 GPixel/s
0 MPixel/s
Texture Rate
492.5 GTexel/s
1638.4 GTexel/s
FP16 (half)
31.52 TFLOPS
52.43 TFLOPS
FP32 (float)
31.52 TFLOPS
52.43 TFLOPS
FP64 (double)
985.0 GFLOPS
52.43 TFLOPS
Graphics Processor
GPU Name
GA102
Ponte Vecchio
GPU Variant
GA102-890-A1
—
Architecture
Ampere
Generation 12.5
Foundry
Samsung
Intel
Process Size
8 nm
10 nm
Transistors
28.3 billion
100 billion
Die Size
628 mm²
1280 mm²
Board Design
TDP
150W
600W
Suggested PSU
450 W
1000 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
—
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.6
—
Shader Model
6.6
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.