Intel Data Center GPU Flex 170 vs NVIDIA GeForce RTX 4090
GPU · Specs Compare
Graphics Card
Release Date
Aug 2022
Sep 2022
Generation
Data Center GPU
GeForce 40
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1950 MHz
2235 MHz
Boost Clock
2050 MHz
2520 MHz
Memory Clock
2000 MHz
1313 MHz
Memory
Memory Size
16GB
24GB
Memory Type
GDDR6
GDDR6X
Memory Bus
256bit
384bit
Bandwidth
512.0GB/s
1.01TB/s
Render Config
Shading Units
4096
16384
TMUs
256
512
ROPs
128
176
RT Cores
32
128
L2 Cache
16 MB
72 MB
SM Count
—
128
Tensor Cores
—
512
L1 Cache
—
128 KB (per SM)
Theoretical Performance
Pixel Rate
262.4 GPixel/s
443.5 GPixel/s
Texture Rate
524.8 GTexel/s
1290.2 GTexel/s
FP16 (half)
33.59 TFLOPS
82.58 TFLOPS
FP32 (float)
16.79 TFLOPS
82.58 TFLOPS
FP64 (double)
—
1290.2 GFLOPS
Graphics Processor
GPU Name
DG2-512
AD102
GPU Variant
ACM-G10
AD102-300-A1
Architecture
Generation 12.7
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
6 nm
5 nm
Transistors
21.7 billion
76.3 billion
Die Size
406 mm²
609 mm²
Board Design
TDP
150W
450W
Suggested PSU
450 W
850 W
Outputs
1x HDMI 2.13x DisplayPort 2.0
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 8-pin
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.4
Shader Model
6.6
6.8
CUDA
—
8.9
▲ Specs Compare
Data sourced from official specifications and benchmark tests.