Intel Data Center GPU Flex 170 vs NVIDIA A100 PCIe 80 GB
GPU Specs Compare
Graphics Card
Release Date
Aug 2022
Jun 2021
Generation
Data Center GPU
Tesla Ampere(Axx)
Type
Professional
Professional
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1950 MHz
1065 MHz
Boost Clock
2050 MHz
1410 MHz
Memory Clock
2000 MHz
1512 MHz
Memory
Memory Size
16GB
80GB
Memory Type
GDDR6
HBM2e
Memory Bus
256bit
5120bit
Bandwidth
512.0GB/s
1.94TB/s
Render Config
Shading Units
4096
6912
TMUs
256
432
ROPs
128
160
RT Cores
32
-
L2 Cache
16 MB
80 MB
SM Count
-
108
Tensor Cores
-
432
L1 Cache
-
192 KB (per SM)
Theoretical Performance
Pixel Rate
262.4 GPixel/s
225.6 GPixel/s
Texture Rate
524.8 GTexel/s
609.1 GTexel/s
FP16 (half)
33.59 TFLOPS
77.97 TFLOPS
FP32 (float)
16.79 TFLOPS
19.49 TFLOPS
FP64 (double)
-
9.746 TFLOPS
Graphics Processor
GPU Name
DG2-512
GA100
GPU Variant
ACM-G10
-
Architecture
Generation 12.7
Ampere
Foundry
TSMC
TSMC
Process Size
6 nm
7 nm
Transistors
21.7 billion
54.2 billion
Die Size
406 mm²
826 mm²
Board Design
TDP
150W
300W
Suggested PSU
450 W
700 W
Outputs
1x HDMI 2.13x DisplayPort 2.0
No outputs
Power Connectors
1x 8-pin
8-pin EPS
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
Shader Model
6.6
N/A
CUDA
-
8.0
📊 Benchmark
OctaneBench
-
310
Blender
-
3,722