NVIDIA GRID A100A vs Intel Data Center GPU Flex 170
We compared two Professional market GPUs: 48GB VRAM GRID A100A and 16GB VRAM Data Center GPU Flex 170 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID A100A 's Advantages
More VRAM (48GB vs 16GB)
Larger VRAM bandwidth (1866GB/s vs 512.0GB/s)
2816 additional rendering cores
Intel Data Center GPU Flex 170 's Advantages
Released 2 years and 3 months late
Boost Clock has increased by 104% (2050MHz vs 1005MHz)
Lower TDP (150W vs 400W)
Score
Benchmark
FP32 (float)
GRID A100A
13.89 TFLOPS
Data Center GPU Flex 170
+20%
16.79 TFLOPS
Graphics Card
May 2020
Release Date
Aug 2022
GRID
Generation
Data Center GPU
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
900 MHz
Base Clock
1950 MHz
1005 MHz
Boost Clock
2050 MHz
1215 MHz
Memory Clock
2000 MHz
Memory
48GB
Memory Size
16GB
HBM2e
Memory Type
GDDR6
6144bit
Memory Bus
256bit
1866GB/s
Bandwidth
512.0GB/s
Render Config
-
-
-
108
SM Count
-
6912
Shading Units
4096
432
TMUs
256
192
ROPs
128
432
Tensor Cores
-
-
RT Cores
32
192 KB (per SM)
L1 Cache
-
48 MB
L2 Cache
16 MB
-
-
-
Theoretical Performance
193.0 GPixel/s
Pixel Rate
262.4 GPixel/s
434.2 GTexel/s
Texture Rate
524.8 GTexel/s
55.57 TFLOPS
FP16 (half)
33.59 TFLOPS
13.89 TFLOPS
FP32 (float)
16.79 TFLOPS
6.947 TFLOPS
FP64 (double)
-
Board Design
400W
TDP
150W
800 W
Suggested PSU
450 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 2.0
None
Power Connectors
1x 8-pin
Graphics Processor
GA100
GPU Name
DG2-512
-
GPU Variant
ACM-G10
Ampere
Architecture
Generation 12.7
TSMC
Foundry
TSMC
7 nm
Process Size
6 nm
54.2 billion
Transistors
21.7 billion
826 mm²
Die Size
406 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
8.0
CUDA
-
N/A
Shader Model
6.6
