NVIDIA Quadro FX 380 vs NVIDIA GRID A100B
We compared two Professional market GPUs: 256MB VRAM Quadro FX 380 and 48GB VRAM GRID A100B to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Quadro FX 380 's Advantages
Lower TDP (34W vs 400W)
NVIDIA GRID A100B 's Advantages
Released 11 years and 2 months late
Boost Clock1005MHz
More VRAM (48GB vs 256GB)
Larger VRAM bandwidth (1866GB/s vs 22.40GB/s)
6896 additional rendering cores
Score
Benchmark
FP32 (float)
Quadro FX 380
0.035 TFLOPS
GRID A100B
+39585%
13.89 TFLOPS
Graphics Card
Mar 2009
Release Date
May 2020
Quadro FX
Generation
GRID
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
900 MHz
-
Boost Clock
1005 MHz
700 MHz
Memory Clock
1215 MHz
Memory
256MB
Memory Size
48GB
GDDR3
Memory Type
HBM2e
128bit
Memory Bus
6144bit
22.40GB/s
Bandwidth
1866GB/s
Render Config
-
-
-
2
SM Count
108
16
Shading Units
6912
8
TMUs
432
8
ROPs
192
-
Tensor Cores
432
-
-
-
-
L1 Cache
192 KB (per SM)
32 KB
L2 Cache
48 MB
-
-
-
Theoretical Performance
3.600 GPixel/s
Pixel Rate
193.0 GPixel/s
3.600 GTexel/s
Texture Rate
434.2 GTexel/s
-
FP16 (half)
55.57 TFLOPS
35.20 GFLOPS
FP32 (float)
13.89 TFLOPS
-
FP64 (double)
6.947 TFLOPS
Board Design
34W
TDP
400W
200 W
Suggested PSU
800 W
2x DVI
Outputs
No outputs
None
Power Connectors
None
Graphics Processor
G96
GPU Name
GA100
-
-
-
Tesla
Architecture
Ampere
UMC
Foundry
TSMC
65 nm
Process Size
7 nm
0.314 billion
Transistors
54.2 billion
144 mm²
Die Size
826 mm²
Graphics Features
11.1 (10_0)
DirectX
N/A
3.3
OpenGL
N/A
1.1
OpenCL
3.0
N/A
Vulkan
N/A
1.1
CUDA
8.0
4.0
Shader Model
N/A
