NVIDIA A10 PCIe vs NVIDIA Quadro Plex 2100 S4
We compared two Professional market GPUs: 24GB VRAM A10 PCIe and 1536MB VRAM Quadro Plex 2100 S4 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A10 PCIe 's Advantages
Released 12 years and 9 months late
Boost Clock1695MHz
More VRAM (24GB vs 1536GB)
Larger VRAM bandwidth (600.2GB/s vs 76.80GB/s)
9088 additional rendering cores
Lower TDP (150W vs 640W)
Score
Benchmark
FP32 (float)
A10 PCIe
+8928%
31.24 TFLOPS
Quadro Plex 2100 S4
0.346 TFLOPS
Graphics Card
Apr 2021
Release Date
Jul 2008
Tesla
Generation
Quadro Plex
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x16
Clock Speeds
885 MHz
Base Clock
-
1695 MHz
Boost Clock
-
1563 MHz
Memory Clock
800 MHz
Memory
24GB
Memory Size
1536MB
GDDR6
Memory Type
GDDR3
384bit
Memory Bus
384bit
600.2GB/s
Bandwidth
76.80GB/s
Render Config
-
-
-
72
SM Count
16
9216
Shading Units
128
288
TMUs
32
96
ROPs
24
288
Tensor Cores
-
72
RT Cores
-
128 KB (per SM)
L1 Cache
-
6 MB
L2 Cache
96 KB
-
-
-
Theoretical Performance
162.7 GPixel/s
Pixel Rate
14.40 GPixel/s
488.2 GTexel/s
Texture Rate
38.40 GTexel/s
31.24 TFLOPS
FP16 (half)
-
31.24 TFLOPS
FP32 (float)
345.6 GFLOPS
976.3 GFLOPS
FP64 (double)
-
Board Design
150W
TDP
640W
450 W
Suggested PSU
1000 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
-
Graphics Processor
GA102
GPU Name
G80
GA102-890-A1
GPU Variant
-
Ampere
Architecture
Tesla
Samsung
Foundry
TSMC
8 nm
Process Size
90 nm
28.3 billion
Transistors
0.681 billion
628 mm²
Die Size
484 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
11.1 (10_0)
4.6
OpenGL
3.3
3.0
OpenCL
1.1 (1.0)
1.3
Vulkan
N/A
8.6
CUDA
1.0
6.6
Shader Model
4.0
