NVIDIA Tesla P40 vs NVIDIA A10G
We compared two Professional market GPUs: 24GB VRAM Tesla P40 and 12GB VRAM A10G to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla P40 's Advantages
More VRAM (24GB vs 12GB)
NVIDIA A10G 's Advantages
Released 4 years and 7 months late
Boost Clock has increased by 12% (1710MHz vs 1531MHz)
Larger VRAM bandwidth (600.2GB/s vs 347.1GB/s)
5376 additional rendering cores
Lower TDP (150W vs 250W)
Score
Benchmark
FP32 (float)
Tesla P40
11.76 TFLOPS
A10G
+168%
31.52 TFLOPS
Blender
Tesla P40
797
A10G
+350%
3589
Graphics Card
Sep 2016
Release Date
Apr 2021
Tesla Pascal
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1303 MHz
Base Clock
1320 MHz
1531 MHz
Boost Clock
1710 MHz
1808 MHz
Memory Clock
1563 MHz
Memory
24GB
Memory Size
12GB
GDDR5
Memory Type
GDDR6
384bit
Memory Bus
384bit
347.1GB/s
Bandwidth
600.2GB/s
Render Config
-
-
-
30
SM Count
72
3840
Shading Units
9216
240
TMUs
288
96
ROPs
96
-
Tensor Cores
288
-
RT Cores
72
48 KB (per SM)
L1 Cache
128 KB (per SM)
3 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
147.0 GPixel/s
Pixel Rate
164.2 GPixel/s
367.4 GTexel/s
Texture Rate
492.5 GTexel/s
183.7 GFLOPS
FP16 (half)
31.52 TFLOPS
11.76 TFLOPS
FP32 (float)
31.52 TFLOPS
367.4 GFLOPS
FP64 (double)
985.0 GFLOPS
Board Design
250W
TDP
150W
600 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
8-pin EPS
Graphics Processor
GP102
GPU Name
GA102
-
GPU Variant
GA102-890-A1
Pascal
Architecture
Ampere
TSMC
Foundry
Samsung
16 nm
Process Size
8 nm
11.8 billion
Transistors
28.3 billion
471 mm²
Die Size
628 mm²
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
6.1
CUDA
8.6
6.7
Shader Model
6.6
