NVIDIA A10 PCIe vs NVIDIA L40G
We compared two Professional market GPUs: 24GB VRAM A10 PCIe and 24GB VRAM L40G to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A10 PCIe 's Advantages
Lower TDP (150W vs 300W)
NVIDIA L40G 's Advantages
Released 1 years and 6 months late
Boost Clock has increased by 46% (2475MHz vs 1695MHz)
Larger VRAM bandwidth (864.0GB/s vs 600.2GB/s)
8960 additional rendering cores
Score
Benchmark
FP32 (float)
A10 PCIe
31.24 TFLOPS
L40G
+187%
89.97 TFLOPS
Graphics Card
Apr 2021
Release Date
Oct 2022
Tesla
Generation
Tesla Ada
Professional
Type
Professional
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
885 MHz
Base Clock
1005 MHz
1695 MHz
Boost Clock
2475 MHz
1563 MHz
Memory Clock
2250 MHz
Memory
24GB
Memory Size
24GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
384bit
600.2GB/s
Bandwidth
864.0GB/s
Render Config
-
-
-
72
SM Count
142
9216
Shading Units
18176
288
TMUs
568
96
ROPs
192
288
Tensor Cores
568
72
RT Cores
142
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
48 MB
-
-
-
Theoretical Performance
162.7 GPixel/s
Pixel Rate
475.2 GPixel/s
488.2 GTexel/s
Texture Rate
1406 GTexel/s
31.24 TFLOPS
FP16 (half)
89.97 TFLOPS
31.24 TFLOPS
FP32 (float)
89.97 TFLOPS
976.3 GFLOPS
FP64 (double)
1406 GFLOPS
Board Design
150W
TDP
300W
450 W
Suggested PSU
700 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 16-pin
Graphics Processor
GA102
GPU Name
AD102
GA102-890-A1
GPU Variant
AD102-???-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
4 nm
28.3 billion
Transistors
76.3 billion
628 mm²
Die Size
608 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
8.9
6.6
Shader Model
6.6
