NVIDIA A40 PCIe vs NVIDIA RTX A400
We compared two Desktop platform GPUs: 48GB VRAM A40 PCIe and 4GB VRAM RTX A400 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A40 PCIe 's Advantages
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (695.8GB/s vs 96.00GB/s)
9984 additional rendering cores
NVIDIA RTX A400 's Advantages
Released 3 years and 6 months late
Boost Clock has increased by 1% (1762MHz vs 1740MHz)
Lower TDP (50W vs 300W)
Score
Benchmark
FP32 (float)
A40 PCIe
+1282%
37.42 TFLOPS
RTX A400
2.706 TFLOPS
Graphics Card
Oct 2020
Release Date
Apr 2024
Tesla
Generation
Quadro Ampere(Ax000)
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1305 MHz
Base Clock
1417 MHz
1740 MHz
Boost Clock
1762 MHz
1812 MHz
Memory Clock
1500 MHz
Memory
48GB
Memory Size
4GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
64bit
695.8GB/s
Bandwidth
96.00GB/s
Render Config
-
-
-
84
SM Count
6
10752
Shading Units
768
336
TMUs
24
112
ROPs
16
336
Tensor Cores
24
84
RT Cores
6
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
194.9 GPixel/s
Pixel Rate
28.19 GPixel/s
584.6 GTexel/s
Texture Rate
42.29 GTexel/s
37.42 TFLOPS
FP16 (half)
2.706 TFLOPS
37.42 TFLOPS
FP32 (float)
2.706 TFLOPS
584.6 GFLOPS
FP64 (double)
42.29 GFLOPS
Board Design
300W
TDP
50W
700 W
Suggested PSU
250 W
3x DisplayPort 1.4a
Outputs
4x mini-DisplayPort 1.4a
8-pin EPS
Power Connectors
None
Graphics Processor
GA102
GPU Name
GA107
-
-
-
Ampere
Architecture
Ampere
Samsung
Foundry
Samsung
8 nm
Process Size
8 nm
28.3 billion
Transistors
8.7 billion
628 mm²
Die Size
200 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
8.6
6.6
Shader Model
6.8
