NVIDIA TITAN RTX vs NVIDIA A40 PCIe
We compared two Desktop platform GPUs: 24GB VRAM TITAN RTX and 48GB VRAM A40 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA TITAN RTX 's Advantages
Boost Clock has increased by 2% (1770MHz vs 1740MHz)
Lower TDP (280W vs 300W)
NVIDIA A40 PCIe 's Advantages
Released 1 years and 10 months late
More VRAM (48GB vs 24GB)
Larger VRAM bandwidth (695.8GB/s vs 672.0GB/s)
6144 additional rendering cores
Score
Benchmark
FP32 (float)
TITAN RTX
16.31 TFLOPS
A40 PCIe
+129%
37.42 TFLOPS
Blender
TITAN RTX
2999
A40 PCIe
+33%
3990
Graphics Card
Dec 2018
Release Date
Oct 2020
GeForce 20
Generation
Tesla
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1350 MHz
Base Clock
1305 MHz
1770 MHz
Boost Clock
1740 MHz
1750 MHz
Memory Clock
1812 MHz
Memory
24GB
Memory Size
48GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
384bit
672.0GB/s
Bandwidth
695.8GB/s
Render Config
-
-
-
72
SM Count
84
4608
Shading Units
10752
288
TMUs
336
96
ROPs
112
576
Tensor Cores
336
72
RT Cores
84
64 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
6 MB
-
-
-
Theoretical Performance
169.9 GPixel/s
Pixel Rate
194.9 GPixel/s
509.8 GTexel/s
Texture Rate
584.6 GTexel/s
32.62 TFLOPS
FP16 (half)
37.42 TFLOPS
16.31 TFLOPS
FP32 (float)
37.42 TFLOPS
509.8 GFLOPS
FP64 (double)
584.6 GFLOPS
Board Design
280W
TDP
300W
600 W
Suggested PSU
700 W
1x HDMI 2.0
3x DisplayPort 1.4a
1x USB Type-C
Outputs
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
8-pin EPS
Graphics Processor
TU102
GPU Name
GA102
TU102-400-A1
GPU Variant
-
Turing
Architecture
Ampere
TSMC
Foundry
Samsung
12 nm
Process Size
8 nm
18.6 billion
Transistors
28.3 billion
754 mm²
Die Size
628 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
7.5
CUDA
8.6
6.6
Shader Model
6.6
