Tesla M40 vs RTX A2000 Embedded
We compared two Professional market GPUs: 12GB VRAM Tesla M40 and 8GB VRAM RTX A2000 Embedded to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla M40 's Advantages
More VRAM (12GB vs 8GB)
Larger VRAM bandwidth (288.4GB/s vs 192.0GB/s)
512 additional rendering cores
RTX A2000 Embedded 's Advantages
Boost Clock has increased by 45% (1612MHz vs 1112MHz)
Lower TDP (60W vs 250W)
Score
Benchmark
FP32 (float)
Tesla M40
6832
RTX A2000 Embedded
+20%
8253
Blender
Tesla M40
106
RTX A2000 Embedded
+1787%
2001
OctaneBench
Tesla M40
123
RTX A2000 Embedded
+120%
271
Graphics Card
Nov 2015
Release Date
Unknown
Tesla Maxwell
Generation
Quadro Mobile
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
948 MHz
Base Clock
1117 MHz
1112 MHz
Boost Clock
1612 MHz
1502 MHz
Memory Clock
1500 MHz
Memory
12GB
Memory Size
8GB
GDDR5
Memory Type
GDDR6
384bit
Memory Bus
128bit
288.4GB/s
Bandwidth
192.0GB/s
Render Config
-
SM Count
20
3072
Shading Units
2560
192
TMUs
80
96
ROPs
48
-
Tensor Cores
80
-
RT Cores
20
48 KB (per SMM)
L1 Cache
128 KB (per SM)
3 MB
L2 Cache
2 MB
Theoretical Performance
106.8 GPixel/s
Pixel Rate
77.38 GPixel/s
213.5 GTexel/s
Texture Rate
129.0 GTexel/s
-
FP16 (half)
8.253 TFLOPS
6.832 TFLOPS
FP32 (float)
8.253 TFLOPS
213.5 GFLOPS
FP64 (double)
129.0 GFLOPS
Board Design
250W
TDP
60W
600 W
Suggested PSU
-
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
None
Graphics Processor
GM200
GPU Name
GA107S
GM200-895-A1
GPU Variant
-
Maxwell 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
8 billion
Transistors
Unknown
601 mm²
Die Size
Unknown
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
5.2
CUDA
8.6
6.7
Shader Model
6.6
