NVIDIA Tesla C870 vs NVIDIA RTX A1000 Embedded
We compared two Professional market GPUs: 1536MB VRAM Tesla C870 and 4GB VRAM RTX A1000 Embedded to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA RTX A1000 Embedded 's Advantages
Released 14 years and 8 months late
Boost Clock1627MHz
More VRAM (4GB vs 1536GB)
Larger VRAM bandwidth (224.0GB/s vs 76.80GB/s)
1920 additional rendering cores
Lower TDP (60W vs 171W)
Score
Benchmark
FP32 (float)
Tesla C870
0.346 TFLOPS
RTX A1000 Embedded
+1826%
6.664 TFLOPS
Graphics Card
May 2007
Release Date
Jan 2022
Tesla
Generation
Quadro Mobile
Professional
Type
Professional
PCIe 1.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1192 MHz
-
Boost Clock
1627 MHz
800 MHz
Memory Clock
1750 MHz
Memory
1536MB
Memory Size
4GB
GDDR3
Memory Type
GDDR6
384bit
Memory Bus
128bit
76.80GB/s
Bandwidth
224.0GB/s
Render Config
-
-
-
16
SM Count
16
128
Shading Units
2048
32
TMUs
64
24
ROPs
48
-
Tensor Cores
64
-
RT Cores
16
-
L1 Cache
128 KB (per SM)
96 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
14.40 GPixel/s
Pixel Rate
78.10 GPixel/s
38.40 GTexel/s
Texture Rate
104.1 GTexel/s
-
FP16 (half)
6.664 TFLOPS
345.6 GFLOPS
FP32 (float)
6.664 TFLOPS
-
FP64 (double)
104.1 GFLOPS
Board Design
171W
TDP
60W
450 W
Suggested PSU
-
No outputs
Outputs
No outputs
2x 6-pin
Power Connectors
None
Graphics Processor
G80
GPU Name
GA107S
-
-
-
Tesla
Architecture
Ampere
TSMC
Foundry
Samsung
90 nm
Process Size
8 nm
0.681 billion
Transistors
Unknown
484 mm²
Die Size
Unknown
Graphics Features
11.1 (10_0)
DirectX
12 Ultimate (12_2)
3.3
OpenGL
4.6
1.1 (1.0)
OpenCL
3.0
N/A
Vulkan
1.3
1.0
CUDA
8.6
4.0
Shader Model
6.6
