Tesla D870 vs RTX A4500 Embedded
We compared two Professional market GPUs: 1536MB VRAM Tesla D870 and 16GB VRAM RTX A4500 Embedded to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
RTX A4500 Embedded 's Advantages
Released 14 years and 10 months late
Boost Clock1215MHz
More VRAM (16GB vs 1536GB)
Larger VRAM bandwidth (384.0GB/s vs 76.80GB/s)
5760 additional rendering cores
Lower TDP (80W vs 520W)
Score
Benchmark
FP32 (float)
Tesla D870
346
RTX A4500 Embedded
+4035%
14310
Graphics Card
May 2007
Release Date
Mar 2022
Tesla
Generation
Quadro Ampere-M
Professional
Type
Professional
PCIe 1.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
510 MHz
-
Boost Clock
1215 MHz
800 MHz
Memory Clock
1500 MHz
Memory
1536MB
Memory Size
16GB
GDDR3
Memory Type
GDDR6
384bit
Memory Bus
256bit
76.80GB/s
Bandwidth
384.0GB/s
Render Config
16
SM Count
46
128
Shading Units
5888
32
TMUs
184
24
ROPs
96
-
Tensor Cores
184
-
RT Cores
46
-
L1 Cache
128 KB (per SM)
96 KB
L2 Cache
4 MB
Theoretical Performance
14.40 GPixel/s
Pixel Rate
116.6 GPixel/s
38.40 GTexel/s
Texture Rate
223.6 GTexel/s
-
FP16 (half)
14.31 TFLOPS
345.6 GFLOPS
FP32 (float)
14.31 TFLOPS
-
FP64 (double)
223.6 GFLOPS
Board Design
520W
TDP
80W
900 W
Suggested PSU
-
No outputs
Outputs
Portable Device Dependent
-
Power Connectors
None
Graphics Processor
G80
GPU Name
GA104
Tesla
Architecture
Ampere
TSMC
Foundry
Samsung
90 nm
Process Size
8 nm
0.681 billion
Transistors
17.4 billion
484 mm²
Die Size
392 mm²
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
6.7
