Home GPU Comparison NVIDIA RTX 3500 Embedded Ada Generation vs Intel Arc A780

NVIDIA RTX 3500 Embedded Ada Generation vs Intel Arc A780

We compared two Desktop platform GPUs: 12GB VRAM RTX 3500 Embedded Ada Generation and 16GB VRAM Arc A780 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA RTX 3500 Embedded Ada Generation 's Advantages
Boost Clock has increased by 2% (2250MHz vs 2200MHz)
1024 additional rendering cores
Lower TDP (100W vs 200W)
Intel Arc A780 's Advantages
More VRAM (16GB vs 12GB)
Larger VRAM bandwidth (559.6GB/s vs 432.0GB/s)

Score

Benchmark

FP32 (float)
RTX 3500 Embedded Ada Generation +27%
23.04 TFLOPS
Arc A780
18.02 TFLOPS
VS

Graphics Card

Mar 2023
Release Date
Unknown
Quadro Ada-M
Generation
Alchemist(Arc 7)
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1725 MHz
Base Clock
2200 MHz
2250 MHz
Boost Clock
2200 MHz
2250 MHz
Memory Clock
1093 MHz

Memory

12GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6X
192bit
Memory Bus
256bit
432.0GB/s
Bandwidth
559.6GB/s

Render Config

-
-
-
40
SM Count
-
5120
Shading Units
4096
160
TMUs
256
64
ROPs
128
160
Tensor Cores
512
40
RT Cores
32
128 KB (per SM)
L1 Cache
-
48 MB
L2 Cache
16 MB
-
-
-

Theoretical Performance

144.0 GPixel/s
Pixel Rate
281.6 GPixel/s
360.0 GTexel/s
Texture Rate
563.2 GTexel/s
23.04 TFLOPS
FP16 (half)
36.04 TFLOPS
23.04 TFLOPS
FP32 (float)
18.02 TFLOPS
360.0 GFLOPS
FP64 (double)
2.253 TFLOPS

Board Design

100W
TDP
200W
300 W
Suggested PSU
550 W
No outputs
Outputs
1x HDMI 2.13x DisplayPort 2.0
None
Power Connectors
2x 8-pin

Graphics Processor

AD104
GPU Name
DG2-512
-
GPU Variant
ACM-G10
Ada Lovelace
Architecture
Generation 12.7
TSMC
Foundry
TSMC
5 nm
Process Size
6 nm
35.8 billion
Transistors
21.7 billion
294 mm²
Die Size
406 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
8.9
CUDA
-
6.7
Shader Model
6.6

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy