GeForce RTX 3070 and Arc A380 - video card comparison
Passmark - benchmark score GeForce RTX 3070 vs Arc A380
GeForce RTX 3070
23060
Arc A380
6425
GeForce RTX 3070
Arc A380
Architecture
Ampere (2020−2022)
Xe HPG (2020−2022)
GPU code name
Ampere GA104
DG2-128
Market segment
Desktop
Desktop
Release date
September 2020
June 2022
Interface
PCIe 4.0 x16
PCIe 4.0 x8
Supplementary power connectors
1x 12-pin
1x 8-pin
Boost clock speed
1725 MHz
2050 MHz
Core clock speed
1500 MHz
2000 MHz
Manufacturing process technology
8 nm
6 nm
Number of transistors
17,400 million
7,200 million
Pipelines / CUDA cores
5888
1024
Power consumption (TDP)
220 Watt
75 Watt
Texture fill rate
317.4
131.2
Memory type
GDDR6
GDDR6
Maximum RAM amount
8 GB
6 GB
Memory bus width
256 Bit
96 Bit
Memory clock speed
14000 MHz
15500 MHz
Memory bandwidth
448.0 GB/s
186.0 GB/s
Shared memory
-
-
Display Connectors
1x HDMI, 3x DisplayPort
1x HDMI 2.1, 3x DisplayPort 2.0
HDMI
+
+
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
CUDA
8.5
-
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.5
6.6
Vulkan
1.2
1.3