Intel Arc A580 vs NVIDIA GeForce RTX 3070 Ti GA102
We compared two Desktop platform GPUs: 8GB VRAM Arc A580 and 8GB VRAM GeForce RTX 3070 Ti GA102 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Arc A580 's Advantages
Released 1 years late
Boost Clock has increased by 13% (2000MHz vs 1770MHz)
Lower TDP (175W vs 290W)
NVIDIA GeForce RTX 3070 Ti GA102 's Advantages
Larger VRAM bandwidth (608.3GB/s vs 512.0GB/s)
3072 additional rendering cores
Score
Benchmark
FP32 (float)
Arc A580
12.29 TFLOPS
GeForce RTX 3070 Ti GA102
+76%
21.75 TFLOPS
3DMark Time Spy
Arc A580
10855
GeForce RTX 3070 Ti GA102
+37%
14872
3DMark Time Spy Extreme
Arc A580
5186
GeForce RTX 3070 Ti GA102
+43%
7416
3DMark Speed Way
Arc A580
2058
GeForce RTX 3070 Ti GA102
+82%
3761
Graphics Card
Oct 2023
Release Date
Oct 2022
Alchemist(Arc 5)
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1700 MHz
Base Clock
1575 MHz
2000 MHz
Boost Clock
1770 MHz
2000 MHz
Memory Clock
1188 MHz
Memory
8GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
256bit
512.0GB/s
Bandwidth
608.3GB/s
Render Config
-
-
-
-
SM Count
48
3072
Shading Units
6144
192
TMUs
192
96
ROPs
96
384
Tensor Cores
192
24
RT Cores
48
-
L1 Cache
128 KB (per SM)
8 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
192.0 GPixel/s
Pixel Rate
169.9 GPixel/s
384.0 GTexel/s
Texture Rate
339.8 GTexel/s
24.58 TFLOPS
FP16 (half)
21.75 TFLOPS
12.29 TFLOPS
FP32 (float)
21.75 TFLOPS
1.536 TFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
175W
TDP
290W
450 W
Suggested PSU
600 W
1x HDMI 2.13x DisplayPort 2.0
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
2x 8-pin
Power Connectors
1x 12-pin
Graphics Processor
DG2-512
GPU Name
GA102
ACM-G10
GPU Variant
GA102-150-A1
Generation 12.7
Architecture
Ampere
TSMC
Foundry
Samsung
6 nm
Process Size
8 nm
21.7 billion
Transistors
28.3 billion
406 mm²
Die Size
628 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
-
CUDA
8.6
6.6
Shader Model
6.6
