Intel Arc B580 vs NVIDIA GeForce GTX 470
We compared two Desktop platform GPUs: 12GB VRAM Arc B580 and 1280MB VRAM GeForce GTX 470 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Arc B580 's Advantages
Released 14 years and 9 months late
Boost Clock2670MHz
More VRAM (12GB vs 1280GB)
Larger VRAM bandwidth (456.0GB/s vs 133.9GB/s)
2112 additional rendering cores
Lower TDP (190W vs 215W)
Score
Benchmark
FP32 (float)
Arc B580
+1155%
13.67 TFLOPS
GeForce GTX 470
1.089 TFLOPS
Graphics Card
Dec 2024
Release Date
Mar 2010
Battlemage
Generation
GeForce 400
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 2.0 x16
Clock Speeds
2670 MHz
Base Clock
-
2670 MHz
Boost Clock
-
2375 MHz
Memory Clock
837 MHz
Memory
12GB
Memory Size
1280MB
GDDR6
Memory Type
GDDR5
192bit
Memory Bus
320bit
456.0GB/s
Bandwidth
133.9GB/s
Render Config
-
-
-
-
SM Count
14
2560
Shading Units
448
160
TMUs
56
80
ROPs
40
160
Tensor Cores
-
20
RT Cores
-
256 KB (per EU)
L1 Cache
64 KB (per SM)
18 MB
L2 Cache
640 KB
-
-
-
Theoretical Performance
213.6 GPixel/s
Pixel Rate
17.02 GPixel/s
427.2 GTexel/s
Texture Rate
34.05 GTexel/s
27.34 TFLOPS
FP16 (half)
-
13.67 TFLOPS
FP32 (float)
1089 GFLOPS
1.709 TFLOPS
FP64 (double)
136.1 GFLOPS
Board Design
190W
TDP
215W
450 W
Suggested PSU
550 W
1x HDMI 2.1a
3x DisplayPort 2.1
Outputs
2x DVI
1x mini-HDMI 1.3a
1x 8-pin
Power Connectors
2x 6-pin
Graphics Processor
BMG-G21
GPU Name
GF100
SRPMF
GPU Variant
GF100-275-A3
Xe2
Architecture
Fermi
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
19.6 billion
Transistors
3.1 billion
272 mm²
Die Size
529 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
1.1
1.4
Vulkan
N/A
-
CUDA
2.0
6.6
Shader Model
5.1
