L20 vs Arc B580
We compared two Desktop platform GPUs: 48GB VRAM L20 and 12GB VRAM Arc B580 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L20 's Advantages
More VRAM (48GB vs 12GB)
Larger VRAM bandwidth (864.0GB/s vs 456.0GB/s)
9216 additional rendering cores
Arc B580 's Advantages
Released 1 years and 1 months late
Boost Clock has increased by 6% (2670MHz vs 2520MHz)
Lower TDP (190W vs 275W)
Score
Benchmark
FP32 (float)
L20
+334%
59350
Arc B580
13670
Graphics Card
Nov 2023
Release Date
Dec 2024
Tesla Ada
Generation
Battlemage
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x8
Clock Speeds
1440 MHz
Base Clock
2670 MHz
2520 MHz
Boost Clock
2670 MHz
2250 MHz
Memory Clock
2375 MHz
Memory
48GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6
384bit
Memory Bus
192bit
864.0GB/s
Bandwidth
456.0GB/s
Render Config
92
SM Count
-
11776
Shading Units
2560
368
TMUs
160
128
ROPs
80
368
Tensor Cores
160
92
RT Cores
20
128 KB (per SM)
L1 Cache
256 KB (per EU)
96 MB
L2 Cache
18 MB
Theoretical Performance
322.6 GPixel/s
Pixel Rate
213.6 GPixel/s
927.4 GTexel/s
Texture Rate
427.2 GTexel/s
59.35 TFLOPS
FP16 (half)
27.34 TFLOPS
59.35 TFLOPS
FP32 (float)
13.67 TFLOPS
927.4 GFLOPS
FP64 (double)
1.709 TFLOPS
Board Design
275W
TDP
190W
600 W
Suggested PSU
450 W
4x DisplayPort 1.4a
Outputs
1x HDMI 2.1a
3x DisplayPort 2.1
1x 16-pin
Power Connectors
1x 8-pin
Graphics Processor
AD102
GPU Name
BMG-G21
AD102
GPU Variant
SRPMF
Ada Lovelace
Architecture
Xe2
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
76.3 billion
Transistors
19.6 billion
609 mm²
Die Size
272 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
1.4
8.9
CUDA
-
6.7
Shader Model
6.6
