NVIDIA L20 vs AMD Radeon HD 6850 X2
We compared two Desktop platform GPUs: 48GB VRAM L20 and 2GB VRAM Radeon HD 6850 X2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA L20 's Advantages
Released 12 years and 2 months late
Boost Clock2520MHz
More VRAM (48GB vs 2GB)
Larger VRAM bandwidth (864.0GB/s vs 134.4GB/s)
10816 additional rendering cores
AMD Radeon HD 6850 X2 's Advantages
Lower TDP (254W vs 275W)
Score
Benchmark
FP32 (float)
L20
+3763%
59.35 TFLOPS
Radeon HD 6850 X2
1.536 TFLOPS
Graphics Card
Nov 2023
Release Date
Sep 2011
Tesla Ada
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1440 MHz
Base Clock
-
2520 MHz
Boost Clock
-
2250 MHz
Memory Clock
1050 MHz
Memory
48GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
256bit
864.0GB/s
Bandwidth
134.4GB/s
Render Config
-
Compute Units
12
92
SM Count
-
11776
Shading Units
960
368
TMUs
48
128
ROPs
32
368
Tensor Cores
-
92
RT Cores
-
128 KB (per SM)
L1 Cache
8 KB (per CU)
96 MB
L2 Cache
512 KB
-
-
-
Theoretical Performance
322.6 GPixel/s
Pixel Rate
25.60 GPixel/s
927.4 GTexel/s
Texture Rate
38.40 GTexel/s
59.35 TFLOPS
FP16 (half)
-
59.35 TFLOPS
FP32 (float)
1.536 TFLOPS
927.4 GFLOPS
FP64 (double)
-
Board Design
275W
TDP
254W
600 W
Suggested PSU
600 W
4x DisplayPort 1.4a
Outputs
2x DVI
1x HDMI 1.3a
1x DisplayPort 1.1
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD102
GPU Name
Barts
AD102
GPU Variant
Barts PRO
(215-0798006)
Ada Lovelace
Architecture
TeraScale 2
TSMC
Foundry
TSMC
5 nm
Process Size
40 nm
76.3 billion
Transistors
1.7 billion
609 mm²
Die Size
255 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
8.9
CUDA
-
6.7
Shader Model
5.0
