L20 vs P104 100
We compared two Desktop platform GPUs: 48GB VRAM L20 and 4GB VRAM P104 100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
L20 's Advantages
Released 5 years and 11 months late
Boost Clock has increased by 45% (2520MHz vs 1733MHz)
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (864.0GB/s vs 320.3GB/s)
9856 additional rendering cores
Score
Benchmark
FP32 (float)
L20
+791%
59350
P104 100
6655
Graphics Card
Nov 2023
Release Date
Dec 2017
Tesla Ada
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
1440 MHz
Base Clock
1607 MHz
2520 MHz
Boost Clock
1733 MHz
2250 MHz
Memory Clock
1251 MHz
Memory
48GB
Memory Size
4GB
GDDR6
Memory Type
GDDR5X
384bit
Memory Bus
256bit
864.0GB/s
Bandwidth
320.3GB/s
Render Config
92
SM Count
15
11776
Shading Units
1920
368
TMUs
120
128
ROPs
64
368
Tensor Cores
-
92
RT Cores
-
128 KB (per SM)
L1 Cache
48 KB (per SM)
96 MB
L2 Cache
2 MB
Theoretical Performance
322.6 GPixel/s
Pixel Rate
110.9 GPixel/s
927.4 GTexel/s
Texture Rate
208.0 GTexel/s
59.35 TFLOPS
FP16 (half)
104.0 GFLOPS
59.35 TFLOPS
FP32 (float)
6.655 TFLOPS
927.4 GFLOPS
FP64 (double)
208.0 GFLOPS
Board Design
275W
TDP
Unknown
600 W
Suggested PSU
200 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
1x 8-pin
Graphics Processor
AD102
GPU Name
GP104
AD102
GPU Variant
GP104-100-A1
Ada Lovelace
Architecture
Pascal
TSMC
Foundry
TSMC
5 nm
Process Size
16 nm
76.3 billion
Transistors
7.2 billion
609 mm²
Die Size
314 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.9
CUDA
6.1
6.7
Shader Model
6.8
