Home GPU Comparison NVIDIA Tesla PG503 216 vs NVIDIA L40S

NVIDIA Tesla PG503 216 vs NVIDIA L40S

We compared two Professional market GPUs: 32GB VRAM Tesla PG503 216 and 48GB VRAM L40S to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA Tesla PG503 216 's Advantages
Larger VRAM bandwidth (1133GB/s vs 864.0GB/s)
Lower TDP (250W vs 300W)
NVIDIA L40S 's Advantages
Released 2 years and 11 months late
Boost Clock has increased by 65% (2520MHz vs 1530MHz)
More VRAM (48GB vs 32GB)
13056 additional rendering cores

Score

Benchmark

FP32 (float)
Tesla PG503 216
15.67 TFLOPS
L40S +484%
91.61 TFLOPS
VS

Graphics Card

Nov 2019
Release Date
Oct 2022
Tesla
Generation
Tesla Ada
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1312 MHz
Base Clock
1110 MHz
1530 MHz
Boost Clock
2520 MHz
1106 MHz
Memory Clock
2250 MHz

Memory

32GB
Memory Size
48GB
HBM2
Memory Type
GDDR6
4096bit
Memory Bus
384bit
1133GB/s
Bandwidth
864.0GB/s

Render Config

-
-
-
80
SM Count
142
5120
Shading Units
18176
320
TMUs
568
128
ROPs
192
640
Tensor Cores
568
-
RT Cores
142
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
48 MB
-
-
-

Theoretical Performance

195.8 GPixel/s
Pixel Rate
483.8 GPixel/s
489.6 GTexel/s
Texture Rate
1431 GTexel/s
31.33 TFLOPS
FP16 (half)
91.61 TFLOPS
15.67 TFLOPS
FP32 (float)
91.61 TFLOPS
7.834 TFLOPS
FP64 (double)
1431 GFLOPS

Board Design

250W
TDP
300W
600 W
Suggested PSU
700 W
No outputs
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
None
Power Connectors
1x 16-pin

Graphics Processor

GV100
GPU Name
AD102
-
GPU Variant
AD102-???-A1
Volta
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
12 nm
Process Size
5 nm
21.1 billion
Transistors
76.3 billion
815 mm²
Die Size
609 mm²

Graphics Features

12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.0
CUDA
8.9
6.6
Shader Model
6.7

Related GPU Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy