Home GPU Comparison NVIDIA H100 SXM5 80 GB vs NVIDIA L40S

NVIDIA H100 SXM5 80 GB vs NVIDIA L40S

AI GPU We compared a GPU: 80GB VRAM H100 SXM5 80 GB and a Professional market GPU: 48GB VRAM L40S to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA H100 SXM5 80 GB 's Advantages
More VRAM (80GB vs 48GB)
Larger VRAM bandwidth (1681GB/s vs 864.0GB/s)
NVIDIA L40S 's Advantages
Boost Clock has increased by 27% (2520MHz vs 1980MHz)
1280 additional rendering cores
Lower TDP (300W vs 700W)

Score

Benchmark

FP32 (float)
H100 SXM5 80 GB
66.91 TFLOPS
L40S +36%
91.61 TFLOPS
VS

Graphics Card

Mar 2023
Release Date
Oct 2022
Tesla Hopper
Generation
Tesla Ada
AI GPU
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

1590 MHz
Base Clock
1110 MHz
1980 MHz
Boost Clock
2520 MHz
1313 MHz
Memory Clock
2250 MHz

Memory

80GB
Memory Size
48GB
HBM3
Memory Type
GDDR6
5120bit
Memory Bus
384bit
1681GB/s
Bandwidth
864.0GB/s

Render Config

132
SM Count
142
-
Compute Units
-
16896
Shading Units
18176
528
TMUs
568
24
ROPs
192
528
Tensor Cores
568
-
RT Cores
142
256 KB (per SM)
L1 Cache
128 KB (per SM)
50 MB
L2 Cache
48 MB

Theoretical Performance

47.52 GPixel/s
Pixel Rate
483.8 GPixel/s
1045 GTexel/s
Texture Rate
1431 GTexel/s
267.6 TFLOPS
FP16 (half)
91.61 TFLOPS
66.91 TFLOPS
FP32 (float)
91.61 TFLOPS
33.45 TFLOPS
FP64 (double)
1431 GFLOPS

Graphics Processor

GH100
GPU Name
AD102
-
GPU Variant
AD102-???-A1
Hopper
Architecture
Ada Lovelace
TSMC
Foundry
TSMC
4 nm
Process Size
5 nm
80 billion
Transistors
76.3 billion
814 mm²
Die Size
609 mm²

Board Design

700W
TDP
300W
1100 W
Suggested PSU
700 W
No outputs
Outputs
1x HDMI 2.1 3x DisplayPort 1.4a
8-pin EPS
Power Connectors
1x 16-pin

Graphics Features

N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
9.0
CUDA
8.9
N/A
Shader Model
6.7

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy