Home GPU Comparison NVIDIA L40 vs NVIDIA H100 PCIe

NVIDIA L40 vs NVIDIA H100 PCIe

AI GPU We compared a Professional market GPU: 48GB VRAM L40 and a GPU: 80GB VRAM H100 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L40 's Advantages
Released 7 months late
Boost Clock has increased by 42% (2490MHz vs 1755MHz)
3584 additional rendering cores
Lower TDP (300W vs 350W)
NVIDIA H100 PCIe 's Advantages
More VRAM (80GB vs 48GB)
Larger VRAM bandwidth (2039GB/s vs 864.0GB/s)

Score

Benchmark

FP32 (float)
L40 +76%
90.52 TFLOPS
H100 PCIe
51.22 TFLOPS
Blender
L40 +95%
9486
H100 PCIe
4845
L40
VS

Graphics Card

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

Clock Speeds

735 MHz
Base Clock
1095 MHz
2490 MHz
Boost Clock
1755 MHz
2250 MHz
Memory Clock
1593 MHz

Memory

48GB
Memory Size
80GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
5120bit
864.0GB/s
Bandwidth
2039GB/s

Render Config

142
SM Count
114
-
Compute Units
-
18176
Shading Units
14592
568
TMUs
456
192
ROPs
24
568
Tensor Cores
456
142
RT Cores
-
128 KB (per SM)
L1 Cache
256 KB (per SM)
96 MB
L2 Cache
50 MB

Theoretical Performance

478.1 GPixel/s
Pixel Rate
42.12 GPixel/s
1414 GTexel/s
Texture Rate
800.3 GTexel/s
90.52 TFLOPS
FP16 (half)
204.9 TFLOPS
90.52 TFLOPS
FP32 (float)
51.22 TFLOPS
1414 GFLOPS
FP64 (double)
25.61 TFLOPS

Graphics Processor

AD102
GPU Name
GH100
AD102-895-A1
GPU Variant
-
Ada Lovelace
Architecture
Hopper
TSMC
Foundry
TSMC
4 nm
Process Size
4 nm
76.3 billion
Transistors
80 billion
608 mm²
Die Size
814 mm²

Board Design

300W
TDP
350W
700 W
Suggested PSU
750 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
1x 16-pin

Graphics Features

12 Ultimate (12_2)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.3
Vulkan
N/A
8.9
CUDA
9.0
6.6
Shader Model
N/A

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy