NVIDIA H100 SXM5 vs NVIDIA L40 CNX
GPU · Specs Compare
Graphics Card
Release Date
Mar 2022
Oct 2022
Generation
Tesla Hopper
Tesla Ada
Type
AI GPU
Professional
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1590 MHz
1005 MHz
Boost Clock
1980 MHz
2475 MHz
Memory Clock
1313 MHz
2250 MHz
Memory
Memory Size
80GB
24GB
Memory Type
HBM3
GDDR6
Memory Bus
5120bit
384bit
Bandwidth
3350GB/s
864.0GB/s
Render Config
SM Count
132
142
Shading Units
16896
18176
TMUs
528
568
ROPs
24
192
Tensor Cores
528
568
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
48 MB
RT Cores
—
142
Theoretical Performance
Pixel Rate
47.52 GPixel/s
475.2 GPixel/s
Texture Rate
1045 GTexel/s
1406 GTexel/s
FP16 (half)
267.6 TFLOPS
89.97 TFLOPS
FP32 (float)
66.91 TFLOPS
89.97 TFLOPS
FP64 (double)
33.45 TFLOPS
1406 GFLOPS
Graphics Processor
GPU Name
GH100
AD102
Architecture
Hopper
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
4 nm
4 nm
Transistors
80 billion
76.3 billion
Die Size
814 mm²
608 mm²
GPU Variant
—
AD102-???-A1
Board Design
TDP
700W
300W
Suggested PSU
1100 W
700 W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
8-pin EPS
1x 16-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
CUDA
9.0
8.9
Shader Model
N/A
6.6
▲ Specs Compare
Data sourced from official specifications and benchmark tests.