Home GPU Comparison NVIDIA L40 vs NVIDIA A30 PCIe

NVIDIA L40 vs NVIDIA A30 PCIe

We compared a Professional market GPU: 48GB VRAM L40 and a Desktop platform GPU: 24GB VRAM A30 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L40 's Advantages
Released 1 years and 6 months late
Boost Clock has increased by 73% (2490MHz vs 1440MHz)
More VRAM (48GB vs 24GB)
14592 additional rendering cores
NVIDIA A30 PCIe 's Advantages
Larger VRAM bandwidth (933.1GB/s vs 864.0GB/s)
Lower TDP (165W vs 300W)

Score

Benchmark

FP32 (float)
L40 +777%
90.52 TFLOPS
A30 PCIe
10.32 TFLOPS
Blender
L40 +365%
9486
A30 PCIe
2036
L40
VS

Graphics Card

Oct 2022
Release Date
Apr 2021
Tesla Ada
Generation
Tesla Ampere
Professional
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

735 MHz
Base Clock
930 MHz
2490 MHz
Boost Clock
1440 MHz
2250 MHz
Memory Clock
1215 MHz

Memory

48GB
Memory Size
24GB
GDDR6
Memory Type
HBM2e
384bit
Memory Bus
3072bit
864.0GB/s
Bandwidth
933.1GB/s

Render Config

142
SM Count
56
-
Compute Units
-
18176
Shading Units
3584
568
TMUs
224
192
ROPs
96
568
Tensor Cores
224
142
RT Cores
-
128 KB (per SM)
L1 Cache
192 KB (per SM)
96 MB
L2 Cache
24 MB

Theoretical Performance

478.1 GPixel/s
Pixel Rate
138.2 GPixel/s
1414 GTexel/s
Texture Rate
322.6 GTexel/s
90.52 TFLOPS
FP16 (half)
10.32 TFLOPS
90.52 TFLOPS
FP32 (float)
10.32 TFLOPS
1414 GFLOPS
FP64 (double)
5.161 TFLOPS

Graphics Processor

AD102
GPU Name
GA100
AD102-895-A1
GPU Variant
-
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
TSMC
4 nm
Process Size
7 nm
76.3 billion
Transistors
54.2 billion
608 mm²
Die Size
826 mm²

Board Design

300W
TDP
165W
700 W
Suggested PSU
450 W
4x DisplayPort 1.4a
Outputs
No outputs
1x 16-pin
Power Connectors
8-pin EPS

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
8.0
6.6
Shader Model
N/A

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy