NVIDIA L40S vs AMD Radeon Instinct MI25

VS

We compared two Professional market GPUs: 48GB VRAM L40S and 16GB VRAM Radeon Instinct MI25 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA L40S 's Advantages

Released 5 years and 4 months late

Boost Clock has increased by 68% (2520MHz vs 1500MHz)

More VRAM (48GB vs 16GB)

Larger VRAM bandwidth (864.0GB/s vs 436.2GB/s)

14080 additional rendering cores

Score

Benchmark

FP32 (float)

L40S +645%

91.61 TFLOPS

Radeon Instinct MI25

12.29 TFLOPS

L40S

VS

Radeon Instinct MI25

Graphics Card

Oct 2022

Release Date

Jun 2017

Tesla Ada

Generation

Radeon Instinct

Professional

Type

Professional

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1110 MHz

Base Clock

1400 MHz

2520 MHz

Boost Clock

1500 MHz

2250 MHz

Memory Clock

852 MHz

Memory

48GB

Memory Size

16GB

GDDR6

Memory Type

HBM2

384bit

Memory Bus

2048bit

864.0GB/s

Bandwidth

436.2GB/s

Render Config

142

SM Count

-

Compute Units

64

18176

Shading Units

4096

568

TMUs

256

192

ROPs

64

568

Tensor Cores

-

142

RT Cores

-

128 KB (per SM)

L1 Cache

16 KB (per CU)

48 MB

L2 Cache

4 MB

Theoretical Performance

483.8 GPixel/s

Pixel Rate

96.00 GPixel/s

1431 GTexel/s

Texture Rate

384.0 GTexel/s

91.61 TFLOPS

FP16 (half)

24.58 TFLOPS

91.61 TFLOPS

FP32 (float)

12.29 TFLOPS

1431 GFLOPS

FP64 (double)

768.0 GFLOPS

Graphics Processor

AD102

GPU Name

Vega 10

AD102-???-A1

GPU Variant

Vega 10 XT GL (215-0894124)

Ada Lovelace

Architecture

GCN 5.0

TSMC

Foundry

GlobalFoundries

5 nm

Process Size

14 nm

76.3 billion

Transistors

12.5 billion

609 mm²

Die Size

495 mm²

Board Design

300W

TDP

300W

700 W

Suggested PSU

700 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

No outputs

1x 16-pin

Power Connectors

2x 8-pin

Graphics Features

12 Ultimate (12_2)

DirectX

12 (12_1)

4.6

OpenGL

4.6

3.0

OpenCL

2.1

1.3

Vulkan

1.2

8.9

CUDA

-

6.7

Shader Model

6.4

Related GPU Comparisons

1

NVIDIA L40 vs NVIDIA L40S

2

NVIDIA RTX 6000 Ada Generation vs NVIDIA L40S

3

NVIDIA GeForce RTX 4090 vs NVIDIA L40S

4

NVIDIA RTX A6000 vs NVIDIA L40S

5

NVIDIA A100 PCIe 80 GB vs NVIDIA L40S

6

NVIDIA L40S vs NVIDIA L4

7

NVIDIA GeForce RTX 4090 Ti vs NVIDIA L40S

8

NVIDIA L40S vs NVIDIA Quadro M3000 SE

9

NVIDIA L40S vs NVIDIA Quadro GP100

10

NVIDIA L40S vs NVIDIA Quadro FX 370 LP

Related News

1

Snapdragon 8 Gen 4 to Feature Frame Interpolation for GPU: A Game-Changing Experience

2

Intel Adds 5 New Device IDs to Latest Linux Xe Kernel in Preparation for Battlemage

3

Ryzen AI 9 365 Benchmark Results Leaked: Significant Improvements in Multi-Core and IPC Performance Over Previous Generation

4

Concerns Raised by Unstable 13th/14th Gen Core CPUs: Motherboard Manufacturers Worry About Impact on Arrow Lake Release and Sales

5

Do You Really Know What a "Rendering Engine" Is? Read This Article to Understand All About It

6

New AMD Zen5 Ryzen 9000 Motherboards X870E/X870 to Adopt USB4! But You’ll Have to Wait Two More Months

7

Surpassing RTX 2050! Intel's Next-Gen Integrated Graphics Benchmark Closely Approaches AMD

8

New Benchmarks for AMD Ryzen AI 9 HX 370 Revealed: Single-Core Parity with R9 7945HX3D, Multi-Core Still Lower

9

X3D Performance Beyond Words! AMD Ryzen 7 9700X May Unlock Power Consumption: From 65W to 120W

10

First Benchmark Leak of Intel Core Ultra 7 268V: Single-Core Performance Soars by 20%, Still Lags Behind AMD