GPUDatacenterReleased Sep 20, 2022

NVIDIA L40

48 GB GDDR6 ECC · 384-bit · 18,176 cores

A dual-slot, passively cooled Ada Lovelace data center GPU built on the AD102 die, announced in September 2022 for graphics, rendering, virtual workstations and NVIDIA Omniverse alongside AI inference. It keeps four DisplayPort 1.4a outputs and 48 GB of ECC-protected GDDR6 within a 300 W budget.

General

Manufacturer: NVIDIA
Model: L40
Segment: Datacenter
GPU chip: AD102
Architecture: Ada Lovelace
Release date: Sep 20, 2022
Price: Search on Amazon

Memory

Memory size: 48 GB
Memory type: GDDR6 ECC
Bus width: 384-bit
Bandwidth: 864 GB/s
Memory clock: 2,250 MHz

Clocks & silicon

GPU clock: —
Boost clock: —
Shader units: 18,176 CUDA Cores
Tensor / AI cores: 568
RT cores: 142
Transistors: 76.3 billion
Technology (nm): 4 nm
TSMC 4N
TDP / TBP: 300 W

Interface & APIs

Bus interface: PCIe 4.0 x16
SLI / multi-GPU: None (no NVLink)
DirectX: 12 Ultimate (12_2)
OpenGL: 4.6
Vulkan: 1.3
Other APIs: CUDA 8.9, OpenCL 3.0

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 4th Gen Tensor Cores (568) + 3rd Gen RT Cores (142)
Peak AI TOPS: 724 TOPS
Notes: Fourth-generation Tensor Cores with FP8 support. Peak throughput with structured sparsity: INT4 1,448 TOPS, FP8 and INT8 724 TFLOPS, FP16 and BFLOAT16 362.1 TFLOPS, TF32 181 TFLOPS; dense rates are half. FP32 is 90.5 TFLOPS and RT Core performance 209 TFLOPS. Three NVENC and three NVDEC engines with AV1 encode and decode.