HPEP67869-001

NVIDIAL40S 48 GB PCIe AcceleratorCard

The HPEP67869-001 is a factory-qualified NVIDIAL40S Acceleratorcard boasting 48 GB of GDDR6 memory and a PCIe4.0 ×16 interface. Based on the NVIDIAAda Lovelace architecture, the L40S delivers leadership-tier performance across AI inferencing, graphics rendering, simulation, and real-time visualization. With 18,176 CUDA cores, 568 fourth-generation Tensor Cores, and 142 RT Cores, it accelerates generative AI (LLM inference/training), ray-traced graphics, scientific computing, and professional visualization workflows. Memory bandwidth reaches ~864 GB/sec and FP8 throughput up to 1,466 TFLOPS (with sparsity), enabling extreme scaling for multi-modal, multi-workload environments. This Acceleratoris ideal for enterprise servers including HPEProLiant DL and Edge platforms optimized for AI and GPU-intensive tasks.

Features

The L40S card fits in servers with PCIe 4.0 ×16 slots, delivering up to 64 GB/s bidirectional interconnect to the host CPU. Its dual-slot passive form factor supports up to 350 W of power consumption and requires a compatible server chassis with adequate cooling and thermal headroom.Supported on HPEplatforms including DL380 Gen11/Gen12, DL385 Gen11/Gen12, DL320 Gen12, DL340 Gen12, and Edge Server e930t/e920d Gen10+, it integrates with HPEiLO for hardware monitoring and management.The GPU combines AI compute and RTX graphics capabilities: 91.6 TFLOPS FP32, 366 TFLOPS TF32, 733 TFLOPS FP16/BF16, and 1,466 TFLOPS FP8 (with structural sparsity) performance. Matrix and tensor workloads, real-time rendering, or simulation applications benefit from DLSS 3 and Transformer Engine. Multi-instance GPU (MIG) is not supported on L40S. Secure boot and NEBS Level 3 readiness add enterprise reliability.

Advanced Options

The NVIDIAL40S excels in generative AI inference workloads, offering up to 5× higher real-time performance compared to its predecessor A40. Its memory and compute architecture deliver smooth, multi-frame real-time graphics or LLM inference with low latency. In models using sparsity-aware formats and sparse tensor acceleration, peak FP8 performance reaches 1,466 TFLOPS, greatly enhancing throughput per watt. Designed for enterprise data centers, the L40S meets stringent reliability and operational standards×featuring passive cooling, support for secure boot, root-of-trust authentication, and NEBS Level 3 readiness. Integrated support via HPEiLO enables health monitoring, firmware updates, and power/thermal alerts. When used in qualified HPEservers, the card benefits from validated thermal and power profiles and compatibility certifications.

Product Key Features

• 48 GB GDDR6 ECC memory with ~864 GB/sec bandwidth

• PCIe Gen 4 ×16 interface (~64 GB/s bidirectional)

• Ada Lovelace architecture: 18,176 CUDA, 568 Tensor, 142 RT cores

• AI and graphics acceleration: up to 1,466 TFLOPS (FP8 with sparsity)

• FP32 @ 91.6 TFLOPS; TF32 @ 366 TFLOPS; FP16/BF16 @ 733 TFLOPS

• Compatible with HPEDL3x0/385 Gen11/Gen12 platforms

• Passive thermal design; max power draw ~350 W; requires sufficient cooling

---

Reliability & Performance

Deployments in AI inference clusters or HPC environments benefit from the card's high-bandwidth PCIe interface and massive compute density. It supports AI frameworks via CUDA-X optimized libraries, NVIDIAAI Enterprise software, and GPUs in HPEservers validated for generative AI workloads. Whether for rendering or multi-instance AI service hosting, the L40S delivers predictable performance at scale.

Key Features :

• 48 GB ECC GDDR6 memory with 864 GB/sec bandwidth

• PCIe Gen4 ×16 interface (~64 GB/s host bandwidth)

• Supports FP8, FP16/BF16, TF32, and FP32 workloads

• Ideal for AI inference, graphics, rendering, simulation

• Compatible with select HPEProLiant Gen11/Gen12 and Edge servers

• Passive-cooled design; max power ~350 W; requires adequate airflow

Specification	Details
Model Number	P67869-001 (HPEpart for NVIDIAL40S 48 GB PCIe Accelerator)
GPU Architecture	NVIDIAAda Lovelace with 18,176 CUDA / 568 Tensor / 142 RT cores
Memory	48 GB ECC GDDR6, ~864 GB/s memory bandwidth
Interface	PCIe Gen4 ×16 (~64 GB/s bidirectional)
TFLOPS Performance	FP32: ~91.6; TF32: ~366; BF16/FP16: ~733; FP8 with sparsity: ~1,466
Form Factor	Dual-slot, passive-cooled PCIe card
Power Consumption	Up to ~350 W
Server Compatibility	HPEDL380 Gen11/12, DL385 Gen11/12, DL320/340 Gen12, Edge e920d/e930t
Software Stack	CUDA-X, NVIDIAAI Enterprise, DLSS 3, Transformer Engine
Security & Compliance	Secure boot, root-of-trust, NEBS Level 3 ready
Warranty	3-year parts warranty via HPE(no labor onsite)