ThinkSystem SR685a V3

The Lenovo ThinkSystem SR685a V3 is a powerful 8U server that features two AMD EPYC 9004 processors and eight high-performance GPUs. This air-cooled server is the ultimate Generative AI server, with advanced GPU-to-GPU communications and high-speed PCIe 5.0 connectivity between the GPUs, CPUs, and networking. It was designed fully in-house by Lenovo from ground up to provide best-in-class modularity, thermal performance and reliability.

Key features

The SR685a V3 provides the performance that finance, healthcare, telco and cloud service provider customers need. The server is designed for use in air-cooled data centers that require maximum compute performance, and its outstanding reliability, availability, and serviceability (RAS) features can improve your business environment and can help save operational costs.

Performance

The following features boost performance, improve scalability and reduce costs: 

• Two fourth-generation AMD EPYC 9004 processors
• Up to 64 cores and 128 threads
• Core speed of up to 3.1GHz
• TDP rating of up to 400W
• Eight high-performance onboard AMD or NVIDIA GPUs with high-speed interconnects
• Eight AMD MI300X 750W OAM GPUs with 192GB HBM3 memory per GPU
• Eight NVIDIA H100 700W SXM5 GPUs with 80GB HBM3 GPU memory per GPU
• Support for DDR5 system memory DIMMs to maximize the performance of the memory subsystem:
• Up to 24 DDR5 memory DIMMs, 12 DIMMs per processor
• 12 memory channels per processor (1 DIMM per channel)
• DIMMs operate at 4800 MHz
• Using 24x 64GB RDIMMs, the server supports 1.5TB of system memory
• Using 24x 96GB RDIMMs, the server supports 2.25TB of system memory
• Ten PCIe 5.0 x16 slots:
• Front: 8x PCIe 5.0 x16 FHHL slots with GPU Direct support
• Rear, choice of:
• 1x PCIe 5.0 x16 FHHL slot + 1x OCP 3.0 slot with PCIe 5.0 x16 interface
• 2x PCIe 5.0 x16 FHHL slots
• Supports eight NDR 400Gb/s InfiniBand adapters with high-speed GPU Direct connections, installed in front-accessible PCIe 5.0 x16 slots.
• Supports a NVIDIA BlueField-3 DPU adapter to enable software-defined, hardware-accelerated IT infrastructures
• Supports up to 16x PCIe 5.0 NVMe drives for high-speed internal storage. The use of NVMe drives maximizes drive I/O performance, in terms of throughput, bandwidth, and latency.
• Supports two M.2 NVMe drives on an M.2 adapter with integrated RAID for convenient operating system boot functions.

Availability and serviceability

The server provides many features to simplify serviceability and increase system uptime:

• Designed to run 24 hours a day, 7 days a week
• The server uses ECC memory and supports memory RAS features including Single Device Data Correction (SDDC, also known as Chipkill), Patrol/Demand Scrubbing, Bounded Fault, DRAM Address Command Parity with Replay, DRAM Uncorrected ECC Error Retry, On-die ECC, ECC Error Check and Scrub (ECS), and Post Package Repair.
• The server offers hot-swap drives for greater system uptime.
• M.2 adapter with RAID support which can enable two NVMe M.2 drives to be configured as a redundant pair.
• The server has up to eight hot-swap redundant power supplies with N+N redundancy
• The server has 15x hot-swap redundant fans to cool all components:
• 5x front-mounted fans for the CPU, memory and rear slots subsystem
• 10x rear-mounted fans for the drive bays and GPU subsystem
• Proactive Platform Alerts (including PFA and SMART alerts): Processors, voltage regulators, memory, internal storage (SAS/SATA HDDs and SSDs, NVMe SSDs, M.2 storage, flash storage adapters), fans, power supplies, RAID controllers, server ambient and subcomponent temperatures. Alerts can be surfaced through the XClarity Controller to managers such as Lenovo XClarity Administrator, VMware vCenter, and Microsoft System Center. These proactive alerts let you take appropriate actions in advance of possible failure, thereby increasing server uptime and application availability.
• The built-in XClarity Controller 2 continuously monitors system parameters, triggers alerts, and performs recovery actions in case of failures to minimize downtime.
• Built-in diagnostics in UEFI, using Lenovo XClarity Provisioning Manager, speed up troubleshooting tasks to reduce service time.
• Lenovo XClarity Provisioning Manager supports diagnostics and can save service data to a USB key drive or remote CIFS share folder for troubleshooting and reduce service time.
• Auto restart in the event of a momentary loss of AC power (based on power policy setting in the XClarity Controller service processor)
• An integrated diagnostics panel with LCD display provides more detailed diagnostics by displaying all error messages and VPD data needed for a service call, thereby aiding with problem resolution and system uptime.
• Support for the XClarity Administrator Mobile app running on a supported smartphone and connected to the server through the service-enabled USB port, enables additional local systems management functions.
• Three-year or one-year customer-replaceable unit and onsite limited warranty, 9 x 5 next business day. Optional service upgrades are available.

Manageability and security

Systems management features simplify local and remote management:

• The server includes an XClarity Controller 2 (XCC2) to monitor server availability. Optional upgrade to XCC Platinum to provide remote control (keyboard video mouse) functions, support for the mounting of remote media files, FIPS 140-3 security, enhanced NIST 800-193 support, boot capture, and other management and security features.
• Lenovo XClarity Administrator offers comprehensive hardware management tools that help to increase uptime, reduce costs and improve productivity through advanced server management capabilities.
• UEFI-based Lenovo XClarity Provisioning Manager, accessible from F1 during boot, provides system inventory information, graphical UEFI Setup, platform update function, RAID Setup wizard, operating system installation function, and diagnostic functions.
• Support for Lenovo XClarity Energy Manager which captures real-time power and temperature data from the server and provides automated controls to lower energy costs.
• An integrated industry-standard Unified Extensible Firmware Interface (UEFI) enables improved setup, configuration, and updates, and simplifies error handling.
• Dedicated RJ45 port at the rear of the server for remote management using standard management protocols
• OCP slot supports shared BMC network sideband connectivity to enable out-of-band systems management.
• Support for industry standard management protocols, IPMI 2.0, SNMP 3.0, Redfish REST API, serial console via IPMI
• An integrated hardware Trusted Platform Module (TPM) supporting TPM 2.0 enables advanced cryptographic functionality, such as digital signatures and remote attestation.
• Administrator and power-on passwords help protect from unauthorized access to the server.
• Supports AMD Secure Root-of-Trust, Secure Run and Secure Move features to minimize potential attacks and protect data as the OS is booted, as applications are run and as applications are migrated from server to server.
• Supports Secure Boot to ensure only a digitally signed operating system can be used.
• Industry-standard Advanced Encryption Standard (AES) NI support for faster, stronger encryption.

Energy efficiency

The following energy-efficiency features help save energy, reduce operational costs, and increase energy availability:

• Energy-efficient planar components help lower operational costs.
• High-efficiency power supplies with 80 PLUS Titanium certifications
• Optional Lenovo XClarity Energy Manager provides advanced data center power notification and analysis to help achieve lower heat output and reduced cooling needs.