Intel Xeon Platinum 8376H

The Intel processor number is just one of several factors, along with processor brand, system configuration, and system-level benchmarks, that you should consider when choosing the right processor for your computing needs. Learn more about interpreting Intel processor numbers® or Intel processor numbers® for data centers.

Lithography refers to the semiconductor technology used to produce an integrated circuit and is expressed in nanometers (nm), which indicates the size of the features built on the semiconductor.

Recommended Customer Price (RCP) is an indicative price for Intel products only. Prices are based on Intel direct customer purchases, are typically based on purchase quantities of 1,000 units, and are subject to change without notice. Prices may vary for other types of packaging and number of shipments. When selling in bulk, the price is per individual unit. The RCP listing is not an official Intel price quote. RCP values may vary depending on tariffs.

Cores are a hardware term that describes the number of independent central processing units in a single computing component (die or chip).

Where applicable, Intel technology® Hyper-Threading is only available for high-performance cores.

Maximum Turbo frequency is the maximum frequency of a single core at which the processor can operate using Intel technology.® Turbo Boost and, if available, Intel technologies® Turbo Boost Max 3.0 and Intel® Thermal Velocity Boost. Frequency is typically measured in gigahertz (GHz) or billions of cycles per second. For more information on dynamic power and frequency range, see the section «Frequently asked questions (FAQ) about Intel processor performance®».

Processor Base Frequency describes the rate at which the processor’s transistors open and close. The processor base frequency is the operating point where TDP is defined. Frequency is typically measured in gigahertz (GHz), or billion cycles per second. For more details regarding the dynamic power and frequency operating range, refer to <a

The processor cache is an area of fast memory located on the processor. Intel® Smart Cache refers to an architecture that allows all cores to dynamically share access to the last level cache.

Intel Channels® Ultra Path Interconnect (UPI) is a high-speed internetworking bus «point-to-point» between processors, providing increased throughput and performance compared to Intel® QPI.

Intel Service provides functional and security updates for Intel processors and platforms, typically through the use of an Intel Platform Update (IPU). For more maintenance information, see «Changes to Customer Support and Service Updates for Select Intel Processors®».

Mark «Built-in options available» means that the SKU is suitable for edge or embedded applications. For more information on edge or embedded use cases for this product, visit the Intel Resource and Documentation Center at (https://rdc.intel.com) or contact an Intel representative. For detailed information on how a specific Intel product is used in an edge or embedded device, contact the device manufacturer.

Maximum memory size refers to the maximum amount of memory supported by the processor.

Intel processors® Available in four different types: single channel, double channel, triple channel and flexible. The maximum supported memory speed may be lower when using multiple DIMMs per channel in products that support multiple memory channels.

The number of memory channels refers to the bandwidth for real-world applications.

Intel Persistent Memory® Optane™ — is a revolutionary layer of persistent memory that straddles the line between memory and storage, delivering large, accessible storage capacity comparable to DRAM performance. By delivering large system-level memory capacity when combined with traditional DRAM, Intel Optane persistent memory helps transform memory-constrained mission-critical workloads-from the cloud, databases, in-memory analytics, virtualization, and content delivery networks.

Supported ECC memory indicates the processor’s memory support for error correction code. ECC memory is a type of system memory that can detect and correct common types of internal data corruption. Note that ECC memory support requires both processor and chipset support.

PCI Express version is the supported version of the PCI Express standard. Peripheral Component Interconnect Express (or PCIe) is a high-speed serial computer expansion bus standard for connecting hardware devices to a computer. Different versions of PCI Express support different data transfer rates.

The PCI Express (PCIe) line consists of two pairs of differential signals: one for receiving data, the other for transmitting data, and is the main element of the PCIe bus. The maximum number of PCI Express lanes is the total number of lanes supported.

A socket is a component that provides the mechanical and electrical connection between the processor and the motherboard.

A new set of embedded processor technologies designed to accelerate deep learning AI use cases. It enhances the Intel AVX-512 with a new Vector Neural Network Instruction (VNNI) that significantly improves deep learning inference performance compared to previous generations.

Intel® RDT provides new levels of visibility and control over how shared resources such as last-level cache (LLC) and memory bandwidth are used by applications, virtual machines (VMs), and containers.

Intel Memory® Optane™ — is a revolutionary new class of non-volatile memory that sits between system memory and storage, improving system performance and responsiveness. Combined with Intel Storage Technology Driver® Rapid it seamlessly manages multiple tiers of storage by providing a single virtual disk to the operating system, ensuring that frequently accessed data resides in the fastest storage tier. Intel Memory® Optane™ requires special hardware and software configuration. Visit www.intel.com/OptaneMemory for configuration requirements.

Intel Technology® Speed Shift uses hardware-controlled P-states to provide significantly faster response in single-threaded, transient (short-term) workloads such as web browsing, allowing the processor to quickly select the best operating frequency and voltage for optimal performance. productivity and energy efficiency.

Intel Technology® Hyper-Threading (Intel® HT Technology) provides two processing threads per physical core. Applications with more threads can do more work in parallel, completing tasks faster.

Intel extensions® Transactional Synchronization Extensions (Intel® TSX is a set of instructions that add hardware support for transactional memory to improve the performance of multi-threaded software.

Intel architecture® provides 64-bit computing on servers, workstations, desktop and mobile platforms when combined with supporting software.¹ Intel 64 architecture improves performance by allowing systems to address more than 4 GB of both virtual and physical memory.

Instruction set extensions are additional instructions that can improve performance when performing the same operations on multiple data objects. These may include SSE (SIMD Streaming Extensions) and AVX (Advanced Vector Extensions).

Intel® Advanced Vector Extensions 512 (AVX-512), new instruction set extensions that provide ultra-wide (512-bit) vector operations capabilities, with two FMA (Fused Multiply Add) instructions, to improve the performance of the most demanding calculations. tasks.

Advanced Intel SpeedStep Technology® — is an industry-leading solution to deliver high performance while meeting the energy-saving needs of mobile systems. Traditional Intel SpeedStep Technology® switches voltage and frequency simultaneously between high and low levels depending on the processor load. Advanced Intel SpeedStep Technology® builds on this architecture using design strategies such as separation between voltage and frequency changes, and clock separation and recovery.

Intel Volume Manager® (VMD) provides a common and reliable method for hot-plugging and driving LEDs for NVMe-based SSDs.

New Intel instructions® AES (Intel® AES-NI is a set of instructions that provide fast and secure encryption and decryption of data. AES-NI is useful for a wide range of cryptographic applications, such as applications performing bulk encryption/decryption, authentication, random number generation, and authenticated encryption.

Execute Disable Bit is a hardware-based security feature that can reduce exposure to viruses and malware attacks, and prevent malicious software from executing and spreading on a server or network.

Intel Technology® Run Sure includes advanced RAS (Reliability, Availability and Serviceability) features that provide high platform reliability and resiliency to maximize uptime for servers running mission-critical workloads.

Mode-based execution control allows you to more reliably verify and ensure the integrity of kernel-level code.

Intel Technology® Virtualization (VT-x) allows one hardware platform to function as several «virtual» platforms. It provides improved manageability by limiting downtime and maintaining performance by isolating computing activity into separate partitions.

Intel Virtualization Technology® for Directed I/O (VT-d) continues existing virtualization support for IA-32 (VT-x) and Itanium processors® (VT-i), adding new support for I/O device virtualization. Intel VT-d can help end users improve system security, reliability, and I/O performance in virtualized environments.

Intel® VT-x with Extended Page Tables (EPT), also known as Second Level Address Translation (SLAT), provides acceleration for memory-intensive virtualized applications. Extended Page Tables on Platforms with Intel Virtualization Technology® reduce memory and power overhead, and increase battery life through hardware optimization of page table management.