meta data for this page
  •  

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
enterprise:intel:start [2024/06/20 11:33] – mchusenterprise:intel:start [2025/01/13 14:01] (current) – mchus
Line 8: Line 8:
 ===== XEON SUFFIX MEANINGS ===== ===== XEON SUFFIX MEANINGS =====
  
-The different letter suffixes at the end of the Xeon processor names tell you a little about the chip’s features. +**4th Gen and 5th Gen processors use these suffixes:** 
-  * E: Embedded +  * +: Includes 1 of each of the four accelerators: DSA, IAA, QAT, DLB 
-  * H: Large memory support (up to 1.12 TB per socket) +  * H: Database and Analytics workloads 
-  * HL: Large memory support (up to 4.5 TB) +  * M: Media Transcode workloads 
-  * L: Large memory support (up to 4.5 TB) +  * N: Network/5G/Edge workloads (High TPT / Low Latency) 
-  * M: Medium memory support (up to 2 TB) +  * P: Cloud and IaaS workloads 
-  * N: Networking specialized ((NFV models are optimized for dynamic density VMs with additional headroom for higher subscribe capacity. NFV SKUs also feature speed select profiles with configurable priority based on the kind of workloads that are running.)) +  * Q: Liquid cooling 
-  * P: Performance and power +  * S: Storage & HCI workloads 
-  * R: Refresh (high performance) +  * T: Long-life Use/High Tcase 
-  * S: Search optimized ((The search-optimized SKU is mainly designed for cloud search applications. Those models are designed such that they have predictable performance and latencies.)) +  * U: 1-socket only (some workload-specific SKUs may also be 1-socket) 
-  * T: Thermal / long life cycle / low power ((Models that are suffixed with “T” have extended lifetime (10 year use) guarantees and NEBS-friendly packing specification)) +  * V: Cloud and SaaS workloads 
-  * U: Uniprocessor +  * Y: SST-PP enabled (some workload-specific SKUs may also support SST-PP) 
-  * V: Virtual machine density optimized ((VM density value optimized are SKUs that have been optimized to provide higher ROI for customers that benefit more from the higher thread count.)) +  * Y+: SST-PP enabled and includes 1 of each of the accelerators 
-  * Y: Speed select+ 
 +**3rd Gen processors use these suffixes:** 
 +  * H: 4-Socket capable processor supporting up to 1.125TB memory per processor 
 +  * HL: 4-Socket capable processor supporting up to 4.5TB memory per processor 
 +  * M: Media Processing optimized 
 +  * N: NFV optimized 
 +  * P: High frequency-optimized for IaaS virtualization customers 
 +  * Q: Optimized for liquid cooling 
 +  * S: Large (512GB) SGX Enclave size 
 +  * T: High Tcase 
 +  * U: Single socket 
 +  * V: High density/low power-optimized for SaaS virtualization customers 
 +  * Y: Speed Select 
 + 
 +**1st Gen and 2nd Gen processors use these suffixes:** 
 +  * F: Integrated Omni-Path Architecture (OPA) Fabric 
 +  * L: Large memory tier (supports total memory up to 4.5TB per processor) 
 +  * M: Medium memory tier (supports total memory up to 2TB per Gen 2 processor or 1.5TB per Gen 1 processor) 
 +  * N: NFV optimized 
 +  * S: Search optimized 
 +  * T: High Tcase 
 +  * U: Single socket 
 +  * V: VM Density optimized 
 +  * Y: Speed Select
  
 ====== gen4: Intel Xeon Scalable "Sapphire Rapids" ====== ====== gen4: Intel Xeon Scalable "Sapphire Rapids" ======