Unterschiede

Hier werden die Unterschiede zwischen zwei Versionen angezeigt.

--- english:omnicompute-oc-8600-oc8600-ai-server-data-sheet [2026/02/12 13:55] – benny
+++ english:omnicompute-oc-8600-oc8600-ai-server-data-sheet [2026/02/12 16:16] (aktuell) – benny
@@ Zeile 3: / Zeile 3: @@
 The Alcatel-Lucent Enterprise OmniCompute 8600 (OC8600) AI Server is a high-performance, scalable, GPU-based server ideally suitable for AI/ML (Artificial Intelligence/Machine Learning) and HPC (High-Performance Computing) applications. The server is ideal for training large language models, automation, object classification, and recognition use cases. The system is designed with eight AMD Instinct MI325X GPUs and dual AMD EPYC 9005/Turin series processors. The AMD MI325X GPU integrates 256 GB of HBM3 memory each.
-Each MI325X offers a 16-lane PCIe Gen5 host interface and seven AMD Infinity FabricTM links for full connectivity between eight GPUs. AMD Infinity Fabric technology delivers excellent I/O efficiency, scaling and communication within and between industry-standard accelerator module (OAM) device packages.
+Each MI325X offers a 16-lane PCIe Gen5 host interface and seven AMD Infinity Fabric(tm) links for full connectivity between eight GPUs. AMD Infinity Fabric technology delivers excellent I/O efficiency, scaling and communication within and between industry-standard accelerator module (OAM) device packages.
 ===== Key Features and Benefits =====
-  * Featuring eight AMD InstinctTM MI325X GPUs based on CDNATM 3 architecture
+  * Featuring eight AMD Instinct(tm) MI325X GPUs based on CDNA(tm) 3 architecture
   * Dual 5th Gen AMD EYPC processors with advanced data center performance and efficiency
-  * 7 Infinity FabricTM links with 128 GB/s for full connectivity between 8 GPUs in a ring (scale-up)
+  * 7 Infinity Fabric(tm) links with 128 GB/s for full connectivity between 8 GPUs in a ring (scale-up)
   * 16 PCIe Gen5 with 128GB/s bandwidth for scale-out network
   * Up to 1.3X AI performance and up to 2.4X HPC performance vs. competitive accelerators
-  * AMD ROCmTM software optimized for generative AI and HPC applications, easy for migrating existing code
+  * AMD ROCm(tm) software optimized for generative AI and HPC applications, easy for migrating existing code
 {{ :english:amd-results-comparison.png?direct |}}
@@ Zeile 18: / Zeile 18: @@
 ===== Product Picture =====
-==== OC8600 AI Server front ====
 Preliminary picture of the OC8600 AI Server, final product may look slightly different.
+==== OC8600 AI Server front ====
 {{ :english:oc8600-front.png?direct |}}
+==== OC8600 AI Server rear-angled ====
+{{ :english:oc8600-rear-angle.png?direct |}}
+==== OC8600 AI Server rear-top ====
+{{ :english:oc8600-rear-top.png?direct |}}
 ===== Specifications =====
@@ Zeile 28: / Zeile 35: @@
 ==== Compute Node ====
-  * CPU: AMD EPYCTM 9005/Turin series processor, 2 sockets EPYC 9575F 64C 3.3GHz 400W SP5
+  * CPU: AMD EPYC(tm) 9005/Turin series processor, 2 sockets EPYC 9575F 64C 3.3GHz 400W SP5
   * Memory: 24 x 64GB RDIMM 2 RANK 5600
   * Operating System: Linux