平衡人工智能的计算、内存和网络——博通公司呈现.pdf

《平衡人工智能的计算、内存和网络——博通公司呈现.pdf》由会员分享，可在线阅读，更多相关《平衡人工智能的计算、内存和网络——博通公司呈现.pdf（12页珍藏版）》请在三个皮匠报告上搜索。

1、29-30 April|Dublin,IrelandFROM IDEAS TO IMPACT!FROM IDEAS TO IMPACT!SVP&GM,Core Switching GroupBroadcomRam VelagaCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiaries.ComputeMemoryNetworkingBalancing compute,memory&networking for optimal perform

2、anceScale-up for AICompute,Memory&Networking for AIXPUHBMCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiaries.AI Scale-up and Scale-out NetworkingSpineLeafScale-upScale-outCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to

3、Broadcom Inc.and/or its subsidiaries.XPUHBMHBMHBMHBMXPUHBMHBMHBMHBMXPU Scale-up:High Bandwidth Memory Sharing Across XPUs4 x HBM3E(9.6Tbps)38.4Tbps8 x HBM4(12.8Tbps)102.4TbpsCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiaries.XPU Scale-up Requ

4、irementsHigh bandwidthEfficient data transferReliable connectivity123XPUHBMHBMHBMHBMCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiaries.Copyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiarie

5、s.Addressing Scale-up NetworkingVery high bandwidth per XPUReliable and power efficient interconnect(copper or fiber)Directly connecting 512+XPUsHigh bandwidth Ethernet switches:50Tbps 100Tbps 200Tbps Advanced semiconductor manufacturing 5nm 3nm 2nm+Increasing SerDes lane speeds:100G 200G 400GNot co

6、nstrained to one rackCopper,CPC,lower power pluggables&CPOCopyright 2025 Broadcom.All Rights Reserved.The term“Broadcom”refers to Broadcom Inc.and/or its subsidiaries.Addressing Scale-up Networking(contd)Low-latencyLink level retryOptimized headersPFC or credi