计算机组成原理 第5章层次化存储 概述，Cache llxx@ustc.edu.cn
计算机组成原理 第5章 层次化存储 概述，Cache llxx@ustc.edu.cn
STC Memory Wall:1995,Wulf@Univ of Virginia,S $ 1 主存速度跟不上CPU性能(25MHz的80386之后) 100MHz的Pentium处理器平均10ns执行一条指令，而DRAM典 型访问时间60~120ns。 指令流水线：单周期访存 ● "处理器性能提升对系统的贡献被DRAM性能所掩盖” Processor-DRAM Memory Gap 100.000 μProc1.20y “Moore'sLaw" 10.000 uProc 1.52/yr. 1.000 (2X115yr DRAM Processo 7%yt. 100 Processor-Memory (2X/10yrs) Performance Gap: (grows 50%/year) 10 Memory 1980 1985 1990 1995 2000 2005 2010 Year
Memory Wall：1995，Wulf@Univ of Virginia，$1.7 • 主存速度跟不上CPU性能(25MHz的80386之后) – 100MHz的Pentium处理器平均10ns执行一条指令，而DRAM典 型访问时间60～120ns。 – 指令流水线：单周期访存 • “处理器性能提升对系统的贡献被DRAM性能所掩盖
PC机中的存储子系统：层次化 JSTC Graphics Co-Processor Frontside bus DRAM bus Backside bus AGP p2p CPU Off-Chip On-Chip Sys Mem Cache Cache/s Controllers DIMMs North Bridge SCSI bus PCI bus Hard SCSI Network Drive/s Controller Interface 1/O Keyboard Other Low-BW Controller 1/O Devices South Bridge Mouse FIGURE Ov.3:Typical PC organization.The memory subsystem is one part of a relatively complex whole.This figure illustrates a two-way multiprocessor,with each processor having its own dedicated off-chip cache.The parts most relevant to this text are shaded in grey:the CPU and its cache system,the system and memory controllers,the DIMMs and their component DRAMs,and the hard drive/s. Bruce Jacob,Memory Systems:Cache,DRAM,Disk,2008
PC机中的存储子系统：层次化 Bruce Jacob，Memory Systems: Cache, DRAM, Disk，2008
层次化存储：性能、容量、价格 寄存器 Processor 缓存 主存 磁盘 磁带 上层是下层的copy Data are transferred Core 0 Core 2 MC os L3 30 L30 3 0 Controller MCU GX L2 MC L3B Core 1 Core 3 本电 图5-2
层次化存储：性能、容量、价格 上层是下层的copy 图5-2
Cache对处理器性能的影响：CP Program execution 200 400 600 800 1000 1200 1400 Time order (in instructions) 1dx1,100(x4) Instruction Reg ALU Data Reg 图4-25 fetch access Data 1dx2,200(x4) 200ps Instruction fetch Reg ALU access Reg Data 1dx3.400(x4) 200ps Instruction fetch Reg ALU access Reg 200ps200ps200ps 200ps200ps Memory CPU 9 bu3 VO bue Memory Vo devicea Registere h Disk memory Regiater Cache Memory reference reference referenoe reference Size:500 bytee 64KB 1 GB 1TB Speed: 250pa 1n8 100n8 10 me
Cache对处理器性能的影响：CPI=1 图4-25