cache1 - Who Cares about Memory Hierarchy Memory Memory...

Info icon This preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Memory Subsystem Design or Nothing Beats Cold, Hard Cache CSE 240A Dean Tullsen Who Cares about Memory Hierarchy? Processor Only Thus Far in Course CPU DRAM G CPU-DRAM Gap 1980: no cache in μproc; 1995 2 level cache 60% trans on Alpha 21164 μproc CSE 240A Dean Tullsen 1995 2-level cache, 60% trans. on Alpha 21164 μproc Memory Cache Can put small, fast memory close to memory close to processor. What do we put there? cpu cache memory CSE 240A Dean Tullsen Memory Locality Memory hierarchies take advantage of memory locality . Memory locality is the principle that future memory accesses are near past accesses. Memory hierarchies take advantage of two types of Memory hierarchies take advantage of two types of locality Temporal locality -- near in time => we will often access the same d i data again very soon Spatial locality -- near in space/distance => our next access is often very close to our last access (or recent accesses). 1,2,3,1,2,3,8,8,47,9,10,8,8... CSE 240A Dean Tullsen
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon