1 COMP 206: Computer Architecture and Implementation Montek Singh Wed, Nov 9, 2005 Topic: Caches (contd.)

2Outline  Improving Cache Performance Reducing misses – summary of previous lecture Reducing misses – summary of previous lecture Reducing miss penalty Reducing miss penalty Reducing hit time Reducing hit time Reading: HP3 Sections

3 Summary: Compiler Optimizations to Reduce Cache Misses

4 Reducing Miss Penalty 1. Read Priority over Write on Miss: Write through: Write through:  Using write buffers: RAW conflicts with reads on cache misses  If simply wait for write buffer to empty might increase read miss penalty by 50% (old MIPS 1000)  Check write buffer contents before read; if no conflicts, let the memory access continue Write Back? Write Back?  Read miss replacing dirty block  Normal: Write dirty block to memory, and then do the read  Instead copy the dirty block to a write buffer, then do the read, and then do the write  CPU stall less since restarts as soon as read completes

5 Valid Bits Fetching Subblocks to Reduce Miss Penalty  Don’t have to load full block on a miss  Have bits per subblock to indicate valid

6 3. Early Restart and Critical Word First  Don’t wait for full block to be loaded before restarting CPU Early Restart —As soon as the requested word of the block arrrives, send it to the CPU and let the CPU continue execution Early Restart —As soon as the requested word of the block arrrives, send it to the CPU and let the CPU continue execution Critical Word First —Request the missed word first from memory and send it to the CPU as soon as it arrives Critical Word First —Request the missed word first from memory and send it to the CPU as soon as it arrives  let the CPU continue while filling the rest of the words in the block.  also called “wrapped fetch” and “requested word first”  Generally useful only in large blocks  Spatial locality a problem tend to want next sequential word, so not clear if benefit by early restart tend to want next sequential word, so not clear if benefit by early restart

7 4. Non-blocking Caches  Non-blocking cache or lockup-free cache allows the data cache to continue to supply cache hits during a miss “Hit under miss” “Hit under miss”  reduces the effective miss penalty by being helpful during a miss instead of ignoring the requests of the CPU “Hit under multiple miss” or “miss under miss” “Hit under multiple miss” or “miss under miss”  may further lower the effective miss penalty by overlapping multiple misses Significantly increases the complexity of the cache controller as there can be multiple outstanding memory accesses Significantly increases the complexity of the cache controller as there can be multiple outstanding memory accesses

8 Value of Hit Under Miss for SPEC  FP programs on average: AMAT= > > > 0.26  Int programs on average: AMAT= > > > 0.19  8 KB Data Cache, Direct Mapped, 32B block, 16 cycle miss Integer Floating Point “Hit under i Misses”

9 5. Miss Penalty Reduction: L2 Cache L2 Equations: AMAT = Hit Time L1 + Miss Rate L1  Miss Penalty L1 Miss Penalty L1 = Hit Time L2 + Miss Rate L2  Miss Penalty L2 AMAT = Hit Time L1 + Miss Rate L1  (Hit Time L2 + Miss Rate L2  Miss Penalty L2 ) Definitions: Local miss rate — misses in this cache divided by the total number of memory accesses to this cache (Miss rate L2 ) Global miss rate —misses in this cache divided by the total number of memory accesses generated by the CPU (Miss Rate L1  Miss Rate L2 )

10 Reducing Misses: Which Apply to L2 Cache?  Reducing Miss Rate 1. Reduce Misses via Larger Block Size 1. Reduce Misses via Larger Block Size 2. Reduce Conflict Misses via Higher Associativity 2. Reduce Conflict Misses via Higher Associativity 3. Reducing Conflict Misses via Victim Cache 3. Reducing Conflict Misses via Victim Cache 4. Reducing Conflict Misses via Pseudo-Associativity 4. Reducing Conflict Misses via Pseudo-Associativity 5. Reducing Misses by HW Prefetching Instr, Data 5. Reducing Misses by HW Prefetching Instr, Data 6. Reducing Misses by SW Prefetching Data 6. Reducing Misses by SW Prefetching Data 7. Reducing Capacity/Conf. Misses by Compiler Optimizations 7. Reducing Capacity/Conf. Misses by Compiler Optimizations

11 L2 cache block size & A.M.A.T.  32KB L1, 8 byte path to memory

12 Reducing Miss Penalty Summary  Five techniques Read priority over write on miss Read priority over write on miss Subblock placement Subblock placement Early Restart and Critical Word First on miss Early Restart and Critical Word First on miss Non-blocking Caches (Hit Under Miss) Non-blocking Caches (Hit Under Miss) Second Level Cache Second Level Cache  reducing L2 miss rate effectively reduces L1 miss penalty!  Can be applied recursively to Multilevel Caches Danger is that time to DRAM will grow with multiple levels in between Danger is that time to DRAM will grow with multiple levels in between

13 Review: Improving Cache Performance 1. Reduce the miss rate, 2. Reduce the miss penalty, or 3. Reduce the time to hit in the cache.

14 1. Fast Hit Times via Small, Simple Caches  Simple caches can be faster cache hit time increasingly a bottleneck to CPU performance cache hit time increasingly a bottleneck to CPU performance  set associativity requires complex tag matching  slower  direct-mapped are simpler  faster  shorter CPU cycle times –tag check can be overlapped with transmission of data  Smaller caches can be faster can fit on the same chip as CPU can fit on the same chip as CPU  avoid penalty of going off-chip for L2 caches: compromise for L2 caches: compromise  keep tags on chip, and data off chip –fast tag check, yet greater cache capacity L1 data cache reduced from 16KB in Pentium III to 8KB in Pentium IV L1 data cache reduced from 16KB in Pentium III to 8KB in Pentium IV

15 2. Fast Hits by Avoiding Addr. Translation  For Virtual Memory: can send virtual address to cache? Called Virtually Addressed Cache or just Virtual Cache, vs. Physical Cache Benefits: avoid translation from virtual to real address; saves time Benefits: avoid translation from virtual to real address; saves time Problems: Problems:  Every time process is switched logically must flush the cache; otherwise get false hits –Cost is time to flush + “compulsory” misses from empty cache  Dealing with aliases (sometimes called synonyms); Two different virtual addresses map to same physical address  I/O must interact with cache, so need mapping to virtual address  Some Solutions partially address these issues HW guarantee: each cache frame holds unique physical address HW guarantee: each cache frame holds unique physical address SW guarantee: lower n bits must have same address; as long as covers index field & direct mapped, they must be unique; called page coloring SW guarantee: lower n bits must have same address; as long as covers index field & direct mapped, they must be unique; called page coloring  Solution to cache flush Add process identifier tag that identifies process as well as address within process: can’t get a hit if wrong process Add process identifier tag that identifies process as well as address within process: can’t get a hit if wrong process

16 Virtually Addressed Caches CPU TLB Cache MEM VA PA Conventional Organization CPU Cache TLB MEM VA PA Virtually Addressed Cache Translate only on miss VA Tags

17 3. Pipeline Write Hits  Write Hits take slightly longer than Read Hits: cannot parallelize tag matching with data transfer cannot parallelize tag matching with data transfer  must match tags before data is written!  Summary of Key Idea: pipeline the writes pipeline the writes  check tag first; if match, let CPU resume  let the actual write take its time

18 TechniqueMRMPHT Complexity Larger Block Size+–0 Higher Associativity+–1 Victim Caches+2 Pseudo-Associative Caches +2 HW Prefetching of Instr/Data+2 Compiler Controlled Prefetching+3 Compiler Reduce Misses+0 Priority to Read Misses+1 Subblock Placement ++1 Early Restart & Critical Word 1st +2 Non-Blocking Caches+3 Second Level Caches+2 Small & Simple Caches–+0 Avoiding Address Translation+2 Cache Optimization Summary

19 Impact of Caches  : Speed = ƒ(no. operations)  1997 Pipelined Execution & Fast Clock Rate Pipelined Execution & Fast Clock Rate Out-of-Order completion Out-of-Order completion Superscalar Instruction Issue Superscalar Instruction Issue  1999: Speed = ƒ(non-cached memory accesses)  Has impact on: Compilers, Architects, Algorithms, Data Structures? Compilers, Architects, Algorithms, Data Structures?