1 / 30

SE-292 High Performance Computing Memory Hierarchy

SE-292 High Performance Computing Memory Hierarchy. Reality Check. Question 1: Are real caches built to work on virtual addresses or physical addresses? Question 2: What about multiple levels in caches? Question 3: Do modern processors use pipelining of the kind that we studied?.

hazel
Télécharger la présentation

SE-292 High Performance Computing Memory Hierarchy

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. SE-292 High Performance Computing Memory Hierarchy

  2. Reality Check • Question 1: Are real caches built to work on virtual addresses or physical addresses? • Question 2: What about multiple levels in caches? • Question 3: Do modern processors use pipelining of the kind that we studied?

  3. Virtual Memory System • To support memory management when multiple processes are running concurrently. • Page based, segment based, ... • Ensures protectionacross processes. • Address Space: range of memory addresses a process can address (includes program (text), data, heap, and stack) • 32-bit address  4 GB • with VM, address generated by the processor is virtual address

  4. Page-Based Virtual Memory • A process’ address space is divided into a no. of pages (of fixed size). • A page is the basic unit of transfer between secondary storage and main memory. • Different processes share the physical memory • Virtual address to be translated to physical address.

  5. Process 1 Main Memory Process k Virtual Pages to Physical Frame Mapping

  6. Page Mapping Info (Page Table) • A page is mapped to any frame in the main memory. • Where to store/access the mapping? • Page Table • Each process will have its own page table! • Address Translation: virtual to physical address translation

  7. Virtual Address Virtual Page No. 18-bits Offset 14 bits Phy. Page # Pr V D Physical Frame No. 18-bits Offset 14 bits Page Table Physical Address Address Translation • Virtual address (issued by processor) to Physical Address (used to access memory)

  8. Memory Hierarchy: Secondary to Main Memory • Analogous to Main memory to Cache. • When the required virtual page is not in main memory: Page Hit • When the required virtual page is not in main memory: Page fault • Page fault penalty very high (~10’s of mSecs.) as it involves disk (secondary storage) access. • Page fault ratio shd. be very low (10-4 to 10-5) • Page fault handled by OS.

  9. Page Placement • A virtual page is placed anywhere in physical memory (fully associative). • Page Table keeps track of the page mapping. • Separate page table for each process. • Page table size is quite large! Assume 32-bit address space and 16KB page size. # of entries in page table = 232 / 214 = 218 = 256K Page table size = 256 K * 4B = 1 MB = 64 pages! • Page table itself may be paged (multi-level page tables)!

  10. Page Identification • Use virtual page number to index into page table. • Accessing page table causes one extra memory access! Virtual Page No. 18-bits Offset 14 bits Phy. Page # Pr V D Physical Frame No. 18-bits Offset 14 bits

  11. Page Replacement • Page replacement can use more sophisticated policies than in Cache. • Least Recently Used • Second-chance algorithm • Recency vs. frequency Write Policies • Write-back • Write-allocate

  12. Translation Look-Aside Buffer • Accessing the page tables causes one extra memory access! • To reduce translation time, use translation look-aside buffer (TLB) which caches recent address translations. • TLB organization similar to cache orgn. (direct mapped, set-, or full-associative). • Size of TLB is small (4 - 512 entries). • TLBs is important for fast translation.

  13. Virtual Page No. Offset Tag 13bits Ind. 5bits Pr D V P. P. # Tag Pr Phy. Page # V D Physical Frame No. Offset = TLB Hit Translation using TLB • Assume 128 entry 4-way associative TLB 14 bits 18 bits

  14. Q1: Caches and Address Translation Physical Addressed Cache Physical Address Virtual Address Cache MMU Physical Address Virtual Address Virtual Address MMU Cache (if cache miss) (to main memory) Virtual Addressed Cache

  15. Which is less preferable? • Physical addressed cache • Hit time higher (cache access after translation) • Virtual addressed cache • Data/instruction of different processes with same virtual address in cache at the same time … • Flush cache on context switch, or • Include Process id as part of each cache directory entry • Synonyms • Virtual addresses that translate to same physical address • More than one copy in cache can lead to a data consistency problem

  16. Another possibility: Overlapped operation MMU Virtual Address Physical Address Tag comparison using physical address Indexing into cache directory using virtual address Cache Virtual indexed physical tagged cache

  17. Addresses and Caches • `Physical Addressed Cache’ Physical Indexed Physical Tagged • `Virtual Addressed Cache’ Virtual Indexed Virtual Tagged • Overlapped cache indexing and translation Virtual Indexed Physical Tagged • Physical Indexed Virtual Tagged (?)

  18. Physical Indexed Physical Tagged Cache 16KB page size 64KB direct mapped cache with 32B block size Virtual Page No 18 bits Page Offset 14 bits Virtual Address MMU = Physical Cache 5 Cache Tag 16 bits C offset Physical Address Physical Page No 18 bits C-Index 11 bits Page Offset 14 bits

  19. Virtual Index Virtual Tagged Cache 5 VPN 18 bits C-Index 11 bits C offset Virtual Address = MMU Hit/Miss Page Offset 14 bits PPN 18 bits Physical Address

  20. Virtual Index Physical Tagged Cache 5 VPN 18 bits C-Index 11 bits C offset Virtual Address = MMU Physical Address Cache Tag 16 bits P-Offset 14 bits

  21. Multi-Level Caches • Small L1 cache -- to give a low hit time, and hence faster CPU cycle time . • Large L2 cache to reduce L1 cache miss penalty. • L2 cache is typically set-associative to reduce L2-cache miss ratio! • Typically, L1 cache is direct mapped, separate I and D cache orgn. L2 is unified and set-associative. • L1 and L2 are on-chip; L3 is also getting in on-chip.

  22. Multi-Level Caches CPU MMU Acc. Time 2 - 4 ns L1 I-Cache L1 D-Cache L2 Unified Cache Acc. Time 16-30 ns Acc. Time 100 ns Memory

  23. Cache Performance • One Level Cache AMAT = Hit TimeL1 + Miss RateL1 x Miss PenaltyL1 • Two-Level Caches AMAT = Hit TimeL1 + Miss RateL1 x Miss PenaltyL1 Miss PenaltyL1 = Hit TimeL2 + Miss RateL2 x Miss PenaltyL2 AMAT = Hit TimeL1 +Miss RateL1 x (Hit TimeL2 + Miss RateL2 + Miss PenaltyL2)

  24. Putting it Together: Alpha 21264 • 48-bit virtual addr. and 44-bit physical address. • 64KB 2-way assoc. L1 I-Cache with 64byte blocks ( 512 sets) • L1 I-Cache is virtually index and tagged (address translation reqd. only on a miss) • 8-bit ASID for each process (to avoid cache flush on context switch)

  25. Alpha 21264 • 8KB page size ( 13 bit page offset) • 128 entry fully associative TLB • 8MB Direct mapped unified L2 cache, 64B block size • Critical word (16B) first • Prefetch next 64B into instrn. prefetcher

  26. 21264 Data Cache • L1 data cache uses virtual addr. index, but physical addr. tag • Addr. translation along with cache access. • 64KB 2-way assoc. L1 data cache with write back.

  27. Q2: High Performance Pipelined Processors • Pipelining • Overlaps execution of consecutive instructions • Performance of processor improves • Current processors use more aggressive techniques for more performance • Some exploit Instruction Level Parallelism - often, many consecutive instructions are independent of each other and can be executed in parallel (at the same time)

  28. Instruction Level Parallelism Processors • Challenge: identifying which instructions are independent • Approach 1: build processor hardware to analyze and keep track of dependences • Superscalar processors: Pentium 4, RS6000,… • Approach 2: compiler does analysis and packs suitable instructions together for parallel execution by processor • VLIW (very long instruction word) processors: Intel Itanium

  29. Pipelined IF IF IF IF IF IF IF IF IF ID ID ID ID ID ID ID ID ID EX EX EX EX EX EX EX EX EX MEM MEM MEM MEM MEM MEM MEM MEM MEM WB WB WB WB WB WB WB WB WB Superscalar VLIW/EPIC EX EX ILP Processors (contd.)

  30. Multicores • Multiple cores in a single die • Early efforts utilized multiple cores for multiple programs • Throughput oriented rather than speedup-oriented! • Can they be used by Parallel Programs?

More Related