Analysis of NUCA Policies for CMPs Using Parsec Benchmark Suite

1
Analysis of NUCA Policies for CMPs Using Parsec
Benchmark Suite
MMCS 2009, Washington DC (USA) - March 7, 2009

• Javier Lira ?
• Carlos Molina ?
• Antonio González ?

? Dept. Enginyeria Informàtica Universitat Rovira
i Virgili Tarragona, Spaincarlos.molina_at_urv.net
? Intel Barcelona Research Center Intel Labs -
UPC Barcelona, Spainantonio.gonzalez_at_intel.com
? Dept. Arquitectura de Computadors Universitat
Politècnica de Catalunya Barcelona, Spain
javier.lira_at_ac.upc.edu
2
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

3
Introduction

• CMPs have emerged as a dominant paradigm in
  system design.
• Keep performance improvement while reducing power
  consumption.
• Take advantage of Thread-level parallelism.
• Commercial CMPs are currently available.
• CMPs incorporate larger and shared last-level
  caches.
• Wire delay is a key constraint.

4
NUCA

• Non-Uniform Cache Architecture (NUCA) was first
  proposed in ASPLOS 2002 by Kim et al.1.
• NUCA divides a large cache in smaller and faster
  banks.
• Banks close to cache controller have smaller
  latencies than further banks.

Processor
1 C. Kim, D. Burger and S.W. Keckler. An
Adaptive, non-uniform cache structure for
wire-delay dominated on-chip caches. ASPLOS 02
5
NUCA Policies
Bank Placement Policy
Bank Access Policy
Bank Replacement Policy
Bank Migration Policy
6
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

7
Methodology

• Simulation tools
• Simics GEMS
• CACTI v6.0
• PARSEC Benchmark Suite

8
Baseline NUCA cache architecture
8 cores 256 banks
2 B. M. Beckmann and D. A. Wood. Managing wire
delay in large chip-multiprocessor caches. MICRO
04
9
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

10
Bank Placement Policy

• 1B Static
• 16B Static
• 16B Local

11
Bank Placement Policy

• 1B Static placement provides fair distribution.
• 16B configurations concentrate data in few banks.
• Placement and migration policies are strictly
  correlated.

12
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

13
Bank Access Policy

• Partially Serial
• 9P 7P
• Parallel

14
Bank Access Policy

• Power efficiency vs. Perfomance.
• 9P 7P is a trade-off, but it is still far from
  the performance potencial.
• These results suggest the broad area of
  improvement on this policy.

15
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

16
Bank Migration Policy

• Static
• Gradual Swapping
• Gradual Replication

17
Bank Migration Policy

• Replication reduces the effective size of the
  cache.
• Migration approaches concentrate data blocks in
  few banks.
• Static approach fairly distribute data blocks in
  the whole cache.
• Placement and migration policies are strictly
  correlated.

18
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

19
Bank Replacement Policy

• Zero-copy
• One-copy
• Last Bank

Last Bank
20
Bank Replacement Policy

• Giving a second chance to evicted data blocks
  provides significant performance gain.
• Last Bank is a promising mechanism, but this is
  restricted by its small size.
• Further exploration on this policy is required.

21
Outline

• Introduction
• Methodology
• Bank Policy Approaches
• Bank Placement Policy
• Bank Access Policy
• Bank Migration Policy
• Bank Replacement Policy
• Conclusions

22
Conclusions

• NUCA is characterized by four policies.
• NUCA policies are related.
• Static placement with no-migration Good
  trade-off.
• Bank placement and bank migration are strictly
  correlated.
• Bank access Power efficiency vs. Performance.
• Bank replacement ? Performance (unbounded last
  bank).
• Still room for improvement in all policies.

23
Analysis of NUCA Policies for CMPs Using Parsec
Benchmark Suite

• Questions?