Dependence-Based Value Prediction

1
Dependence-Based Value Prediction

• Yiannakis Sazeides
• University of Cyprus
• yanos_at_ucy.ac.cy
• UPC-Barcelona 17/5/2001

2
Motivation

• Improve Performance (reduce complexity, save
  power...)
• What limits performance? Dependences
• Break dependences Prediction
• Exploits regularity and/or non-uniformity in
  predicted information

3
Predicted Information

• Architectural
• dependences control, address, value, memory
• Non-Architectural
• structural constrains cache misses, bank
  conflicts
• reduce hardware complexity cache sets, shared
  patterns

4
Use of Predicted Information

• Speculative/Non-Speculative
• Depends on whether predicted information can
  directly/indirectly cause an incorrect update of
  architected state
• non-speculative branch prediction for
  instruction prefetching
• speculative branch prediction for instruction
  execution
• Hardware/Software

5
Trends

• Identify and eliminate predictability at
  computational levels below programming
• Predictors in almost all high performance
  processors and many compilers
• Technological evolution and limitations will
  increase latency and make predictive techniques
  more important
• deeper pipelines
• fast processor/slow memory
• distributed microarchitectures

6
Our motivation

• Can value prediction help?
• How to use value predictability?
• Wholistic approach all types not just vp and
  coarser grain
• Absolutely curious to discover, understand and
  use the esoteric program properties causing the
  predictability and non-uniformity observed in
  program information

7
This talk...

• Hypothesis dependence information influences the
  predictability of program values
• Propose and evaluate various dependence-based
  value predictors
• Approach theoretical and practical
• Work in progress...

8
Outline

• Introduction
• Background on value prediction
• Dependence Info and Predictability
• Dependence-based Value Predictors
• Results
• Future work

9
Value Sequences Produced by Instructions

• Basic Sequences
• Constant 0 0 0 0 0
• Stride 4 3 2 1 0
• Non-Stride -1 23 10 94
• Repeating Sequences (composition of basic
  sequences)
• Repeated Stride 4 3 2 1 0 4 3 2 1 0
• Repeated Non-Stride -1 23 10 94 -1 23 10 94

10
Local History Value Predictors

• Computational-Based
• compute next value by performing a computation on
  previous value(s)
• Context-Based
• learn the value that follows a finite number of
  previous values (context) and predict that value
  when context repeats
• need to observe a context-value before predicting
  correctly
• Hybrid Delta-Predictor

11
Last Value Predictor
12
Stride Predictor
13
Context-Based Predictor
14
Hybrid Predictor
15
Causes of Predictability

• Model Based on Dependence Graph
• Robustness predictability due to program control
  structure and immediate values not input data
• Predictability generation-propagation termination
• need to consider info beyond local scope
• dependence information holds potential to
  increase accuracy of value prediction

16
Hypothesis/Fact

• The predictability of an instruction is
  determined by the information on the dependence
  path that leads to it
• Predict the value produced by an instruction
  based on the values and/or information of its
  predecessors

17
Outline

• Introduction
• Background on value prediction
• Dependence Info and Predictability
• Dependence-based Value Predictors
• Results
• Future work

18
Example
19
Observations

• All instructions can trace dependence back to 6
• 6 used as an induction variable
• Use information about 6 to get predictions

20
Example

• Use value in 6 to predict instruction 7
  Value of 6 Output of Instr. 7
  0,..,13, 15, 31..63 1
  14, 16..30 0
• Local history with lt47 previous values mispredicts

21
Dependence-Based Prediction

• Prediction based on information from the
  component of the predicted instruction
  i Output PF(Componenti)
• Component
• backward dynamic data dependence slice
• node info pcs, optypes, immed., outcomes
• livein values (values not produced by component,
  register and memory)

22
Dependence-Based Prediction

• In general, use information from components of
  previous instructions Output
  PF(Ci-n..Ci-1,Ci)

23
Perspective

• Virtually all predictors are functions of
  component approximations to values
• Practical Limitation predictors can rely on a
  subset of components and information

24
Component Approximation

• Approximation accuracy depends on information
  used from component
• What limits approximation accuracy
• finite resources and aliasing
• amount of information to be stored
• how soon a prediction can be made

25
Existing Predictors

• Interesting with how little information
  predictors work well
• Global History Branch Predictors
• use information from multiple previous branch
  components OutputPF(Ci-n..Ci-1,Ci)
• Note components may be unrelated (longer learning
  and destructive aliasing)

26
Dependence Information

• A lot of information to choose from
• Which predecessors
• recent, recurrent, earliest, all
• Information
• values
• register, memory names
• pc, optypes, immediates
• dependence distance
• Propagation through registers or memory

27
Ideas predict based on

• Values of recurrent predecessors
• values indicating location in program

28
Based on Recurrent Predecessors
29
Ideas predict based on

• Values of recurrent predecessors
• values indicating location in program
• no sp
• sp with last SP value and PC selection of stride

30
(No Transcript)
31
Dependence-Based Stack Pointer Predictor
32
(No Transcript)
33
Ideas predict based on

• Values of recurrent predecessors
• values indicating location in program
• no sp
• sp with last SP value and PC selection of stride
• Distance from predecessors
• distance indicates coordinates in program
• predict values not based on values
• no sp

34
Based on Dependence Distance
35
Ideas predict based on

• Values of recurrent predecessors
• values indicating location in program
• no sp
• sp with last SP value and PC selection of stride
• Distance from predecessors
• distance indicates coordinates in program
• predict values not based on values
• no sp
• Most recently known processor state
• isolate non-determinism

36
Based on Recent Predecessors
37
Outline

• Introduction
• Background on value prediction
• Dependence Info and Predictability
• Dependence-based Value Predictors
• Results
• Future work

38
Prediction Process

• To predict an instruction
• Construction of Dependence Record (DR)
• approximation of the information on the component
  of the instruction
• Use DR to obtain a prediction (directly or
  indirectly)

39
DBVP Predictor with CT
40
DBVP Register (DBVP-R)

• Component subset instructions those fetched but
  have not updated yet the architectural state
• isolates the non-determinism in execution
• Information used
• Generate Registers(GR)livein registers (most
  recently known architected state)
• Dependence Path Id(DPI)pcs, optypes, immediates
  (info about unknown state)

41
Construction of DR for an instruction (GR)
42
Construction of DR for an instruction
- Many instructions same GRs - Differentiate with
DPI
43
DR Construction

• Information encoded in instructions
• May be done incrementally off-line and stored in
  a table where it can be retrieved (imprecise?)
• No investigation of implementation specifics of
  DR construction
• Memory instructions propagate the dependence info
  through address operands (can be problematic -
  later)

44
DBVP-R Predictor
History Table indexed with register names
contains architected state
45
DBVP Memory (DBVP-M)

• DBVP-R ignores memory dependences
• often no correlation between load address and
  value
• DBVP-M same as DBVP-R with additional
  functionality and information
• propagation of DR through memory
• convert def-store-load-use dependence in a
  component to def-use
• livein memory locations(generate locations GLs)
• converts values from memory to liveins

46
DR Propagation Through Memory (spilled variable)
47
Livein Memory Locations
48
Generate Locations (GL) and Memory History
Table(MHT)

• GL is an index into a table (MHT) with values
  written to memory
• Store-load dependent pairs are assigned MHT
  location
• Memory Dependence Prediction mechanisms can
  provide the extra functionality required by DBVP-M

49
DBVP-M Predictor
50
Differences DBVP and CB

• Information used to access tables and table sizes
• History table is register indexed (vs PC indexed)
• smaller
• may be easier to manage speculative updates
• -possibly provide predictions later
• Smaller context is required to capture repeated
  behavior

51
Outline

• Introduction
• Background on value prediction
• Dependence Info and Predictability
• Dependence-based Value Predictors
• Results
• Future work

52
Experimental Framework

• SPECINT95 Benchmarks
• Study predictors with simple delay model
• predict d instructions (or up to first
  misprediction)
• update
• d is also maximum component size
• DPI pc, optypes and immediates

53
DBVP-R DPI Information d1, 64K entry VPT
54
DBVP-R VPT Sized1
55
DBVP-R Sensitivity to Delay64K VPT size
56
Problems with increasing d

• Capacity instruction in different components
  requires more information to be learned

57
Component Redundancy
58
Problems with increasing d

• Capacity instruction in different components
  requires more information to be learned
• Destr. Aliasing multiple instances of same
  instruction same prediction

59
Multiple instances same GR and DPI
60
Problems with increasing d

• Capacity instruction in different components
  requires more information to be learned
  (destructive aliasing)
• Destr. Aliasing multiple instances of same
  instruction same prediction
• Capacity increasing d means more information
  needs to be learned

61
Information to be learned

Two combinations
62
Information to be learned
64 combinations
63
Solutions for increasing d

• Careful partitioning
• Transform different structure to same
• Better DPI
• position
• count of outstanding instances of an instruction
• predict only liveouts
• Predict based on other information
• recurrence, dependence distance...

64
DBVP-M MHT Sized1, 64K VPT size
65
DBVP-M Sensitivity to Delay
66
DBVP vs CB
67
Conclusions

• Dependence-based prediction holds potential to
  improve accuracy
• Use dependence information for prediction
• Propagation of dependence information through
  memory useful for increased accuracy

68
Current and Future Work

• Refinement and evaluation of dependence-based
  prediction methods
• Evaluation in a processor
• DR construction
• Characterize program full components
• size, uniqueness, correlation to predictability

69
Other Work/Interests

• Prediction and Speculation
• Program Behavior
• Distributed Microarchitectures
• SMT
• Benchmark characterization

70
I had a great time - thank you all! Hasta luego
amigas y amigos!