Download presentation
Presentation is loading. Please wait.
Published byColleen Bridges Modified over 8 years ago
1
DEPENDENCE-DRIVEN LOOP MANIPULATION Based on notes by David Padua University of Illinois at Urbana-Champaign 1
2
DEPENDENCES 2
3
DEPENDENCES (continued) 3
4
DEPENDENCE ANDPARALLELIZATION (SPREADING) 4
5
OpenMP Implementation 5
6
RENAMING: To Remove Memory Related Dependencies 6
7
DEPENDENCES IN LOOPS 7
8
DEPENDENCES IN LOOPS (Cont.) 8
9
DEPENDENCE ANALYSIS 9
10
DEPENDENCE ANALYSIS (continued) 10
11
LOOP PARALLELIZATION AND VECTORIZATION 11 The reason is that if there are no cycles in the dependence graph, then there will be no races in the parallel loop. A loop whose dependence graph is cycle free can be parallelized or vectorized
12
ALGORITHM REPLACEMENT 12 Some program patterns occur frequently in programs. They can be replaced with a parallel algorithm.
13
LOOP DISTRIBUTION To insulate these patterns, we can decompose loops into several loops, one for each strongly-connected component (π-block)in the dependence graph. 13
14
LOOP DISTRIBUTION (continued) 14
15
LOOP INTERCHANGING The dependence information determines whether or not the loop headers can be interchanged. The headers of the following loop can be interchanged 15
16
LOOP INTERCHANGING (continued) The headers of the following loop can not be interchanged 16
17
DEPENDENCE REMOVAL: Scalar Expansion: Some cycles in the dependence graph can be eliminated by using elementary transformations. 17
18
Induction variable recognition Induction variable: a variable that gets increased or decreased by a fixed amount on every iteration of a loop 18
19
More about the DO to PARALLEL DO transformation When the dependence graph inside a loop has no cross- iteration dependences, it can be transformed into a PARALLEL loop. 19 do i=1,n S1: a(i) = b(i) + c(i) S2: d(i) = x(i) + 1 end do do i=1,n S1: a(i) = b(i) + c(i) S2: d(i) = a(i) + 1 end do
20
20
21
Loop Alignment When there are cross iteration dependences, but no cycles, do loops can be aligned to be transformed into parallel loops (DOALLs) 21
22
Loop Distribution Another method for eliminating cross-iteration dependences 22
23
Loop Coalescing for DOALL loops Consider a perfectly nested DOALL loop such as 23 This could be trivially transformed into a singly nested loop with a tuple of variables as index: This coalescing transformation is convenient for scheduling and could reduce the overhead involved in starting DOALL loops.
24
Extra Slides 24
25
25 Why loop Interchange: Matrix Multiplication Example A classic example for locality-aware programming is matrix multiplication for (i=0;i<N;i++) for (j=0;j<N;j++) for (k=0;k<N;k++) c[i,j] += a[i][k] * b[k][j]; There are 6 possible orders for the three loops i-j-k, i-k-j, j-i-k, j-k-i, k-i-j, k-j-i Each order corresponds to a different access patterns of the matrices Let’s focus on the inner loop, as it is the one that’s executed most often
26
26 Inner Loop Memory Accesses Each matrix element can be accessed in three modes in the inner loop Constant: doesn’t depend on the inner loop’s index Sequential: contiguous addresses Stride: non-contiguous addresses (N elements apart) c[i][j] += a[i][k] * b[k][j]; i-j-k: Constant SequentialStrided i-k-j: Sequential ConstantSequential j-i-k: Constant SequentialStrided j-k-i: Strided StridedConstant k-i-j: Sequential ConstantSequential k-j-i: Strided StridedConstant
27
27 Loop order and Performance Constant access is better than sequential access it’s always good to have constants in loops because they can be put in registers Sequential access is better than strided access sequential access is better than strided because it utilizes the cache better Let’s go back to the previous slides
28
28 Best Loop Ordering? c[i][j] += a[i][k] * b[k][j]; i-j-k: Constant SequentialStrided i-k-j: Sequential ConstantSequential j-i-k: ConstantSequentialStrided j-k-i: StridedStridedConstant k-i-j: SequentialConstantSequential k-j-i: StridedStridedConstant k-i-j and i-k-j should have the best performance (no Strided) i-j-k and j-i-k should be worse ( 1 strided) j-k-i and k-j-i should be the worst (2 strided)
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.