maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/ScheduleOptimizer/one-dimensional-band.ll

108 lines
4.0 KiB
LLVM
Raw Normal View History

tests: Drop -polly-detect-unprofitable and -polly-no-early-exit These flags are now always passed to all tests and need to be disabled if not needed. Disabling these flags, rather than passing them to almost all tests, significantly simplfies our RUN: lines. llvm-svn: 249422
2015-10-06 23:36:44 +08:00
; RUN: opt %loadPolly -polly-opt-isl -polly-ast -analyze < %s | FileCheck %s
Use schedule trees to perform post-scheduling transformations Replacing the old band_tree based code with code that is based on the new schedule tree [1] interface makes applying complex schedule transformations a lot more straightforward. We now do not need to reason about the meaning of flat schedules, but can use a more straightforward tree structure. We do not yet exploit this a lot in the current code, but hopefully we will be able to do so soon. This change also allows us to drop some code, as isl now provides some higher level interfaces to apply loop transformations such as tiling. This change causes some small test case changes as isl uses a slightly different way to perform loop tiling, but no significant functional changes are intended. [1] http://impact.gforge.inria.fr/impact2014/papers/impact2014-verdoolaege.pdf llvm-svn: 232911
2015-03-22 20:06:39 +08:00
;
; void jacobi1d(long T, long N, float *A, float *B) {
; long t, i, j;
; for (t = 0; t < T; t++) {
; for (i = 1; i < N - 1; i++)
; B[i] = 0.33333 * (A[i - 1] + A[i] + A[i + 1]);
; for (j = 1; j < N - 1; j++)
; A[j] = 0.33333 * (B[i - 1] + B[i] + B[i + 1]);
; }
; }
; Verify that we do not tile bands that have just a single dimension.
; CHECK: for (int c0 = 0; c0 < T; c0 += 1) {
Use schedule trees to represent execution order of statements Instead of flat schedules, we now use so-called schedule trees to represent the execution order of the statements in a SCoP. Schedule trees make it a lot easier to analyze, understand and modify properties of a schedule, as specific nodes in the tree can be choosen and possibly replaced. This patch does not yet fully move our DependenceInfo pass to schedule trees, as some additional performance analysis is needed here. (In general schedule trees should be faster in compile-time, as the more structured representation is generally easier to analyze and work with). We also can not yet perform the reduction analysis on schedule trees. For more information regarding schedule trees, please see Section 6 of https://lirias.kuleuven.be/handle/123456789/497238 llvm-svn: 242130
2015-07-14 17:33:13 +08:00
; CHECK: for (int c1 = 0; c1 < N - 2; c1 += 1)
; CHECK: Stmt_for_body3(c0, c1);
; CHECK: for (int c1 = 0; c1 < N - 2; c1 += 1)
; CHECK: Stmt_for_body15(c0, c1);
Use schedule trees to perform post-scheduling transformations Replacing the old band_tree based code with code that is based on the new schedule tree [1] interface makes applying complex schedule transformations a lot more straightforward. We now do not need to reason about the meaning of flat schedules, but can use a more straightforward tree structure. We do not yet exploit this a lot in the current code, but hopefully we will be able to do so soon. This change also allows us to drop some code, as isl now provides some higher level interfaces to apply loop transformations such as tiling. This change causes some small test case changes as isl uses a slightly different way to perform loop tiling, but no significant functional changes are intended. [1] http://impact.gforge.inria.fr/impact2014/papers/impact2014-verdoolaege.pdf llvm-svn: 232911
2015-03-22 20:06:39 +08:00
; CHECK: }
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @jacobi1d(i64 %T, i64 %N, float* %A, float* %B) {
entry:
%tmp = add i64 %N, -1
%tmp1 = icmp sgt i64 %tmp, 1
%smax = select i1 %tmp1, i64 %tmp, i64 1
br label %for.cond
for.cond: ; preds = %for.inc30, %entry
%t.0 = phi i64 [ 0, %entry ], [ %inc31, %for.inc30 ]
%cmp = icmp slt i64 %t.0, %T
br i1 %cmp, label %for.body, label %for.end32
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%i.0 = phi i64 [ 1, %for.body ], [ %inc, %for.inc ]
%sub = add nsw i64 %N, -1
%cmp2 = icmp slt i64 %i.0, %sub
br i1 %cmp2, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%sub4 = add nsw i64 %i.0, -1
%arrayidx = getelementptr inbounds float, float* %A, i64 %sub4
%tmp2 = load float, float* %arrayidx, align 4
%arrayidx5 = getelementptr inbounds float, float* %A, i64 %i.0
%tmp3 = load float, float* %arrayidx5, align 4
%add = fadd float %tmp2, %tmp3
%add6 = add nuw nsw i64 %i.0, 1
%arrayidx7 = getelementptr inbounds float, float* %A, i64 %add6
%tmp4 = load float, float* %arrayidx7, align 4
%add8 = fadd float %add, %tmp4
%conv = fpext float %add8 to double
%mul = fmul double %conv, 3.333300e-01
%conv9 = fptrunc double %mul to float
%arrayidx10 = getelementptr inbounds float, float* %B, i64 %i.0
store float %conv9, float* %arrayidx10, align 4
br label %for.inc
for.inc: ; preds = %for.body3
%inc = add nuw nsw i64 %i.0, 1
br label %for.cond1
for.end: ; preds = %for.cond1
br label %for.cond11
for.cond11: ; preds = %for.inc27, %for.end
%j.0 = phi i64 [ 1, %for.end ], [ %inc28, %for.inc27 ]
%sub12 = add nsw i64 %N, -1
%cmp13 = icmp slt i64 %j.0, %sub12
br i1 %cmp13, label %for.body15, label %for.end29
for.body15: ; preds = %for.cond11
%sub16 = add nsw i64 %smax, -1
%arrayidx17 = getelementptr inbounds float, float* %B, i64 %sub16
%tmp5 = load float, float* %arrayidx17, align 4
%arrayidx18 = getelementptr inbounds float, float* %B, i64 %smax
%tmp6 = load float, float* %arrayidx18, align 4
%add19 = fadd float %tmp5, %tmp6
%add20 = add nsw i64 %smax, 1
%arrayidx21 = getelementptr inbounds float, float* %B, i64 %add20
%tmp7 = load float, float* %arrayidx21, align 4
%add22 = fadd float %add19, %tmp7
%conv23 = fpext float %add22 to double
%mul24 = fmul double %conv23, 3.333300e-01
%conv25 = fptrunc double %mul24 to float
%arrayidx26 = getelementptr inbounds float, float* %A, i64 %j.0
store float %conv25, float* %arrayidx26, align 4
br label %for.inc27
for.inc27: ; preds = %for.body15
%inc28 = add nuw nsw i64 %j.0, 1
br label %for.cond11
for.end29: ; preds = %for.cond11
br label %for.inc30
for.inc30: ; preds = %for.end29
%inc31 = add nuw nsw i64 %t.0, 1
br label %for.cond
for.end32: ; preds = %for.cond
ret void
}