mono/linux-packaging-mono
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Imported Upstream version 5.18.0.167

Browse Source 
Former-commit-id: 289509151e0fee68a1b591a20c9f109c3c789d3a
This commit is contained in:
Xamarin Public Jenkins (auto-signing)
2018-10-20 08:25:10 +00:00
parent e19d552987
commit b084638f15
28489 changed files with 184 additions and 3866856 deletions
Download Patch File Download Diff File Expand all files Collapse all files

158
external/llvm/test/Transforms/LoopInterchange/call-instructions.ll vendored
View File

@ -1,158 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
declare void @foo(i64 %a)
declare void @bar(i64 %a) readnone
;;--------------------------------------Test case 01------------------------------------
;; Not safe to interchange, because the called function `foo` is not marked as
;; readnone, so it could introduce dependences.
;;
;; for(int i=0;i<N;i++) {
;; for(int j=1;j<N;j++) {
;; foo(i);
;; A[j][i] = A[j][i]+k;
;; }
;; }
define void @interchange_01(i32 %k, i32 %N) {
entry:
%cmp21 = icmp sgt i32 %N, 0
br i1 %cmp21, label %for1.ph, label %exit
for1.ph:
%cmp219 = icmp sgt i32 %N, 1
%0 = add i32 %N, -1
br label %for1.header
for1.header:
%indvars.iv23 = phi i64 [ 0, %for1.ph ], [ %indvars.iv.next24, %for1.inc10 ]
br i1 %cmp219, label %for2.ph, label %for1.inc10
for2.ph:
br label %for2
for2:
%indvars.iv = phi i64 [ %indvars.iv.next, %for2 ], [ 1, %for2.ph ]
call void @foo(i64 %indvars.iv23)
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv23
%1 = load i32, i32* %arrayidx5
%add = add nsw i32 %1, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for2.loopexit , label %for2
for2.loopexit:
br label %for1.inc10
for1.inc10:
%indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
%lftr.wideiv25 = trunc i64 %indvars.iv23 to i32
%exitcond26 = icmp eq i32 %lftr.wideiv25, %0
br i1 %exitcond26, label %for1.loopexit, label %for1.header
for1.loopexit:
br label %exit
exit:
ret void
}
; CHECK-LABEL: @interchange_01
; CHECK: for1.ph:
; CHECK: br label %for1.header
; CHECK: for1.header:
; CHECK-NEXT: %indvars.iv23 = phi i64 [ 0, %for1.ph ], [ %indvars.iv.next24, %for1.inc10 ]
; CHECK-NEXT: br i1 %cmp219, label %for2.ph, label %for1.inc10
; CHECK: for2:
; CHECK: br i1 %exitcond, label %for2.loopexit, label %for2
; CHECK: for1.inc10:
; CHECK: br i1 %exitcond26, label %for1.loopexit, label %for1.header
; CHECK: for1.loopexit:
; CHECK-NEXT: br label %exit
;;--------------------------------------Test case 02------------------------------------
;; Safe to interchange, because the called function `bar` is marked as readnone,
;; so it cannot introduce dependences.
;;
;; for(int i=0;i<N;i++) {
;; for(int j=1;j<N;j++) {
;; bar(i);
;; A[j][i] = A[j][i]+k;
;; }
;; }
define void @interchange_02(i32 %k, i32 %N) {
entry:
%cmp21 = icmp sgt i32 %N, 0
br i1 %cmp21, label %for1.ph, label %exit
for1.ph:
%cmp219 = icmp sgt i32 %N, 1
%0 = add i32 %N, -1
br label %for1.header
for1.header:
%indvars.iv23 = phi i64 [ 0, %for1.ph ], [ %indvars.iv.next24, %for1.inc10 ]
br i1 %cmp219, label %for2.ph, label %for1.inc10
for2.ph:
br label %for2
for2:
%indvars.iv = phi i64 [ %indvars.iv.next, %for2 ], [ 1, %for2.ph ]
call void @bar(i64 %indvars.iv23)
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv23
%1 = load i32, i32* %arrayidx5
%add = add nsw i32 %1, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for2.loopexit , label %for2
for2.loopexit:
br label %for1.inc10
for1.inc10:
%indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
%lftr.wideiv25 = trunc i64 %indvars.iv23 to i32
%exitcond26 = icmp eq i32 %lftr.wideiv25, %0
br i1 %exitcond26, label %for1.loopexit, label %for1.header
for1.loopexit:
br label %exit
exit:
ret void
}
; CHECK-LABEL: @interchange_02
; CHECK: for1.header:
; CHECK-NEXT: %indvars.iv23 = phi i64 [ 0, %for1.ph ], [ %indvars.iv.next24, %for1.inc10 ]
; CHECK-NEXT: br i1 %cmp219, label %for2.split1, label %for1.loopexit
; CHECK: for2.split1:
; CHECK: br label %for2.loopexit
; CHECK: for2.split:
; CHECK-NEXT: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: br i1 %exitcond, label %for1.loopexit, label %for2
; CHECK: for2.loopexit:
; CHECK-NEXT: br label %for1.inc10
; CHECK: for1.inc10:
; CHECK: br i1 %exitcond26, label %for2.split, label %for1.header

76
external/llvm/test/Transforms/LoopInterchange/current-limitations-lcssa.ll vendored
View File

@ -1,76 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@C = common global [100 x [100 x i32]] zeroinitializer
;; FIXME:
;; Test for interchange when we have an lcssa phi. This should ideally be interchanged but it is currently not supported.
;; for(gi=1;gi<N;gi++)
;; for(gj=1;gj<M;gj++)
;; A[gj][gi] = A[gj - 1][gi] + C[gj][gi];
@gi = common global i32 0
@gj = common global i32 0
define void @interchange_07(i32 %N, i32 %M){
entry:
store i32 1, i32* @gi
%cmp21 = icmp sgt i32 %N, 1
br i1 %cmp21, label %for.cond1.preheader.lr.ph, label %for.end16
for.cond1.preheader.lr.ph:
%cmp218 = icmp sgt i32 %M, 1
%gi.promoted = load i32, i32* @gi
%0 = add i32 %M, -1
%1 = sext i32 %gi.promoted to i64
%2 = sext i32 %N to i64
%3 = add i32 %gi.promoted, 1
%4 = icmp slt i32 %3, %N
%smax = select i1 %4, i32 %N, i32 %3
br label %for.cond1.preheader
for.cond1.preheader:
%indvars.iv25 = phi i64 [ %1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next26, %for.inc14 ]
br i1 %cmp218, label %for.body3, label %for.inc14
for.body3:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.cond1.preheader ]
%5 = add nsw i64 %indvars.iv, -1
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %5, i64 %indvars.iv25
%6 = load i32, i32* %arrayidx5
%arrayidx9 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @C, i64 0, i64 %indvars.iv, i64 %indvars.iv25
%7 = load i32, i32* %arrayidx9
%add = add nsw i32 %7, %6
%arrayidx13 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv25
store i32 %add, i32* %arrayidx13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc14, label %for.body3
for.inc14:
%inc.lcssa23 = phi i32 [ 1, %for.cond1.preheader ], [ %M, %for.body3 ]
%indvars.iv.next26 = add nsw i64 %indvars.iv25, 1
%cmp = icmp slt i64 %indvars.iv.next26, %2
br i1 %cmp, label %for.cond1.preheader, label %for.cond.for.end16_crit_edge
for.cond.for.end16_crit_edge:
store i32 %inc.lcssa23, i32* @gj
store i32 %smax, i32* @gi
br label %for.end16
for.end16:
ret void
}
; CHECK-LABEL: @interchange_07
; CHECK: for.body3: ; preds = %for.body3.preheader, %for.body3
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.body3.preheader ]
; CHECK: %5 = add nsw i64 %indvars.iv, -1
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %5, i64 %indvars.iv25
; CHECK: %6 = load i32, i32* %arrayidx5
; CHECK: %arrayidx9 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @C, i64 0, i64 %indvars.iv, i64 %indvars.iv25

58
external/llvm/test/Transforms/LoopInterchange/currentLimitation.ll vendored
View File

@ -1,58 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; These are test that fail to interchange due to current limitation. This will go off once we extend the loop interchange pass.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x [100 x [100 x i32]]] zeroinitializer
;;--------------------------------------Test case 01------------------------------------
;; [FIXME] This loop though valid is currently not interchanged due to the limitation that we cannot split the inner loop latch due to multiple use of inner induction
;; variable.(used to increment the loop counter and to access A[j+1][i+1]
;; for(int i=0;i<N-1;i++)
;; for(int j=1;j<N-1;j++)
;; A[j+1][i+1] = A[j+1][i+1] + k;
define void @interchange_01(i32 %k, i32 %N) {
entry:
%sub = add nsw i32 %N, -1
%cmp26 = icmp sgt i32 %N, 1
br i1 %cmp26, label %for.cond1.preheader.lr.ph, label %for.end17
for.cond1.preheader.lr.ph:
%cmp324 = icmp sgt i32 %sub, 1
%0 = add i32 %N, -2
%1 = sext i32 %sub to i64
br label %for.cond1.preheader
for.cond.loopexit:
%cmp = icmp slt i64 %indvars.iv.next29, %1
br i1 %cmp, label %for.cond1.preheader, label %for.end17
for.cond1.preheader:
%indvars.iv28 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next29, %for.cond.loopexit ]
%indvars.iv.next29 = add nuw nsw i64 %indvars.iv28, 1
br i1 %cmp324, label %for.body4, label %for.cond.loopexit
for.body4:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body4 ], [ 1, %for.cond1.preheader ]
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv.next, i64 %indvars.iv.next29
%2 = load i32, i32* %arrayidx7
%add8 = add nsw i32 %2, %k
store i32 %add8, i32* %arrayidx7
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.cond.loopexit, label %for.body4
for.end17:
ret void
}
;; Inner loop not split so it is not interchanged.
; CHECK-LABEL: @interchange_01
; CHECK: for.body4:
; CHECK-NEXT: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body4 ], [ 1, %for.body4.preheader ]
; CHECK-NEXT: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK-NEXT: %arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv.next, i64 %indvars.iv.next29

118
external/llvm/test/Transforms/LoopInterchange/interchange-flow-dep-outer.ll vendored
View File

@ -1,118 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
@C = common global [100 x [100 x i32]] zeroinitializer
@D = common global [100 x [100 x [100 x i32]]] zeroinitializer
;; Test that a flow dependency in outer loop doesn't prevent interchange in
;; loops i and j.
;;
;; for (int k = 0; k < 100; ++k) {
;; T[k] = fn1();
;; for (int i = 0; i < 1000; ++i)
;; for(int j = 1; j < 1000; ++j)
;; Arr[j][i] = Arr[j][i]+k;
;; fn2(T[k]);
;; }
@T = internal global [100 x double] zeroinitializer, align 4
@Arr = internal global [1000 x [1000 x i32]] zeroinitializer, align 4
define void @interchange_09(i32 %k) {
entry:
br label %for.body
for.cond.cleanup: ; preds = %for.cond.cleanup4
ret void
for.body: ; preds = %for.cond.cleanup4, %entry
%indvars.iv45 = phi i64 [ 0, %entry ], [ %indvars.iv.next46, %for.cond.cleanup4 ]
%call = call double @fn1()
%arrayidx = getelementptr inbounds [100 x double], [100 x double]* @T, i64 0, i64 %indvars.iv45
store double %call, double* %arrayidx, align 8
br label %for.cond6.preheader
for.cond6.preheader: ; preds = %for.cond.cleanup8, %for.body
%indvars.iv42 = phi i64 [ 0, %for.body ], [ %indvars.iv.next43, %for.cond.cleanup8 ]
br label %for.body9
for.cond.cleanup4: ; preds = %for.cond.cleanup8
%tmp = load double, double* %arrayidx, align 8
call void @fn2(double %tmp)
%indvars.iv.next46 = add nuw nsw i64 %indvars.iv45, 1
%exitcond47 = icmp ne i64 %indvars.iv.next46, 100
br i1 %exitcond47, label %for.body, label %for.cond.cleanup
for.cond.cleanup8: ; preds = %for.body9
%indvars.iv.next43 = add nuw nsw i64 %indvars.iv42, 1
%exitcond44 = icmp ne i64 %indvars.iv.next43, 1000
br i1 %exitcond44, label %for.cond6.preheader, label %for.cond.cleanup4
for.body9: ; preds = %for.body9, %for.cond6.preheader
%indvars.iv = phi i64 [ 1, %for.cond6.preheader ], [ %indvars.iv.next, %for.body9 ]
%arrayidx13 = getelementptr inbounds [1000 x [1000 x i32]], [1000 x [1000 x i32]]* @Arr, i64 0, i64 %indvars.iv, i64 %indvars.iv42
%tmp1 = load i32, i32* %arrayidx13, align 4
%tmp2 = trunc i64 %indvars.iv45 to i32
%add = add nsw i32 %tmp1, %tmp2
store i32 %add, i32* %arrayidx13, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 1000
br i1 %exitcond, label %for.body9, label %for.cond.cleanup8
}
declare double @fn1() readnone
declare void @fn2(double) readnone
;; After interchange %indvars.iv (j) should increment as the middle loop.
;; After interchange %indvars.iv42 (i) should increment with the inner most loop.
; CHECK-LABEL: @interchange_09
; CHECK: for.body:
; CHECK: %indvars.iv45 = phi i64 [ %indvars.iv.next46, %for.cond.cleanup4 ], [ 0, %for.body.preheader ]
; CHECK: %call = call double @fn1()
; CHECK: %arrayidx = getelementptr inbounds [100 x double], [100 x double]* @T, i64 0, i64 %indvars.iv45
; CHECK: store double %call, double* %arrayidx, align 8
; CHECK: br label %for.body9.preheader
; CHECK: for.cond6.preheader.preheader:
; CHECK: br label %for.cond6.preheader
; CHECK: for.cond6.preheader:
; CHECK: %indvars.iv42 = phi i64 [ %indvars.iv.next43, %for.cond.cleanup8 ], [ 0, %for.cond6.preheader.preheader ]
; CHECK: br label %for.body9.split1
; CHECK: for.body9.preheader:
; CHECK: br label %for.body9
; CHECK: for.cond.cleanup4:
; CHECK: %tmp = load double, double* %arrayidx, align 8
; CHECK: call void @fn2(double %tmp)
; CHECK: %indvars.iv.next46 = add nuw nsw i64 %indvars.iv45, 1
; CHECK: %exitcond47 = icmp ne i64 %indvars.iv.next46, 100
; CHECK: br i1 %exitcond47, label %for.body, label %for.cond.cleanup
; CHECK: for.cond.cleanup8:
; CHECK: %indvars.iv.next43 = add nuw nsw i64 %indvars.iv42, 1
; CHECK: %exitcond44 = icmp ne i64 %indvars.iv.next43, 1000
; CHECK: br i1 %exitcond44, label %for.cond6.preheader, label %for.body9.split
; CHECK: for.body9:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body9.split ], [ 1, %for.body9.preheader ]
; CHECK: br label %for.cond6.preheader.preheader
; CHECK: for.body9.split1:
; CHECK: %arrayidx13 = getelementptr inbounds [1000 x [1000 x i32]], [1000 x [1000 x i32]]* @Arr, i64 0, i64 %indvars.iv, i64 %indvars.iv42
; CHECK: store i32 %add, i32* %arrayidx13, align 4
; CHECK: br label %for.cond.cleanup8
; CHECK: for.body9.split:
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %exitcond = icmp ne i64 %indvars.iv.next, 1000
; CHECK: br i1 %exitcond, label %for.body9, label %for.cond.cleanup4

80
external/llvm/test/Transforms/LoopInterchange/interchange-insts-between-indvar.ll vendored
View File

@ -1,80 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
@A10 = local_unnamed_addr global [3 x [3 x i32]] zeroinitializer, align 16
;; Test to make sure we can handle zext intructions introduced by
;; IndVarSimplify.
;;
;; for (int i = 0; i < 2; ++i)
;; for(int j = 0; j < n; ++j) {
;; A[j][i] = i;
;; }
@A11 = local_unnamed_addr global [3 x [3 x i32]] zeroinitializer, align 16
define void @interchange_11(i32 %n) {
entry:
br label %for.cond1.preheader
for.cond.loopexit: ; preds = %for.body4
%exitcond28 = icmp ne i64 %indvars.iv.next27, 2
br i1 %exitcond28, label %for.cond1.preheader, label %for.cond.cleanup
for.cond1.preheader: ; preds = %for.cond.loopexit, %entry
%indvars.iv26 = phi i64 [ 0, %entry ], [ %indvars.iv.next27, %for.cond.loopexit ]
%indvars.iv.next27 = add nuw nsw i64 %indvars.iv26, 1
br label %for.body4
for.cond.cleanup: ; preds = %for.cond.loopexit
ret void
for.body4: ; preds = %for.body4, %for.cond1.preheader
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body4 ]
%arrayidx6 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv26
%tmp = trunc i64 %indvars.iv26 to i32
store i32 %tmp, i32* %arrayidx6, align 4
%arrayidx10 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv.next27
%tmp1 = trunc i64 %indvars.iv to i32
store i32 %tmp1, i32* %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%n.wide = zext i32 %n to i64
%exitcond = icmp ne i64 %indvars.iv.next, %n.wide
br i1 %exitcond, label %for.body4, label %for.cond.loopexit
}
; CHECK-LABEL: @interchange_11
; CHECK: entry:
; CHECK: br label %for.body4.preheader
; CHECK: for.cond1.preheader.preheader:
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond.loopexit:
; CHECK: %exitcond28 = icmp ne i64 %indvars.iv.next27, 2
; CHECK: br i1 %exitcond28, label %for.cond1.preheader, label %for.body4.split
; CHECK: for.cond1.preheader:
; CHECK: %indvars.iv26 = phi i64 [ %indvars.iv.next27, %for.cond.loopexit ], [ 0, %for.cond1.preheader.preheader ]
; CHECK: %indvars.iv.next27 = add nuw nsw i64 %indvars.iv26, 1
; CHECK: br label %for.body4.split1
; CHECK: for.body4.preheader:
; CHECK: br label %for.body4
; CHECK: for.cond.cleanup:
; CHECK: ret void
; CHECK: for.body4:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body4.split ], [ 0, %for.body4.preheader ]
; CHECK: br label %for.cond1.preheader.preheader
; CHECK: for.body4.split1:
; CHECK: %arrayidx6 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv26
; CHECK: %tmp = trunc i64 %indvars.iv26 to i32
; CHECK: store i32 %tmp, i32* %arrayidx6, align 4
; CHECK: br label %for.cond.loopexit
; CHECK: for.body4.split:
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %exitcond = icmp ne i64 %indvars.iv.next, %n.wide
; CHECK: br i1 %exitcond, label %for.body4, label %for.cond.cleanup

66
external/llvm/test/Transforms/LoopInterchange/interchange-not-profitable.ll vendored
View File

@ -1,66 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
;; Loops should not be interchanged in this case as it is not profitable.
;; for(int i=0;i<100;i++)
;; for(int j=0;j<100;j++)
;; A[i][j] = A[i][j]+k;
define void @interchange_03(i32 %k) {
entry:
br label %for.cond1.preheader
for.cond1.preheader:
%indvars.iv21 = phi i64 [ 0, %entry ], [ %indvars.iv.next22, %for.inc10 ]
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ]
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv21, i64 %indvars.iv
%0 = load i32, i32* %arrayidx5
%add = add nsw i32 %0, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 100
br i1 %exitcond, label %for.inc10, label %for.body3
for.inc10:
%indvars.iv.next22 = add nuw nsw i64 %indvars.iv21, 1
%exitcond23 = icmp eq i64 %indvars.iv.next22, 100
br i1 %exitcond23, label %for.end12, label %for.cond1.preheader
for.end12:
ret void
}
; CHECK-LABEL: @interchange_03
; CHECK: entry:
; CHECK: br label %for.cond1.preheader.preheader
; CHECK: for.cond1.preheader.preheader: ; preds = %entry
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond1.preheader: ; preds = %for.cond1.preheader.preheader, %for.inc10
; CHECK: %indvars.iv21 = phi i64 [ %indvars.iv.next22, %for.inc10 ], [ 0, %for.cond1.preheader.preheader ]
; CHECK: br label %for.body3.preheader
; CHECK: for.body3.preheader: ; preds = %for.cond1.preheader
; CHECK: br label %for.body3
; CHECK: for.body3: ; preds = %for.body3.preheader, %for.body3
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.body3.preheader ]
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv21, i64 %indvars.iv
; CHECK: %0 = load i32, i32* %arrayidx5
; CHECK: %add = add nsw i32 %0, %k
; CHECK: store i32 %add, i32* %arrayidx5
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %exitcond = icmp eq i64 %indvars.iv.next, 100
; CHECK: br i1 %exitcond, label %for.inc10, label %for.body3
; CHECK: for.inc10: ; preds = %for.body3
; CHECK: %indvars.iv.next22 = add nuw nsw i64 %indvars.iv21, 1
; CHECK: %exitcond23 = icmp eq i64 %indvars.iv.next22, 100
; CHECK: br i1 %exitcond23, label %for.end12, label %for.cond1.preheader
; CHECK: for.end12: ; preds = %for.inc10
; CHECK: ret void

86
external/llvm/test/Transforms/LoopInterchange/interchange-output-dependencies.ll vendored
View File

@ -1,86 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
;; Test to make sure we can handle output dependencies.
;;
;; for (int i = 0; i < 2; ++i)
;; for(int j = 0; j < 3; ++j) {
;; A[j][i] = i;
;; A[j][i+1] = j;
;; }
@A10 = local_unnamed_addr global [3 x [3 x i32]] zeroinitializer, align 16
define void @interchange_10() {
entry:
br label %for.cond1.preheader
for.cond.loopexit: ; preds = %for.body4
%exitcond28 = icmp ne i64 %indvars.iv.next27, 2
br i1 %exitcond28, label %for.cond1.preheader, label %for.cond.cleanup
for.cond1.preheader: ; preds = %for.cond.loopexit, %entry
%indvars.iv26 = phi i64 [ 0, %entry ], [ %indvars.iv.next27, %for.cond.loopexit ]
%indvars.iv.next27 = add nuw nsw i64 %indvars.iv26, 1
br label %for.body4
for.cond.cleanup: ; preds = %for.cond.loopexit
ret void
for.body4: ; preds = %for.body4, %for.cond1.preheader
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body4 ]
%arrayidx6 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv26
%tmp = trunc i64 %indvars.iv26 to i32
store i32 %tmp, i32* %arrayidx6, align 4
%arrayidx10 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv.next27
%tmp1 = trunc i64 %indvars.iv to i32
store i32 %tmp1, i32* %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 3
br i1 %exitcond, label %for.body4, label %for.cond.loopexit
}
; CHECK-LABEL: @interchange_10
; CHECK: entry:
; CHECK: br label %for.body4.preheader
; CHECK: for.cond1.preheader.preheader:
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond.loopexit:
; CHECK: %exitcond28 = icmp ne i64 %indvars.iv.next27, 2
; CHECK: br i1 %exitcond28, label %for.cond1.preheader, label %for.body4.split
; CHECK: for.cond1.preheader:
; CHECK: %indvars.iv26 = phi i64 [ %indvars.iv.next27, %for.cond.loopexit ], [ 0, %for.cond1.preheader.preheader ]
; CHECK: %indvars.iv.next27 = add nuw nsw i64 %indvars.iv26, 1
; CHECK: br label %for.body4.split1
; CHECK: for.body4.preheader:
; CHECK: br label %for.body4
; CHECK: for.cond.cleanup:
; CHECK: ret void
; CHECK: for.body4:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body4.split ], [ 0, %for.body4.preheader ]
; CHECK: br label %for.cond1.preheader.preheader
; CHECK: for.body4.split1:
; CHECK: %arrayidx6 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv26
; CHECK: %tmp = trunc i64 %indvars.iv26 to i32
; CHECK: store i32 %tmp, i32* %arrayidx6, align 4
; CHECK: %arrayidx10 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv.next27
; CHECK: %tmp1 = trunc i64 %indvars.iv to i32
; CHECK: store i32 %tmp1, i32* %arrayidx10, align 4
; CHECK: br label %for.cond.loopexit
; CHECK: for.body4.split:
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %exitcond = icmp ne i64 %indvars.iv.next, 3
; CHECK: br i1 %exitcond, label %for.body4, label %for.cond.cleanup

69
external/llvm/test/Transforms/LoopInterchange/interchange-simple-count-down.ll vendored
View File

@ -1,69 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
;; for(int i=0;i<100;i++)
;; for(int j=100;j>=0;j--)
;; A[j][i] = A[j][i]+k;
define void @interchange_02(i32 %k) {
entry:
br label %for.cond1.preheader
for.cond1.preheader:
%indvars.iv19 = phi i64 [ 0, %entry ], [ %indvars.iv.next20, %for.inc10 ]
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 100, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ]
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv19
%0 = load i32, i32* %arrayidx5
%add = add nsw i32 %0, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nsw i64 %indvars.iv, -1
%cmp2 = icmp sgt i64 %indvars.iv, 0
br i1 %cmp2, label %for.body3, label %for.inc10
for.inc10:
%indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
%exitcond = icmp eq i64 %indvars.iv.next20, 100
br i1 %exitcond, label %for.end11, label %for.cond1.preheader
for.end11:
ret void
}
; CHECK-LABEL: @interchange_02
; CHECK: entry:
; CHECK: br label %for.body3.preheader
; CHECK: for.cond1.preheader.preheader:
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond1.preheader:
; CHECK: %indvars.iv19 = phi i64 [ %indvars.iv.next20, %for.inc10 ], [ 0, %for.cond1.preheader.preheader ]
; CHECK: br label %for.body3.split1
; CHECK: for.body3.preheader:
; CHECK: br label %for.body3
; CHECK: for.body3:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3.split ], [ 100, %for.body3.preheader ]
; CHECK: br label %for.cond1.preheader.preheader
; CHECK: for.body3.split1: ; preds = %for.cond1.preheader
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv19
; CHECK: %0 = load i32, i32* %arrayidx5
; CHECK: %add = add nsw i32 %0, %k
; CHECK: store i32 %add, i32* %arrayidx5
; CHECK: br label %for.inc10
; CHECK: for.body3.split:
; CHECK: %indvars.iv.next = add nsw i64 %indvars.iv, -1
; CHECK: %cmp2 = icmp sgt i64 %indvars.iv, 0
; CHECK: br i1 %cmp2, label %for.body3, label %for.end11
; CHECK: for.inc10:
; CHECK: %indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
; CHECK: %exitcond = icmp eq i64 %indvars.iv.next20, 100
; CHECK: br i1 %exitcond, label %for.body3.split, label %for.cond1.preheader
; CHECK: for.end11:
; CHECK: ret void

86
external/llvm/test/Transforms/LoopInterchange/interchange-simple-count-up.ll vendored
View File

@ -1,86 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
;; for(int i=0;i<N;i++)
;; for(int j=1;j<N;j++)
;; A[j][i] = A[j][i]+k;
define void @interchange_01(i32 %k, i32 %N) {
entry:
%cmp21 = icmp sgt i32 %N, 0
br i1 %cmp21, label %for.cond1.preheader.lr.ph, label %for.end12
for.cond1.preheader.lr.ph:
%cmp219 = icmp sgt i32 %N, 1
%0 = add i32 %N, -1
br label %for.cond1.preheader
for.cond1.preheader:
%indvars.iv23 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next24, %for.inc10 ]
br i1 %cmp219, label %for.body3, label %for.inc10
for.body3:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.cond1.preheader ]
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv23
%1 = load i32, i32* %arrayidx5
%add = add nsw i32 %1, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc10, label %for.body3
for.inc10:
%indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
%lftr.wideiv25 = trunc i64 %indvars.iv23 to i32
%exitcond26 = icmp eq i32 %lftr.wideiv25, %0
br i1 %exitcond26, label %for.end12, label %for.cond1.preheader
for.end12:
ret void
}
; CHECK-LABEL: @interchange_01
; CHECK: entry:
; CHECK: %cmp21 = icmp sgt i32 %N, 0
; CHECK: br i1 %cmp21, label %for.body3.preheader, label %for.end12
; CHECK: for.cond1.preheader.lr.ph:
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond1.preheader:
; CHECK: %indvars.iv23 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next24, %for.inc10 ]
; CHECK: br i1 %cmp219, label %for.body3.split1, label %for.end12.loopexit
; CHECK: for.body3.preheader:
; CHECK: %cmp219 = icmp sgt i32 %N, 1
; CHECK: %0 = add i32 %N, -1
; CHECK: br label %for.body3
; CHECK: for.body3:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3.split ], [ 1, %for.body3.preheader ]
; CHECK: br label %for.cond1.preheader.lr.ph
; CHECK: for.body3.split1:
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv23
; CHECK: %1 = load i32, i32* %arrayidx5
; CHECK: %add = add nsw i32 %1, %k
; CHECK: store i32 %add, i32* %arrayidx5
; CHECK: br label %for.inc10.loopexit
; CHECK: for.body3.split:
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %lftr.wideiv = trunc i64 %indvars.iv to i32
; CHECK: %exitcond = icmp eq i32 %lftr.wideiv, %0
; CHECK: br i1 %exitcond, label %for.end12.loopexit, label %for.body3
; CHECK: for.inc10.loopexit:
; CHECK: br label %for.inc10
; CHECK: for.inc10:
; CHECK: %indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
; CHECK: %lftr.wideiv25 = trunc i64 %indvars.iv23 to i32
; CHECK: %exitcond26 = icmp eq i32 %lftr.wideiv25, %0
; CHECK: br i1 %exitcond26, label %for.body3.split, label %for.cond1.preheader
; CHECK: for.end12.loopexit:
; CHECK: br label %for.end12
; CHECK: for.end12:
; CHECK: ret void

220
external/llvm/test/Transforms/LoopInterchange/loop-interchange-optimization-remarks.ll vendored
View File

@ -1,220 +0,0 @@
; Test optimization remarks generated by the LoopInterchange pass.
;
; RUN: opt < %s -basicaa -loop-interchange -pass-remarks-output=%t -pass-remarks-missed='loop-interchange' \
; RUN: -pass-remarks='loop-interchange' -S
; RUN: cat %t | FileCheck %s
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x [100 x i32]] zeroinitializer
@C = common global [100 x i32] zeroinitializer
;;---------------------------------------Test case 01---------------------------------
;; Loops interchange is not profitable.
;; for(int i=1;i<N;i++)
;; for(int j=1;j<N;j++)
;; A[i-1][j-1] = A[i - 1][j-1] + B[i][j];
define void @test01(i32 %N){
entry:
%cmp31 = icmp sgt i32 %N, 1
br i1 %cmp31, label %for.cond1.preheader.lr.ph, label %for.end19
for.cond1.preheader.lr.ph:
%0 = add i32 %N, -1
br label %for.body3.lr.ph
for.body3.lr.ph:
%indvars.iv34 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next35, %for.inc17 ]
%1 = add nsw i64 %indvars.iv34, -1
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 1, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
%2 = add nsw i64 %indvars.iv, -1
%arrayidx6 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %1, i64 %2
%3 = load i32, i32* %arrayidx6
%arrayidx10 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %indvars.iv34, i64 %indvars.iv
%4 = load i32, i32* %arrayidx10
%add = add nsw i32 %4, %3
store i32 %add, i32* %arrayidx6
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc17, label %for.body3
for.inc17:
%indvars.iv.next35 = add nuw nsw i64 %indvars.iv34, 1
%lftr.wideiv37 = trunc i64 %indvars.iv34 to i32
%exitcond38 = icmp eq i32 %lftr.wideiv37, %0
br i1 %exitcond38, label %for.end19, label %for.body3.lr.ph
for.end19:
ret void
}
; CHECK: --- !Missed
; CHECK-NEXT: Pass: loop-interchange
; CHECK-NEXT: Name: InterchangeNotProfitable
; CHECK-NEXT: Function: test01
; CHECK-NEXT: Args:
; CHECK-NEXT: - String: 'Interchanging loops is too costly (cost='
; CHECK-NEXT: - Cost: '2'
; CHECK-NEXT: - String: ', threshold='
; CHECK-NEXT: - Threshold: '0'
; CHECK-NEXT: - String: ') and it does not improve parallelism.'
; CHECK-NEXT: ...
;;--------------------------------------Test case 02------------------------------------
;; [FIXME] This loop though valid is currently not interchanged due to the
;; limitation that we cannot split the inner loop latch due to multiple use of inner induction
;; variable.(used to increment the loop counter and to access A[j+1][i+1]
;; for(int i=0;i<N-1;i++)
;; for(int j=1;j<N-1;j++)
;; A[j+1][i+1] = A[j+1][i+1] + k;
define void @test02(i32 %k, i32 %N) {
entry:
%sub = add nsw i32 %N, -1
%cmp26 = icmp sgt i32 %N, 1
br i1 %cmp26, label %for.cond1.preheader.lr.ph, label %for.end17
for.cond1.preheader.lr.ph:
%cmp324 = icmp sgt i32 %sub, 1
%0 = add i32 %N, -2
%1 = sext i32 %sub to i64
br label %for.cond1.preheader
for.cond.loopexit:
%cmp = icmp slt i64 %indvars.iv.next29, %1
br i1 %cmp, label %for.cond1.preheader, label %for.end17
for.cond1.preheader:
%indvars.iv28 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next29, %for.cond.loopexit ]
%indvars.iv.next29 = add nuw nsw i64 %indvars.iv28, 1
br i1 %cmp324, label %for.body4, label %for.cond.loopexit
for.body4:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body4 ], [ 1, %for.cond1.preheader ]
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv.next, i64 %indvars.iv.next29
%2 = load i32, i32* %arrayidx7
%add8 = add nsw i32 %2, %k
store i32 %add8, i32* %arrayidx7
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.cond.loopexit, label %for.body4
for.end17:
ret void
}
; CHECK: --- !Missed
; CHECK-NEXT: Pass: loop-interchange
; CHECK-NEXT: Name: UnsupportedInsBetweenInduction
; CHECK-NEXT: Function: test02
; CHECK-NEXT: Args:
; CHECK-NEXT: - String: Found unsupported instruction between induction variable increment and branch.
; CHECK-NEXT: ...
;;-----------------------------------Test case 03-------------------------------
;; Test to make sure we can handle output dependencies.
;;
;; for (int i = 0; i < 2; ++i)
;; for(int j = 0; j < 3; ++j) {
;; A[j][i] = i;
;; A[j][i+1] = j;
;; }
@A10 = local_unnamed_addr global [3 x [3 x i32]] zeroinitializer, align 16
define void @test03() {
entry:
br label %for.cond1.preheader
for.cond.loopexit: ; preds = %for.body4
%exitcond28 = icmp ne i64 %indvars.iv.next27, 2
br i1 %exitcond28, label %for.cond1.preheader, label %for.cond.cleanup
for.cond1.preheader: ; preds = %for.cond.loopexit, %entry
%indvars.iv26 = phi i64 [ 0, %entry ], [ %indvars.iv.next27, %for.cond.loopexit ]
%indvars.iv.next27 = add nuw nsw i64 %indvars.iv26, 1
br label %for.body4
for.cond.cleanup: ; preds = %for.cond.loopexit
ret void
for.body4: ; preds = %for.body4, %for.cond1.preheader
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body4 ]
%arrayidx6 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv26
%tmp = trunc i64 %indvars.iv26 to i32
store i32 %tmp, i32* %arrayidx6, align 4
%arrayidx10 = getelementptr inbounds [3 x [3 x i32]], [3 x [3 x i32]]* @A10, i64 0, i64 %indvars.iv, i64 %indvars.iv.next27
%tmp1 = trunc i64 %indvars.iv to i32
store i32 %tmp1, i32* %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 3
br i1 %exitcond, label %for.body4, label %for.cond.loopexit
}
; CHECK: --- !Passed
; CHECK-NEXT: Pass: loop-interchange
; CHECK-NEXT: Name: Interchanged
; CHECK-NEXT: Function: test03
; CHECK-NEXT: Args:
; CHECK-NEXT: - String: Loop interchanged with enclosing loop.
; CHECK-NEXT: ...
;;--------------------------------------Test case 04-------------------------------------
;; Loops not tightly nested are not interchanged
;; for(int j=0;j<N;j++) {
;; B[j] = j+k;
;; for(int i=0;i<N;i++)
;; A[j][i] = A[j][i]+B[j];
;; }
define void @test04(i32 %k, i32 %N){
entry:
%cmp30 = icmp sgt i32 %N, 0
br i1 %cmp30, label %for.body.lr.ph, label %for.end17
for.body.lr.ph:
%0 = add i32 %N, -1
%1 = zext i32 %k to i64
br label %for.body
for.body:
%indvars.iv32 = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next33, %for.inc15 ]
%2 = add nsw i64 %indvars.iv32, %1
%arrayidx = getelementptr inbounds [100 x i32], [100 x i32]* @C, i64 0, i64 %indvars.iv32
%3 = trunc i64 %2 to i32
store i32 %3, i32* %arrayidx
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 0, %for.body ], [ %indvars.iv.next, %for.body3 ]
%arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv32, i64 %indvars.iv
%4 = load i32, i32* %arrayidx7
%add10 = add nsw i32 %3, %4
store i32 %add10, i32* %arrayidx7
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc15, label %for.body3
for.inc15:
%indvars.iv.next33 = add nuw nsw i64 %indvars.iv32, 1
%lftr.wideiv35 = trunc i64 %indvars.iv32 to i32
%exitcond36 = icmp eq i32 %lftr.wideiv35, %0
br i1 %exitcond36, label %for.end17, label %for.body
for.end17:
ret void
}
; CHECK: --- !Missed
; CHECK-NEXT: Pass: loop-interchange
; CHECK-NEXT: Name: NotTightlyNested
; CHECK-NEXT: Function: test04
; CHECK-NEXT: Args:
; CHECK-NEXT: - String: Cannot interchange loops because they are not tightly nested.
; CHECK-NEXT: ...

64
external/llvm/test/Transforms/LoopInterchange/not-interchanged-dependencies-1.ll vendored
View File

@ -1,64 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
;; Loops should not be interchanged in this case as it is not legal due to dependency.
;; for(int j=0;j<99;j++)
;; for(int i=0;i<99;i++)
;; A[j][i+1] = A[j+1][i]+k;
define void @interchange_04(i32 %k){
entry:
br label %for.cond1.preheader
for.cond1.preheader:
%indvars.iv23 = phi i64 [ 0, %entry ], [ %indvars.iv.next24, %for.inc12 ]
%indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ]
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv.next24, i64 %indvars.iv
%0 = load i32, i32* %arrayidx5
%add6 = add nsw i32 %0, %k
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx11 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv23, i64 %indvars.iv.next
store i32 %add6, i32* %arrayidx11
%exitcond = icmp eq i64 %indvars.iv.next, 99
br i1 %exitcond, label %for.inc12, label %for.body3
for.inc12:
%exitcond25 = icmp eq i64 %indvars.iv.next24, 99
br i1 %exitcond25, label %for.end14, label %for.cond1.preheader
for.end14:
ret void
}
; CHECK-LABEL: @interchange_04
; CHECK: entry:
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond1.preheader: ; preds = %for.inc12, %entry
; CHECK: %indvars.iv23 = phi i64 [ 0, %entry ], [ %indvars.iv.next24, %for.inc12 ]
; CHECK: %indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
; CHECK: br label %for.body3
; CHECK: for.body3: ; preds = %for.body3, %for.cond1.preheader
; CHECK: %indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ]
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv.next24, i64 %indvars.iv
; CHECK: %0 = load i32, i32* %arrayidx5
; CHECK: %add6 = add nsw i32 %0, %k
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %arrayidx11 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv23, i64 %indvars.iv.next
; CHECK: store i32 %add6, i32* %arrayidx11
; CHECK: %exitcond = icmp eq i64 %indvars.iv.next, 99
; CHECK: br i1 %exitcond, label %for.inc12, label %for.body3
; CHECK: for.inc12: ; preds = %for.body3
; CHECK: %exitcond25 = icmp eq i64 %indvars.iv.next24, 99
; CHECK: br i1 %exitcond25, label %for.end14, label %for.cond1.preheader
; CHECK: for.end14: ; preds = %for.inc12
; CHECK: ret void

87
external/llvm/test/Transforms/LoopInterchange/not-interchanged-loop-nest-3.ll vendored
View File

@ -1,87 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@D = common global [100 x [100 x [100 x i32]]] zeroinitializer
;; Test for interchange in loop nest greater than 2.
;; for(int i=0;i<100;i++)
;; for(int j=0;j<100;j++)
;; for(int k=0;k<100;k++)
;; D[i][k][j] = D[i][k][j]+t;
define void @interchange_08(i32 %t){
entry:
br label %for.cond1.preheader
for.cond1.preheader: ; preds = %for.inc15, %entry
%i.028 = phi i32 [ 0, %entry ], [ %inc16, %for.inc15 ]
br label %for.cond4.preheader
for.cond4.preheader: ; preds = %for.inc12, %for.cond1.preheader
%j.027 = phi i32 [ 0, %for.cond1.preheader ], [ %inc13, %for.inc12 ]
br label %for.body6
for.body6: ; preds = %for.body6, %for.cond4.preheader
%k.026 = phi i32 [ 0, %for.cond4.preheader ], [ %inc, %for.body6 ]
%arrayidx8 = getelementptr inbounds [100 x [100 x [100 x i32]]], [100 x [100 x [100 x i32]]]* @D, i32 0, i32 %i.028, i32 %k.026, i32 %j.027
%0 = load i32, i32* %arrayidx8
%add = add nsw i32 %0, %t
store i32 %add, i32* %arrayidx8
%inc = add nuw nsw i32 %k.026, 1
%exitcond = icmp eq i32 %inc, 100
br i1 %exitcond, label %for.inc12, label %for.body6
for.inc12: ; preds = %for.body6
%inc13 = add nuw nsw i32 %j.027, 1
%exitcond29 = icmp eq i32 %inc13, 100
br i1 %exitcond29, label %for.inc15, label %for.cond4.preheader
for.inc15: ; preds = %for.inc12
%inc16 = add nuw nsw i32 %i.028, 1
%exitcond30 = icmp eq i32 %inc16, 100
br i1 %exitcond30, label %for.end17, label %for.cond1.preheader
for.end17: ; preds = %for.inc15
ret void
}
; CHECK-LABEL: @interchange_08
; CHECK: entry:
; CHECK: br label %for.cond1.preheader.preheader
; CHECK: for.cond1.preheader.preheader: ; preds = %entry
; CHECK: br label %for.cond1.preheader
; CHECK: for.cond1.preheader: ; preds = %for.cond1.preheader.preheader, %for.inc15
; CHECK: %i.028 = phi i32 [ %inc16, %for.inc15 ], [ 0, %for.cond1.preheader.preheader ]
; CHECK: br label %for.body6.preheader
; CHECK: for.cond4.preheader.preheader: ; preds = %for.body6
; CHECK: br label %for.cond4.preheader
; CHECK: for.cond4.preheader: ; preds = %for.cond4.preheader.preheader, %for.inc12
; CHECK: %j.027 = phi i32 [ %inc13, %for.inc12 ], [ 0, %for.cond4.preheader.preheader ]
; CHECK: br label %for.body6.split1
; CHECK: for.body6.preheader: ; preds = %for.cond1.preheader
; CHECK: br label %for.body6
; CHECK: for.body6: ; preds = %for.body6.preheader, %for.body6.split
; CHECK: %k.026 = phi i32 [ %inc, %for.body6.split ], [ 0, %for.body6.preheader ]
; CHECK: br label %for.cond4.preheader.preheader
; CHECK: for.body6.split1: ; preds = %for.cond4.preheader
; CHECK: %arrayidx8 = getelementptr inbounds [100 x [100 x [100 x i32]]], [100 x [100 x [100 x i32]]]* @D, i32 0, i32 %i.028, i32 %k.026, i32 %j.027
; CHECK: %0 = load i32, i32* %arrayidx8
; CHECK: %add = add nsw i32 %0, %t
; CHECK: store i32 %add, i32* %arrayidx8
; CHECK: br label %for.inc12
; CHECK: for.body6.split: ; preds = %for.inc12
; CHECK: %inc = add nuw nsw i32 %k.026, 1
; CHECK: %exitcond = icmp eq i32 %inc, 100
; CHECK: br i1 %exitcond, label %for.inc15, label %for.body6
; CHECK: for.inc12: ; preds = %for.body6.split1
; CHECK: %inc13 = add nuw nsw i32 %j.027, 1
; CHECK: %exitcond29 = icmp eq i32 %inc13, 100
; CHECK: br i1 %exitcond29, label %for.body6.split, label %for.cond4.preheader
; CHECK: for.inc15: ; preds = %for.body6.split
; CHECK: %inc16 = add nuw nsw i32 %i.028, 1
; CHECK: %exitcond30 = icmp eq i32 %inc16, 100
; CHECK: br i1 %exitcond30, label %for.end17, label %for.cond1.preheader
; CHECK: for.end17: ; preds = %for.inc15
; CHECK: ret void

143
external/llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll vendored
View File

@ -1,143 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test the complete .ll for adjustment in outer loop header/latch and inner loop header/latch.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x i32] zeroinitializer
@C = common global [100 x [100 x i32]] zeroinitializer
@D = common global [100 x [100 x [100 x i32]]] zeroinitializer
;; Loops not tightly nested are not interchanged
;; for(int j=0;j<N;j++) {
;; B[j] = j+k;
;; for(int i=0;i<N;i++)
;; A[j][i] = A[j][i]+B[j];
;; }
define void @interchange_05(i32 %k, i32 %N){
entry:
%cmp30 = icmp sgt i32 %N, 0
br i1 %cmp30, label %for.body.lr.ph, label %for.end17
for.body.lr.ph:
%0 = add i32 %N, -1
%1 = zext i32 %k to i64
br label %for.body
for.body:
%indvars.iv32 = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next33, %for.inc15 ]
%2 = add nsw i64 %indvars.iv32, %1
%arrayidx = getelementptr inbounds [100 x i32], [100 x i32]* @B, i64 0, i64 %indvars.iv32
%3 = trunc i64 %2 to i32
store i32 %3, i32* %arrayidx
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 0, %for.body ], [ %indvars.iv.next, %for.body3 ]
%arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv32, i64 %indvars.iv
%4 = load i32, i32* %arrayidx7
%add10 = add nsw i32 %3, %4
store i32 %add10, i32* %arrayidx7
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc15, label %for.body3
for.inc15:
%indvars.iv.next33 = add nuw nsw i64 %indvars.iv32, 1
%lftr.wideiv35 = trunc i64 %indvars.iv32 to i32
%exitcond36 = icmp eq i32 %lftr.wideiv35, %0
br i1 %exitcond36, label %for.end17, label %for.body
for.end17:
ret void
}
; CHECK-LABEL: @interchange_05
; CHECK: entry:
; CHECK: %cmp30 = icmp sgt i32 %N, 0
; CHECK: br i1 %cmp30, label %for.body.lr.ph, label %for.end17
; CHECK: for.body.lr.ph:
; CHECK: %0 = add i32 %N, -1
; CHECK: %1 = zext i32 %k to i64
; CHECK: br label %for.body
; CHECK: for.body:
; CHECK: %indvars.iv32 = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next33, %for.inc15 ]
; CHECK: %2 = add nsw i64 %indvars.iv32, %1
; CHECK: %arrayidx = getelementptr inbounds [100 x i32], [100 x i32]* @B, i64 0, i64 %indvars.iv32
; CHECK: %3 = trunc i64 %2 to i32
; CHECK: store i32 %3, i32* %arrayidx
; CHECK: br label %for.body3.preheader
; CHECK: for.body3.preheader:
; CHECK: br label %for.body3
; CHECK: for.body3:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.body3.preheader ]
; CHECK: %arrayidx7 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv32, i64 %indvars.iv
; CHECK: %4 = load i32, i32* %arrayidx7
; CHECK: %add10 = add nsw i32 %3, %4
; CHECK: store i32 %add10, i32* %arrayidx7
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %lftr.wideiv = trunc i64 %indvars.iv to i32
; CHECK: %exitcond = icmp eq i32 %lftr.wideiv, %0
; CHECK: br i1 %exitcond, label %for.inc15, label %for.body3
; CHECK: for.inc15:
; CHECK: %indvars.iv.next33 = add nuw nsw i64 %indvars.iv32, 1
; CHECK: %lftr.wideiv35 = trunc i64 %indvars.iv32 to i32
; CHECK: %exitcond36 = icmp eq i32 %lftr.wideiv35, %0
; CHECK: br i1 %exitcond36, label %for.end17.loopexit, label %for.body
; CHECK: for.end17.loopexit:
; CHECK: br label %for.end17
; CHECK: for.end17:
; CHECK: ret void
declare void @foo(...) readnone
;; Loops not tightly nested are not interchanged
;; for(int j=0;j<N;j++) {
;; foo();
;; for(int i=2;i<N;i++)
;; A[j][i] = A[j][i]+k;
;; }
define void @interchange_06(i32 %k, i32 %N) {
entry:
%cmp22 = icmp sgt i32 %N, 0
br i1 %cmp22, label %for.body.lr.ph, label %for.end12
for.body.lr.ph:
%0 = add i32 %N, -1
br label %for.body
for.body:
%indvars.iv24 = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next25, %for.inc10 ]
tail call void (...) @foo()
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 2, %for.body ]
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv24, i64 %indvars.iv
%1 = load i32, i32* %arrayidx5
%add = add nsw i32 %1, %k
store i32 %add, i32* %arrayidx5
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc10, label %for.body3
for.inc10:
%indvars.iv.next25 = add nuw nsw i64 %indvars.iv24, 1
%lftr.wideiv26 = trunc i64 %indvars.iv24 to i32
%exitcond27 = icmp eq i32 %lftr.wideiv26, %0
br i1 %exitcond27, label %for.end12, label %for.body
for.end12:
ret void
}
;; Here we are checking if the inner phi is not split then we have not interchanged.
; CHECK-LABEL: @interchange_06
; CHECK: phi i64 [ %indvars.iv.next, %for.body3 ], [ 2, %for.body3.preheader ]
; CHECK-NEXT: getelementptr
; CHECK-NEXT: %1 = load

90
external/llvm/test/Transforms/LoopInterchange/phi-ordering.ll vendored
View File

@ -1,90 +0,0 @@
; RUN: opt < %s -loop-interchange -S | FileCheck %s
;; Checks the order of the inner phi nodes does not cause havoc.
;; The inner loop has a reduction into c. The IV is not the first phi.
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "armv8--linux-gnueabihf"
; Function Attrs: norecurse nounwind
define void @test(i32 %T, [90 x i32]* noalias nocapture %C, i16* noalias nocapture readonly %A, i16* noalias nocapture readonly %B) local_unnamed_addr #0 {
entry:
%cmp45 = icmp sgt i32 %T, 0
br i1 %cmp45, label %for.body3.lr.ph.preheader, label %for.end21
for.body3.lr.ph.preheader: ; preds = %entry
br label %for.body3.lr.ph
for.body3.lr.ph: ; preds = %for.body3.lr.ph.preheader, %for.inc19
%i.046 = phi i32 [ %inc20, %for.inc19 ], [ 0, %for.body3.lr.ph.preheader ]
%mul = mul nsw i32 %i.046, %T
br label %for.body6.lr.ph
for.body6.lr.ph: ; preds = %for.inc16, %for.body3.lr.ph
%j.043 = phi i32 [ 0, %for.body3.lr.ph ], [ %inc17, %for.inc16 ]
%arrayidx14 = getelementptr inbounds [90 x i32], [90 x i32]* %C, i32 %i.046, i32 %j.043
%arrayidx14.promoted = load i32, i32* %arrayidx14, align 4
br label %for.body6
for.body6: ; preds = %for.body6, %for.body6.lr.ph
%add1541 = phi i32 [ %arrayidx14.promoted, %for.body6.lr.ph ], [ %add15, %for.body6 ]
%k.040 = phi i32 [ 0, %for.body6.lr.ph ], [ %inc, %for.body6 ]
%add = add nsw i32 %k.040, %mul
%arrayidx = getelementptr inbounds i16, i16* %A, i32 %add
%0 = load i16, i16* %arrayidx, align 2
%conv = sext i16 %0 to i32
%mul7 = mul nsw i32 %k.040, %T
%add8 = add nsw i32 %mul7, %j.043
%arrayidx9 = getelementptr inbounds i16, i16* %B, i32 %add8
%1 = load i16, i16* %arrayidx9, align 2
%conv10 = sext i16 %1 to i32
%mul11 = mul nsw i32 %conv10, %conv
%add15 = add nsw i32 %mul11, %add1541
%inc = add nuw nsw i32 %k.040, 1
%exitcond = icmp eq i32 %inc, %T
br i1 %exitcond, label %for.inc16, label %for.body6
for.inc16: ; preds = %for.body6
%add15.lcssa = phi i32 [ %add15, %for.body6 ]
store i32 %add15.lcssa, i32* %arrayidx14, align 4
%inc17 = add nuw nsw i32 %j.043, 1
%exitcond47 = icmp eq i32 %inc17, %T
br i1 %exitcond47, label %for.inc19, label %for.body6.lr.ph
for.inc19: ; preds = %for.inc16
%inc20 = add nuw nsw i32 %i.046, 1
%exitcond48 = icmp eq i32 %inc20, %T
br i1 %exitcond48, label %for.end21.loopexit, label %for.body3.lr.ph
for.end21.loopexit: ; preds = %for.inc19
br label %for.end21
for.end21: ; preds = %for.end21.loopexit, %entry
ret void
}
; CHECK-LABEL: test
; CHECK: entry:
; CHECK: br i1 %cmp45, label %for.body6.preheader, label %for.end21
; CHECK: for.body3.lr.ph.preheader:
; CHECK: br label %for.body3.lr.ph
; CHECK: for.body3.lr.ph:
; CHECK: br label %for.body6.lr.ph.preheader
; CHECK: for.body6.lr.ph.preheader:
; CHECK: br label %for.body6.lr.ph
; CHECK: for.body6.lr.ph:
; CHECK: br label %for.body6.split1
; CHECK: for.body6.preheader:
; CHECK: br label %for.body6
; CHECK: for.body6:
; CHECK: br label %for.body3.lr.ph.preheader
; CHECK: for.body6.split1:
; CHECK: br label %for.inc16
; CHECK: for.body6.split:
; CHECK: add nuw nsw i32 %k.040, 1
; CHECK: br i1 %exitcond, label %for.end21.loopexit, label %for.body6
; CHECK: for.inc16:
; CHECK: br i1 %exitcond47, label %for.inc19, label %for.body6.lr.ph
; CHECK: for.inc19:
; CHECK: br i1 %exitcond48, label %for.body6.split, label %for.body3.lr.ph
; CHECK: for.end21:

205
external/llvm/test/Transforms/LoopInterchange/profitability.ll vendored
View File

@ -1,205 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
;; We test profitability model in these test cases.
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [100 x [100 x i32]] zeroinitializer
@B = common global [100 x [100 x i32]] zeroinitializer
;;---------------------------------------Test case 01---------------------------------
;; Loops interchange will result in code vectorization and hence profitable. Check for interchange.
;; for(int i=1;i<N;i++)
;; for(int j=1;j<N;j++)
;; A[j][i] = A[j - 1][i] + B[j][i];
define void @interchange_01(i32 %N) {
entry:
%cmp27 = icmp sgt i32 %N, 1
br i1 %cmp27, label %for.cond1.preheader.lr.ph, label %for.end16
for.cond1.preheader.lr.ph:
%0 = add i32 %N, -1
br label %for.body3.preheader
for.body3.preheader:
%indvars.iv30 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next31, %for.inc14 ]
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.body3.preheader ]
%1 = add nsw i64 %indvars.iv, -1
%arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %1, i64 %indvars.iv30
%2 = load i32, i32* %arrayidx5
%arrayidx9 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %indvars.iv, i64 %indvars.iv30
%3 = load i32, i32* %arrayidx9
%add = add nsw i32 %3, %2
%arrayidx13 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv30
store i32 %add, i32* %arrayidx13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc14, label %for.body3
for.inc14:
%indvars.iv.next31 = add nuw nsw i64 %indvars.iv30, 1
%lftr.wideiv32 = trunc i64 %indvars.iv30 to i32
%exitcond33 = icmp eq i32 %lftr.wideiv32, %0
br i1 %exitcond33, label %for.end16, label %for.body3.preheader
for.end16:
ret void
}
;; Here we are checking partial .ll to check if loop are interchanged.
; CHECK-LABEL: @interchange_01
; CHECK: for.body3.preheader: ; preds = %for.inc14, %for.cond1.preheader.lr.ph
; CHECK: %indvars.iv30 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next31, %for.inc14 ]
; CHECK: br label %for.body3.split2
; CHECK: for.body3.preheader1: ; preds = %entry
; CHECK: br label %for.body3
; CHECK: for.body3: ; preds = %for.body3.preheader1, %for.body3.split
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3.split ], [ 1, %for.body3.preheader1 ]
; CHECK: br label %for.cond1.preheader.lr.ph
; CHECK: for.body3.split2: ; preds = %for.body3.preheader
; CHECK: %1 = add nsw i64 %indvars.iv, -1
; CHECK: %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %1, i64 %indvars.iv30
; CHECK: %2 = load i32, i32* %arrayidx5
; CHECK: %arrayidx9 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %indvars.iv, i64 %indvars.iv30
; CHECK: %3 = load i32, i32* %arrayidx9
; CHECK: %add = add nsw i32 %3, %2
; CHECK: %arrayidx13 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv30
; CHECK: store i32 %add, i32* %arrayidx13
; CHECK: br label %for.inc14
;; ---------------------------------------Test case 02---------------------------------
;; Check loop interchange profitability model.
;; This tests profitability model when operands of getelementpointer and not exactly the induction variable but some
;; arithmetic operation on them.
;; for(int i=1;i<N;i++)
;; for(int j=1;j<N;j++)
;; A[j-1][i-1] = A[j - 1][i-1] + B[j-1][i-1];
define void @interchange_02(i32 %N) {
entry:
%cmp32 = icmp sgt i32 %N, 1
br i1 %cmp32, label %for.cond1.preheader.lr.ph, label %for.end21
for.cond1.preheader.lr.ph:
%0 = add i32 %N, -1
br label %for.body3.lr.ph
for.body3.lr.ph:
%indvars.iv35 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next36, %for.inc19 ]
%1 = add nsw i64 %indvars.iv35, -1
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 1, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
%2 = add nsw i64 %indvars.iv, -1
%arrayidx6 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %2, i64 %1
%3 = load i32, i32* %arrayidx6
%arrayidx12 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %2, i64 %1
%4 = load i32, i32* %arrayidx12
%add = add nsw i32 %4, %3
store i32 %add, i32* %arrayidx6
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc19, label %for.body3
for.inc19:
%indvars.iv.next36 = add nuw nsw i64 %indvars.iv35, 1
%lftr.wideiv38 = trunc i64 %indvars.iv35 to i32
%exitcond39 = icmp eq i32 %lftr.wideiv38, %0
br i1 %exitcond39, label %for.end21, label %for.body3.lr.ph
for.end21:
ret void
}
; CHECK-LABEL: @interchange_02
; CHECK: for.body3.lr.ph: ; preds = %for.inc19, %for.cond1.preheader.lr.ph
; CHECK: %indvars.iv35 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next36, %for.inc19 ]
; CHECK: %0 = add nsw i64 %indvars.iv35, -1
; CHECK: br label %for.body3.split1
; CHECK: for.body3.preheader: ; preds = %entry
; CHECK: %1 = add i32 %N, -1
; CHECK: br label %for.body3
; CHECK: for.body3: ; preds = %for.body3.preheader, %for.body3.split
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3.split ], [ 1, %for.body3.preheader ]
; CHECK: br label %for.cond1.preheader.lr.ph
; CHECK: for.body3.split1: ; preds = %for.body3.lr.ph
; CHECK: %2 = add nsw i64 %indvars.iv, -1
; CHECK: %arrayidx6 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %2, i64 %0
; CHECK: %3 = load i32, i32* %arrayidx6
; CHECK: %arrayidx12 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %2, i64 %0
; CHECK: %4 = load i32, i32* %arrayidx12
; CHECK: %add = add nsw i32 %4, %3
; CHECK: store i32 %add, i32* %arrayidx6
; CHECK: br label %for.inc19
;;---------------------------------------Test case 03---------------------------------
;; Loops interchange is not profitable.
;; for(int i=1;i<N;i++)
;; for(int j=1;j<N;j++)
;; A[i-1][j-1] = A[i - 1][j-1] + B[i][j];
define void @interchange_03(i32 %N){
entry:
%cmp31 = icmp sgt i32 %N, 1
br i1 %cmp31, label %for.cond1.preheader.lr.ph, label %for.end19
for.cond1.preheader.lr.ph:
%0 = add i32 %N, -1
br label %for.body3.lr.ph
for.body3.lr.ph:
%indvars.iv34 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next35, %for.inc17 ]
%1 = add nsw i64 %indvars.iv34, -1
br label %for.body3
for.body3:
%indvars.iv = phi i64 [ 1, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
%2 = add nsw i64 %indvars.iv, -1
%arrayidx6 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %1, i64 %2
%3 = load i32, i32* %arrayidx6
%arrayidx10 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %indvars.iv34, i64 %indvars.iv
%4 = load i32, i32* %arrayidx10
%add = add nsw i32 %4, %3
store i32 %add, i32* %arrayidx6
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv to i32
%exitcond = icmp eq i32 %lftr.wideiv, %0
br i1 %exitcond, label %for.inc17, label %for.body3
for.inc17:
%indvars.iv.next35 = add nuw nsw i64 %indvars.iv34, 1
%lftr.wideiv37 = trunc i64 %indvars.iv34 to i32
%exitcond38 = icmp eq i32 %lftr.wideiv37, %0
br i1 %exitcond38, label %for.end19, label %for.body3.lr.ph
for.end19:
ret void
}
; CHECK-LABEL: @interchange_03
; CHECK: for.body3.lr.ph:
; CHECK: %indvars.iv34 = phi i64 [ 1, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next35, %for.inc17 ]
; CHECK: %1 = add nsw i64 %indvars.iv34, -1
; CHECK: br label %for.body3.preheader
; CHECK: for.body3.preheader:
; CHECK: br label %for.body3
; CHECK: for.body3:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 1, %for.body3.preheader ]
; CHECK: %2 = add nsw i64 %indvars.iv, -1
; CHECK: %arrayidx6 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i64 0, i64 %1, i64 %2
; CHECK: %3 = load i32, i32* %arrayidx6
; CHECK: %arrayidx10 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @B, i64 0, i64 %indvars.iv34, i64 %indvars.iv
; CHECK: %4 = load i32, i32* %arrayidx10

235
external/llvm/test/Transforms/LoopInterchange/reductions.ll vendored
View File

@ -1,235 +0,0 @@
; RUN: opt < %s -basicaa -loop-interchange -S | FileCheck %s
@A = common global [500 x [500 x i32]] zeroinitializer
@X = common global i32 0
@B = common global [500 x [500 x i32]] zeroinitializer
@Y = common global i32 0
;; for( int i=1;i<N;i++)
;; for( int j=1;j<N;j++)
;; X+=A[j][i];
define void @reduction_01(i32 %N) {
entry:
%cmp16 = icmp sgt i32 %N, 1
br i1 %cmp16, label %for.body3.lr.ph, label %for.end8
for.body3.lr.ph: ; preds = %entry, %for.cond1.for.inc6_crit_edge
%indvars.iv18 = phi i64 [ %indvars.iv.next19, %for.cond1.for.inc6_crit_edge ], [ 1, %entry ]
%X.promoted = load i32, i32* @X
br label %for.body3
for.body3: ; preds = %for.body3, %for.body3.lr.ph
%indvars.iv = phi i64 [ 1, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
%add15 = phi i32 [ %X.promoted, %for.body3.lr.ph ], [ %add, %for.body3 ]
%arrayidx5 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv18
%0 = load i32, i32* %arrayidx5
%add = add nsw i32 %add15, %0
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.cond1.for.inc6_crit_edge, label %for.body3
for.cond1.for.inc6_crit_edge: ; preds = %for.body3
store i32 %add, i32* @X
%indvars.iv.next19 = add nuw nsw i64 %indvars.iv18, 1
%lftr.wideiv20 = trunc i64 %indvars.iv.next19 to i32
%exitcond21 = icmp eq i32 %lftr.wideiv20, %N
br i1 %exitcond21, label %for.end8, label %for.body3.lr.ph
for.end8: ; preds = %for.cond1.for.inc6_crit_edge, %entry
ret void
}
;; Loop is interchanged check that the phi nodes are split and the promoted value is used instead of the reduction phi.
; CHECK-LABEL: @reduction_01
; CHECK: for.body3: ; preds = %for.body3.preheader, %for.body3.split
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3.split ], [ 1, %for.body3.preheader ]
; CHECK: br label %for.body3.lr.ph.preheader
; CHECK: %add = add nsw i32 %X.promoted
;; Test for more than 1 reductions inside a loop.
;; for( int i=1;i<N;i++)
;; for( int j=1;j<N;j++)
;; for( int k=1;k<N;k++) {
;; X+=A[k][j];
;; Y+=B[k][i];
;; }
define void @reduction_02(i32 %N) {
entry:
%cmp34 = icmp sgt i32 %N, 1
br i1 %cmp34, label %for.cond4.preheader.preheader, label %for.end19
for.cond4.preheader.preheader: ; preds = %entry, %for.inc17
%indvars.iv40 = phi i64 [ %indvars.iv.next41, %for.inc17 ], [ 1, %entry ]
br label %for.body6.lr.ph
for.body6.lr.ph: ; preds = %for.cond4.for.inc14_crit_edge, %for.cond4.preheader.preheader
%indvars.iv36 = phi i64 [ %indvars.iv.next37, %for.cond4.for.inc14_crit_edge ], [ 1, %for.cond4.preheader.preheader ]
%X.promoted = load i32, i32* @X
%Y.promoted = load i32, i32* @Y
br label %for.body6
for.body6: ; preds = %for.body6, %for.body6.lr.ph
%indvars.iv = phi i64 [ 1, %for.body6.lr.ph ], [ %indvars.iv.next, %for.body6 ]
%add1331 = phi i32 [ %Y.promoted, %for.body6.lr.ph ], [ %add13, %for.body6 ]
%add30 = phi i32 [ %X.promoted, %for.body6.lr.ph ], [ %add, %for.body6 ]
%arrayidx8 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv36
%0 = load i32, i32* %arrayidx8
%add = add nsw i32 %add30, %0
%arrayidx12 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @B, i64 0, i64 %indvars.iv, i64 %indvars.iv40
%1 = load i32, i32* %arrayidx12
%add13 = add nsw i32 %add1331, %1
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.cond4.for.inc14_crit_edge, label %for.body6
for.cond4.for.inc14_crit_edge: ; preds = %for.body6
store i32 %add, i32* @X
store i32 %add13, i32* @Y
%indvars.iv.next37 = add nuw nsw i64 %indvars.iv36, 1
%lftr.wideiv38 = trunc i64 %indvars.iv.next37 to i32
%exitcond39 = icmp eq i32 %lftr.wideiv38, %N
br i1 %exitcond39, label %for.inc17, label %for.body6.lr.ph
for.inc17: ; preds = %for.cond4.for.inc14_crit_edge
%indvars.iv.next41 = add nuw nsw i64 %indvars.iv40, 1
%lftr.wideiv42 = trunc i64 %indvars.iv.next41 to i32
%exitcond43 = icmp eq i32 %lftr.wideiv42, %N
br i1 %exitcond43, label %for.end19, label %for.cond4.preheader.preheader
for.end19: ; preds = %for.inc17, %entry
ret void
}
;; Loop is interchanged check that the phi nodes are split and the promoted value is used instead of the reduction phi.
; CHECK-LABEL: @reduction_02
; CHECK: for.body6: ; preds = %for.body6.preheader, %for.body6.split
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body6.split ], [ 1, %for.body6.preheader ]
; CHECK: br label %for.cond4.preheader.preheader.preheader
; CHECK: %add13 = add nsw i32 %Y.promoted
;; Not tightly nested. Do not interchange.
;; for( int i=1;i<N;i++)
;; for( int j=1;j<N;j++) {
;; for( int k=1;k<N;k++) {
;; X+=A[k][j];
;; }
;; Y+=B[j][i];
;; }
define void @reduction_03(i32 %N) {
entry:
%cmp35 = icmp sgt i32 %N, 1
br i1 %cmp35, label %for.cond4.preheader.lr.ph, label %for.end19
for.cond4.preheader.lr.ph: ; preds = %entry, %for.cond1.for.inc17_crit_edge
%indvars.iv41 = phi i64 [ %indvars.iv.next42, %for.cond1.for.inc17_crit_edge ], [ 1, %entry ]
%Y.promoted = load i32, i32* @Y
br label %for.body6.lr.ph
for.body6.lr.ph: ; preds = %for.cond4.preheader.lr.ph, %for.cond4.for.end_crit_edge
%indvars.iv37 = phi i64 [ 1, %for.cond4.preheader.lr.ph ], [ %indvars.iv.next38, %for.cond4.for.end_crit_edge ]
%add1334 = phi i32 [ %Y.promoted, %for.cond4.preheader.lr.ph ], [ %add13, %for.cond4.for.end_crit_edge ]
%X.promoted = load i32, i32* @X
br label %for.body6
for.body6: ; preds = %for.body6, %for.body6.lr.ph
%indvars.iv = phi i64 [ 1, %for.body6.lr.ph ], [ %indvars.iv.next, %for.body6 ]
%add31 = phi i32 [ %X.promoted, %for.body6.lr.ph ], [ %add, %for.body6 ]
%arrayidx8 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv37
%0 = load i32, i32* %arrayidx8
%add = add nsw i32 %add31, %0
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.cond4.for.end_crit_edge, label %for.body6
for.cond4.for.end_crit_edge: ; preds = %for.body6
store i32 %add, i32* @X
%arrayidx12 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @B, i64 0, i64 %indvars.iv37, i64 %indvars.iv41
%1 = load i32, i32* %arrayidx12
%add13 = add nsw i32 %add1334, %1
%indvars.iv.next38 = add nuw nsw i64 %indvars.iv37, 1
%lftr.wideiv39 = trunc i64 %indvars.iv.next38 to i32
%exitcond40 = icmp eq i32 %lftr.wideiv39, %N
br i1 %exitcond40, label %for.cond1.for.inc17_crit_edge, label %for.body6.lr.ph
for.cond1.for.inc17_crit_edge: ; preds = %for.cond4.for.end_crit_edge
store i32 %add13, i32* @Y
%indvars.iv.next42 = add nuw nsw i64 %indvars.iv41, 1
%lftr.wideiv43 = trunc i64 %indvars.iv.next42 to i32
%exitcond44 = icmp eq i32 %lftr.wideiv43, %N
br i1 %exitcond44, label %for.end19, label %for.cond4.preheader.lr.ph
for.end19: ; preds = %for.cond1.for.inc17_crit_edge, %entry
ret void
}
;; Not tightly nested. Do not interchange.
;; Not interchanged hence the phi's in the inner loop will not be split. Check for the same.
; CHECK-LABEL: @reduction_03
; CHECK: for.body6: ; preds = %for.body6.preheader, %for.body6
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body6 ], [ 1, %for.body6.preheader ]
; CHECK: %add31 = phi i32 [ %add, %for.body6 ], [ %X.promoted, %for.body6.preheader ]
;; Multiple use of reduction not safe. Do not interchange.
;; for( int i=1;i<N;i++)
;; for( int j=1;j<N;j++)
;; for( int k=1;k<N;k++) {
;; X+=A[k][j];
;; Y+=X;
;; }
define void @reduction_04(i32 %N) {
entry:
%cmp28 = icmp sgt i32 %N, 1
br i1 %cmp28, label %for.cond4.preheader.preheader, label %for.end15
for.cond4.preheader.preheader: ; preds = %entry, %for.inc13
%i.029 = phi i32 [ %inc14, %for.inc13 ], [ 1, %entry ]
br label %for.body6.lr.ph
for.body6.lr.ph: ; preds = %for.cond4.for.inc10_crit_edge, %for.cond4.preheader.preheader
%indvars.iv30 = phi i64 [ %indvars.iv.next31, %for.cond4.for.inc10_crit_edge ], [ 1, %for.cond4.preheader.preheader ]
%X.promoted = load i32, i32* @X
%Y.promoted = load i32, i32* @Y
br label %for.body6
for.body6: ; preds = %for.body6, %for.body6.lr.ph
%indvars.iv = phi i64 [ 1, %for.body6.lr.ph ], [ %indvars.iv.next, %for.body6 ]
%add925 = phi i32 [ %Y.promoted, %for.body6.lr.ph ], [ %add9, %for.body6 ]
%add24 = phi i32 [ %X.promoted, %for.body6.lr.ph ], [ %add, %for.body6 ]
%arrayidx8 = getelementptr inbounds [500 x [500 x i32]], [500 x [500 x i32]]* @A, i64 0, i64 %indvars.iv, i64 %indvars.iv30
%0 = load i32, i32* %arrayidx8
%add = add nsw i32 %add24, %0
%add9 = add nsw i32 %add925, %add
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.cond4.for.inc10_crit_edge, label %for.body6
for.cond4.for.inc10_crit_edge: ; preds = %for.body6
store i32 %add, i32* @X
store i32 %add9, i32* @Y
%indvars.iv.next31 = add nuw nsw i64 %indvars.iv30, 1
%lftr.wideiv32 = trunc i64 %indvars.iv.next31 to i32
%exitcond33 = icmp eq i32 %lftr.wideiv32, %N
br i1 %exitcond33, label %for.inc13, label %for.body6.lr.ph
for.inc13: ; preds = %for.cond4.for.inc10_crit_edge
%inc14 = add nuw nsw i32 %i.029, 1
%exitcond34 = icmp eq i32 %inc14, %N
br i1 %exitcond34, label %for.end15, label %for.cond4.preheader.preheader
for.end15: ; preds = %for.inc13, %entry
ret void
}
;; Not interchanged hence the phi's in the inner loop will not be split. Check for the same.
; CHECK-LABEL: @reduction_04
; CHECK: for.body6: ; preds = %for.body6.preheader, %for.body6
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body6 ], [ 1, %for.body6.preheader ]
; CHECK: %add925 = phi i32 [ %add9, %for.body6 ], [ %Y.promoted, %for.body6.preheader ]