[NFC][PhaseOrdering] Add a test demonstrating pitfails of common code hoisting on loop rotation

Depending on the -rotation-max-header-size=?,
hoisting common code early makes loop rotation impossible.

Author: LebedevRI

llvm/test/Transforms/PhaseOrdering/loop-rotation-vs-common-code-hoisting.ll

@@ -0,0 +1,224 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -O3 -rotation-max-header-size=0 -S < %s                    | FileCheck %s --check-prefixes=HOIST,THR0,FALLBACK0
+; RUN: opt -passes='default<O3>' -rotation-max-header-size=0 -S < %s  | FileCheck %s --check-prefixes=HOIST,THR0,FALLBACK1
+
+; RUN: opt -O3 -rotation-max-header-size=1 -S < %s                    | FileCheck %s --check-prefixes=HOIST,THR1,FALLBACK2
+; RUN: opt -passes='default<O3>' -rotation-max-header-size=1 -S < %s  | FileCheck %s --check-prefixes=HOIST,THR1,FALLBACK3
+
+; RUN: opt -O3 -rotation-max-header-size=2 -S < %s                    | FileCheck %s --check-prefixes=HOIST,THR2,FALLBACK4
+; RUN: opt -passes='default<O3>' -rotation-max-header-size=2 -S < %s  | FileCheck %s --check-prefixes=HOIST,THR2,FALLBACK5
+
+; RUN: opt -O3 -rotation-max-header-size=3 -S < %s                    | FileCheck %s --check-prefixes=ROTATED_LATER,ROTATED_LATER_OLDPM,FALLBACK6
+; RUN: opt -passes='default<O3>' -rotation-max-header-size=3 -S < %s  | FileCheck %s --check-prefixes=ROTATED_LATER,ROTATED_LATER_NEWPM,FALLBACK7
+
+; RUN: opt -O3 -rotation-max-header-size=4 -S < %s                    | FileCheck %s --check-prefixes=ROTATE,ROTATE_OLDPM,FALLBACK8
+; RUN: opt -passes='default<O3>' -rotation-max-header-size=4 -S < %s  | FileCheck %s --check-prefixes=ROTATE,ROTATE_NEWPM,FALLBACK9
+
+; This example is produced from a very basic C code:
+;
+;   void f0();
+;   void f1();
+;   void f2();
+;
+;   void loop(int width) {
+;       if(width < 1)
+;           return;
+;       for(int i = 0; i < width - 1; ++i) {
+;           f0();
+;           f1();
+;       }
+;       f0();
+;       f2();
+;   }
+
+; We have a choice here. We can either
+; * hoist the f0() call into loop header,
+;   * which potentially makes loop rotation unprofitable since loop header might
+;     have grown above certain threshold, and such unrotated loops will be
+;     ignored by LoopVectorizer, preventing vectorization
+;   * or loop rotation will succeed, resulting in some weird PHIs that will also
+;     harm vectorization
+; * or not hoist f0() call before performing loop rotation,
+;   at the cost of potential code bloat and/or potentially successfully rotating
+;   the loops, vectorizing them at the cost of compile time.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+
+declare void @f0()
+declare void @f1()
+declare void @f2()
+
+declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)
+declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
+
+define void @_Z4loopi(i32 %width) {
+; HOIST-LABEL: @_Z4loopi(
+; HOIST-NEXT:  entry:
+; HOIST-NEXT:    [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
+; HOIST-NEXT:    br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
+; HOIST:       for.cond.preheader:
+; HOIST-NEXT:    [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -1
+; HOIST-NEXT:    br label [[FOR_COND:%.*]]
+; HOIST:       for.cond:
+; HOIST-NEXT:    [[I_0:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY:%.*]] ], [ 0, [[FOR_COND_PREHEADER]] ]
+; HOIST-NEXT:    tail call void @f0()
+; HOIST-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[I_0]], [[TMP0]]
+; HOIST-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; HOIST:       for.cond.cleanup:
+; HOIST-NEXT:    tail call void @f2()
+; HOIST-NEXT:    br label [[RETURN]]
+; HOIST:       for.body:
+; HOIST-NEXT:    tail call void @f1()
+; HOIST-NEXT:    [[INC]] = add nuw i32 [[I_0]], 1
+; HOIST-NEXT:    br label [[FOR_COND]]
+; HOIST:       return:
+; HOIST-NEXT:    ret void
+;
+; ROTATED_LATER_OLDPM-LABEL: @_Z4loopi(
+; ROTATED_LATER_OLDPM-NEXT:  entry:
+; ROTATED_LATER_OLDPM-NEXT:    [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
+; ROTATED_LATER_OLDPM-NEXT:    br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
+; ROTATED_LATER_OLDPM:       for.cond.preheader:
+; ROTATED_LATER_OLDPM-NEXT:    [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -1
+; ROTATED_LATER_OLDPM-NEXT:    tail call void @f0()
+; ROTATED_LATER_OLDPM-NEXT:    [[EXITCOND_NOT3:%.*]] = icmp eq i32 [[TMP0]], 0
+; ROTATED_LATER_OLDPM-NEXT:    br i1 [[EXITCOND_NOT3]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY:%.*]]
+; ROTATED_LATER_OLDPM:       for.cond.cleanup:
+; ROTATED_LATER_OLDPM-NEXT:    tail call void @f2()
+; ROTATED_LATER_OLDPM-NEXT:    br label [[RETURN]]
+; ROTATED_LATER_OLDPM:       for.body:
+; ROTATED_LATER_OLDPM-NEXT:    [[I_04:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_COND_PREHEADER]] ]
+; ROTATED_LATER_OLDPM-NEXT:    tail call void @f1()
+; ROTATED_LATER_OLDPM-NEXT:    [[INC]] = add nuw i32 [[I_04]], 1
+; ROTATED_LATER_OLDPM-NEXT:    tail call void @f0()
+; ROTATED_LATER_OLDPM-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[TMP0]]
+; ROTATED_LATER_OLDPM-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]]
+; ROTATED_LATER_OLDPM:       return:
+; ROTATED_LATER_OLDPM-NEXT:    ret void
+;
+; ROTATED_LATER_NEWPM-LABEL: @_Z4loopi(
+; ROTATED_LATER_NEWPM-NEXT:  entry:
+; ROTATED_LATER_NEWPM-NEXT:    [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
+; ROTATED_LATER_NEWPM-NEXT:    br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
+; ROTATED_LATER_NEWPM:       for.cond.preheader:
+; ROTATED_LATER_NEWPM-NEXT:    [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -1
+; ROTATED_LATER_NEWPM-NEXT:    tail call void @f0()
+; ROTATED_LATER_NEWPM-NEXT:    [[EXITCOND_NOT3:%.*]] = icmp eq i32 [[TMP0]], 0
+; ROTATED_LATER_NEWPM-NEXT:    br i1 [[EXITCOND_NOT3]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_COND_PREHEADER_FOR_BODY_CRIT_EDGE:%.*]]
+; ROTATED_LATER_NEWPM:       for.cond.preheader.for.body_crit_edge:
+; ROTATED_LATER_NEWPM-NEXT:    [[INC_1:%.*]] = add nuw i32 0, 1
+; ROTATED_LATER_NEWPM-NEXT:    br label [[FOR_BODY:%.*]]
+; ROTATED_LATER_NEWPM:       for.cond.cleanup:
+; ROTATED_LATER_NEWPM-NEXT:    tail call void @f2()
+; ROTATED_LATER_NEWPM-NEXT:    br label [[RETURN]]
+; ROTATED_LATER_NEWPM:       for.body:
+; ROTATED_LATER_NEWPM-NEXT:    [[INC_PHI:%.*]] = phi i32 [ [[INC_0:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE:%.*]] ], [ [[INC_1]], [[FOR_COND_PREHEADER_FOR_BODY_CRIT_EDGE]] ]
+; ROTATED_LATER_NEWPM-NEXT:    tail call void @f1()
+; ROTATED_LATER_NEWPM-NEXT:    tail call void @f0()
+; ROTATED_LATER_NEWPM-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC_PHI]], [[TMP0]]
+; ROTATED_LATER_NEWPM-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY_FOR_BODY_CRIT_EDGE]]
+; ROTATED_LATER_NEWPM:       for.body.for.body_crit_edge:
+; ROTATED_LATER_NEWPM-NEXT:    [[INC_0]] = add nuw i32 [[INC_PHI]], 1
+; ROTATED_LATER_NEWPM-NEXT:    br label [[FOR_BODY]]
+; ROTATED_LATER_NEWPM:       return:
+; ROTATED_LATER_NEWPM-NEXT:    ret void
+;
+; ROTATE_OLDPM-LABEL: @_Z4loopi(
+; ROTATE_OLDPM-NEXT:  entry:
+; ROTATE_OLDPM-NEXT:    [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
+; ROTATE_OLDPM-NEXT:    br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
+; ROTATE_OLDPM:       for.cond.preheader:
+; ROTATE_OLDPM-NEXT:    [[CMP13_NOT:%.*]] = icmp eq i32 [[WIDTH]], 1
+; ROTATE_OLDPM-NEXT:    tail call void @f0()
+; ROTATE_OLDPM-NEXT:    br i1 [[CMP13_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
+; ROTATE_OLDPM:       for.body.preheader:
+; ROTATE_OLDPM-NEXT:    [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -1
+; ROTATE_OLDPM-NEXT:    br label [[FOR_BODY:%.*]]
+; ROTATE_OLDPM:       for.cond.cleanup:
+; ROTATE_OLDPM-NEXT:    tail call void @f2()
+; ROTATE_OLDPM-NEXT:    br label [[RETURN]]
+; ROTATE_OLDPM:       for.body:
+; ROTATE_OLDPM-NEXT:    [[I_04:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
+; ROTATE_OLDPM-NEXT:    tail call void @f1()
+; ROTATE_OLDPM-NEXT:    [[INC]] = add nuw nsw i32 [[I_04]], 1
+; ROTATE_OLDPM-NEXT:    tail call void @f0()
+; ROTATE_OLDPM-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC]], [[TMP0]]
+; ROTATE_OLDPM-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]]
+; ROTATE_OLDPM:       return:
+; ROTATE_OLDPM-NEXT:    ret void
+;
+; ROTATE_NEWPM-LABEL: @_Z4loopi(
+; ROTATE_NEWPM-NEXT:  entry:
+; ROTATE_NEWPM-NEXT:    [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
+; ROTATE_NEWPM-NEXT:    br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
+; ROTATE_NEWPM:       for.cond.preheader:
+; ROTATE_NEWPM-NEXT:    [[CMP13_NOT:%.*]] = icmp eq i32 [[WIDTH]], 1
+; ROTATE_NEWPM-NEXT:    tail call void @f0()
+; ROTATE_NEWPM-NEXT:    br i1 [[CMP13_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
+; ROTATE_NEWPM:       for.body.preheader:
+; ROTATE_NEWPM-NEXT:    [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -1
+; ROTATE_NEWPM-NEXT:    [[INC_1:%.*]] = add nuw nsw i32 0, 1
+; ROTATE_NEWPM-NEXT:    br label [[FOR_BODY:%.*]]
+; ROTATE_NEWPM:       for.cond.cleanup:
+; ROTATE_NEWPM-NEXT:    tail call void @f2()
+; ROTATE_NEWPM-NEXT:    br label [[RETURN]]
+; ROTATE_NEWPM:       for.body:
+; ROTATE_NEWPM-NEXT:    [[INC_PHI:%.*]] = phi i32 [ [[INC_0:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE:%.*]] ], [ [[INC_1]], [[FOR_BODY_PREHEADER]] ]
+; ROTATE_NEWPM-NEXT:    tail call void @f1()
+; ROTATE_NEWPM-NEXT:    tail call void @f0()
+; ROTATE_NEWPM-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i32 [[INC_PHI]], [[TMP0]]
+; ROTATE_NEWPM-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY_FOR_BODY_CRIT_EDGE]]
+; ROTATE_NEWPM:       for.body.for.body_crit_edge:
+; ROTATE_NEWPM-NEXT:    [[INC_0]] = add nuw nsw i32 [[INC_PHI]], 1
+; ROTATE_NEWPM-NEXT:    br label [[FOR_BODY]]
+; ROTATE_NEWPM:       return:
+; ROTATE_NEWPM-NEXT:    ret void
+;
+entry:
+  %width.addr = alloca i32, align 4
+  %i = alloca i32, align 4
+  store i32 %width, i32* %width.addr, align 4
+  %i1 = load i32, i32* %width.addr, align 4
+  %cmp = icmp slt i32 %i1, 1
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:
+  br label %return
+
+if.end:
+  %i2 = bitcast i32* %i to i8*
+  call void @llvm.lifetime.start.p0i8(i64 4, i8* %i2)
+  store i32 0, i32* %i, align 4
+  br label %for.cond
+
+for.cond:
+  %i3 = load i32, i32* %i, align 4
+  %i4 = load i32, i32* %width.addr, align 4
+  %sub = sub nsw i32 %i4, 1
+  %cmp1 = icmp slt i32 %i3, %sub
+  br i1 %cmp1, label %for.body, label %for.cond.cleanup
+
+for.cond.cleanup:
+  %i5 = bitcast i32* %i to i8*
+  call void @llvm.lifetime.end.p0i8(i64 4, i8* %i5)
+  br label %for.end
+
+for.body:
+  call void @f0()
+  call void @f1()
+  br label %for.inc
+
+for.inc:
+  %i6 = load i32, i32* %i, align 4
+  %inc = add nsw i32 %i6, 1
+  store i32 %inc, i32* %i, align 4
+  br label %for.cond
+
+for.end:
+  call void @f0()
+  call void @f2()
+  br label %return
+
+return:
+  ret void
+}