Index: llvm/lib/Transforms/Scalar/LoopInterchange.cpp =================================================================== --- llvm/lib/Transforms/Scalar/LoopInterchange.cpp +++ llvm/lib/Transforms/Scalar/LoopInterchange.cpp @@ -120,8 +120,6 @@ std::vector Dep; Instruction *Src = cast(*I); Instruction *Dst = cast(*J); - if (Src == Dst) - continue; // Ignore Input dependencies. if (isa(Src) && isa(Dst)) continue; Index: llvm/test/Transforms/LoopInterchange/lcssa-preheader.ll =================================================================== --- llvm/test/Transforms/LoopInterchange/lcssa-preheader.ll +++ llvm/test/Transforms/LoopInterchange/lcssa-preheader.ll @@ -2,107 +2,6 @@ ; RUN: opt < %s -basic-aa -loop-interchange -pass-remarks-missed='loop-interchange' -verify-loop-lcssa -S | FileCheck %s target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" - -; void foo(int n, int m) { -; int temp[16][16]; -; int res[16][16]; -; for(int i = 0; i < n; i++) { -; for(int j = 0; j < m; j++) -; res[j][i] = temp[j][i]; -; } -; } - -define void @lcssa_08(i32 %n, i32 %m) { -; CHECK-LABEL: @lcssa_08( -; CHECK-NEXT: entry: -; CHECK-NEXT: [[TEMP:%.*]] = alloca [16 x [16 x i32]], align 4 -; CHECK-NEXT: [[RES:%.*]] = alloca [16 x [16 x i32]], align 4 -; CHECK-NEXT: [[CMP24:%.*]] = icmp sgt i32 [[N:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP24]], label [[INNER_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]] -; CHECK: outer.preheader: -; CHECK-NEXT: br label [[OUTER_HEADER:%.*]] -; CHECK: outer.header: -; CHECK-NEXT: [[INDVARS_IV27:%.*]] = phi i64 [ 0, [[OUTER_PREHEADER:%.*]] ], [ [[INDVARS_IV_NEXT28:%.*]], [[OUTER_LATCH:%.*]] ] -; CHECK-NEXT: [[CMP222:%.*]] = icmp sgt i32 [[M:%.*]], 0 -; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[M]] to i64 -; CHECK-NEXT: br i1 [[CMP222]], label [[INNER_FOR_BODY_SPLIT1:%.*]], label [[INNER_FOR_BODY_SPLIT:%.*]] -; CHECK: inner.preheader: -; CHECK-NEXT: [[WIDE_TRIP_COUNT29:%.*]] = zext i32 [[N]] to i64 -; CHECK-NEXT: br label [[INNER_FOR_BODY:%.*]] -; CHECK: inner.for.body: -; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[INNER_PREHEADER]] ], [ [[TMP1:%.*]], [[INNER_FOR_BODY_SPLIT]] ] -; CHECK-NEXT: br label [[OUTER_PREHEADER]] -; CHECK: inner.for.body.split1: -; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [16 x [16 x i32]], [16 x [16 x i32]]* [[TEMP]], i64 0, i64 [[INDVARS_IV]], i64 [[INDVARS_IV27]] -; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4 -; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds [16 x [16 x i32]], [16 x [16 x i32]]* [[RES]], i64 0, i64 [[INDVARS_IV]], i64 [[INDVARS_IV27]] -; CHECK-NEXT: store i32 [[TMP0]], i32* [[ARRAYIDX8]], align 4 -; CHECK-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1 -; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]] -; CHECK-NEXT: br label [[INNER_CRIT_EDGE:%.*]] -; CHECK: inner.for.body.split: -; CHECK-NEXT: [[WIDE_TRIP_COUNT_LCSSA:%.*]] = phi i64 [ [[WIDE_TRIP_COUNT]], [[OUTER_LATCH]] ], [ [[WIDE_TRIP_COUNT]], [[OUTER_HEADER]] ] -; CHECK-NEXT: [[TMP1]] = add nuw nsw i64 [[INDVARS_IV]], 1 -; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i64 [[TMP1]], [[WIDE_TRIP_COUNT_LCSSA]] -; CHECK-NEXT: br i1 [[TMP2]], label [[INNER_FOR_BODY]], label [[OUTER_CRIT_EDGE:%.*]] -; CHECK: inner.crit_edge: -; CHECK-NEXT: br label [[OUTER_LATCH]] -; CHECK: outer.latch: -; CHECK-NEXT: [[INDVARS_IV_NEXT28]] = add nuw nsw i64 [[INDVARS_IV27]], 1 -; CHECK-NEXT: [[EXITCOND30:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT28]], [[WIDE_TRIP_COUNT29]] -; CHECK-NEXT: br i1 [[EXITCOND30]], label [[OUTER_HEADER]], label [[INNER_FOR_BODY_SPLIT]] -; CHECK: outer.crit_edge: -; CHECK-NEXT: br label [[FOR_COND_CLEANUP]] -; CHECK: for.cond.cleanup: -; CHECK-NEXT: ret void -; -entry: - %temp = alloca [16 x [16 x i32]], align 4 - %res = alloca [16 x [16 x i32]], align 4 - %cmp24 = icmp sgt i32 %n, 0 - br i1 %cmp24, label %outer.preheader, label %for.cond.cleanup - -outer.preheader: ; preds = %entry - %wide.trip.count29 = zext i32 %n to i64 - br label %outer.header - -outer.header: ; preds = %outer.preheader, %outer.latch - %indvars.iv27 = phi i64 [ 0, %outer.preheader ], [ %indvars.iv.next28, %outer.latch ] - %cmp222 = icmp sgt i32 %m, 0 - br i1 %cmp222, label %inner.preheader, label %outer.latch - -inner.preheader: ; preds = %outer.header - ; When inner.preheader becomes the outer preheader, do not move - ; %wide.trip.count into the inner loop header lest LCSSA break - ; (if %wide.trip.count gets moved, its use is now outside the inner loop). - %wide.trip.count = zext i32 %m to i64 - br label %inner.for.body - -inner.for.body: ; preds = %inner.preheader, %inner.for.body - %indvars.iv = phi i64 [ 0, %inner.preheader ], [ %indvars.iv.next, %inner.for.body ] - %arrayidx6 = getelementptr inbounds [16 x [16 x i32]], [16 x [16 x i32]]* %temp, i64 0, i64 %indvars.iv, i64 %indvars.iv27 - %0 = load i32, i32* %arrayidx6, align 4 - %arrayidx8 = getelementptr inbounds [16 x [16 x i32]], [16 x [16 x i32]]* %res, i64 0, i64 %indvars.iv, i64 %indvars.iv27 - store i32 %0, i32* %arrayidx8, align 4 - %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 - %exitcond = icmp ne i64 %indvars.iv.next, %wide.trip.count - br i1 %exitcond, label %inner.for.body, label %inner.crit_edge - -inner.crit_edge: ; preds = %inner.for.body - br label %outer.latch - -outer.latch: ; preds = %inner.crit_edge, %outer.header - %indvars.iv.next28 = add nuw nsw i64 %indvars.iv27, 1 - %exitcond30 = icmp ne i64 %indvars.iv.next28, %wide.trip.count29 - br i1 %exitcond30, label %outer.header, label %outer.crit_edge - -outer.crit_edge: ; preds = %outer.latch - br label %for.cond.cleanup - -for.cond.cleanup: ; preds = %outer.crit_edge, %entry - ret void -} - @global = external local_unnamed_addr global [4 x [4 x [2 x i16]]] align 16 ; %N.ext is defined in the outer loop header and used in the inner loop. After Index: llvm/test/Transforms/LoopInterchange/perserve-lcssa.ll =================================================================== --- llvm/test/Transforms/LoopInterchange/perserve-lcssa.ll +++ llvm/test/Transforms/LoopInterchange/perserve-lcssa.ll @@ -5,7 +5,7 @@ @a = common dso_local global i64 0, align 4 @b = common dso_local global i64 0, align 4 -@c = common dso_local global [10 x [1 x i32 ]] zeroinitializer, align 16 +@c = common dso_local global [10 x [10 x i32 ]] zeroinitializer, align 16 define void @test_lcssa_indvars1() { @@ -34,7 +34,7 @@ inner.body: ; preds = %inner.body, %outer.header %iv.inner = phi i64 [ 5, %outer.header ], [ %iv.inner.next, %inner.body ] - %v7 = getelementptr inbounds [10 x [1 x i32]], [10 x [1 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer + %v7 = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer store i32 0, i32* %v7, align 4 %iv.inner.next = add nsw i64 %iv.inner, -1 %v9 = icmp eq i64 %iv.inner, 0 @@ -81,7 +81,7 @@ inner.body: ; preds = %inner.body, %outer.header %iv.inner = phi i64 [ 5, %outer.header ], [ %iv.inner.next, %inner.body ] - %v7 = getelementptr inbounds [10 x [1 x i32]], [10 x [1 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer + %v7 = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer store i32 0, i32* %v7, align 4 %iv.inner.next = add nsw i64 %iv.inner, -1 %v9 = icmp eq i64 %iv.inner.next, 0 @@ -130,7 +130,7 @@ inner.body: ; preds = %inner.body, %outer.header %iv.inner = phi i64 [ 5, %outer.header ], [ %iv.inner.next, %inner.body ] - %v7 = getelementptr inbounds [10 x [1 x i32]], [10 x [1 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer + %v7 = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @c, i64 0, i64 %iv.inner, i64 %iv.outer store i32 0, i32* %v7, align 4 %iv.inner.next = add nsw i64 %iv.inner, -1 %v9 = icmp eq i64 %iv.inner, 0 Index: llvm/test/Transforms/LoopInterchange/pr45743-move-from-inner-preheader.ll =================================================================== --- llvm/test/Transforms/LoopInterchange/pr45743-move-from-inner-preheader.ll +++ llvm/test/Transforms/LoopInterchange/pr45743-move-from-inner-preheader.ll @@ -1,7 +1,7 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt -loop-interchange -S %s | FileCheck %s -@global = external local_unnamed_addr global [2 x [10 x i32]], align 16 +@global = external local_unnamed_addr global [400 x [400 x i32]], align 16 ; We need to move %tmp4 from the inner loop pre header to the outer loop header ; before interchanging. @@ -23,7 +23,7 @@ ; CHECK-NEXT: [[OUTER_RED]] = phi i32 [ [[RED_NEXT_LCSSA:%.*]], [[INNER_SPLIT]] ], [ 0, [[INNER_PH]] ] ; CHECK-NEXT: br label [[OUTER_HEADER_PREHEADER]] ; CHECK: inner.split1: -; CHECK-NEXT: [[PTR:%.*]] = getelementptr inbounds [2 x [10 x i32]], [2 x [10 x i32]]* @global, i64 0, i64 [[INNER_IV]], i64 [[TMP4]] +; CHECK-NEXT: [[PTR:%.*]] = getelementptr inbounds [400 x [400 x i32]], [400 x [400 x i32]]* @global, i64 0, i64 [[INNER_IV]], i64 [[TMP4]] ; CHECK-NEXT: store i32 0, i32* [[PTR]], align 4 ; CHECK-NEXT: [[RED_NEXT]] = or i32 [[INNER_RED]], 20 ; CHECK-NEXT: [[INNER_IV_NEXT:%.*]] = add nsw i64 [[INNER_IV]], 1 @@ -56,7 +56,7 @@ inner: ; preds = %bb5, %bb3 %inner.iv = phi i64 [ 0, %inner.ph ], [ %inner.iv.next, %inner ] %inner.red = phi i32 [ %outer.red, %inner.ph ], [ %red.next, %inner ] - %ptr = getelementptr inbounds [2 x [10 x i32]], [2 x [10 x i32]]* @global, i64 0, i64 %inner.iv, i64 %tmp4 + %ptr = getelementptr inbounds [400 x [400 x i32]], [400 x [400 x i32]]* @global, i64 0, i64 %inner.iv, i64 %tmp4 store i32 0, i32* %ptr %red.next = or i32 %inner.red, 20 %inner.iv.next = add nsw i64 %inner.iv, 1 @@ -93,7 +93,7 @@ ; CHECK: inner: ; CHECK-NEXT: [[INNER_IV:%.*]] = phi i64 [ 0, [[INNER_PH]] ], [ [[INNER_IV_NEXT:%.*]], [[INNER]] ] ; CHECK-NEXT: [[INNER_RED:%.*]] = phi i32 [ [[OUTER_RED]], [[INNER_PH]] ], [ [[RED_NEXT:%.*]], [[INNER]] ] -; CHECK-NEXT: [[PTR:%.*]] = getelementptr inbounds [2 x [10 x i32]], [2 x [10 x i32]]* @global, i64 0, i64 [[INNER_IV]], i64 [[TMP4]] +; CHECK-NEXT: [[PTR:%.*]] = getelementptr inbounds [400 x [400 x i32]], [400 x [400 x i32]]* @global, i64 0, i64 [[INNER_IV]], i64 [[TMP4]] ; CHECK-NEXT: store i32 0, i32* [[PTR]], align 4 ; CHECK-NEXT: [[RED_NEXT]] = or i32 [[INNER_RED]], 20 ; CHECK-NEXT: [[INNER_IV_NEXT]] = add nsw i64 [[INNER_IV]], 1 @@ -123,7 +123,7 @@ inner: ; preds = %bb5, %bb3 %inner.iv = phi i64 [ 0, %inner.ph ], [ %inner.iv.next, %inner ] %inner.red = phi i32 [ %outer.red, %inner.ph ], [ %red.next, %inner ] - %ptr = getelementptr inbounds [2 x [10 x i32]], [2 x [10 x i32]]* @global, i64 0, i64 %inner.iv, i64 %tmp4 + %ptr = getelementptr inbounds [400 x [400 x i32]], [400 x [400 x i32]]* @global, i64 0, i64 %inner.iv, i64 %tmp4 store i32 0, i32* %ptr %red.next = or i32 %inner.red, 20 %inner.iv.next = add nsw i64 %inner.iv, 1