| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6 | |
| ; RUN: opt < %s -passes=loop-interchange -cache-line-size=64 -S | FileCheck %s | |
| ; Outer loop only reductions are not supported currently. | |
| @A = common global [500 x [500 x i32]] zeroinitializer | |
| ;; global X | |
| ;; for( int i=1;i<N;i++) { | |
| ;; for( int j=1;j<N;j++) | |
| ;; ; | |
| ;; X+=A[j][i]; | |
| ;; } | |
| define i32 @reduction_01(i32 %N) { | |
| ; CHECK-LABEL: define i32 @reduction_01( | |
| ; CHECK-SAME: i32 [[N:%.*]]) { | |
| ; CHECK-NEXT: [[ENTRY:.*]]: | |
| ; CHECK-NEXT: br label %[[OUTER_HEADER:.*]] | |
| ; CHECK: [[OUTER_HEADER]]: | |
| ; CHECK-NEXT: [[INDVARS_IV18:%.*]] = phi i64 [ [[INDVARS_IV_NEXT19:%.*]], %[[OUTER_INC:.*]] ], [ 1, %[[ENTRY]] ] | |
| ; CHECK-NEXT: [[ADD15:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[ADD:%.*]], %[[OUTER_INC]] ] | |
| ; CHECK-NEXT: br label %[[FOR_BODY3:.*]] | |
| ; CHECK: [[FOR_BODY3]]: | |
| ; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 1, %[[OUTER_HEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY3]] ] | |
| ; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 | |
| ; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32 | |
| ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]] | |
| ; CHECK-NEXT: br i1 [[EXITCOND]], label %[[OUTER_INC]], label %[[FOR_BODY3]] | |
| ; CHECK: [[OUTER_INC]]: | |
| ; CHECK-NEXT: [[INDVARS_IV_LCSSA:%.*]] = phi i64 [ [[INDVARS_IV]], %[[FOR_BODY3]] ] | |
| ; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [500 x [500 x i32]], ptr @A, i64 0, i64 [[INDVARS_IV_LCSSA]], i64 [[INDVARS_IV18]] | |
| ; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX5]], align 4 | |
| ; CHECK-NEXT: [[ADD]] = add nsw i32 [[ADD15]], [[TMP0]] | |
| ; CHECK-NEXT: [[INDVARS_IV_NEXT19]] = add nuw nsw i64 [[INDVARS_IV18]], 1 | |
| ; CHECK-NEXT: [[LFTR_WIDEIV20:%.*]] = trunc i64 [[INDVARS_IV_NEXT19]] to i32 | |
| ; CHECK-NEXT: [[EXITCOND21:%.*]] = icmp eq i32 [[LFTR_WIDEIV20]], [[N]] | |
| ; CHECK-NEXT: br i1 [[EXITCOND21]], label %[[FOR_END8:.*]], label %[[OUTER_HEADER]] | |
| ; CHECK: [[FOR_END8]]: | |
| ; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD]], %[[OUTER_INC]] ] | |
| ; CHECK-NEXT: ret i32 [[ADD_LCSSA]] | |
| ; | |
| entry: | |
| br label %outer.header | |
| outer.header: ; preds = %for.cond1.for.inc6_crit_edge, %entry | |
| %indvars.iv18 = phi i64 [ %indvars.iv.next19, %outer.inc ], [ 1, %entry ] | |
| %add15 = phi i32 [ 0, %entry ], [ %add, %outer.inc ] | |
| br label %for.body3 | |
| for.body3: ; preds = %for.body3, %for.body3.lr.ph | |
| %indvars.iv = phi i64 [ 1, %outer.header ], [ %indvars.iv.next, %for.body3 ] | |
| %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 %outer.inc, label %for.body3 | |
| outer.inc: ; preds = %for.body3 | |
| %arrayidx5 = getelementptr inbounds [500 x [500 x i32]], ptr @A, i64 0, i64 %indvars.iv, i64 %indvars.iv18 | |
| %0 = load i32, ptr %arrayidx5 | |
| %add = add nsw i32 %add15, %0 | |
| %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 %outer.header | |
| for.end8: ; preds = %for.cond1.for.inc6_crit_edge, %entry | |
| ret i32 %add | |
| } |