; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=indvars -S | FileCheck %s
target datalayout = "e-m:e-i64:64-p:64:64:64-n8:16:32:64-S128"
; When widening IV and its users, trunc and zext/sext are not needed
; if the original 32-bit user is known to be non-negative, whether
; the IV is considered signed or unsigned.
define void @foo(ptr %A, ptr %B, ptr %C, i32 %N) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 0, [[N:%.*]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP0]], [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = trunc nuw nsw i64 [[TMP1]] to i32
; CHECK-NEXT: [[DIV0:%.*]] = udiv i32 5, [[TMP3]]
; CHECK-NEXT: [[ADD4:%.*]] = add nsw i32 [[ADD3]], [[DIV0]]
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store i32 [[ADD4]], ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; 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 i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp1 = icmp slt i32 0, %N
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%idxprom = sext i32 %i.02 to i64
%arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
%0 = load i32, ptr %arrayidx, align 4
%add = add nsw i32 %i.02, 2
%idxprom1 = zext i32 %add to i64
%arrayidx2 = getelementptr inbounds i32, ptr %C, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%add3 = add nsw i32 %0, %1
%div0 = udiv i32 5, %add
%add4 = add nsw i32 %add3, %div0
%idxprom4 = zext i32 %i.02 to i64
%arrayidx5 = getelementptr inbounds i32, ptr %A, i64 %idxprom4
store i32 %add4, ptr %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nsw i32 %i.02, 1
%cmp = icmp slt i32 %inc, %N
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
ret void
}
define void @foo1(ptr %A, ptr %B, ptr %C, i32 %N) {
; CHECK-LABEL: @foo1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 0, [[N:%.*]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 2
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, ptr [[C:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP0]], [[TMP2]]
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store i32 [[ADD3]], ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; 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 i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp1 = icmp slt i32 0, %N
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%idxprom = zext i32 %i.02 to i64
%arrayidx = getelementptr inbounds i32, ptr %B, i64 %idxprom
%0 = load i32, ptr %arrayidx, align 4
%add = add nsw i32 %i.02, 2
%idxprom1 = sext i32 %add to i64
%arrayidx2 = getelementptr inbounds i32, ptr %C, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%add3 = add nsw i32 %0, %1
%idxprom4 = sext i32 %i.02 to i64
%arrayidx5 = getelementptr inbounds i32, ptr %A, i64 %idxprom4
store i32 %add3, ptr %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nsw i32 %i.02, 1
%cmp = icmp slt i32 %inc, %N
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
ret void
}
@a = common global [100 x i32] zeroinitializer, align 16
@b = common global [100 x i32] zeroinitializer, align 16
define i32 @foo2(i32 %M) {
; CHECK-LABEL: @foo2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 0, [[M:%.*]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[M]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[M]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [100 x i32], ptr @b, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = add nsw i64 [[INDVARS_IV]], [[TMP0]]
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 [[TMP3]]
; CHECK-NEXT: store i32 [[ADD]], ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; 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 i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: [[CALL:%.*]] = call i32 @dummy(ptr @a, ptr @b)
; CHECK-NEXT: ret i32 0
;
entry:
%cmp1 = icmp slt i32 0, %M
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%idxprom = zext i32 %i.02 to i64
%arrayidx = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 %idxprom
%0 = load i32, ptr %arrayidx, align 4
%idxprom1 = sext i32 %i.02 to i64
%arrayidx2 = getelementptr inbounds [100 x i32], ptr @b, i64 0, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %0, %1
%add3 = add nsw i32 %i.02, %M
%idxprom4 = sext i32 %add3 to i64
%arrayidx5 = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 %idxprom4
store i32 %add, ptr %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nsw i32 %i.02, 1
%cmp = icmp slt i32 %inc, %M
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
%call = call i32 @dummy(ptr @a, ptr @b)
ret i32 0
}
declare i32 @dummy(ptr, ptr)
; A case where zext should not be eliminated when its operands could only be extended by sext.
define i32 @foo3(i32 %M) {
; CHECK-LABEL: @foo3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 0, [[M:%.*]]
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[M]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[M]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [100 x i32], ptr @b, i64 0, i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = add nsw i64 [[INDVARS_IV]], [[TMP0]]
; CHECK-NEXT: [[TMP4:%.*]] = trunc nsw i64 [[TMP3]] to i32
; CHECK-NEXT: [[IDXPROM4:%.*]] = zext i32 [[TMP4]] to i64
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 [[IDXPROM4]]
; CHECK-NEXT: store i32 [[ADD]], ptr [[ARRAYIDX5]], align 4
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; 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 i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]]
; CHECK: for.cond.for.end_crit_edge:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: [[CALL:%.*]] = call i32 @dummy(ptr @a, ptr @b)
; CHECK-NEXT: ret i32 0
;
entry:
%cmp1 = icmp slt i32 0, %M
br i1 %cmp1, label %for.body.lr.ph, label %for.end
for.body.lr.ph: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.lr.ph, %for.inc
%i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
%idxprom = sext i32 %i.02 to i64
%arrayidx = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 %idxprom
%0 = load i32, ptr %arrayidx, align 4
%idxprom1 = sext i32 %i.02 to i64
%arrayidx2 = getelementptr inbounds [100 x i32], ptr @b, i64 0, i64 %idxprom1
%1 = load i32, ptr %arrayidx2, align 4
%add = add nsw i32 %0, %1
%add3 = add nsw i32 %i.02, %M
%idxprom4 = zext i32 %add3 to i64
%arrayidx5 = getelementptr inbounds [100 x i32], ptr @a, i64 0, i64 %idxprom4
store i32 %add, ptr %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %for.body
%inc = add nsw i32 %i.02, 1
%cmp = icmp slt i32 %inc, %M
br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
for.cond.for.end_crit_edge: ; preds = %for.inc
br label %for.end
for.end: ; preds = %for.cond.for.end_crit_edge, %entry
%call = call i32 @dummy(ptr @a, ptr @b)
ret i32 0
}
%struct.image = type {i32, i32}
define i32 @foo4(ptr %input, i32 %length, ptr %in) {
; CHECK-LABEL: @foo4(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STRIDE:%.*]] = getelementptr inbounds [[STRUCT_IMAGE:%.*]], ptr [[INPUT:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[STRIDE]], align 4
; CHECK-NEXT: [[CMP17:%.*]] = icmp sgt i32 [[LENGTH:%.*]], 1
; CHECK-NEXT: br i1 [[CMP17]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP1:%.*]] = sext i32 [[TMP0]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[LENGTH]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup.loopexit:
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP10:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: [[TMP3:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP2]], [[FOR_COND_CLEANUP_LOOPEXIT:%.*]] ]
; CHECK-NEXT: ret i32 [[TMP3]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 1, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[INPUT]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = sext i32 [[TMP4]] to i64
; CHECK-NEXT: [[TMP6:%.*]] = mul nsw i64 [[TMP5]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[IN:%.*]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr [[ADD_PTR]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = mul nsw i64 [[TMP1]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds i32, ptr [[IN]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = load i32, ptr [[ADD_PTR1]], align 4
; CHECK-NEXT: [[TMP10]] = add i32 [[TMP7]], [[TMP9]]
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]]
;
entry:
%stride = getelementptr inbounds %struct.image, ptr %input, i64 0, i32 1
%0 = load i32, ptr %stride, align 4
%cmp17 = icmp sgt i32 %length, 1
br i1 %cmp17, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
%1 = phi i32 [ %6, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
%2 = phi i32 [ 0, %entry ], [ %1, %for.cond.cleanup.loopexit ]
ret i32 %2
; mul instruction below is widened instead of generating a truncate instruction for it
; regardless if Load operand of mul is inside or outside the loop (we have both cases).
for.body: ; preds = %for.body.lr.ph, %for.body
%x.018 = phi i32 [ 1, %for.body.lr.ph ], [ %add, %for.body ]
%add = add nuw nsw i32 %x.018, 1
%3 = load i32, ptr %input, align 8
%mul = mul nsw i32 %3, %add
%idx.ext = sext i32 %mul to i64
%add.ptr = getelementptr inbounds i32, ptr %in, i64 %idx.ext
%4 = load i32, ptr %add.ptr, align 4
%mul1 = mul nsw i32 %0, %add
%idx.ext1 = sext i32 %mul1 to i64
%add.ptr1 = getelementptr inbounds i32, ptr %in, i64 %idx.ext1
%5 = load i32, ptr %add.ptr1, align 4
%6 = add i32 %4, %5
%cmp = icmp slt i32 %add, %length
br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit
}
define i32 @foo5(ptr %input, i32 %length, ptr %in) {
; CHECK-LABEL: @foo5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STRIDE:%.*]] = getelementptr inbounds [[STRUCT_IMAGE:%.*]], ptr [[INPUT:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[STRIDE]], align 4
; CHECK-NEXT: [[CMP17:%.*]] = icmp sgt i32 [[LENGTH:%.*]], 1
; CHECK-NEXT: br i1 [[CMP17]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP1:%.*]] = sext i32 [[TMP0]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[LENGTH]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup.loopexit:
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP10:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: [[TMP3:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP2]], [[FOR_COND_CLEANUP_LOOPEXIT:%.*]] ]
; CHECK-NEXT: ret i32 [[TMP3]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 1, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[INPUT]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = trunc nuw nsw i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP4]], [[TMP5]]
; CHECK-NEXT: [[IDX_EXT:%.*]] = sext i32 [[MUL]] to i64
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[IN:%.*]], i64 [[IDX_EXT]]
; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[ADD_PTR]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = mul nsw i64 [[TMP1]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds i32, ptr [[IN]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP8:%.*]] = load i32, ptr [[ADD_PTR1]], align 4
; CHECK-NEXT: [[TMP9:%.*]] = add i32 [[TMP6]], [[TMP8]]
; CHECK-NEXT: [[TMP10]] = add i32 [[TMP9]], [[MUL]]
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]]
;
entry:
%stride = getelementptr inbounds %struct.image, ptr %input, i64 0, i32 1
%0 = load i32, ptr %stride, align 4
%cmp17 = icmp sgt i32 %length, 1
br i1 %cmp17, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
%1 = phi i32 [ %7, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
%2 = phi i32 [ 0, %entry ], [ %1, %for.cond.cleanup.loopexit ]
ret i32 %2
; This example is the same as above except that the first mul is used in two places
; and this may result in having two versions of the multiply: an i32 and i64 version.
; In this case, keep the trucate instructions to avoid this redundancy.
for.body: ; preds = %for.body.lr.ph, %for.body
%x.018 = phi i32 [ 1, %for.body.lr.ph ], [ %add, %for.body ]
%add = add nuw nsw i32 %x.018, 1
%3 = load i32, ptr %input, align 8
%mul = mul nsw i32 %3, %add
%idx.ext = sext i32 %mul to i64
%add.ptr = getelementptr inbounds i32, ptr %in, i64 %idx.ext
%4 = load i32, ptr %add.ptr, align 4
%mul1 = mul nsw i32 %0, %add
%idx.ext1 = sext i32 %mul1 to i64
%add.ptr1 = getelementptr inbounds i32, ptr %in, i64 %idx.ext1
%5 = load i32, ptr %add.ptr1, align 4
%6 = add i32 %4, %5
%7 = add i32 %6, %mul
%cmp = icmp slt i32 %add, %length
br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit
}
define i32 @foo6(ptr %input, i32 %length, ptr %in) {
; CHECK-LABEL: @foo6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[STRIDE:%.*]] = getelementptr inbounds [[STRUCT_IMAGE:%.*]], ptr [[INPUT:%.*]], i64 0, i32 1
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[STRIDE]], align 4
; CHECK-NEXT: [[CMP17:%.*]] = icmp sgt i32 [[LENGTH:%.*]], 1
; CHECK-NEXT: br i1 [[CMP17]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[LENGTH]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup.loopexit:
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP12:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: [[TMP3:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP2]], [[FOR_COND_CLEANUP_LOOPEXIT:%.*]] ]
; CHECK-NEXT: ret i32 [[TMP3]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 1, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[TMP4:%.*]] = and i32 [[LENGTH]], [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = zext i32 [[TMP4]] to i64
; CHECK-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, ptr [[IN:%.*]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr [[ADD_PTR]], align 4
; CHECK-NEXT: [[TMP8:%.*]] = mul nuw i64 [[TMP1]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds i32, ptr [[IN]], i64 [[TMP8]]
; CHECK-NEXT: [[TMP9:%.*]] = load i32, ptr [[ADD_PTR1]], align 4
; CHECK-NEXT: [[OR:%.*]] = or i32 [[LENGTH]], [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = zext i32 [[OR]] to i64
; CHECK-NEXT: [[TMP11:%.*]] = sub nuw i64 [[TMP10]], [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[PTR_OR:%.*]] = getelementptr inbounds i32, ptr [[IN]], i64 [[TMP11]]
; CHECK-NEXT: [[VAL_OR:%.*]] = load i32, ptr [[PTR_OR]], align 4
; CHECK-NEXT: [[TMP12]] = add i32 [[TMP7]], [[VAL_OR]]
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT]]
;
entry:
%stride = getelementptr inbounds %struct.image, ptr %input, i64 0, i32 1
%0 = load i32, ptr %stride, align 4
%cmp17 = icmp sgt i32 %length, 1
br i1 %cmp17, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
%1 = phi i32 [ %6, %for.body ]
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
%2 = phi i32 [ 0, %entry ], [ %1, %for.cond.cleanup.loopexit ]
ret i32 %2
; Extend foo4 so that any loop variants (%3 and %or) with mul/sub/add then extend will not
; need a trunc instruction
for.body: ; preds = %for.body.lr.ph, %for.body
%x.018 = phi i32 [ 1, %for.body.lr.ph ], [ %add, %for.body ]
%add = add nuw nsw i32 %x.018, 1
%3 = and i32 %length, %0
%mul = mul nuw i32 %3, %add
%idx.ext = zext i32 %mul to i64
%add.ptr = getelementptr inbounds i32, ptr %in, i64 %idx.ext
%4 = load i32, ptr %add.ptr, align 4
%mul1 = mul nuw i32 %0, %add
%idx.ext1 = zext i32 %mul1 to i64
%add.ptr1 = getelementptr inbounds i32, ptr %in, i64 %idx.ext1
%5 = load i32, ptr %add.ptr1, align 4
%or = or i32 %length, %5
%sub.or = sub nuw i32 %or, %add
%or.ext = zext i32 %sub.or to i64
%ptr.or = getelementptr inbounds i32, ptr %in, i64 %or.ext
%val.or = load i32, ptr %ptr.or
%6 = add i32 %4, %val.or
%cmp = icmp ult i32 %add, %length
br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit
}
; Test that we can handle shl and disjoint or in getExtendedOperandRecurrence.
define void @foo7(i32 %n, ptr %a, i32 %x) {
; CHECK-LABEL: @foo7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP6]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
; CHECK: for.body.lr.ph:
; CHECK-NEXT: [[ADD1:%.*]] = add nsw i32 [[X:%.*]], 2
; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[ADD1]] to i64
; CHECK-NEXT: [[TMP1:%.*]] = sext i32 [[N]] to i64
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup.loopexit:
; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_LR_PH]] ]
; CHECK-NEXT: [[TMP2:%.*]] = shl nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[TMP3:%.*]] = or disjoint i64 [[TMP2]], 1
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[TMP3]]
; CHECK-NEXT: [[TMP4:%.*]] = trunc nsw i64 [[INDVARS_IV]] to i32
; CHECK-NEXT: store i32 [[TMP4]], ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nsw i64 [[INDVARS_IV]], [[TMP0]]
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT]], [[TMP1]]
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]]
;
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body.lr.ph, label %for.cond.cleanup
for.body.lr.ph: ; preds = %entry
%add1 = add nsw i32 %x, 2
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
for.body: ; preds = %for.body.lr.ph, %for.body
%i.07 = phi i32 [ 0, %for.body.lr.ph ], [ %add2, %for.body ]
%mul = shl nsw i32 %i.07, 1
%add = or disjoint i32 %mul, 1
%idxprom = sext i32 %add to i64
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %idxprom
store i32 %i.07, ptr %arrayidx, align 4
%add2 = add nsw i32 %add1, %i.07
%cmp = icmp slt i32 %add2, %n
br i1 %cmp, label %for.body, label %for.cond.cleanup.loopexit
}
Codebase Browser
llvm