RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
Code Issues Projects Releases Wiki Activity
ffb4271d86
llvm-mirror/test/Transforms/LICM/hoist-deref-load.ll
Philip Reames b12ecd2ebd [tests] Stablize tests for possible change in deref semantics 
There's a potential change in dereferenceability attribute semantics in the nearish future.  See llvm-dev thread "RFC: Decomposing deref(N) into deref(N) + nofree" and D99100 for context.

This change simply adds appropriate attributes to tests to keep transform logic exercised under both old and new/proposed semantics.  Note that for many of these cases, O3 would infer exactly these attributes on the test IR.

This change handles the idiomatic pattern of a dereferenceable object being passed to a call which can not free that memory.  There's a couple other tests which need more one-off attention, they'll be handled in another change.
2021-07-14 13:05:43 -07:00

1171 lines
54 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -basic-aa -licm < %s | FileCheck %s
; RUN: opt -aa-pipeline=basic-aa -passes='require<opt-remark-emit>,loop(loop-simplifycfg,licm)' -S < %s | FileCheck %s
; RUN: opt -S -basic-aa -licm -enable-mssa-loop-dependency=true -verify-memoryssa < %s | FileCheck %s
; RUN: opt -aa-pipeline=basic-aa -passes='require<opt-remark-emit>,loop-mssa(loop-simplifycfg,licm)' -verify-memoryssa -S < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; This test represents the following function:
; void test1(int * __restrict__ a, int * __restrict__ b, int &c, int n) {
; for (int i = 0; i < n; ++i)
; if (a[i] > 0)
; a[i] = c*b[i];
; }
; and we want to hoist the load of %c out of the loop. This can be done only
; because the dereferenceable attribute is on %c.
define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull dereferenceable(4) align 4 %c, i32 %n) #0 {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C:%.*]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; This is the same as @test1, but without the dereferenceable attribute on %c.
; Without this attribute, we should not hoist the load of %c.
define void @test2(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull %c, i32 %n) #0 {
; CHECK-LABEL: @test2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; This test represents the following function:
; void test3(int * restrict a, int * restrict b, int c[static 3], int n) {
; for (int i = 0; i < n; ++i)
; if (a[i] > 0)
; a[i] = c[2]*b[i];
; }
; and we want to hoist the load of c[2] out of the loop. This can be done only
; because the dereferenceable attribute is on %c.
define void @test3(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly dereferenceable(12) align 4 %c, i32 %n) #0 {
; CHECK-LABEL: @test3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[C2:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C2]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%c2 = getelementptr inbounds i32, i32* %c, i64 2
%1 = load i32, i32* %c2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; This is the same as @test3, but with a dereferenceable attribute on %c with a
; size too small to cover c[2] (and so we should not hoist it).
define void @test4(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly dereferenceable(11) %c, i32 %n) #0 {
; CHECK-LABEL: @test4(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[C2:%.*]] = getelementptr inbounds i32, i32* [[C:%.*]], i64 2
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C2]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%c2 = getelementptr inbounds i32, i32* %c, i64 2
%1 = load i32, i32* %c2, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; This test represents the following function:
; void test1(int * __restrict__ a, int *b, int &c, int n) {
; if (c != null)
; for (int i = 0; i < n; ++i)
; if (a[i] > 0)
; a[i] = c*b[i];
; }
; and we want to hoist the load of %c out of the loop. This can be done only
; because the dereferenceable_or_null attribute is on %c and there is a null
; check on %c.
define void @test5(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) align 4 %c, i32 %n) #0 {
; CHECK-LABEL: @test5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: br i1 [[NOT_NULL]], label [[NOT_NULL:%.*]], label [[FOR_END:%.*]]
; CHECK: not.null:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp ne i32* %c, null
br i1 %not_null, label %not.null, label %for.end
not.null:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %not.null, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %not.null ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %not.null
ret void
}
; This is the same as @test5, but without the null check on %c.
; Without this check, we should not hoist the load of %c.
; This test case has an icmp on c but the use of this comparison is
; not a branch.
define i1 @test6(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) %c, i32 %n) #0 {
; CHECK-LABEL: @test6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret i1 [[NOT_NULL]]
;
entry:
%not_null = icmp ne i32* %c, null
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret i1 %not_null
}
; This test represents the following function:
; void test1(int * __restrict__ a, int *b, int **cptr, int n) {
; c = *cptr;
; for (int i = 0; i < n; ++i)
; if (a[i] > 0)
; a[i] = (*c)*b[i];
; }
; and we want to hoist the load of %c out of the loop. This can be done only
; because the dereferenceable meatdata on the c = *cptr load.
define void @test7(i32* noalias %a, i32* %b, i32** %cptr, i32 %n) #0 {
; CHECK-LABEL: @test7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[C:%.*]] = load i32*, i32** [[CPTR:%.*]], align 8, !dereferenceable !0, !align !0
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%c = load i32*, i32** %cptr, !dereferenceable !0, !align !{i64 4}
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; This test represents the following function:
; void test1(int * __restrict__ a, int *b, int **cptr, int n) {
; c = *cptr;
; if (c != null)
; for (int i = 0; i < n; ++i)
; if (a[i] > 0)
; a[i] = (*c)*b[i];
; }
; and we want to hoist the load of %c out of the loop. This can be done only
; because the dereferenceable_or_null meatdata on the c = *cptr load and there
; is a null check on %c.
define void @test8(i32* noalias %a, i32* %b, i32** %cptr, i32 %n) #0 {
; CHECK-LABEL: @test8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[C:%.*]] = load i32*, i32** [[CPTR:%.*]], align 8, !dereferenceable_or_null !0, !align !0
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C]], null
; CHECK-NEXT: br i1 [[NOT_NULL]], label [[NOT_NULL:%.*]], label [[FOR_END:%.*]]
; CHECK: not.null:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%c = load i32*, i32** %cptr, !dereferenceable_or_null !0, !align !{i64 4}
%not_null = icmp ne i32* %c, null
br i1 %not_null, label %not.null, label %for.end
not.null:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %not.null, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %not.null ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %not.null
ret void
}
; This is the same as @test8, but without the null check on %c.
; Without this check, we should not hoist the load of %c.
define void @test9(i32* noalias %a, i32* %b, i32** %cptr, i32 %n) #0 {
; CHECK-LABEL: @test9(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[C:%.*]] = load i32*, i32** [[CPTR:%.*]], align 8, !dereferenceable_or_null !0
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%c = load i32*, i32** %cptr, !dereferenceable_or_null !0
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; In this test we should be able to only hoist load from %cptr. We can't hoist
; load from %c because it's dereferenceability can depend on %cmp1 condition.
; By moving it out of the loop we break this dependency and can not rely
; on the dereferenceability anymore.
; In other words this test checks that we strip dereferenceability metadata
; after hoisting an instruction.
define void @test10(i32* noalias %a, i32* %b, i32** dereferenceable(8) align 8 %cptr, i32 %n) #0 {
; CHECK-LABEL: @test10(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[C:%.*]] = load i32*, i32** [[CPTR:%.*]], align 8
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%c = load i32*, i32** %cptr, !dereferenceable !0
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
define void @test11(i32* noalias %a, i32* %b, i32** dereferenceable(8) %cptr, i32 %n) #0 {
; CHECK-LABEL: @test11(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[C:%.*]] = load i32*, i32** [[CPTR:%.*]], align 8, !dereferenceable !0
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[D:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[E:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[E]], [[D]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
%c = load i32*, i32** %cptr, !dereferenceable !0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%d = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%e = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %e, %d
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
declare void @llvm.experimental.guard(i1, ...)
; Prove non-null ness of %c via a guard, not a branch.
define void @test12(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) align 4 %c, i32 %n) #0 {
; CHECK-LABEL: @test12(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[NOT_NULL]]) [ "deopt"() ]
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp ne i32* %c, null
call void(i1, ...) @llvm.experimental.guard(i1 %not_null) [ "deopt"() ]
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %entry
ret void
}
; Like @test12, but has a post-dominating guard, which cannot be used
; to prove %c is nonnull at the point of the load.
define void @test13(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) %c, i32 %n) #0 {
; CHECK-LABEL: @test13(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[NOT_NULL]]) [ "deopt"() ]
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp ne i32* %c, null
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %entry
call void(i1, ...) @llvm.experimental.guard(i1 %not_null) [ "deopt"() ]
ret void
}
; Check that branch by condition "null check AND something" allows to hoist the
; load.
define void @test14(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) align 4 %c, i32 %n, i1 %dummy_cond) #0 {
; CHECK-LABEL: @test14(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: [[DUMMY_AND:%.*]] = and i1 [[NOT_NULL]], [[DUMMY_COND:%.*]]
; CHECK-NEXT: br i1 [[DUMMY_AND]], label [[NOT_NULL:%.*]], label [[FOR_END:%.*]]
; CHECK: not.null:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp ne i32* %c, null
%dummy_and = and i1 %not_null, %dummy_cond
br i1 %dummy_and, label %not.null, label %for.end
not.null:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %not.null, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %not.null ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %not.null
ret void
}
; Check that guard by condition "null check AND something" allows to hoist the
; load.
define void @test15(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) align 4 %c, i32 %n, i1 %dummy_cond) #0 {
; CHECK-LABEL: @test15(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp ne i32* [[C:%.*]], null
; CHECK-NEXT: [[DUMMY_AND:%.*]] = and i1 [[NOT_NULL]], [[DUMMY_COND:%.*]]
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[DUMMY_AND]]) [ "deopt"() ]
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP1]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP0]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp ne i32* %c, null
%dummy_and = and i1 %not_null, %dummy_cond
call void(i1, ...) @llvm.experimental.guard(i1 %dummy_and) [ "deopt"() ]
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
; Ensure that (c == null && other_cond) does not automatically mean that c is
; non-null in false branch. So the condition ((c == null && other_cond) == false)
; is not sufficient to conclude that c != null.
define void @test16(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) %c, i32 %n, i1 %dummy_cond) #0 {
; CHECK-LABEL: @test16(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp eq i32* [[C:%.*]], null
; CHECK-NEXT: [[DUMMY_AND:%.*]] = and i1 [[NOT_NULL]], [[DUMMY_COND:%.*]]
; CHECK-NEXT: br i1 [[DUMMY_AND]], label [[FOR_END:%.*]], label [[NOT_NULL:%.*]]
; CHECK: not.null:
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp eq i32* %c, null
%dummy_and = and i1 %not_null, %dummy_cond
br i1 %dummy_and, label %for.end, label %not.null
not.null:
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.body, label %for.end
for.body: ; preds = %not.null, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %not.null ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry, %not.null
ret void
}
; Ensure that (c == null && other_cond) does not automatically mean that c is
; non-null in false branch. So the condition ((c == null && other_cond) == false)
; is not sufficient to conclude that c != null.
define void @test17(i32* noalias %a, i32* %b, i32* dereferenceable_or_null(4) %c, i32 %n, i1 %dummy_cond) #0 {
; CHECK-LABEL: @test17(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NOT_NULL:%.*]] = icmp eq i32* [[C:%.*]], null
; CHECK-NEXT: [[DUMMY_AND:%.*]] = and i1 [[NOT_NULL]], [[DUMMY_COND:%.*]]
; CHECK-NEXT: call void (i1, ...) @llvm.experimental.guard(i1 [[DUMMY_AND]]) [ "deopt"() ]
; CHECK-NEXT: [[CMP11:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP11]], label [[FOR_END:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp sgt i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[C]], align 4
; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX3]], align 4
; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: store i32 [[MUL]], i32* [[ARRAYIDX]], 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: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT:%.*]], label [[FOR_BODY]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%not_null = icmp eq i32* %c, null
%dummy_and = and i1 %not_null, %dummy_cond
call void(i1, ...) @llvm.experimental.guard(i1 %dummy_and) [ "deopt"() ]
%cmp11 = icmp sgt i32 %n, 0
br i1 %cmp11, label %for.end, label %for.body
for.body: ; preds = %entry, %for.inc
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 0
br i1 %cmp1, label %if.then, label %for.inc
if.then: ; preds = %for.body
%1 = load i32, i32* %c, align 4
%arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
%2 = load i32, i32* %arrayidx3, align 4
%mul = mul nsw i32 %2, %1
store i32 %mul, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%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.end, label %for.body
for.end: ; preds = %for.inc, %entry
ret void
}
attributes #0 = { nounwind uwtable nofree nosync }
!0 = !{i64 4}
Reference in New Issue View Git Blame Copy Permalink