; CHECK-NOT: store
}
+; This is a loop that was rotated but where the blocks weren't merged. This
+; shouldn't perturb us.
+define void @test1a(i8* %Base, i64 %Size) nounwind ssp {
+bb.nph: ; preds = %entry
+ br label %for.body
+
+for.body: ; preds = %bb.nph, %for.body
+ %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body.cont ]
+ %I.0.014 = getelementptr i8* %Base, i64 %indvar
+ store i8 0, i8* %I.0.014, align 1
+ %indvar.next = add i64 %indvar, 1
+ br label %for.body.cont
+for.body.cont:
+ %exitcond = icmp eq i64 %indvar.next, %Size
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+; CHECK: @test1a
+; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK-NOT: store
+}
+
+
define void @test2(i32* %Base, i64 %Size) nounwind ssp {
entry:
%cmp10 = icmp eq i64 %Size, 0
; CHECK: ret void
}
+
+;; memcpy formation
+define void @test6(i64 %Size) nounwind ssp {
+bb.nph:
+ %Base = alloca i8, i32 10000
+ %Dest = alloca i8, i32 10000
+ br label %for.body
+
+for.body: ; preds = %bb.nph, %for.body
+ %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
+ %I.0.014 = getelementptr i8* %Base, i64 %indvar
+ %DestI = getelementptr i8* %Dest, i64 %indvar
+ %V = load i8* %I.0.014, align 1
+ store i8 %V, i8* %DestI, align 1
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, %Size
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+; CHECK: @test6
+; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %Dest, i8* %Base, i64 %Size, i32 1, i1 false)
+; CHECK-NOT: store
+; CHECK: ret void
+}
+
+
+; This is a loop that was rotated but where the blocks weren't merged. This
+; shouldn't perturb us.
+define void @test7(i8* %Base, i64 %Size) nounwind ssp {
+bb.nph: ; preds = %entry
+ br label %for.body
+
+for.body: ; preds = %bb.nph, %for.body
+ %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body.cont ]
+ br label %for.body.cont
+for.body.cont:
+ %I.0.014 = getelementptr i8* %Base, i64 %indvar
+ store i8 0, i8* %I.0.014, align 1
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, %Size
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+; CHECK: @test7
+; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK-NOT: store
+}
+
+; This is a loop should not be transformed, it only executes one iteration.
+define void @test8(i64* %Ptr, i64 %Size) nounwind ssp {
+bb.nph: ; preds = %entry
+ br label %for.body
+
+for.body: ; preds = %bb.nph, %for.body
+ %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
+ %PI = getelementptr i64* %Ptr, i64 %indvar
+ store i64 0, i64 *%PI
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, 1
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+; CHECK: @test8
+; CHECK: store i64 0, i64* %PI
+}
+
+declare i8* @external(i8*)
+
+;; This cannot be transformed into a memcpy, because the read-from location is
+;; mutated by the loop.
+define void @test9(i64 %Size) nounwind ssp {
+bb.nph:
+ %Base = alloca i8, i32 10000
+ %Dest = alloca i8, i32 10000
+
+ %BaseAlias = call i8* @external(i8* %Base)
+ br label %for.body
+
+for.body: ; preds = %bb.nph, %for.body
+ %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
+ %I.0.014 = getelementptr i8* %Base, i64 %indvar
+ %DestI = getelementptr i8* %Dest, i64 %indvar
+ %V = load i8* %I.0.014, align 1
+ store i8 %V, i8* %DestI, align 1
+
+ ;; This store can clobber the input.
+ store i8 4, i8* %BaseAlias
+
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, %Size
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ ret void
+; CHECK: @test9
+; CHECK-NOT: llvm.memcpy
+; CHECK: ret void
+}
+
+; Two dimensional nested loop should be promoted to one big memset.
+define void @test10(i8* %X) nounwind ssp {
+entry:
+ br label %bb.nph
+
+bb.nph: ; preds = %entry, %for.inc10
+ %i.04 = phi i32 [ 0, %entry ], [ %inc12, %for.inc10 ]
+ br label %for.body5
+
+for.body5: ; preds = %for.body5, %bb.nph
+ %j.02 = phi i32 [ 0, %bb.nph ], [ %inc, %for.body5 ]
+ %mul = mul nsw i32 %i.04, 100
+ %add = add nsw i32 %j.02, %mul
+ %idxprom = sext i32 %add to i64
+ %arrayidx = getelementptr inbounds i8* %X, i64 %idxprom
+ store i8 0, i8* %arrayidx, align 1
+ %inc = add nsw i32 %j.02, 1
+ %cmp4 = icmp eq i32 %inc, 100
+ br i1 %cmp4, label %for.inc10, label %for.body5
+
+for.inc10: ; preds = %for.body5
+ %inc12 = add nsw i32 %i.04, 1
+ %cmp = icmp eq i32 %inc12, 100
+ br i1 %cmp, label %for.end13, label %bb.nph
+
+for.end13: ; preds = %for.inc10
+ ret void
+; CHECK: @test10
+; CHECK: entry:
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false)
+; CHECK-NOT: store
+; CHECK: ret void
+}
+
+; On darwin10 (which is the triple in this .ll file) this loop can be turned
+; into a memset_pattern call.
+; rdar://9009151
+define void @test11_pattern(i32* nocapture %P) nounwind ssp {
+entry:
+ br label %for.body
+
+for.body: ; preds = %entry, %for.body
+ %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %for.body ]
+ %arrayidx = getelementptr i32* %P, i64 %indvar
+ store i32 1, i32* %arrayidx, align 4
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, 10000
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+; CHECK: @test11_pattern
+; CHECK-NEXT: entry:
+; CHECK-NEXT: bitcast
+; CHECK-NEXT: memset_pattern
+; CHECK-NOT: store
+; CHECK: ret void
+}
+
+; Store of null should turn into memset of zero.
+define void @test12(i32** nocapture %P) nounwind ssp {
+entry:
+ br label %for.body
+
+for.body: ; preds = %entry, %for.body
+ %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %for.body ]
+ %arrayidx = getelementptr i32** %P, i64 %indvar
+ store i32* null, i32** %arrayidx, align 4
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, 10000
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+; CHECK: @test12
+; CHECK-NEXT: entry:
+; CHECK-NEXT: bitcast
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %P1, i8 0, i64 80000, i32 4, i1 false)
+; CHECK-NOT: store
+; CHECK: ret void
+}
+
+@G = global i32 5
+
+; This store-of-address loop can be turned into a memset_pattern call.
+; rdar://9009151
+define void @test13_pattern(i32** nocapture %P) nounwind ssp {
+entry:
+ br label %for.body
+
+for.body: ; preds = %entry, %for.body
+ %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %for.body ]
+ %arrayidx = getelementptr i32** %P, i64 %indvar
+ store i32* @G, i32** %arrayidx, align 4
+ %indvar.next = add i64 %indvar, 1
+ %exitcond = icmp eq i64 %indvar.next, 10000
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+; CHECK: @test13_pattern
+; CHECK-NEXT: entry:
+; CHECK-NEXT: bitcast
+; CHECK-NEXT: memset_pattern
+; CHECK-NOT: store
+; CHECK: ret void
+}
+
+
+
+; PR9815 - This is a partial overlap case that cannot be safely transformed
+; into a memcpy.
+@g_50 = global [7 x i32] [i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0], align 16
+
+define i32 @test14() nounwind {
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.inc, %for.body.lr.ph
+ %tmp5 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
+ %add = add nsw i32 %tmp5, 4
+ %idxprom = sext i32 %add to i64
+ %arrayidx = getelementptr inbounds [7 x i32]* @g_50, i32 0, i64 %idxprom
+ %tmp2 = load i32* %arrayidx, align 4
+ %add4 = add nsw i32 %tmp5, 5
+ %idxprom5 = sext i32 %add4 to i64
+ %arrayidx6 = getelementptr inbounds [7 x i32]* @g_50, i32 0, i64 %idxprom5
+ store i32 %tmp2, i32* %arrayidx6, align 4
+ %inc = add nsw i32 %tmp5, 1
+ %cmp = icmp slt i32 %inc, 2
+ br i1 %cmp, label %for.body, label %for.end
+
+for.end: ; preds = %for.inc
+ %tmp8 = load i32* getelementptr inbounds ([7 x i32]* @g_50, i32 0, i64 6), align 4
+ ret i32 %tmp8
+; CHECK: @test14
+; CHECK: for.body:
+; CHECK: load i32
+; CHECK: store i32
+; CHECK: br i1 %cmp
+
+}
+
+
projects / oota-llvm.git / blobdiff