Teach getZeroExtendExpr and getSignExtendExpr to use trip-count

information to simplify [sz]ext({a,+,b}) to {zext(a),+,[zs]ext(b)},
as appropriate.

These functions and the trip count code each call into the other, so
this requires careful handling to avoid infinite recursion. During
the initial trip count computation, conservative SCEVs are used,
which are subsequently discarded once the trip count is actually
known.

Among other benefits, this change lets LSR automatically eliminate
some unnecessary zext-inreg and sext-inreg operation where the
operand is an induction variable.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@70241 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 244 insertions, 0 deletions

diff --git a/test/CodeGen/X86/masked-iv-safe.ll b/test/CodeGen/X86/masked-iv-safe.ll
new file mode 100644
index 0000000..2ba3f83
--- /dev/null
+++ b/test/CodeGen/X86/masked-iv-safe.ll
@@ -0,0 +1,244 @@
+; RUN: llvm-as < %s | llc -march=x86-64 > %t
+; RUN: not grep and %t
+; RUN: not grep movz %t
+; RUN: not grep sar %t
+; RUN: not grep shl %t
+; RUN: grep add %t | count 6
+; RUN: grep inc %t | count 4
+; RUN: grep dec %t | count 2
+; RUN: grep lea %t | count 2
+
+; Optimize away zext-inreg and sext-inreg on the loop induction
+; variable using trip-count information.
+
+define void @count_up(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 0, %entry ], [ %indvar.next, %loop ]
+	%indvar.i8 = and i64 %indvar, 255
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%indvar.i24 = and i64 %indvar, 16777215
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = add i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 10
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @count_down(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 10, %entry ], [ %indvar.next, %loop ]
+	%indvar.i8 = and i64 %indvar, 255
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%indvar.i24 = and i64 %indvar, 16777215
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = sub i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 0
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @count_up_signed(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 0, %entry ], [ %indvar.next, %loop ]
+        %s0 = shl i64 %indvar, 8
+	%indvar.i8 = ashr i64 %s0, 8
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%s1 = shl i64 %indvar, 24
+	%indvar.i24 = ashr i64 %s1, 24
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = add i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 10
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @count_down_signed(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 10, %entry ], [ %indvar.next, %loop ]
+        %s0 = shl i64 %indvar, 8
+	%indvar.i8 = ashr i64 %s0, 8
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%s1 = shl i64 %indvar, 24
+	%indvar.i24 = ashr i64 %s1, 24
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = sub i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 0
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @another_count_up(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 18446744073709551615, %entry ], [ %indvar.next, %loop ]
+	%indvar.i8 = and i64 %indvar, 255
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%indvar.i24 = and i64 %indvar, 16777215
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = add i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 0
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @another_count_down(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 0, %entry ], [ %indvar.next, %loop ]
+	%indvar.i8 = and i64 %indvar, 255
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%indvar.i24 = and i64 %indvar, 16777215
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = sub i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 18446744073709551615
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @another_count_up_signed(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 18446744073709551615, %entry ], [ %indvar.next, %loop ]
+        %s0 = shl i64 %indvar, 8
+	%indvar.i8 = ashr i64 %s0, 8
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%s1 = shl i64 %indvar, 24
+	%indvar.i24 = ashr i64 %s1, 24
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = add i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 0
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}
+
+define void @another_count_down_signed(double* %d, i64 %n) nounwind {
+entry:
+	br label %loop
+
+loop:
+	%indvar = phi i64 [ 0, %entry ], [ %indvar.next, %loop ]
+        %s0 = shl i64 %indvar, 8
+	%indvar.i8 = ashr i64 %s0, 8
+	%t0 = getelementptr double* %d, i64 %indvar.i8
+	%t1 = load double* %t0
+	%t2 = mul double %t1, 0.1
+	store double %t2, double* %t0
+	%s1 = shl i64 %indvar, 24
+	%indvar.i24 = ashr i64 %s1, 24
+	%t3 = getelementptr double* %d, i64 %indvar.i24
+	%t4 = load double* %t3
+	%t5 = mul double %t4, 2.3
+	store double %t5, double* %t3
+	%t6 = getelementptr double* %d, i64 %indvar
+	%t7 = load double* %t6
+	%t8 = mul double %t7, 4.5
+	store double %t8, double* %t6
+	%indvar.next = sub i64 %indvar, 1
+	%exitcond = icmp eq i64 %indvar.next, 18446744073709551615
+	br i1 %exitcond, label %return, label %loop
+
+return:
+	ret void
+}