[ValueTracking] Extend range metadata to call/invoke

Summary:
With this patch, range metadata can be added to call/invoke including
IntrinsicInst. Previously, it could only be added to load.

Rename computeKnownBitsLoad to computeKnownBitsFromRangeMetadata because
range metadata is not only used by load.

Update the language reference to reflect this change.

Test Plan:
Add several tests in range-2.ll to confirm the verifier is happy with
having range metadata on call/invoke.

Add two tests in AddOverFlow.ll to confirm annotating range metadata to
call/invoke can benefit InstCombine.

Reviewers: meheff, nlewycky, reames, hfinkel, eliben

Reviewed By: eliben

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D4187

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211281 91177308-0d34-0410-b5e6-96231b3b80d8

Author: Jingyue Wu

docs/LangRef.rst

@@ -2749,11 +2749,12 @@ number representing the maximum relative error, for example:
 '``range``' Metadata
 ^^^^^^^^^^^^^^^^^^^^
 
-``range`` metadata may be attached only to loads of integer types. It
-expresses the possible ranges the loaded value is in. The ranges are
-represented with a flattened list of integers. The loaded value is known
-to be in the union of the ranges defined by each consecutive pair. Each
-pair has the following properties:
+``range`` metadata may be attached only to ``load``, ``call`` and ``invoke`` of
+integer types. It expresses the possible ranges the loaded value or the value
+returned by the called function at this call site is in. The ranges are
+represented with a flattened list of integers. The loaded value or the value
+returned is known to be in the union of the ranges defined by each consecutive
+pair. Each pair has the following properties:
 
 -  The type must match the type loaded by the instruction.
 -  The pair ``a,b`` represents the range ``[a,b)``.
@@ -2771,8 +2772,9 @@ Examples:
 
       %a = load i8* %x, align 1, !range !0 ; Can only be 0 or 1
       %b = load i8* %y, align 1, !range !1 ; Can only be 255 (-1), 0 or 1
-      %c = load i8* %z, align 1, !range !2 ; Can only be 0, 1, 3, 4 or 5
-      %d = load i8* %z, align 1, !range !3 ; Can only be -2, -1, 3, 4 or 5
+      %c = call i8 @foo(),       !range !2 ; Can only be 0, 1, 3, 4 or 5
+      %d = invoke i8 @bar() to label %cont
+             unwind label %lpad, !range !3 ; Can only be -2, -1, 3, 4 or 5
     ...
     !0 = metadata !{ i8 0, i8 2 }
     !1 = metadata !{ i8 255, i8 2 }

include/llvm/Analysis/ValueTracking.h

@@ -37,7 +37,10 @@ namespace llvm {
   /// for all of the elements in the vector.
   void computeKnownBits(Value *V,  APInt &KnownZero, APInt &KnownOne,
                         const DataLayout *TD = nullptr, unsigned Depth = 0);
-  void computeKnownBitsLoad(const MDNode &Ranges, APInt &KnownZero);
+  /// Compute known bits from the range metadata.
+  /// \p KnownZero the set of bits that are known to be zero
+  void computeKnownBitsFromRangeMetadata(const MDNode &Ranges,
+                                         APInt &KnownZero);
 
   /// ComputeSignBit - Determine whether the sign bit is known to be zero or
   /// one.  Convenience wrapper around computeKnownBits.

lib/Analysis/ValueTracking.cpp

@@ -188,7 +188,8 @@ static void computeKnownBitsMul(Value *Op0, Value *Op1, bool NSW,
     KnownOne.setBit(BitWidth - 1);
 }
 
-void llvm::computeKnownBitsLoad(const MDNode &Ranges, APInt &KnownZero) {
+void llvm::computeKnownBitsFromRangeMetadata(const MDNode &Ranges,
+                                             APInt &KnownZero) {
   unsigned BitWidth = KnownZero.getBitWidth();
   unsigned NumRanges = Ranges.getNumOperands() / 2;
   assert(NumRanges >= 1);
@@ -338,7 +339,7 @@ void llvm::computeKnownBits(Value *V, APInt &KnownZero, APInt &KnownOne,
   default: break;
   case Instruction::Load:
     if (MDNode *MD = cast<LoadInst>(I)->getMetadata(LLVMContext::MD_range))
-      computeKnownBitsLoad(*MD, KnownZero);
+      computeKnownBitsFromRangeMetadata(*MD, KnownZero);
     break;
   case Instruction::And: {
     // If either the LHS or the RHS are Zero, the result is zero.
@@ -733,6 +734,12 @@ void llvm::computeKnownBits(Value *V, APInt &KnownZero, APInt &KnownOne,
     break;
   }
   case Instruction::Call:
+  case Instruction::Invoke:
+    if (MDNode *MD = cast<Instruction>(I)->getMetadata(LLVMContext::MD_range))
+      computeKnownBitsFromRangeMetadata(*MD, KnownZero);
+    // If a range metadata is attached to this IntrinsicInst, intersect the
+    // explicit range specified by the metadata and the implicit range of
+    // the intrinsic.
     if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
       switch (II->getIntrinsicID()) {
       default: break;
@@ -742,16 +749,16 @@ void llvm::computeKnownBits(Value *V, APInt &KnownZero, APInt &KnownOne,
         // If this call is undefined for 0, the result will be less than 2^n.
         if (II->getArgOperand(1) == ConstantInt::getTrue(II->getContext()))
           LowBits -= 1;
-        KnownZero = APInt::getHighBitsSet(BitWidth, BitWidth - LowBits);
+        KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - LowBits);
         break;
       }
       case Intrinsic::ctpop: {
         unsigned LowBits = Log2_32(BitWidth)+1;
-        KnownZero = APInt::getHighBitsSet(BitWidth, BitWidth - LowBits);
+        KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - LowBits);
         break;
       }
       case Intrinsic::x86_sse42_crc32_64_64:
-        KnownZero = APInt::getHighBitsSet(64, 32);
+        KnownZero |= APInt::getHighBitsSet(64, 32);
         break;
       }
     }

lib/CodeGen/SelectionDAG/SelectionDAG.cpp

@@ -2084,7 +2084,7 @@ void SelectionDAG::computeKnownBits(SDValue Op, APInt &KnownZero,
       unsigned MemBits = VT.getScalarType().getSizeInBits();
       KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - MemBits);
     } else if (const MDNode *Ranges = LD->getRanges()) {
-      computeKnownBitsLoad(*Ranges, KnownZero);
+      computeKnownBitsFromRangeMetadata(*Ranges, KnownZero);
     }
     break;
   }

lib/IR/Verifier.cpp

@@ -2233,7 +2233,8 @@ void Verifier::visitInstruction(Instruction &I) {
   }
 
   MDNode *MD = I.getMetadata(LLVMContext::MD_range);
-  Assert1(!MD || isa<LoadInst>(I), "Ranges are only for loads!", &I);
+  Assert1(!MD || isa<LoadInst>(I) || isa<CallInst>(I) || isa<InvokeInst>(I),
+          "Ranges are only for loads, calls and invokes!", &I);
 
   InstsInThisBlock.insert(&I);
 }

test/Transforms/InstCombine/AddOverFlow.ll

@@ -34,6 +34,44 @@ define i16 @zero_sign_bit2(i16 %a, i16 %b) {
   ret i16 %3
 }
 
+declare i16 @bounded(i16 %input);
+declare i32 @__gxx_personality_v0(...);
+!0 = metadata !{i16 0, i16 32768} ; [0, 32767]
+!1 = metadata !{i16 0, i16 32769} ; [0, 32768]
+
+define i16 @add_bounded_values(i16 %a, i16 %b) {
+; CHECK-LABEL: @add_bounded_values(
+entry:
+  %c = call i16 @bounded(i16 %a), !range !0
+  %d = invoke i16 @bounded(i16 %b) to label %cont unwind label %lpad, !range !0
+cont:
+; %c and %d are in [0, 32767]. Therefore, %c + %d doesn't unsigned overflow.
+  %e = add i16 %c, %d
+; CHECK: add nuw i16 %c, %d
+  ret i16 %e
+lpad:
+  %0 = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
+          filter [0 x i8*] zeroinitializer
+  ret i16 42
+}
+
+define i16 @add_bounded_values_2(i16 %a, i16 %b) {
+; CHECK-LABEL: @add_bounded_values_2(
+entry:
+  %c = call i16 @bounded(i16 %a), !range !1
+  %d = invoke i16 @bounded(i16 %b) to label %cont unwind label %lpad, !range !1
+cont:
+; Similar to add_bounded_values, but %c and %d are in [0, 32768]. Therefore,
+; %c + %d may unsigned overflow and we cannot add NUW.
+  %e = add i16 %c, %d
+; CHECK: add i16 %c, %d
+  ret i16 %e
+lpad:
+  %0 = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
+          filter [0 x i8*] zeroinitializer
+  ret i16 42
+}
+
 ; CHECK-LABEL: @ripple_nsw1
 ; CHECK: add nsw i16 %a, %b
 define i16 @ripple_nsw1(i16 %x, i16 %y) {

test/Transforms/InstCombine/add2.ll

@@ -217,3 +217,44 @@ define i32 @mul_add_to_mul_6(i32 %x, i32 %y) {
 ; CHECK-NEXT: %add = mul nsw i32 %mul1, 6
 ; CHECK-NEXT: ret i32 %add
 }
+
+; This test and the next test verify that when a range metadata is attached to
+; llvm.cttz, ValueTracking correctly intersects the range specified by the
+; metadata and the range implied by the intrinsic.
+;
+; In this test, the range specified by the metadata is more strict. Therefore,
+; ValueTracking uses that range.
+define i16 @add_cttz(i16 %a) {
+; CHECK-LABEL: @add_cttz(
+  ; llvm.cttz.i16(..., /*is_zero_undefined=*/true) implies the value returned
+  ; is in [0, 16). The range metadata indicates the value returned is in [0, 8).
+  ; Intersecting these ranges, we know the value returned is in [0, 8).
+  ; Therefore, InstCombine will transform
+  ;     add %cttz, 1111 1111 1111 1000 ; decimal -8
+  ; to
+  ;     or  %cttz, 1111 1111 1111 1000
+  %cttz = call i16 @llvm.cttz.i16(i16 %a, i1 true), !range !0
+  %b = add i16 %cttz, -8
+; CHECK: or i16 %cttz, -8
+  ret i16 %b
+}
+declare i16 @llvm.cttz.i16(i16, i1)
+!0 = metadata !{i16 0, i16 8}
+
+; Similar to @add_cttz, but in this test, the range implied by the
+; intrinsic is more strict. Therefore, ValueTracking uses that range.
+define i16 @add_cttz_2(i16 %a) {
+; CHECK-LABEL: @add_cttz_2(
+  ; llvm.cttz.i16(..., /*is_zero_undefined=*/true) implies the value returned
+  ; is in [0, 16). The range metadata indicates the value returned is in
+  ; [0, 32). Intersecting these ranges, we know the value returned is in
+  ; [0, 16). Therefore, InstCombine will transform
+  ;     add %cttz, 1111 1111 1111 0000 ; decimal -16
+  ; to
+  ;     or  %cttz, 1111 1111 1111 0000
+  %cttz = call i16 @llvm.cttz.i16(i16 %a, i1 true), !range !1
+  %b = add i16 %cttz, -16
+; CHECK: or i16 %cttz, -16
+  ret i16 %b
+}
+!1 = metadata !{i16 0, i16 32}

test/Verifier/range-1.ll

@@ -6,7 +6,7 @@ entry:
   ret void
 }
 !0 = metadata !{i8 0, i8 1}
-; CHECK: Ranges are only for loads!
+; CHECK: Ranges are only for loads, calls and invokes!
 ; CHECK-NEXT: store i8 0, i8* %x, align 1, !range !0
 
 define i8 @f2(i8* %x) {

test/Verifier/range-2.ll

@@ -34,3 +34,33 @@ entry:
   ret i8 %y
 }
 !4 = metadata !{i8 -1, i8 0, i8 1, i8 -2}
+
+; We can annotate the range of the return value of a CALL.
+define void @call_all(i8* %x) {
+entry:
+  %v1 = call i8 @f1(i8* %x), !range !0
+  %v2 = call i8 @f2(i8* %x), !range !1
+  %v3 = call i8 @f3(i8* %x), !range !2
+  %v4 = call i8 @f4(i8* %x), !range !3
+  %v5 = call i8 @f5(i8* %x), !range !4
+  ret void
+}
+
+; We can annotate the range of the return value of an INVOKE.
+define void @invoke_all(i8* %x) {
+entry:
+  %v1 = invoke i8 @f1(i8* %x) to label %cont unwind label %lpad, !range !0
+  %v2 = invoke i8 @f2(i8* %x) to label %cont unwind label %lpad, !range !1
+  %v3 = invoke i8 @f3(i8* %x) to label %cont unwind label %lpad, !range !2
+  %v4 = invoke i8 @f4(i8* %x) to label %cont unwind label %lpad, !range !3
+  %v5 = invoke i8 @f5(i8* %x) to label %cont unwind label %lpad, !range !4
+
+cont:
+  ret void
+
+lpad:
+  %4 = landingpad { i8*, i32 } personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*)
+          filter [0 x i8*] zeroinitializer
+  ret void
+}
+declare i32 @__gxx_personality_v0(...)