From: Sanjay Patel <spatel@rotateright.com>
Date: Thu, 8 Oct 2015 16:56:55 +0000 (+0000)
Subject: [ValueTracking] teach computeKnownBits that a fabs() clears sign bits
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=1938c39ce4afd671ccf309f08233e2e3dfd8fcdc;p=oota-llvm.git

[ValueTracking] teach computeKnownBits that a fabs() clears sign bits

This was requested in D13076: if we're going to canonicalize to fabs(), ValueTracking
should know that fabs() clears sign bits.

In this patch (as in D13076), we're not handling vectors yet even though computeKnownBits'
fabs() case itself should be vector-ready via the splat in this patch.
Fixing this will require follow-on patches to correct other logic that uses 'getScalarType'.

Differential Revision: http://reviews.llvm.org/D13222



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@249701 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Analysis/ValueTracking.cpp b/lib/Analysis/ValueTracking.cpp
index d8a449193a3..2259d871c8c 100644
--- a/lib/Analysis/ValueTracking.cpp
+++ b/lib/Analysis/ValueTracking.cpp
@@ -1065,7 +1065,8 @@ static void computeKnownBitsFromOperator(Operator *I, APInt &KnownZero,
   }
   case Instruction::BitCast: {
     Type *SrcTy = I->getOperand(0)->getType();
-    if ((SrcTy->isIntegerTy() || SrcTy->isPointerTy()) &&
+    if ((SrcTy->isIntegerTy() || SrcTy->isPointerTy() ||
+         SrcTy->isFloatingPointTy()) &&
         // TODO: For now, not handling conversions like:
         // (bitcast i64 %x to <2 x i32>)
         !I->getType()->isVectorTy()) {
@@ -1378,6 +1379,12 @@ static void computeKnownBitsFromOperator(Operator *I, APInt &KnownZero,
         KnownZero |= APInt::getHighBitsSet(BitWidth, BitWidth - LowBits);
         break;
       }
+      case Intrinsic::fabs: {
+        Type *Ty = II->getType();
+        APInt SignBit = APInt::getSignBit(Ty->getScalarSizeInBits());
+        KnownZero |= APInt::getSplat(Ty->getPrimitiveSizeInBits(), SignBit);
+        break;
+      }
       case Intrinsic::x86_sse42_crc32_64_64:
         KnownZero |= APInt::getHighBitsSet(64, 32);
         break;
@@ -1477,8 +1484,9 @@ void computeKnownBits(Value *V, APInt &KnownZero, APInt &KnownOne,
   unsigned BitWidth = KnownZero.getBitWidth();
 
   assert((V->getType()->isIntOrIntVectorTy() ||
+          V->getType()->isFPOrFPVectorTy() ||
           V->getType()->getScalarType()->isPointerTy()) &&
-         "Not integer or pointer type!");
+         "Not integer, floating point, or pointer type!");
   assert((DL.getTypeSizeInBits(V->getType()->getScalarType()) == BitWidth) &&
          (!V->getType()->isIntOrIntVectorTy() ||
           V->getType()->getScalarSizeInBits() == BitWidth) &&
diff --git a/test/Transforms/InstCombine/fabs.ll b/test/Transforms/InstCombine/fabs.ll
index 0479549bea3..941270df0e9 100644
--- a/test/Transforms/InstCombine/fabs.ll
+++ b/test/Transforms/InstCombine/fabs.ll
@@ -41,6 +41,7 @@ define fp128 @square_fabs_call_f128(fp128 %x) {
 declare float @llvm.fabs.f32(float)
 declare double @llvm.fabs.f64(double)
 declare fp128 @llvm.fabs.f128(fp128)
+declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
 
 define float @square_fabs_intrinsic_f32(float %x) {
   %mul = fmul float %x, %x
@@ -98,3 +99,27 @@ define float @square_fabs_shrink_call2(float %x) {
 ; CHECK-NEXT: ret float %sq
 }
 
+; A scalar fabs op makes the sign bit zero, so masking off all of the other bits means we can return zero.
+
+define i32 @fabs_value_tracking_f32(float %x) {
+  %call = call float @llvm.fabs.f32(float %x)
+  %bc = bitcast float %call to i32
+  %and = and i32 %bc, 2147483648
+  ret i32 %and
+
+; CHECK-LABEL: fabs_value_tracking_f32(
+; CHECK:       ret i32 0
+}
+
+; TODO: A vector fabs op makes the sign bits zero, so masking off all of the other bits means we can return zero.
+
+define <4 x i32> @fabs_value_tracking_v4f32(<4 x float> %x) {
+  %call = call <4 x float> @llvm.fabs.v4f32(<4 x float> %x)
+  %bc = bitcast <4 x float> %call to <4 x i32>
+  %and = and <4 x i32> %bc, <i32 2147483648, i32 2147483648, i32 2147483648, i32 2147483648>
+  ret <4 x i32> %and
+
+; CHECK-LABEL: fabs_value_tracking_v4f32(
+; CHECK:       ret <4 x i32> %and
+}
+