[llvm] 89440df - [ValueTracking] Improve ComputeNumSignBits for SRem.

[Craig Topper via llvm-commits]

Author: Craig Topper
Date: 2021-02-22T14:36:25-08:00
New Revision: 89440df64a5bf9981111e5980647e958f132b6a9

URL: https://github.com/llvm/llvm-project/commit/89440df64a5bf9981111e5980647e958f132b6a9
DIFF: https://github.com/llvm/llvm-project/commit/89440df64a5bf9981111e5980647e958f132b6a9.diff

LOG: [ValueTracking] Improve ComputeNumSignBits for SRem.

The result will have the same sign as the dividend unless the
result is 0. The magnitude of the result will always be less
than or equal to the dividend. So the result will have at least
as many sign bits as the dividend.

Previously we would do this if the divisor was a positive constant,
but that isn't required.

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D97170

Added: 
    

Modified: 
    llvm/lib/Analysis/ValueTracking.cpp
    llvm/test/Transforms/InstCombine/with_overflow.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 04919414ae48..520c7f98b9be 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -2784,6 +2784,8 @@ static unsigned ComputeNumSignBitsImpl(const Value *V,
     }
 
     case Instruction::SRem: {
+      Tmp = ComputeNumSignBits(U->getOperand(0), Depth + 1, Q);
+
       const APInt *Denominator;
       // srem X, C -> we know that the result is within [-C+1,C) when C is a
       // positive constant.  This let us put a lower bound on the number of sign
@@ -2791,30 +2793,25 @@ static unsigned ComputeNumSignBitsImpl(const Value *V,
       if (match(U->getOperand(1), m_APInt(Denominator))) {
 
         // Ignore non-positive denominator.
-        if (!Denominator->isStrictlyPositive())
-          break;
-
-        // Calculate the incoming numerator bits. SRem by a positive constant
-        // can't lower the number of sign bits.
-        unsigned NumrBits = ComputeNumSignBits(U->getOperand(0), Depth + 1, Q);
-
-        // Calculate the leading sign bit constraints by examining the
-        // denominator.  Given that the denominator is positive, there are two
-        // cases:
-        //
-        //  1. the numerator is positive. The result range is [0,C) and [0,C) u<
-        //     (1 << ceilLogBase2(C)).
-        //
-        //  2. the numerator is negative. Then the result range is (-C,0] and
-        //     integers in (-C,0] are either 0 or >u (-1 << ceilLogBase2(C)).
-        //
-        // Thus a lower bound on the number of sign bits is `TyBits -
-        // ceilLogBase2(C)`.
-
-        unsigned ResBits = TyBits - Denominator->ceilLogBase2();
-        return std::max(NumrBits, ResBits);
+        if (Denominator->isStrictlyPositive()) {
+          // Calculate the leading sign bit constraints by examining the
+          // denominator.  Given that the denominator is positive, there are two
+          // cases:
+          //
+          //  1. The numerator is positive. The result range is [0,C) and
+          //     [0,C) u< (1 << ceilLogBase2(C)).
+          //
+          //  2. The numerator is negative. Then the result range is (-C,0] and
+          //     integers in (-C,0] are either 0 or >u (-1 << ceilLogBase2(C)).
+          //
+          // Thus a lower bound on the number of sign bits is `TyBits -
+          // ceilLogBase2(C)`.
+
+          unsigned ResBits = TyBits - Denominator->ceilLogBase2();
+          Tmp = std::max(Tmp, ResBits);
+        }
       }
-      break;
+      return Tmp;
     }
 
     case Instruction::AShr: {

diff  --git a/llvm/test/Transforms/InstCombine/with_overflow.ll b/llvm/test/Transforms/InstCombine/with_overflow.ll
index 12db6b795293..bff6ce8bc847 100644
--- a/llvm/test/Transforms/InstCombine/with_overflow.ll
+++ b/llvm/test/Transforms/InstCombine/with_overflow.ll
@@ -332,11 +332,7 @@ define i1 @overflow_mod_overflow_mul(i32 %v1, i32 %v2) nounwind {
 
 define i1 @overflow_mod_mul2(i16 %v1, i32 %v2) nounwind {
 ; CHECK-LABEL: @overflow_mod_mul2(
-; CHECK-NEXT:    [[A:%.*]] = sext i16 [[V1:%.*]] to i32
-; CHECK-NEXT:    [[REM:%.*]] = srem i32 [[A]], [[V2:%.*]]
-; CHECK-NEXT:    [[T:%.*]] = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[REM]], i32 [[REM]])
-; CHECK-NEXT:    [[OBIT:%.*]] = extractvalue { i32, i1 } [[T]], 1
-; CHECK-NEXT:    ret i1 [[OBIT]]
+; CHECK-NEXT:    ret i1 false
 ;
   %a = sext i16 %v1 to i32
   %rem = srem i32 %a, %v2