[InstCombine] dropRedundantMaskingOfLeftShiftInput(): pat. a/b with mask (PR42563)

Summary:
And this is **finally** the interesting part of that fold!

If we have a pattern `(x & (~(-1 << maskNbits))) << shiftNbits`,
we already know (have a fold) that will drop the `& (~(-1 << maskNbits))`
mask iff `(maskNbits+shiftNbits) u>= bitwidth(x)`.
But that is actually ignorant, there's more general fold here:

In this pattern, `(maskNbits+shiftNbits)` actually correlates
with the number of low bits that will remain in the final value.
So even if `(maskNbits+shiftNbits) u< bitwidth(x)`, we can still
fold, we will just need to apply a **constant** mask afterwards:
```
Name: a, normal+mask
  %onebit = shl i32 -1, C1
  %mask = xor i32 %onebit, -1
  %masked = and i32 %mask, %x
  %r = shl i32 %masked, C2
=>
  %n0 = shl i32 %x, C2
  %n1 = add i32 C1, C2
  %n2 = zext i32 %n1 to i64
  %n3 = shl i64 -1, %n2
  %n4 = xor i64 %n3, -1
  %n5 = trunc i64 %n4 to i32
  %r = and i32 %n0, %n5
```
https://rise4fun.com/Alive/F5R

Naturally, old `%masked` will have to be one-use.
Similar fold exists for patterns c,d,e, will post patch later.

https://bugs.llvm.org/show_bug.cgi?id=42563

Reviewers: spatel, nikic, xbolva00

Reviewed By: spatel

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67677

llvm-svn: 372629

llvm/lib/Transforms/InstCombine/InstCombineShifts.cpp

@@ -152,6 +152,7 @@ dropRedundantMaskingOfLeftShiftInput(BinaryOperator *OuterShift,
       m_Shr(m_Shl(m_AllOnes(), m_Value(MaskShAmt)), m_Deferred(MaskShAmt));
 
   Value *X;
+  Constant *NewMask;
   if (match(Masked, m_c_And(m_CombineOr(MaskA, MaskB), m_Value(X)))) {
     // Can we simplify (MaskShAmt+ShiftShAmt) ?
     auto *SumOfShAmts = dyn_cast_or_null<Constant>(
@@ -166,8 +167,27 @@ dropRedundantMaskingOfLeftShiftInput(BinaryOperator *OuterShift,
     // bitwidth, we'll need to also produce a mask to keep SumOfShAmts low bits.
     // So, does *any* channel need a mask?
     if (!match(SumOfShAmts, m_SpecificInt_ICMP(ICmpInst::Predicate::ICMP_UGE,
-                                               APInt(BitWidth, BitWidth))))
+                                               APInt(BitWidth, BitWidth)))) {
-      return nullptr; // FIXME.
+      // But for a mask we need to get rid of old masking instruction.
+      if (!Masked->hasOneUse())
+        return nullptr; // Else we can't perform the fold.
+      // We should produce compute the mask in wider type, and truncate later!
+      // Get type twice as wide element-wise (same number of elements!).
+      Type *ExtendedScalarTy = Type::getIntNTy(Ty->getContext(), 2 * BitWidth);
+      Type *ExtendedTy =
+          Ty->isVectorTy()
+              ? VectorType::get(ExtendedScalarTy, Ty->getVectorNumElements())
+              : ExtendedScalarTy;
+      auto *ExtendedSumOfShAmts =
+          ConstantExpr::getZExt(SumOfShAmts, ExtendedTy);
+      // And compute the mask as usual: ~(-1 << (SumOfShAmts))
+      auto *ExtendedAllOnes = ConstantExpr::getAllOnesValue(ExtendedTy);
+      auto *ExtendedInvertedMask =
+          ConstantExpr::getShl(ExtendedAllOnes, ExtendedSumOfShAmts);
+      auto *ExtendedMask = ConstantExpr::getNot(ExtendedInvertedMask);
+      NewMask = ConstantExpr::getTrunc(ExtendedMask, Ty);
+    } else
+      NewMask = nullptr; // No mask needed.
     // All good, we can do this fold.
   } else if (match(Masked, m_c_And(m_CombineOr(MaskC, MaskD), m_Value(X))) ||
              match(Masked, m_Shr(m_Shl(m_Value(X), m_Value(MaskShAmt)),
@@ -185,12 +205,19 @@ dropRedundantMaskingOfLeftShiftInput(BinaryOperator *OuterShift,
     if (!match(ShAmtsDiff, m_NonNegative()))
       return nullptr; // FIXME.
     // All good, we can do this fold.
+    NewMask = nullptr; // No mask needed.
   } else
     return nullptr; // Don't know anything about this pattern.
 
   // No 'NUW'/'NSW'!
   // We no longer know that we won't shift-out non-0 bits.
-  return BinaryOperator::Create(OuterShift->getOpcode(), X, ShiftShAmt);
+  auto *NewShift =
+      BinaryOperator::Create(OuterShift->getOpcode(), X, ShiftShAmt);
+  if (!NewMask)
+    return NewShift;
+
+  Builder.Insert(NewShift);
+  return BinaryOperator::Create(Instruction::And, NewShift, NewMask);
 }
 
 Instruction *InstCombiner::commonShiftTransforms(BinaryOperator &I) {

llvm/test/Transforms/InstCombine/partally-redundant-left-shift-input-masking-variant-a.ll

@@ -18,13 +18,13 @@ define i32 @t0_basic(i32 %x, i32 %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add i32 [[NBITS:%.*]], -1
 ; CHECK-NEXT:    [[T1:%.*]] = shl i32 1, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = add i32 [[T1]], -1
-; CHECK-NEXT:    [[T3:%.*]] = and i32 [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub i32 32, [[NBITS]]
 ; CHECK-NEXT:    call void @use32(i32 [[T0]])
 ; CHECK-NEXT:    call void @use32(i32 [[T1]])
 ; CHECK-NEXT:    call void @use32(i32 [[T2]])
 ; CHECK-NEXT:    call void @use32(i32 [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl i32 [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl i32 [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and i32 [[TMP1]], 2147483647
 ; CHECK-NEXT:    ret i32 [[T5]]
 ;
   %t0 = add i32 %nbits, -1
@@ -49,13 +49,13 @@ define <8 x i32> @t1_vec_splat(<8 x i32> %x, <8 x i32> %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
 ; CHECK-NEXT:    [[T1:%.*]] = shl <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = add <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T3:%.*]] = and <8 x i32> [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, [[NBITS]]
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T0]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T1]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T2]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl <8 x i32> [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
 ; CHECK-NEXT:    ret <8 x i32> [[T5]]
 ;
   %t0 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
@@ -76,13 +76,13 @@ define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>
 ; CHECK-NEXT:    [[T1:%.*]] = shl <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = add <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T3:%.*]] = and <8 x i32> [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, [[NBITS]]
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T0]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T1]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T2]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl <8 x i32> [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 undef, i32 0, i32 1, i32 2147483647, i32 -1, i32 -1, i32 -1, i32 undef>
 ; CHECK-NEXT:    ret <8 x i32> [[T5]]
 ;
   %t0 = add <8 x i32> %nbits, <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>

llvm/test/Transforms/InstCombine/partally-redundant-left-shift-input-masking-variant-b.ll

@@ -18,13 +18,13 @@ define i32 @t0_basic(i32 %x, i32 %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add i32 [[NBITS:%.*]], -1
 ; CHECK-NEXT:    [[T1:%.*]] = shl i32 -1, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = xor i32 [[T1]], -1
-; CHECK-NEXT:    [[T3:%.*]] = and i32 [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub i32 32, [[NBITS]]
 ; CHECK-NEXT:    call void @use32(i32 [[T0]])
 ; CHECK-NEXT:    call void @use32(i32 [[T1]])
 ; CHECK-NEXT:    call void @use32(i32 [[T2]])
 ; CHECK-NEXT:    call void @use32(i32 [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl i32 [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl i32 [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and i32 [[TMP1]], 2147483647
 ; CHECK-NEXT:    ret i32 [[T5]]
 ;
   %t0 = add i32 %nbits, -1
@@ -49,13 +49,13 @@ define <8 x i32> @t1_vec_splat(<8 x i32> %x, <8 x i32> %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
 ; CHECK-NEXT:    [[T1:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = xor <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T3:%.*]] = and <8 x i32> [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, [[NBITS]]
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T0]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T1]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T2]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl <8 x i32> [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
 ; CHECK-NEXT:    ret <8 x i32> [[T5]]
 ;
   %t0 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
@@ -76,13 +76,13 @@ define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
 ; CHECK-NEXT:    [[T0:%.*]] = add <8 x i32> [[NBITS:%.*]], <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>
 ; CHECK-NEXT:    [[T1:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[T0]]
 ; CHECK-NEXT:    [[T2:%.*]] = xor <8 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
-; CHECK-NEXT:    [[T3:%.*]] = and <8 x i32> [[T2]], [[X:%.*]]
 ; CHECK-NEXT:    [[T4:%.*]] = sub <8 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>, [[NBITS]]
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T0]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T1]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T2]])
 ; CHECK-NEXT:    call void @use8xi32(<8 x i32> [[T4]])
-; CHECK-NEXT:    [[T5:%.*]] = shl <8 x i32> [[T3]], [[T4]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T4]]
+; CHECK-NEXT:    [[T5:%.*]] = and <8 x i32> [[TMP1]], <i32 undef, i32 0, i32 1, i32 2147483647, i32 -1, i32 -1, i32 -1, i32 undef>
 ; CHECK-NEXT:    ret <8 x i32> [[T5]]
 ;
   %t0 = add <8 x i32> %nbits, <i32 -33, i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32>