[InstCombine] lshr (mul (X, 2^N + 1)), N -> add (X, lshr(X, N))

A generalization of the proposed x * 3/2 -> x + (x >> 1) transformation but applies to all multiplications that are one more than a power of 2.

Proof: https://alive2.llvm.org/ce/z/WaZYvn

Author: AZero13

llvm/lib/Transforms/InstCombine/InstCombineShifts.cpp

@@ -1411,13 +1411,24 @@ Instruction *InstCombinerImpl::visitLShr(BinaryOperator &I) {
 
     const APInt *MulC;
     if (match(Op0, m_NUWMul(m_Value(X), m_APInt(MulC)))) {
-      // Look for a "splat" mul pattern - it replicates bits across each half of
-      // a value, so a right shift is just a mask of the low bits:
-      // lshr i[2N] (mul nuw X, (2^N)+1), N --> and iN X, (2^N)-1
-      // TODO: Generalize to allow more than just half-width shifts?
-      if (BitWidth > 2 && ShAmtC * 2 == BitWidth && (*MulC - 1).isPowerOf2() &&
-          MulC->logBase2() == ShAmtC)
-        return BinaryOperator::CreateAnd(X, ConstantInt::get(Ty, *MulC - 2));
+      if (BitWidth > 2 && (*MulC - 1).isPowerOf2() &&
+          MulC->logBase2() == ShAmtC) {
+        // Look for a "splat" mul pattern - it replicates bits across each half
+        // of a value, so a right shift is just a mask of the low bits:
+        // lshr i[2N] (mul nuw X, (2^N)+1), N --> and iN X, (2^N)-1
+        if (ShAmtC * 2 == BitWidth)
+          return BinaryOperator::CreateAnd(X, ConstantInt::get(Ty, *MulC - 2));
+
+        // lshr (mul nuw (X, 2^N + 1)), N -> add nuw (X, lshr(X, N))
+        if (Op0->hasOneUse()) {
+          auto *NewAdd = BinaryOperator::CreateNUWAdd(
+              X, Builder.CreateLShr(X, ConstantInt::get(Ty, ShAmtC), "",
+                                    I.isExact()));
+          NewAdd->setHasNoSignedWrap(
+              cast<OverflowingBinaryOperator>(Op0)->hasNoSignedWrap());
+          return NewAdd;
+        }
+      }
 
       // The one-use check is not strictly necessary, but codegen may not be
       // able to invert the transform and perf may suffer with an extra mul
@@ -1437,6 +1448,16 @@ Instruction *InstCombinerImpl::visitLShr(BinaryOperator &I) {
       }
     }
 
+    // lshr (mul nsw (X, 2^N + 1)), N -> add nsw (X, lshr(X, N))
+    if (match(Op0, m_OneUse(m_NSWMul(m_Value(X), m_APInt(MulC))))) {
+      if (BitWidth > 2 && (*MulC - 1).isPowerOf2() &&
+          MulC->logBase2() == ShAmtC) {
+        return BinaryOperator::CreateNSWAdd(
+            X, Builder.CreateLShr(X, ConstantInt::get(Ty, ShAmtC), "",
+                                  I.isExact()));
+      }
+    }
+
     // Try to narrow bswap.
     // In the case where the shift amount equals the bitwidth difference, the
     // shift is eliminated.

llvm/test/Transforms/InstCombine/ashr-lshr.ll

@@ -605,56 +605,10 @@ define <2 x i8> @ashr_known_pos_exact_vec(<2 x i8> %x, <2 x i8> %y) {
   ret <2 x i8> %r
 }
 
-define i32 @ashr_mul_times_3_div_2(i32 %0) {
-; CHECK-LABEL: @ashr_mul_times_3_div_2(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nuw nsw i32 [[TMP0:%.*]], 3
-; CHECK-NEXT:    [[ASHR:%.*]] = ashr i32 [[MUL]], 1
-; CHECK-NEXT:    ret i32 [[ASHR]]
-;
-  %mul = mul nsw nuw i32 %0, 3
-  %ashr = ashr i32 %mul, 1
-  ret i32 %ashr
-}
-
-define i32 @ashr_mul_times_3_div_2_exact(i32 %x) {
-; CHECK-LABEL: @ashr_mul_times_3_div_2_exact(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[X:%.*]], 3
-; CHECK-NEXT:    [[ASHR:%.*]] = ashr exact i32 [[MUL]], 1
-; CHECK-NEXT:    ret i32 [[ASHR]]
-;
-  %mul = mul nsw i32 %x, 3
-  %ashr = ashr exact i32 %mul, 1
-  ret i32 %ashr
-}
-
-define i32 @mul_times_3_div_2_multiuse(i32 %x) {
-; CHECK-LABEL: @mul_times_3_div_2_multiuse(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nuw i32 [[X:%.*]], 3
-; CHECK-NEXT:    [[RES:%.*]] = ashr i32 [[MUL]], 1
-; CHECK-NEXT:    call void @use(i32 [[MUL]])
-; CHECK-NEXT:    ret i32 [[RES]]
-;
-  %mul = mul nuw i32 %x, 3
-  %res = ashr i32 %mul, 1
-  call void @use (i32 %mul)
-  ret i32 %res
-}
-
-define i32 @ashr_mul_times_3_div_2_exact_2(i32 %x) {
-; CHECK-LABEL: @ashr_mul_times_3_div_2_exact_2(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nuw i32 [[X:%.*]], 3
-; CHECK-NEXT:    [[ASHR:%.*]] = ashr exact i32 [[MUL]], 1
-; CHECK-NEXT:    ret i32 [[ASHR]]
-;
-  %mul = mul nuw i32 %x, 3
-  %ashr = ashr exact i32 %mul, 1
-  ret i32 %ashr
-}
-
 define i32 @lshr_mul_times_3_div_2(i32 %0) {
 ; CHECK-LABEL: @lshr_mul_times_3_div_2(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nuw nsw i32 [[TMP0:%.*]], 3
-; CHECK-NEXT:    [[LSHR:%.*]] = lshr i32 [[MUL]], 1
+; CHECK-NEXT:    [[TMP2:%.*]] = lshr i32 [[TMP0:%.*]], 1
+; CHECK-NEXT:    [[LSHR:%.*]] = add nuw nsw i32 [[TMP2]], [[TMP0]]
 ; CHECK-NEXT:    ret i32 [[LSHR]]
 ;
   %mul = mul nsw nuw i32 %0, 3
@@ -664,8 +618,8 @@ define i32 @lshr_mul_times_3_div_2(i32 %0) {
 
 define i32 @lshr_mul_times_3_div_2_exact(i32 %x) {
 ; CHECK-LABEL: @lshr_mul_times_3_div_2_exact(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[X:%.*]], 3
-; CHECK-NEXT:    [[LSHR:%.*]] = lshr exact i32 [[MUL]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr exact i32 [[X:%.*]], 1
+; CHECK-NEXT:    [[LSHR:%.*]] = add nsw i32 [[TMP1]], [[X]]
 ; CHECK-NEXT:    ret i32 [[LSHR]]
 ;
   %mul = mul nsw i32 %x, 3
@@ -688,8 +642,8 @@ define i32 @mul_times_3_div_2_multiuse_lshr(i32 %x) {
 
 define i32 @lshr_mul_times_3_div_2_exact_2(i32 %x) {
 ; CHECK-LABEL: @lshr_mul_times_3_div_2_exact_2(
-; CHECK-NEXT:    [[MUL:%.*]] = mul nuw i32 [[X:%.*]], 3
-; CHECK-NEXT:    [[LSHR:%.*]] = lshr exact i32 [[MUL]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr exact i32 [[X:%.*]], 1
+; CHECK-NEXT:    [[LSHR:%.*]] = add nuw i32 [[TMP1]], [[X]]
 ; CHECK-NEXT:    ret i32 [[LSHR]]
 ;
   %mul = mul nuw i32 %x, 3

llvm/test/Transforms/InstCombine/lshr.ll

@@ -390,8 +390,8 @@ define i32 @mul_splat_fold_wrong_lshr_const(i32 %x) {
 
 define i32 @mul_splat_fold_no_nuw(i32 %x) {
 ; CHECK-LABEL: @mul_splat_fold_no_nuw(
-; CHECK-NEXT:    [[M:%.*]] = mul nsw i32 [[X:%.*]], 65537
-; CHECK-NEXT:    [[T:%.*]] = lshr i32 [[M]], 16
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i32 [[X:%.*]], 16
+; CHECK-NEXT:    [[T:%.*]] = add nsw i32 [[TMP1]], [[X]]
 ; CHECK-NEXT:    ret i32 [[T]]
 ;
   %m = mul nsw i32 %x, 65537