[llvm] [InstCombine] lshr (mul (X, 2^N + 1)), N -> add (X, lshr(X, N)) (PR #90295)

[via llvm-commits]

https://github.com/AtariDreams updated https://github.com/llvm/llvm-project/pull/90295

>From 600cad2cc518dc9ea15d1ff2b3b87a925b52fac9 Mon Sep 17 00:00:00 2001
From: Rose <gfunni234 at gmail.com>
Date: Wed, 1 May 2024 22:50:44 -0400
Subject: [PATCH 1/2] [InstCombine] Pre-commit tests (NFC)

---
 llvm/test/Transforms/InstCombine/ashr-lshr.ll | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/llvm/test/Transforms/InstCombine/ashr-lshr.ll b/llvm/test/Transforms/InstCombine/ashr-lshr.ll
index ac206dc7999dd2..73cc9ca88e8b86 100644
--- a/llvm/test/Transforms/InstCombine/ashr-lshr.ll
+++ b/llvm/test/Transforms/InstCombine/ashr-lshr.ll
@@ -604,3 +604,51 @@ define <2 x i8> @ashr_known_pos_exact_vec(<2 x i8> %x, <2 x i8> %y) {
   %r = ashr exact <2 x i8> %p, %y
   ret <2 x i8> %r
 }
+
+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:    ret i32 [[LSHR]]
+;
+  %mul = mul nsw nuw i32 %0, 3
+  %lshr = lshr i32 %mul, 1
+  ret i32 %lshr
+}
+
+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:    ret i32 [[LSHR]]
+;
+  %mul = mul nsw i32 %x, 3
+  %lshr = lshr exact i32 %mul, 1
+  ret i32 %lshr
+}
+
+define i32 @mul_times_3_div_2_multiuse_lshr(i32 %x) {
+; CHECK-LABEL: @mul_times_3_div_2_multiuse_lshr(
+; CHECK-NEXT:    [[MUL:%.*]] = mul nuw i32 [[X:%.*]], 3
+; CHECK-NEXT:    [[RES:%.*]] = lshr i32 [[MUL]], 1
+; CHECK-NEXT:    call void @use(i32 [[MUL]])
+; CHECK-NEXT:    ret i32 [[RES]]
+;
+  %mul = mul nuw i32 %x, 3
+  %res = lshr i32 %mul, 1
+  call void @use (i32 %mul)
+  ret i32 %res
+}
+
+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:    ret i32 [[LSHR]]
+;
+  %mul = mul nuw i32 %x, 3
+  %lshr = lshr exact i32 %mul, 1
+  ret i32 %lshr
+}
+
+declare void @use(i32)

>From 1a9b7f51a3da82a2a0602b355ff5e0f4b4a2d0d0 Mon Sep 17 00:00:00 2001
From: Rose <gfunni234 at gmail.com>
Date: Mon, 6 May 2024 17:07:29 -0400
Subject: [PATCH 2/2] [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
---
 .../InstCombine/InstCombineShifts.cpp         | 37 +++++++++++++++----
 1 file changed, 29 insertions(+), 8 deletions(-)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineShifts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineShifts.cpp
index 1cb21a1d81af4b..cced403ce0b244 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineShifts.cpp
+++ b/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.
@@ -1681,4 +1702,4 @@ Instruction *InstCombinerImpl::visitAShr(BinaryOperator &I) {
   }
 
   return nullptr;
-}
+}
\ No newline at end of file