[llvm] [WebAssembly] Optimize away mask of 63 for shl ( zext (and i32 63))) (PR #152397)

[Jasmine Tang via llvm-commits]

https://github.com/badumbatish created https://github.com/llvm/llvm-project/pull/152397

 Fixes https://github.com/llvm/llvm-project/issues/71844

>From b707a7dffc37f9ee1c79377c2234d73969a9523e Mon Sep 17 00:00:00 2001
From: Jasmine Tang <jjasmine at igalia.com>
Date: Wed, 6 Aug 2025 15:06:18 -0700
Subject: [PATCH 1/2] Precommit test

---
 llvm/test/CodeGen/WebAssembly/masked-shifts.ll | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/llvm/test/CodeGen/WebAssembly/masked-shifts.ll b/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
index 5bcb023e546b5..47b3b5c9fdc0f 100644
--- a/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
+++ b/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
@@ -18,6 +18,23 @@ define i32 @shl_i32(i32 %v, i32 %x) {
   ret i32 %a
 }
 
+define i64 @shl_i64_i32(i64 %v, i32 %x) {
+; CHECK-LABEL: shl_i64_i32:
+; CHECK:         .functype shl_i64_i32 (i64, i32) -> (i64)
+; CHECK-NEXT:  # %bb.0:
+; CHECK-NEXT:    local.get 0
+; CHECK-NEXT:    local.get 1
+; CHECK-NEXT:    i32.const 63
+; CHECK-NEXT:    i32.and
+; CHECK-NEXT:    i64.extend_i32_u
+; CHECK-NEXT:    i64.shl
+; CHECK-NEXT:    # fallthrough-return
+  %m = and i32 %x, 63
+  %z = zext i32 %m to i64
+  %a = shl i64 %v, %z
+  ret i64 %a
+}
+
 define i32 @sra_i32(i32 %v, i32 %x) {
 ; CHECK-LABEL: sra_i32:
 ; CHECK:         .functype sra_i32 (i32, i32) -> (i32)

>From eae6e80ff20235672dcd556d66416e9c8933db06 Mon Sep 17 00:00:00 2001
From: Jasmine Tang <jjasmine at igalia.com>
Date: Wed, 6 Aug 2025 15:09:22 -0700
Subject: [PATCH 2/2] Optimize a mask 63 of shl (zext

---
 .../WebAssembly/WebAssemblyISelLowering.cpp    | 18 ++++++++++++++++++
 llvm/test/CodeGen/WebAssembly/masked-shifts.ll |  2 --
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
index 3f80b2ab2bd6d..325b01eccf67d 100644
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -216,6 +216,7 @@ WebAssemblyTargetLowering::WebAssemblyTargetLowering(
 
     setTargetDAGCombine(ISD::TRUNCATE);
 
+    setTargetDAGCombine(ISD::SHL);
     // Support saturating add/sub for i8x16 and i16x8
     for (auto Op : {ISD::SADDSAT, ISD::UADDSAT, ISD::SSUBSAT, ISD::USUBSAT})
       for (auto T : {MVT::v16i8, MVT::v8i16})
@@ -3562,6 +3563,21 @@ static SDValue performMulCombine(SDNode *N,
       {0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30});
 }
 
+static SDValue performSHLCombine(SDNode *N, SelectionDAG &DAG) {
+  assert(N->getOpcode() == ISD::SHL);
+  if (N->getValueType(0) != MVT::i64)
+    return SDValue();
+  using namespace llvm::SDPatternMatch;
+  SDValue A, B;
+  APInt I;
+  if (sd_match(N,
+               m_Shl(m_Value(A), m_ZExt(m_And(m_Value(B), m_ConstInt(I)))))) {
+    if (I.getSExtValue() == 63)
+      return DAG.getNode(ISD::SHL, SDLoc(N), MVT::i64, {A, B});
+  }
+  return SDValue();
+}
+
 SDValue
 WebAssemblyTargetLowering::PerformDAGCombine(SDNode *N,
                                              DAGCombinerInfo &DCI) const {
@@ -3597,5 +3613,7 @@ WebAssemblyTargetLowering::PerformDAGCombine(SDNode *N,
   }
   case ISD::MUL:
     return performMulCombine(N, DCI);
+  case ISD::SHL:
+    return performSHLCombine(N, DCI.DAG);
   }
 }
diff --git a/llvm/test/CodeGen/WebAssembly/masked-shifts.ll b/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
index 47b3b5c9fdc0f..45c79df5f3f2b 100644
--- a/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
+++ b/llvm/test/CodeGen/WebAssembly/masked-shifts.ll
@@ -24,8 +24,6 @@ define i64 @shl_i64_i32(i64 %v, i32 %x) {
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    i32.const 63
-; CHECK-NEXT:    i32.and
 ; CHECK-NEXT:    i64.extend_i32_u
 ; CHECK-NEXT:    i64.shl
 ; CHECK-NEXT:    # fallthrough-return