[llvm] [X86] Prefer andl to andb to save one byte encoding (PR #86921)

[Phoebe Wang via llvm-commits]

https://github.com/phoebewang created https://github.com/llvm/llvm-project/pull/86921

None

>From d24a32aa38396eb19051c4909e3e06e2826f3b08 Mon Sep 17 00:00:00 2001
From: Phoebe Wang <phoebe.wang at intel.com>
Date: Thu, 28 Mar 2024 16:28:44 +0800
Subject: [PATCH] [X86] Prefer andl to andb to save one byte encoding

---
 llvm/lib/Target/X86/X86ISelDAGToDAG.cpp  | 21 ++++++++++++++++++---
 llvm/test/CodeGen/X86/extract-lowbits.ll |  4 ++--
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
index 4e4241efd63d6b..dcc279f0d34d79 100644
--- a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -3928,9 +3928,17 @@ bool X86DAGToDAGISel::matchBitExtract(SDNode *Node) {
 
   SDLoc DL(Node);
 
-  // Truncate the shift amount.
-  NBits = CurDAG->getNode(ISD::TRUNCATE, DL, MVT::i8, NBits);
-  insertDAGNode(*CurDAG, SDValue(Node, 0), NBits);
+  if (NBits.getSimpleValueType() != MVT::i8) {
+    // Truncate the shift amount.
+    NBits = CurDAG->getNode(ISD::TRUNCATE, DL, MVT::i8, NBits);
+    insertDAGNode(*CurDAG, SDValue(Node, 0), NBits);
+  }
+
+  // Turn (i32)(x & imm8) into (i32)x & imm32.
+  ConstantSDNode *Imm = nullptr;
+  if (NBits->getOpcode() == ISD::AND)
+    if ((Imm = dyn_cast<ConstantSDNode>(NBits->getOperand(1))))
+      NBits = NBits->getOperand(0);
 
   // Insert 8-bit NBits into lowest 8 bits of 32-bit register.
   // All the other bits are undefined, we do not care about them.
@@ -3945,6 +3953,13 @@ bool X86DAGToDAGISel::matchBitExtract(SDNode *Node) {
                   0);
   insertDAGNode(*CurDAG, SDValue(Node, 0), NBits);
 
+  if (Imm) {
+    NBits =
+        CurDAG->getNode(ISD::AND, DL, MVT::i32, NBits,
+                        CurDAG->getConstant(Imm->getZExtValue(), DL, MVT::i32));
+    insertDAGNode(*CurDAG, SDValue(Node, 0), NBits);
+  }
+
   // We might have matched the amount of high bits to be cleared,
   // but we want the amount of low bits to be kept, so negate it then.
   if (NegateNBits) {
diff --git a/llvm/test/CodeGen/X86/extract-lowbits.ll b/llvm/test/CodeGen/X86/extract-lowbits.ll
index 848b920490ab83..85b242c22c47cb 100644
--- a/llvm/test/CodeGen/X86/extract-lowbits.ll
+++ b/llvm/test/CodeGen/X86/extract-lowbits.ll
@@ -439,14 +439,14 @@ define i64 @bzhi64_a0_masked(i64 %val, i64 %numlowbits) nounwind {
 ;
 ; X64-BMI1-LABEL: bzhi64_a0_masked:
 ; X64-BMI1:       # %bb.0:
-; X64-BMI1-NEXT:    andb $63, %sil
+; X64-BMI1-NEXT:    andl $63, %esi
 ; X64-BMI1-NEXT:    shll $8, %esi
 ; X64-BMI1-NEXT:    bextrq %rsi, %rdi, %rax
 ; X64-BMI1-NEXT:    retq
 ;
 ; X64-BMI2-LABEL: bzhi64_a0_masked:
 ; X64-BMI2:       # %bb.0:
-; X64-BMI2-NEXT:    andb $63, %sil
+; X64-BMI2-NEXT:    andl $63, %esi
 ; X64-BMI2-NEXT:    bzhiq %rsi, %rdi, %rax
 ; X64-BMI2-NEXT:    retq
   %numlowbits.masked = and i64 %numlowbits, 63