[X86] Truncate i64 sub to i32 when upper 33 bits are zeros

Author: omkar-mohanty

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -58191,8 +58191,28 @@ static SDValue combineSub(SDNode *N, SelectionDAG &DAG,
   EVT VT = N->getValueType(0);
   SDValue Op0 = N->getOperand(0);
   SDValue Op1 = N->getOperand(1);
+  unsigned int Opcode = N->getOpcode();
   SDLoc DL(N);
 
+  // Use a 32-bit sub+zext if upper 33 bits known zero.
+  if (VT == MVT::i64 && Subtarget.is64Bit()) {
+    APInt HiMask = APInt::getHighBitsSet(64, 33);
+    if (DAG.MaskedValueIsZero(Op0, HiMask) &&
+        DAG.MaskedValueIsZero(Op1, HiMask)) {
+      SDValue LHS = DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, Op0);
+      SDValue RHS = DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, Op1);
+      bool NUW = Op0->getFlags().hasNoUnsignedWrap();
+      NUW = NUW & DAG.willNotOverflowAdd(false, LHS, RHS);
+      SDNodeFlags Flags;
+      Flags.setNoUnsignedWrap(NUW);
+      // Always true since in the worst case 0 - 2147483647 = -2147483647, still
+      // fits in i32
+      Flags.setNoSignedWrap(true);
+      SDValue Sub = DAG.getNode(Opcode, DL, MVT::i32, LHS, RHS, Flags);
+      return DAG.getNode(ISD::ZERO_EXTEND, DL, MVT::i64, Sub);
+    }
+  }
+
   auto IsNonOpaqueConstant = [&](SDValue Op) {
     return DAG.isConstantIntBuildVectorOrConstantInt(Op,
                                                      /*AllowOpaques*/ false);

llvm/test/CodeGen/X86/reduce-i64-sub.ll

@@ -0,0 +1,78 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=X64
+
+; Truncate to 32 bit subtraction since first 48 bits are zeros
+define i64 @test1(i16 %a, i16 %b) nounwind {
+; X86-LABEL: test1:
+; X86:       # %bb.0:
+; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    xorl %edx, %edx
+; X86-NEXT:    subl %ecx, %eax
+; X86-NEXT:    sbbl %edx, %edx
+; X86-NEXT:    retl
+;
+; X64-LABEL: test1:
+; X64:       # %bb.0:
+; X64-NEXT:    movzwl %si, %ecx
+; X64-NEXT:    movzwl %di, %eax
+; X64-NEXT:    subl %ecx, %eax
+; X64-NEXT:    retq
+  %zext_a = zext i16 %a to i64
+  %zext_b = zext i16 %b to i64
+  %sub = sub i64 %zext_a, %zext_b
+  ret i64 %sub
+}
+
+; Do not truncate to 32 bit subtraction if 32nd bit is set
+define i64 @test2(i16 %a, i16 %b) nounwind {
+; X86-LABEL: test2:
+; X86:       # %bb.0:
+; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    subl %ecx, %eax
+; X86-NEXT:    movl $1, %edx
+; X86-NEXT:    sbbl $0, %edx
+; X86-NEXT:    retl
+;
+; X64-LABEL: test2:
+; X64:       # %bb.0:
+; X64-NEXT:    movzwl %di, %ecx
+; X64-NEXT:    movzwl %si, %edx
+; X64-NEXT:    movabsq $4294967296, %rax # imm = 0x100000000
+; X64-NEXT:    orq %rcx, %rax
+; X64-NEXT:    subq %rdx, %rax
+; X64-NEXT:    retq
+  %zext_a = zext i16 %a to i64
+  %zext_b = zext i16 %b to i64
+  %or_a = or i64 %zext_a, 4294967296
+  %sub = sub i64 %or_a, %zext_b
+  ret i64 %sub
+}
+
+; Do not truncate to 32 bit subtraction in case of sign extension
+define i64 @test3(i16 %a, i16 %b) nounwind {
+; X86-LABEL: test3:
+; X86:       # %bb.0:
+; X86-NEXT:    movswl {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    movl %eax, %edx
+; X86-NEXT:    sarl $31, %edx
+; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    subl %ecx, %eax
+; X86-NEXT:    sbbl $0, %edx
+; X86-NEXT:    retl
+;
+; X64-LABEL: test3:
+; X64:       # %bb.0:
+; X64-NEXT:    # kill: def $edi killed $edi def $rdi
+; X64-NEXT:    movswq %di, %rax
+; X64-NEXT:    movzwl %si, %ecx
+; X64-NEXT:    subq %rcx, %rax
+; X64-NEXT:    retq
+  %sext_a = sext i16 %a to i64
+  %zext_b = zext i16 %b to i64
+  %sub = sub i64 %sext_a, %zext_b
+  ret i64 %sub
+}
+