[AArch64][SVE] Add patterns for logical immediate operations.

Summary:
Add pattern matching for the following SVE logical vector and immediate instructions:
- and/bic, orr/orn, eor/eon.

Reviewers: sdesmalen, huntergr, rengolin, efriedma, c-rhodes, mgudim, kmclaughlin

Subscribers: tschuett, kristof.beyls, hiraditya, rkruppe, psnobl, llvm-commits, amehsan

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71483

diff --git a/llvm/include/llvm/IR/IntrinsicsAArch64.td b/llvm/include/llvm/IR/IntrinsicsAArch64.td
index 32ed762..a3827aa 100644 (file)
--- a/llvm/include/llvm/IR/IntrinsicsAArch64.td
+++ b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -1104,6 +1104,12 @@ class AdvSIMD_ScatterStore_VectorBase_Intrinsic
                ],
                [IntrWriteMem, IntrArgMemOnly, ImmArg<3>]>;
 
+class AdvSIMD_1VectorArg_Imm64_Intrinsic
+    : Intrinsic<[llvm_anyvector_ty],
+                [LLVMMatchType<0>,
+                 llvm_i64_ty],
+                [IntrNoMem, ImmArg<1>]>;
+
 //
 // Loads
 //
@@ -1271,6 +1277,10 @@ def int_aarch64_sve_orns        : AdvSIMD_Pred2VectorArg_Intrinsic;
 def int_aarch64_sve_nors        : AdvSIMD_Pred2VectorArg_Intrinsic;
 def int_aarch64_sve_nands       : AdvSIMD_Pred2VectorArg_Intrinsic;
 
+def int_aarch64_sve_orr_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
+def int_aarch64_sve_eor_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
+def int_aarch64_sve_and_imm  : AdvSIMD_1VectorArg_Imm64_Intrinsic;
+
 //
 // Conversion
 //

diff --git a/llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp b/llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp
index 4640dcf..e138c2d 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp
@@ -164,6 +164,11 @@ public:
     return SelectSVEAddSubImm(N, VT, Imm, Shift);
   }
 
+  template<MVT::SimpleValueType VT>
+  bool SelectSVELogicalImm(SDValue N, SDValue &Imm) {
+    return SelectSVELogicalImm(N, VT, Imm);
+  }
+
   /// Form sequences of consecutive 64/128-bit registers for use in NEON
   /// instructions making use of a vector-list (e.g. ldN, tbl). Vecs must have
   /// between 1 and 4 elements. If it contains a single element that is returned
@@ -241,6 +246,8 @@ private:
   bool SelectCMP_SWAP(SDNode *N);
 
   bool SelectSVEAddSubImm(SDValue N, MVT VT, SDValue &Imm, SDValue &Shift);
+
+  bool SelectSVELogicalImm(SDValue N, MVT VT, SDValue &Imm);
 };
 } // end anonymous namespace
 
@@ -2851,6 +2858,35 @@ bool AArch64DAGToDAGISel::SelectSVEAddSubImm(SDValue N, MVT VT, SDValue &Imm, SD
   return false;
 }
 
+bool AArch64DAGToDAGISel::SelectSVELogicalImm(SDValue N, MVT VT, SDValue &Imm) {
+  if (auto CNode = dyn_cast<ConstantSDNode>(N)) {
+    uint64_t ImmVal = CNode->getZExtValue();
+    SDLoc DL(N);
+
+    // Shift mask depending on type size.
+    switch (VT.SimpleTy) {
+      case MVT::i8:
+        ImmVal &= 0xFF;
+        ImmVal |= (ImmVal << 8);
+      case MVT::i16:
+        ImmVal &= 0xFFFF;
+        ImmVal |= (ImmVal << 16);
+      case MVT::i32:
+        ImmVal &= 0xFFFFFFFF;
+        ImmVal |= (ImmVal << 32);
+        break;
+      default:
+        break;
+    }
+
+    uint64_t encoding;
+    if (AArch64_AM::processLogicalImmediate(ImmVal, 64, encoding)) {
+      Imm = CurDAG->getTargetConstant(encoding, DL, MVT::i64);
+      return true;
+    }
+  }
+  return false;
+}
 
 bool AArch64DAGToDAGISel::trySelectStackSlotTagP(SDNode *N) {
   // tagp(FrameIndex, IRGstack, tag_offset):

diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
index dbfa5e2..2a282d3 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -117,9 +117,9 @@ let Predicates = [HasSVE] in {
   defm EORV_VPZ  : sve_int_reduce_2<0b001, "eorv", AArch64eorv_pred>;
   defm ANDV_VPZ  : sve_int_reduce_2<0b010, "andv", AArch64andv_pred>;
 
-  defm ORR_ZI : sve_int_log_imm<0b00, "orr", "orn">;
-  defm EOR_ZI : sve_int_log_imm<0b01, "eor", "eon">;
-  defm AND_ZI : sve_int_log_imm<0b10, "and", "bic">;
+  defm ORR_ZI : sve_int_log_imm<0b00, "orr", "orn", int_aarch64_sve_orr_imm>;
+  defm EOR_ZI : sve_int_log_imm<0b01, "eor", "eon", int_aarch64_sve_eor_imm>;
+  defm AND_ZI : sve_int_log_imm<0b10, "and", "bic", int_aarch64_sve_and_imm>;
 
   defm SMAX_ZI   : sve_int_arith_imm1<0b00, "smax", simm8>;
   defm SMIN_ZI   : sve_int_arith_imm1<0b10, "smin", simm8>;

diff --git a/llvm/lib/Target/AArch64/SVEInstrFormats.td b/llvm/lib/Target/AArch64/SVEInstrFormats.td
index 9de24bb..244397c 100644 (file)
--- a/llvm/lib/Target/AArch64/SVEInstrFormats.td
+++ b/llvm/lib/Target/AArch64/SVEInstrFormats.td
@@ -207,6 +207,12 @@ def SVEAddSubImm16Pat : ComplexPattern<i32, 2, "SelectSVEAddSubImm<MVT::i16>", [
 def SVEAddSubImm32Pat : ComplexPattern<i32, 2, "SelectSVEAddSubImm<MVT::i32>", []>;
 def SVEAddSubImm64Pat : ComplexPattern<i32, 2, "SelectSVEAddSubImm<MVT::i64>", []>;
 
+def SVELogicalImm8Pat  : ComplexPattern<i64, 1, "SelectSVELogicalImm<MVT::i8>", []>;
+def SVELogicalImm16Pat : ComplexPattern<i64, 1, "SelectSVELogicalImm<MVT::i16>", []>;
+def SVELogicalImm32Pat : ComplexPattern<i64, 1, "SelectSVELogicalImm<MVT::i32>", []>;
+def SVELogicalImm64Pat : ComplexPattern<i64, 1, "SelectSVELogicalImm<MVT::i64>", []>;
+
+
 class SVEExactFPImm<string Suffix, string ValA, string ValB> : AsmOperandClass {
   let Name = "SVEExactFPImmOperand" # Suffix;
   let DiagnosticType = "Invalid" # Name;
@@ -298,6 +304,11 @@ class SVE_1_Op_Imm_OptLsl_Pat<ValueType vt, SDPatternOperator op, ZPRRegOp zprty
   : Pat<(vt (op (vt zprty:$Op1), (i32 (cpx i32:$imm, i32:$shift)))),
         (inst $Op1, i32:$imm, i32:$shift)>;
 
+class SVE_1_Op_Imm_Log_Pat<ValueType vt, SDPatternOperator op, ZPRRegOp zprty,
+                           ComplexPattern cpx, Instruction inst>
+  : Pat<(vt (op (vt zprty:$Op1), (i64 (cpx i64:$imm)))),
+        (inst $Op1, i64:$imm)>;
+
 class SVE_2_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
                    ValueType vt2, Instruction inst>
 : Pat<(vtd (op vt1:$Op1, vt2:$Op2)),
@@ -1129,9 +1140,14 @@ class sve_int_log_imm<bits<2> opc, string asm>
   let ElementSize = ElementSizeNone;
 }
 
-multiclass sve_int_log_imm<bits<2> opc, string asm, string alias> {
+multiclass sve_int_log_imm<bits<2> opc, string asm, string alias, SDPatternOperator op> {
   def NAME : sve_int_log_imm<opc, asm>;
 
+  def : SVE_1_Op_Imm_Log_Pat<nxv16i8, op, ZPR8,  SVELogicalImm8Pat,  !cast<Instruction>(NAME)>;
+  def : SVE_1_Op_Imm_Log_Pat<nxv8i16, op, ZPR16, SVELogicalImm16Pat, !cast<Instruction>(NAME)>;
+  def : SVE_1_Op_Imm_Log_Pat<nxv4i32, op, ZPR32, SVELogicalImm32Pat, !cast<Instruction>(NAME)>;
+  def : SVE_1_Op_Imm_Log_Pat<nxv2i64, op, ZPR64, SVELogicalImm64Pat, !cast<Instruction>(NAME)>;
+
   def : InstAlias<asm # "\t$Zdn, $Zdn, $imm",
                   (!cast<Instruction>(NAME) ZPR8:$Zdn, sve_logical_imm8:$imm), 4>;
   def : InstAlias<asm # "\t$Zdn, $Zdn, $imm",

diff --git a/llvm/test/CodeGen/AArch64/sve-int-log-imm.ll b/llvm/test/CodeGen/AArch64/sve-int-log-imm.ll
new file mode 100644 (file)
index 0000000..0b95300
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sve-int-log-imm.ll
@@ -0,0 +1,122 @@
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @orr_i8(<vscale x 16 x i8> %a) {
+; CHECK-LABEL: orr_i8:
+; CHECK: orr z0.b, z0.b, #0xf
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.orr.imm.nxv16i8(<vscale x 16 x i8> %a, 
+                                                                   i64 15)
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 8 x i16> @orr_i16(<vscale x 8 x i16> %a) {
+; CHECK-LABEL: orr_i16:
+; CHECK: orr z0.h, z0.h, #0xfc07
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.orr.imm.nxv8i16(<vscale x 8 x i16> %a, 
+                                                                   i64 64519)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 4 x i32> @orr_i32(<vscale x 4 x i32> %a) {
+; CHECK-LABEL: orr_i32:
+; CHECK: orr z0.s, z0.s, #0xffff00
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.orr.imm.nxv4i32(<vscale x 4 x i32> %a, 
+                                                                   i64 16776960)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @orr_i64(<vscale x 2 x i64> %a) {
+; CHECK-LABEL: orr_i64:
+; CHECK: orr z0.d, z0.d, #0xfffc000000000000
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.orr.imm.nxv2i64(<vscale x 2 x i64> %a, 
+                                                                   i64 18445618173802708992)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 16 x i8> @eor_i8(<vscale x 16 x i8> %a) {
+; CHECK-LABEL: eor_i8:
+; CHECK: eor z0.b, z0.b, #0xf
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.eor.imm.nxv16i8(<vscale x 16 x i8> %a, 
+                                                                   i64 15)
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 8 x i16> @eor_i16(<vscale x 8 x i16> %a) {
+; CHECK-LABEL: eor_i16:
+; CHECK: eor z0.h, z0.h, #0xfc07
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.eor.imm.nxv8i16(<vscale x 8 x i16> %a, 
+                                                                   i64 64519)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 4 x i32> @eor_i32(<vscale x 4 x i32> %a) {
+; CHECK-LABEL: eor_i32:
+; CHECK: eor z0.s, z0.s, #0xffff00
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.eor.imm.nxv4i32(<vscale x 4 x i32> %a, 
+                                                                   i64 16776960)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @eor_i64(<vscale x 2 x i64> %a) {
+; CHECK-LABEL: eor_i64:
+; CHECK: eor z0.d, z0.d, #0xfffc000000000000
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.eor.imm.nxv2i64(<vscale x 2 x i64> %a, 
+                                                                   i64 18445618173802708992)
+  ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 16 x i8> @and_i8(<vscale x 16 x i8> %a) {
+; CHECK-LABEL: and_i8:
+; CHECK: and z0.b, z0.b, #0xf
+; CHECK-NEXT: ret
+  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.and.imm.nxv16i8(<vscale x 16 x i8> %a, 
+                                                                   i64 15)
+  ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 8 x i16> @and_i16(<vscale x 8 x i16> %a) {
+; CHECK-LABEL: and_i16:
+; CHECK: and z0.h, z0.h, #0xfc07
+; CHECK-NEXT: ret
+  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.and.imm.nxv8i16(<vscale x 8 x i16> %a, 
+                                                                   i64 64519)
+  ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 4 x i32> @and_i32(<vscale x 4 x i32> %a) {
+; CHECK-LABEL: and_i32:
+; CHECK: and z0.s, z0.s, #0xffff00
+; CHECK-NEXT: ret
+  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.and.imm.nxv4i32(<vscale x 4 x i32> %a, 
+                                                                   i64 16776960)
+  ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 2 x i64> @and_i64(<vscale x 2 x i64> %a) {
+; CHECK-LABEL: and_i64:
+; CHECK: and z0.d, z0.d, #0xfffc000000000000
+; CHECK-NEXT: ret
+  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.and.imm.nxv2i64(<vscale x 2 x i64> %a,
+                                                                   i64 18445618173802708992)
+  ret <vscale x 2 x i64> %res
+}
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.orr.imm.nxv16i8(<vscale x 16 x i8>, i64)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.orr.imm.nxv8i16(<vscale x 8 x i16>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.orr.imm.nxv4i32(<vscale x 4 x i32>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.orr.imm.nxv2i64(<vscale x 2 x i64>, i64)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.eor.imm.nxv16i8(<vscale x 16 x i8>, i64)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.eor.imm.nxv8i16(<vscale x 8 x i16>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.eor.imm.nxv4i32(<vscale x 4 x i32>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.eor.imm.nxv2i64(<vscale x 2 x i64>, i64)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.and.imm.nxv16i8(<vscale x 16 x i8>, i64)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.and.imm.nxv8i16(<vscale x 8 x i16>, i64)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.and.imm.nxv4i32(<vscale x 4 x i32>, i64)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.and.imm.nxv2i64(<vscale x 2 x i64>, i64)