Subzero: ARM32: lowering of vector insert and extract.

src/IceInstARM32.h

 //===- subzero/src/IceInstARM32.h - ARM32 machine instructions --*- C++ -*-===//
 //
 //                        The Subzero Code Generator
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 ///
 /// \file
 /// \brief Declares the InstARM32 and OperandARM32 classes and their subclasses.
 ///
 /// This represents the machine instructions and operands used for ARM32 code
 /// selection.
 ///
 //===----------------------------------------------------------------------===//
 
 #ifndef SUBZERO_SRC_ICEINSTARM32_H
 #define SUBZERO_SRC_ICEINSTARM32_H
 
 #include "IceConditionCodesARM32.h"
 #include "IceDefs.h"
 #include "IceInst.h"
 #include "IceInstARM32.def"
 #include "IceOperand.h"
+#include "IceRegistersARM32.h"
 
 namespace Ice {
 namespace ARM32 {
 
 /// Encoding of an ARM 32-bit instruction.
 using IValueT = uint32_t;
 
 /// An Offset value (+/-) used in an ARM 32-bit instruction.
 using IOffsetT = int32_t;
 
@@ skipping 346 matching lines @@
     And,
     Asr,
     Bic,
     Br,
     Call,
     Clz,
     Cmn,
     Cmp,
     Dmb,
     Eor,
+    Extract,
+    Insert,
     Label,
     Ldr,
     Ldrex,
     Lsl,
     Lsr,
     Mla,
     Mls,
     Mov,
     Movt,
     Movw,
@@ skipping 940 matching lines @@
 private:
   InstARM32Mov(Cfg *Func, Variable *Dest, Operand *Src,
                CondARM32::Cond Predicate);
   void emitMultiDestSingleSource(const Cfg *Func) const;
   void emitSingleDestMultiSource(const Cfg *Func) const;
   void emitSingleDestSingleSource(const Cfg *Func) const;
 
   Variable *DestHi = nullptr;
 };
 
+/// Generates vmov Rd, Dn[x] instructions, and their related floating point
+/// versions.
+class InstARM32Extract final : public InstARM32Pred {
+  InstARM32Extract() = delete;
+  InstARM32Extract(const InstARM32Extract &) = delete;
+  InstARM32Extract &operator=(const InstARM32Extract &) = delete;
+
+public:
+  static InstARM32Extract *create(Cfg *Func, Variable *Dest, Variable *Src0,
+                                  uint32_t Index, CondARM32::Cond Predicate) {
+    return new (Func->allocate<InstARM32Extract>())
+        InstARM32Extract(Func, Dest, Src0, Index, Predicate);
+  }
+  void emit(const Cfg *Func) const override;
+  static bool classof(const Inst *Inst) { return isClassof(Inst, Extract); }
+
+private:
+  InstARM32Extract(Cfg *Func, Variable *Dest, Variable *Src0, uint32_t Index,
+                   CondARM32::Cond Predicate)
+      : InstARM32Pred(Func, InstARM32::Extract, 1, Dest, Predicate),
+        Index(Index) {

[Jim Stichnoth, 2016/02/08 20:13:59]

Could you add an assert to validate that Index is within the proper bounds?

That validation is probably already being done a few layers up, but it's hard to
look at the .cpp file and reason about whether or not you might be accessing
something outside the array of registers.

Same for the Insert instruction.

[Eric Holk, 2016/02/08 21:24:17]

Done.

+    addSource(Src0);
+  }
+
+  const uint32_t Index;
+};
+
+/// Generates vmov Dn[x], Rd instructions, and their related floating point
+/// versions.
+class InstARM32Insert final : public InstARM32Pred {
+  InstARM32Insert() = delete;
+  InstARM32Insert(const InstARM32Insert &) = delete;
+  InstARM32Insert &operator=(const InstARM32Insert &) = delete;
+
+public:
+  static InstARM32Insert *create(Cfg *Func, Variable *Dest, Variable *Src0,
+                                 uint32_t Index, CondARM32::Cond Predicate) {
+    return new (Func->allocate<InstARM32Insert>())
+        InstARM32Insert(Func, Dest, Src0, Index, Predicate);
+  }
+  void emit(const Cfg *Func) const override;
+  static bool classof(const Inst *Inst) { return isClassof(Inst, Insert); }
+
+private:
+  InstARM32Insert(Cfg *Func, Variable *Dest, Variable *Src0, uint32_t Index,
+                  CondARM32::Cond Predicate)
+      : InstARM32Pred(Func, InstARM32::Insert, 1, Dest, Predicate),
+        Index(Index) {
+    addSource(Src0);
+  }
+
+  const uint32_t Index;
+};
+
 class InstARM32Vcmp final : public InstARM32Pred {
   InstARM32Vcmp() = delete;
   InstARM32Vcmp(const InstARM32Vcmp &) = delete;
   InstARM32Vcmp &operator=(const InstARM32Vcmp &) = delete;
 
 public:
   static InstARM32Vcmp *create(Cfg *Func, Variable *Src0, Variable *Src1,
                                CondARM32::Cond Predicate) {
     return new (Func->allocate<InstARM32Vcmp>())
         InstARM32Vcmp(Func, Src0, Src1, Predicate);
@@ skipping 77 matching lines @@
 // violations and link errors.
 
 template <> void InstARM32Ldr::emit(const Cfg *Func) const;
 template <> void InstARM32Movw::emit(const Cfg *Func) const;
 template <> void InstARM32Movt::emit(const Cfg *Func) const;
 
 } // end of namespace ARM32
 } // end of namespace Ice
 
 #endif // SUBZERO_SRC_ICEINSTARM32_H