X86 CodeGenPrep: sink shufflevectors before shifts

[oota-llvm.git] / lib / Target / X86 / X86ISelLowering.h

diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index 03d645c10607520e3512e4e6e7633d0c73f3041e..ce9594ae3ed657c6d9d79fb501b10a876f6896e5 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -245,12 +245,9 @@ namespace llvm {
       /// the list of operands.
       TC_RETURN,
 
-      // VZEXT_MOVL - Vector move low and zero extend.
+      // VZEXT_MOVL - Vector move to low scalar and zero higher vector elements.
       VZEXT_MOVL,
 
-      // VSEXT_MOVL - Vector move low and sign extend.
-      VSEXT_MOVL,
-
       // VZEXT - Vector integer zero-extend.
       VZEXT,
 
@@ -260,9 +257,6 @@ namespace llvm {
       // VTRUNC - Vector integer truncate.
       VTRUNC,
 
-      // TRUNC - Integer truncate
-      TRUNC,
-
       // VTRUNC - Vector integer truncate with mask.
       VTRUNCM,
 
@@ -298,9 +292,6 @@ namespace llvm {
       ADD, SUB, ADC, SBB, SMUL,
       INC, DEC, OR, XOR, AND,
 
-      BLSI,   // BLSI - Extract lowest set isolated bit
-      BLSMSK, // BLSMSK - Get mask up to lowest set bit
-      BLSR,   // BLSR - Reset lowest set bit
       BZHI,   // BZHI - Zero high bits
       BEXTR,  // BEXTR - Bit field extract
 
@@ -315,8 +306,9 @@ namespace llvm {
       // TESTP - Vector packed fp sign bitwise comparisons.
       TESTP,
 
-      // TESTM - Vector "test" in AVX-512, the result is in a mask vector.
+      // TESTM, TESTNM - Vector "test" in AVX-512, the result is in a mask vector.
       TESTM,
+      TESTNM,
 
       // OR/AND test for masks
       KORTEST,
@@ -342,12 +334,15 @@ namespace llvm {
       VPERMILP,
       VPERMV,
       VPERMV3,
+      VPERMIV3,
       VPERMI,
       VPERM2X128,
       VBROADCAST,
       // masked broadcast
       VBROADCASTM,
+      // Insert/Extract vector element
       VINSERT,
+      VEXTRACT,
 
       // PMULUDQ - Vector multiply packed unsigned doubleword integers
       PMULUDQ,
@@ -581,7 +576,8 @@ namespace llvm {
     /// allowsUnalignedMemoryAccesses - Returns true if the target allows
     /// unaligned memory accesses. of the specified type. Returns whether it
     /// is "fast" by reference in the second argument.
-    virtual bool allowsUnalignedMemoryAccesses(EVT VT, bool *Fast) const;
+    virtual bool allowsUnalignedMemoryAccesses(EVT VT, unsigned AS,
+                                               bool *Fast) const;
 
     /// LowerOperation - Provide custom lowering hooks for some operations.
     ///
@@ -683,6 +679,9 @@ namespace llvm {
     /// the immediate into a register.
     virtual bool isLegalAddImmediate(int64_t Imm) const;
 
+
+    virtual bool isVectorShiftByScalarCheap(Type *Ty) const;
+
     /// isTruncateFree - Return true if it's free to truncate a value of
     /// type Ty1 to type Ty2. e.g. On x86 it's free to truncate a i32 value in
     /// register EAX to i16 by referencing its sub-register AX.
@@ -766,6 +765,11 @@ namespace llvm {
       return isTargetFTOL() && VT == MVT::i64;
     }
 
+    /// \brief Returns true if it is beneficial to convert a load of a constant
+    /// to just the constant itself.
+    virtual bool shouldConvertConstantLoadToIntImm(const APInt &Imm,
+                                                   Type *Ty) const;
+
     /// createFastISel - This method returns a target specific FastISel object,
     /// or null if the target does not support "fast" ISel.
     virtual FastISel *createFastISel(FunctionLoweringInfo &funcInfo,
@@ -870,7 +874,6 @@ namespace llvm {
     SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerExternalSymbol(SDValue Op, SelectionDAG &DAG) const;
-    SDValue LowerShiftParts(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerUINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerUINT_TO_FP_i64(SDValue Op, SelectionDAG &DAG) const;
@@ -879,9 +882,6 @@ namespace llvm {
     SDValue LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerFP_TO_SINT(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerFP_TO_UINT(SDValue Op, SelectionDAG &DAG) const;
-    SDValue LowerFABS(SDValue Op, SelectionDAG &DAG) const;
-    SDValue LowerFNEG(SDValue Op, SelectionDAG &DAG) const;
-    SDValue LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerToBT(SDValue And, ISD::CondCode CC,
                       SDLoc dl, SelectionDAG &DAG) const;
     SDValue LowerSETCC(SDValue Op, SelectionDAG &DAG) const;
@@ -978,6 +978,9 @@ namespace llvm {
     MachineBasicBlock *emitEHSjLjLongJmp(MachineInstr *MI,
                                          MachineBasicBlock *MBB) const;
 
+    MachineBasicBlock *emitFMA3Instr(MachineInstr *MI,
+                                     MachineBasicBlock *MBB) const;
+
     /// Emit nodes that will be selected as "test Op0,Op0", or something
     /// equivalent, for use with the given x86 condition code.
     SDValue EmitTest(SDValue Op0, unsigned X86CC, SelectionDAG &DAG) const;