[PowerPC] Yet another approach to __tls_get_addr

[oota-llvm.git] / lib / Target / PowerPC / PPCInstrVSX.td

diff --git a/lib/Target/PowerPC/PPCInstrVSX.td b/lib/Target/PowerPC/PPCInstrVSX.td
index 522e0de73869596bfd9331a52fa4dcb3c816e485..c97dfbf439ea4851bec0e6fb57f51e6f564d9f14 100644 (file)
--- a/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/lib/Target/PowerPC/PPCInstrVSX.td
@@ -25,6 +25,23 @@ def vsfrc : RegisterOperand<VSFRC> {
   let ParserMatchClass = PPCRegVSFRCAsmOperand;
 }
 
+// Little-endian-specific nodes.
+def SDT_PPClxvd2x : SDTypeProfile<1, 1, [
+  SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
+]>;
+def SDT_PPCstxvd2x : SDTypeProfile<0, 2, [
+  SDTCisVT<0, v2f64>, SDTCisPtrTy<1>
+]>;
+def SDT_PPCxxswapd : SDTypeProfile<1, 1, [
+  SDTCisSameAs<0, 1>
+]>;
+
+def PPClxvd2x  : SDNode<"PPCISD::LXVD2X", SDT_PPClxvd2x,
+                        [SDNPHasChain, SDNPMayLoad]>;
+def PPCstxvd2x : SDNode<"PPCISD::STXVD2X", SDT_PPCstxvd2x,
+                        [SDNPHasChain, SDNPMayStore]>;
+def PPCxxswapd : SDNode<"PPCISD::XXSWAPD", SDT_PPCxxswapd, [SDNPHasChain]>;
+
 multiclass XX3Form_Rcr<bits<6> opcode, bits<7> xo, dag OOL, dag IOL,
                     string asmbase, string asmstr, InstrItinClass itin,
                     list<dag> pattern> {
@@ -40,9 +57,12 @@ multiclass XX3Form_Rcr<bits<6> opcode, bits<7> xo, dag OOL, dag IOL,
 }
 
 def HasVSX : Predicate<"PPCSubTarget->hasVSX()">;
+def IsLittleEndian : Predicate<"PPCSubTarget->isLittleEndian()">;
+def IsBigEndian : Predicate<"!PPCSubTarget->isLittleEndian()">;
+
 let Predicates = [HasVSX] in {
 let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
-let neverHasSideEffects = 1 in { // VSX instructions don't have side effects.
+let hasSideEffects = 0 in { // VSX instructions don't have side effects.
 let Uses = [RM] in {
 
   // Load indexed instructions
@@ -77,12 +97,12 @@ let Uses = [RM] in {
     def STXVD2X : XX1Form<31, 972,
                          (outs), (ins vsrc:$XT, memrr:$dst),
                          "stxvd2x $XT, $dst", IIC_LdStSTFD,
-                         [(int_ppc_vsx_stxvd2x v2f64:$XT, xoaddr:$dst)]>;
+                         [(store v2f64:$XT, xoaddr:$dst)]>;
 
     def STXVW4X : XX1Form<31, 908,
                          (outs), (ins vsrc:$XT, memrr:$dst),
                          "stxvw4x $XT, $dst", IIC_LdStSTFD,
-                         [(int_ppc_vsx_stxvw4x v4i32:$XT, xoaddr:$dst)]>;
+                         [(store v4i32:$XT, xoaddr:$dst)]>;
   }
 
   // Add/Mul Instructions
@@ -728,7 +748,7 @@ let Uses = [RM] in {
   def XXSPLTW : XX2Form_2<60, 164,
                        (outs vsrc:$XT), (ins vsrc:$XB, u2imm:$UIM),
                        "xxspltw $XT, $XB, $UIM", IIC_VecPerm, []>;
-} // neverHasSideEffects
+} // hasSideEffects
 
 // SELECT_CC_* - Used to implement the SELECT_CC DAG operation.  Expanded after
 // instruction selection into a branch sequence.
@@ -773,6 +793,8 @@ def : InstAlias<"xxswapd $XT, $XB",
                 (XXPERMDI vsrc:$XT, vsrc:$XB, vsrc:$XB, 2)>;
 
 let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
+
+let Predicates = [IsBigEndian] in {
 def : Pat<(v2f64 (scalar_to_vector f64:$A)),
           (v2f64 (SUBREG_TO_REG (i64 1), $A, sub_64))>;
 
@@ -780,6 +802,18 @@ def : Pat<(f64 (vector_extract v2f64:$S, 0)),
           (f64 (EXTRACT_SUBREG $S, sub_64))>;
 def : Pat<(f64 (vector_extract v2f64:$S, 1)),
           (f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
+}
+
+let Predicates = [IsLittleEndian] in {
+def : Pat<(v2f64 (scalar_to_vector f64:$A)),
+          (v2f64 (XXPERMDI (SUBREG_TO_REG (i64 1), $A, sub_64),
+                           (SUBREG_TO_REG (i64 1), $A, sub_64), 0))>;
+
+def : Pat<(f64 (vector_extract v2f64:$S, 0)),
+          (f64 (EXTRACT_SUBREG (XXPERMDI $S, $S, 2), sub_64))>;
+def : Pat<(f64 (vector_extract v2f64:$S, 1)),
+          (f64 (EXTRACT_SUBREG $S, sub_64))>;
+}
 
 // Additional fnmsub patterns: -a*c + b == -(a*c - b)
 def : Pat<(fma (fneg f64:$A), f64:$C, f64:$B),
@@ -854,11 +888,21 @@ def : Pat<(v2f64 (sint_to_fp (sext_inreg v2i64:$C, v2i32))),
 def : Pat<(v2f64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
 def : Pat<(v2i64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
 def : Pat<(v4i32 (load xoaddr:$src)), (LXVW4X xoaddr:$src)>;
+def : Pat<(v2f64 (PPClxvd2x xoaddr:$src)), (LXVD2X xoaddr:$src)>;
 
 // Stores.
-def : Pat<(store v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
+def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, xoaddr:$dst),
+          (STXVD2X $rS, xoaddr:$dst)>;
 def : Pat<(store v2i64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
-def : Pat<(store v4i32:$rS, xoaddr:$dst), (STXVW4X $rS, xoaddr:$dst)>;
+def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, xoaddr:$dst),
+          (STXVW4X $rS, xoaddr:$dst)>;
+def : Pat<(PPCstxvd2x v2f64:$rS, xoaddr:$dst), (STXVD2X $rS, xoaddr:$dst)>;
+
+// Permutes.
+def : Pat<(v2f64 (PPCxxswapd v2f64:$src)), (XXPERMDI $src, $src, 2)>;
+def : Pat<(v2i64 (PPCxxswapd v2i64:$src)), (XXPERMDI $src, $src, 2)>;
+def : Pat<(v4f32 (PPCxxswapd v4f32:$src)), (XXPERMDI $src, $src, 2)>;
+def : Pat<(v4i32 (PPCxxswapd v4i32:$src)), (XXPERMDI $src, $src, 2)>;
 
 // Selects.
 def : Pat<(v2f64 (selectcc i1:$lhs, i1:$rhs, v2f64:$tval, v2f64:$fval, SETLT)),
@@ -887,6 +931,12 @@ def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETGT)),
 def : Pat<(f64 (selectcc i1:$lhs, i1:$rhs, f64:$tval, f64:$fval, SETNE)),
           (SELECT_VSFRC (CRXOR $lhs, $rhs), $tval, $fval)>;
 
+// Divides.
+def : Pat<(int_ppc_vsx_xvdivsp v4f32:$A, v4f32:$B),
+          (XVDIVSP $A, $B)>;
+def : Pat<(int_ppc_vsx_xvdivdp v2f64:$A, v2f64:$B),
+          (XVDIVDP $A, $B)>;
+
 } // AddedComplexity
 } // HasVSX