[X86] Separate DAG node for valign and palignr

They have different semantics (valign is interlane while palingr is intralane)
and palingr is still needed even in the AVX512 context.  According to the
latest spec AVX512BW provides these.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214887 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 3b1daf74d0b15d58907f1ee36fa8c8aff84f6ac4..10867ef31116307501f60c2a40dfd3b94969af93 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -17080,6 +17080,7 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
   case X86ISD::PACKSS:             return "X86ISD::PACKSS";
   case X86ISD::PACKUS:             return "X86ISD::PACKUS";
   case X86ISD::PALIGNR:            return "X86ISD::PALIGNR";
+  case X86ISD::VALIGN:             return "X86ISD::VALIGN";
   case X86ISD::PSHUFD:             return "X86ISD::PSHUFD";
   case X86ISD::PSHUFHW:            return "X86ISD::PSHUFHW";
   case X86ISD::PSHUFLW:            return "X86ISD::PSHUFLW";

diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index f0e4cf8280b1b07d265c9acaa93106a76a67bf53..a384009d9ce7cd351f10911bbd3e28ab6f2c9166 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -320,7 +320,10 @@ namespace llvm {
       // Several flavors of instructions with vector shuffle behaviors.
       PACKSS,
       PACKUS,
+      // Intra-lane alignr
       PALIGNR,
+      // AVX512 inter-lane alignr
+      VALIGN,
       PSHUFD,
       PSHUFHW,
       PSHUFLW,

diff --git a/lib/Target/X86/X86InstrFragmentsSIMD.td b/lib/Target/X86/X86InstrFragmentsSIMD.td
index f5758f89a1898f25fc5250d79de1015b74b2b27f..d94dcee6f62fad846115c118e85543b833fa67fe 100644 (file)
--- a/lib/Target/X86/X86InstrFragmentsSIMD.td
+++ b/lib/Target/X86/X86InstrFragmentsSIMD.td
@@ -203,6 +203,7 @@ def SDTFma : SDTypeProfile<1, 3, [SDTCisSameAs<0,1>,
                            SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;
 
 def X86PAlignr : SDNode<"X86ISD::PALIGNR", SDTShuff3OpI>;
+def X86VAlign  : SDNode<"X86ISD::VALIGN", SDTShuff3OpI>;
 
 def X86PShufd  : SDNode<"X86ISD::PSHUFD", SDTShuff2OpI>;
 def X86PShufhw : SDNode<"X86ISD::PSHUFHW", SDTShuff2OpI>;