[X86][XOP] Support for VPPERM byte shuffle instruction

This patch begins adding support for lowering to the XOP VPPERM instruction - adding the X86ISD::VPPERM opcode.

Differential Revision: http://reviews.llvm.org/D18189

llvm-svn: 264260

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 774a253..9ed1e07 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -21514,6 +21514,7 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
   case X86ISD::VSRAI:              return "X86ISD::VSRAI";
   case X86ISD::VROTLI:             return "X86ISD::VROTLI";
   case X86ISD::VROTRI:             return "X86ISD::VROTRI";
+  case X86ISD::VPPERM:             return "X86ISD::VPPERM";
   case X86ISD::CMPP:               return "X86ISD::CMPP";
   case X86ISD::PCMPEQ:             return "X86ISD::PCMPEQ";
   case X86ISD::PCMPGT:             return "X86ISD::PCMPGT";

diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index 94e2f54..cf42eb8 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -441,6 +441,8 @@ namespace llvm {
       VPSHA, VPSHL,
       // XOP signed/unsigned integer comparisons
       VPCOM, VPCOMU,
+      // XOP packed permute bytes
+      VPPERM,
 
       // Vector multiply packed unsigned doubleword integers
       PMULUDQ,

diff --git a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
index 260e846..a5adfd3 100644 (file)
--- a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
+++ b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
@@ -251,6 +251,10 @@ def X86vpcomu  : SDNode<"X86ISD::VPCOMU",
                                              SDTCisSameAs<0,2>,
                                              SDTCisVT<3, i8>]>>;
 
+def X86vpperm : SDNode<"X86ISD::VPPERM",
+                        SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
+                                             SDTCisSameAs<0,2>]>>;
+
 def SDTX86CmpPTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
                                           SDTCisVec<1>,
                                           SDTCisSameAs<2, 1>]>;

diff --git a/llvm/lib/Target/X86/X86InstrXOP.td b/llvm/lib/Target/X86/X86InstrXOP.td
index 6308291..cc3ec22 100644 (file)
--- a/llvm/lib/Target/X86/X86InstrXOP.td
+++ b/llvm/lib/Target/X86/X86InstrXOP.td
@@ -222,8 +222,47 @@ let ExeDomain = SSEPackedInt in { // SSE integer instructions
   defm VPCOMUQ : xopvpcom<0xEF, "uq", X86vpcomu, v2i64>;
 }
 
+multiclass xop4op<bits<8> opc, string OpcodeStr, SDNode OpNode,
+                  ValueType vt128> {
+  def rr : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
+           (ins VR128:$src1, VR128:$src2, VR128:$src3),
+           !strconcat(OpcodeStr,
+           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
+           [(set VR128:$dst,
+             (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
+                            (vt128 VR128:$src3))))]>,
+           XOP_4V, VEX_I8IMM;
+  def rm : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
+           (ins VR128:$src1, VR128:$src2, i128mem:$src3),
+           !strconcat(OpcodeStr,
+           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
+           [(set VR128:$dst,
+             (vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
+                            (vt128 (bitconvert (loadv2i64 addr:$src3))))))]>,
+           XOP_4V, VEX_I8IMM, VEX_W, MemOp4;
+  def mr : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
+           (ins VR128:$src1, i128mem:$src2, VR128:$src3),
+           !strconcat(OpcodeStr,
+           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
+           [(set VR128:$dst,
+             (v16i8 (OpNode (vt128 VR128:$src1), (vt128 (bitconvert (loadv2i64 addr:$src2))),
+                            (vt128 VR128:$src3))))]>,
+           XOP_4V, VEX_I8IMM;
+  // For disassembler
+  let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
+  def rr_REV : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
+           (ins VR128:$src1, VR128:$src2, VR128:$src3),
+           !strconcat(OpcodeStr,
+           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
+           []>, XOP_4V, VEX_I8IMM, VEX_W, MemOp4;
+}
+
+let ExeDomain = SSEPackedInt in {
+  defm VPPERM : xop4op<0xA3, "vpperm", X86vpperm, v16i8>;
+}
+
 // Instruction where either second or third source can be memory
-multiclass xop4op<bits<8> opc, string OpcodeStr, Intrinsic Int> {
+multiclass xop4op_int<bits<8> opc, string OpcodeStr, Intrinsic Int> {
   def rr : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
            (ins VR128:$src1, VR128:$src2, VR128:$src3),
            !strconcat(OpcodeStr,
@@ -256,8 +295,7 @@ multiclass xop4op<bits<8> opc, string OpcodeStr, Intrinsic Int> {
 }
 
 let ExeDomain = SSEPackedInt in {
-  defm VPPERM : xop4op<0xA3, "vpperm", int_x86_xop_vpperm>;
-  defm VPCMOV : xop4op<0xA2, "vpcmov", int_x86_xop_vpcmov>;
+  defm VPCMOV : xop4op_int<0xA2, "vpcmov", int_x86_xop_vpcmov>;
 }
 
 multiclass xop4op256<bits<8> opc, string OpcodeStr, Intrinsic Int> {

diff --git a/llvm/lib/Target/X86/X86IntrinsicsInfo.h b/llvm/lib/Target/X86/X86IntrinsicsInfo.h
index 65aea3d..1c8ec14 100644 (file)
--- a/llvm/lib/Target/X86/X86IntrinsicsInfo.h
+++ b/llvm/lib/Target/X86/X86IntrinsicsInfo.h
@@ -2278,6 +2278,7 @@ static const IntrinsicData  IntrinsicsWithoutChain[] = {
   X86_INTRINSIC_DATA(xop_vpcomuq,       INTR_TYPE_3OP, X86ISD::VPCOMU, 0),
   X86_INTRINSIC_DATA(xop_vpcomuw,       INTR_TYPE_3OP, X86ISD::VPCOMU, 0),
   X86_INTRINSIC_DATA(xop_vpcomw,        INTR_TYPE_3OP, X86ISD::VPCOM, 0),
+  X86_INTRINSIC_DATA(xop_vpperm,        INTR_TYPE_3OP, X86ISD::VPPERM, 0),
   X86_INTRINSIC_DATA(xop_vprotb,        INTR_TYPE_2OP, X86ISD::VPROT, 0),
   X86_INTRINSIC_DATA(xop_vprotbi,       INTR_TYPE_2OP, X86ISD::VPROTI, 0),
   X86_INTRINSIC_DATA(xop_vprotd,        INTR_TYPE_2OP, X86ISD::VPROT, 0),

diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll
index 6d7439b..00294cf 100644 (file)
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-xop.ll
@@ -21,11 +21,20 @@ define <16 x i8> @combine_vpperm_identity(<16 x i8> %a0, <16 x i8> %a1) {
   ret <16 x i8> %res1
 }
 
-define <16 x i8> @combine_vpperm_as_unpckhwd(<16 x i8> %a0, <16 x i8> %a1) {
-; CHECK-LABEL: combine_vpperm_as_unpckhwd:
+define <16 x i8> @combine_vpperm_as_unary_unpckhwd(<16 x i8> %a0, <16 x i8> %a1) {
+; CHECK-LABEL: combine_vpperm_as_unary_unpckhwd:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm0, %xmm0, %xmm0
 ; CHECK-NEXT:    retq
   %res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a0, <16 x i8> <i8 8, i8 24, i8 9, i8 25, i8 10, i8 26, i8 11, i8 27, i8 12, i8 28, i8 13, i8 29, i8 14, i8 30, i8 15, i8 31>)
   ret <16 x i8> %res0
 }
+
+define <16 x i8> @combine_vpperm_as_unpckhwd(<16 x i8> %a0, <16 x i8> %a1) {
+; CHECK-LABEL: combine_vpperm_as_unpckhwd:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpperm {{.*}}(%rip), %xmm1, %xmm0, %xmm0
+; CHECK-NEXT:    retq
+  %res0 = call <16 x i8> @llvm.x86.xop.vpperm(<16 x i8> %a0, <16 x i8> %a1, <16 x i8> <i8 8, i8 24, i8 9, i8 25, i8 10, i8 26, i8 11, i8 27, i8 12, i8 28, i8 13, i8 29, i8 14, i8 30, i8 15, i8 31>)
+  ret <16 x i8> %res0
+}