Add remaining AVX instructions (most of them dealing with GR64 destinations. This complete the assembler support for the general AVX ISA. But we still miss instructions from FMA3 and CLMUL specific feature flags, which are now the next step

llvm-svn: 109168

2 files changed, 62 insertions, 5 deletions

diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index d8bb435c29c..75c1b2ca478 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -1391,12 +1391,25 @@ let isAsmParserOnly = 1 in {
   defm VMOVMSKPD : sse12_extr_sign_mask<VR128, int_x86_sse2_movmsk_pd,
                                         "movmskpd", SSEPackedDouble>, OpSize,
                                         VEX;
+
   // FIXME: merge with multiclass above when the intrinsics come.
+  def VMOVMSKPSr64r : PI<0x50, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
+             "movmskps\t{$src, $dst|$dst, $src}", [], SSEPackedSingle>, VEX;
+  def VMOVMSKPDr64r : PI<0x50, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
+             "movmskpd\t{$src, $dst|$dst, $src}", [], SSEPackedDouble>, OpSize,
+             VEX;
+
   def VMOVMSKPSYrr : PI<0x50, MRMSrcReg, (outs GR32:$dst), (ins VR256:$src),
              "movmskps\t{$src, $dst|$dst, $src}", [], SSEPackedSingle>, VEX;
   def VMOVMSKPDYrr : PI<0x50, MRMSrcReg, (outs GR32:$dst), (ins VR256:$src),
              "movmskpd\t{$src, $dst|$dst, $src}", [], SSEPackedDouble>, OpSize,
-                                                                        VEX;
+             VEX;
+
+  def VMOVMSKPSYr64r : PI<0x50, MRMSrcReg, (outs GR64:$dst), (ins VR256:$src),
+             "movmskps\t{$src, $dst|$dst, $src}", [], SSEPackedSingle>, VEX;
+  def VMOVMSKPDYr64r : PI<0x50, MRMSrcReg, (outs GR64:$dst), (ins VR256:$src),
+             "movmskpd\t{$src, $dst|$dst, $src}", [], SSEPackedDouble>, OpSize,
+             VEX;
 }
 
 //===----------------------------------------------------------------------===//
@@ -2715,8 +2728,13 @@ def PEXTRWri : PDIi8<0xC5, MRMSrcReg,
                                                 imm:$src2))]>;
 
 // Insert
-let isAsmParserOnly = 1, Predicates = [HasAVX] in
+let isAsmParserOnly = 1, Predicates = [HasAVX] in {
   defm PINSRW : sse2_pinsrw<0>, OpSize, VEX_4V;
+  def  PINSRWrr64i : Ii8<0xC4, MRMSrcReg, (outs VR128:$dst),
+       (ins VR128:$src1, GR64:$src2, i32i8imm:$src3),
+       "vpinsrw\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}",
+       []>, OpSize, VEX_4V;
+}
 
 let Constraints = "$src1 = $dst" in
   defm VPINSRW : sse2_pinsrw, TB, OpSize;
@@ -2729,10 +2747,13 @@ let Constraints = "$src1 = $dst" in
 
 let ExeDomain = SSEPackedInt in {
 
-let isAsmParserOnly = 1 in
-def VPMOVMSKBrr : VPDI<0xD7, MRMSrcReg, (outs GR32:$dst), (ins VR128:$src),
+let isAsmParserOnly = 1 in {
+def VPMOVMSKBrr  : VPDI<0xD7, MRMSrcReg, (outs GR32:$dst), (ins VR128:$src),
            "pmovmskb\t{$src, $dst|$dst, $src}",
            [(set GR32:$dst, (int_x86_sse2_pmovmskb_128 VR128:$src))]>, VEX;
+def VPMOVMSKBr64r : VPDI<0xD7, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
+           "pmovmskb\t{$src, $dst|$dst, $src}", []>, VEX;
+}
 def PMOVMSKBrr : PDI<0xD7, MRMSrcReg, (outs GR32:$dst), (ins VR128:$src),
            "pmovmskb\t{$src, $dst|$dst, $src}",
            [(set GR32:$dst, (int_x86_sse2_pmovmskb_128 VR128:$src))]>;
@@ -4019,8 +4040,12 @@ multiclass SS41I_extract8<bits<8> opc, string OpcodeStr> {
 // (store (i8 (trunc (X86pextrb (v16i8 VR128:$src1), imm:$src2))), addr:$dst)
 }
 
-let isAsmParserOnly = 1, Predicates = [HasAVX] in
+let isAsmParserOnly = 1, Predicates = [HasAVX] in {
   defm VPEXTRB : SS41I_extract8<0x14, "vpextrb">, VEX;
+  def  VPEXTRBrr64 : SS4AIi8<0x14, MRMDestReg, (outs GR64:$dst),
+         (ins VR128:$src1, i32i8imm:$src2),
+         "vpextrb\t{$src2, $src1, $dst|$dst, $src1, $src2}", []>, OpSize, VEX;
+}
 
 defm PEXTRB      : SS41I_extract8<0x14, "pextrb">;
 
diff --git a/llvm/test/MC/AsmParser/X86/x86_64-encoding.s b/llvm/test/MC/AsmParser/X86/x86_64-encoding.s
index f709bcdf41e..d60bde1be4e 100644
--- a/llvm/test/MC/AsmParser/X86/x86_64-encoding.s
+++ b/llvm/test/MC/AsmParser/X86/x86_64-encoding.s
@@ -3400,3 +3400,35 @@ pshufb	CPI1_0(%rip), %xmm1
 // CHECK: encoding: [0xc4,0xe1,0xf9,0x7e,0xe1]
           vmovd  %xmm4, %rcx
 
+// CHECK: vmovmskpd  %xmm4, %rcx
+// CHECK: encoding: [0xc5,0xf9,0x50,0xcc]
+          vmovmskpd  %xmm4, %rcx
+
+// CHECK: vmovmskpd  %ymm4, %rcx
+// CHECK: encoding: [0xc5,0xfd,0x50,0xcc]
+          vmovmskpd  %ymm4, %rcx
+
+// CHECK: vmovmskps  %xmm4, %rcx
+// CHECK: encoding: [0xc5,0xf8,0x50,0xcc]
+          vmovmskps  %xmm4, %rcx
+
+// CHECK: vmovmskps  %ymm4, %rcx
+// CHECK: encoding: [0xc5,0xfc,0x50,0xcc]
+          vmovmskps  %ymm4, %rcx
+
+// CHECK: vpextrb  $7, %xmm4, %rcx
+// CHECK: encoding: [0xc4,0xe3,0x79,0x14,0xe1,0x07]
+          vpextrb  $7, %xmm4, %rcx
+
+// CHECK: vpinsrw  $7, %r8, %xmm15, %xmm8
+// CHECK: encoding: [0xc4,0x41,0x01,0xc4,0xc0,0x07]
+          vpinsrw  $7, %r8, %xmm15, %xmm8
+
+// CHECK: vpinsrw  $7, %rcx, %xmm4, %xmm6
+// CHECK: encoding: [0xc5,0xd9,0xc4,0xf1,0x07]
+          vpinsrw  $7, %rcx, %xmm4, %xmm6
+
+// CHECK: vpmovmskb  %xmm4, %rcx
+// CHECK: encoding: [0xc5,0xf9,0xd7,0xcc]
+          vpmovmskb  %xmm4, %rcx
+