integrate the 64-bit shifts into X86InstrShiftRotate.td. Enough for tonight.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115608 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 249 insertions, 302 deletions

diff --git a/lib/Target/X86/X86Instr64bit.td b/lib/Target/X86/X86Instr64bit.td
index 274ef26b22..e89cf130c0 100644
--- a/lib/Target/X86/X86Instr64bit.td
+++ b/lib/Target/X86/X86Instr64bit.td
@@ -444,227 +444,6 @@ def DEC64_32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst), "dec{l}\t$dst",
 } // Defs = [EFLAGS], CodeSize
 
 
-let Defs = [EFLAGS] in {
-// Shift instructions
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in
-def SHL64rCL : RI<0xD3, MRM4r, (outs GR64:$dst), (ins GR64:$src1),
-                  "shl{q}\t{%cl, $dst|$dst, %CL}",
-                  [(set GR64:$dst, (shl GR64:$src1, CL))]>;
-let isConvertibleToThreeAddress = 1 in   // Can transform into LEA.
-def SHL64ri  : RIi8<0xC1, MRM4r, (outs GR64:$dst), 
-                    (ins GR64:$src1, i8imm:$src2),
-                    "shl{q}\t{$src2, $dst|$dst, $src2}",
-                    [(set GR64:$dst, (shl GR64:$src1, (i8 imm:$src2)))]>;
-// NOTE: We don't include patterns for shifts of a register by one, because
-// 'add reg,reg' is cheaper.
-def SHL64r1  : RI<0xD1, MRM4r, (outs GR64:$dst), (ins GR64:$src1),
-                 "shl{q}\t$dst", []>;
-} // Constraints = "$src1 = $dst"
-
-let Uses = [CL] in
-def SHL64mCL : RI<0xD3, MRM4m, (outs), (ins i64mem:$dst),
-                  "shl{q}\t{%cl, $dst|$dst, %CL}",
-                  [(store (shl (loadi64 addr:$dst), CL), addr:$dst)]>;
-def SHL64mi : RIi8<0xC1, MRM4m, (outs), (ins i64mem:$dst, i8imm:$src),
-                  "shl{q}\t{$src, $dst|$dst, $src}",
-                 [(store (shl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def SHL64m1 : RI<0xD1, MRM4m, (outs), (ins i64mem:$dst),
-                  "shl{q}\t$dst",
-                 [(store (shl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
-
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in
-def SHR64rCL : RI<0xD3, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
-                  "shr{q}\t{%cl, $dst|$dst, %CL}",
-                  [(set GR64:$dst, (srl GR64:$src1, CL))]>;
-def SHR64ri : RIi8<0xC1, MRM5r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
-                  "shr{q}\t{$src2, $dst|$dst, $src2}",
-                  [(set GR64:$dst, (srl GR64:$src1, (i8 imm:$src2)))]>;
-def SHR64r1  : RI<0xD1, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
-                 "shr{q}\t$dst",
-                 [(set GR64:$dst, (srl GR64:$src1, (i8 1)))]>;
-} // Constraints = "$src1 = $dst"
-
-let Uses = [CL] in
-def SHR64mCL : RI<0xD3, MRM5m, (outs), (ins i64mem:$dst),
-                  "shr{q}\t{%cl, $dst|$dst, %CL}",
-                  [(store (srl (loadi64 addr:$dst), CL), addr:$dst)]>;
-def SHR64mi : RIi8<0xC1, MRM5m, (outs), (ins i64mem:$dst, i8imm:$src),
-                  "shr{q}\t{$src, $dst|$dst, $src}",
-                 [(store (srl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def SHR64m1 : RI<0xD1, MRM5m, (outs), (ins i64mem:$dst),
-                  "shr{q}\t$dst",
-                 [(store (srl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
-
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in
-def SAR64rCL : RI<0xD3, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
-                 "sar{q}\t{%cl, $dst|$dst, %CL}",
-                 [(set GR64:$dst, (sra GR64:$src1, CL))]>;
-def SAR64ri  : RIi8<0xC1, MRM7r, (outs GR64:$dst),
-                    (ins GR64:$src1, i8imm:$src2),
-                    "sar{q}\t{$src2, $dst|$dst, $src2}",
-                    [(set GR64:$dst, (sra GR64:$src1, (i8 imm:$src2)))]>;
-def SAR64r1  : RI<0xD1, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
-                 "sar{q}\t$dst",
-                 [(set GR64:$dst, (sra GR64:$src1, (i8 1)))]>;
-} // Constraints = "$src = $dst"
-
-let Uses = [CL] in
-def SAR64mCL : RI<0xD3, MRM7m, (outs), (ins i64mem:$dst), 
-                 "sar{q}\t{%cl, $dst|$dst, %CL}",
-                 [(store (sra (loadi64 addr:$dst), CL), addr:$dst)]>;
-def SAR64mi  : RIi8<0xC1, MRM7m, (outs), (ins i64mem:$dst, i8imm:$src),
-                    "sar{q}\t{$src, $dst|$dst, $src}",
-                 [(store (sra (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def SAR64m1 : RI<0xD1, MRM7m, (outs), (ins i64mem:$dst),
-                  "sar{q}\t$dst",
-                 [(store (sra (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
-
-// Rotate instructions
-
-let Constraints = "$src = $dst" in {
-def RCL64r1 : RI<0xD1, MRM2r, (outs GR64:$dst), (ins GR64:$src),
-                 "rcl{q}\t{1, $dst|$dst, 1}", []>;
-def RCL64ri : RIi8<0xC1, MRM2r, (outs GR64:$dst), (ins GR64:$src, i8imm:$cnt),
-                   "rcl{q}\t{$cnt, $dst|$dst, $cnt}", []>;
-
-def RCR64r1 : RI<0xD1, MRM3r, (outs GR64:$dst), (ins GR64:$src),
-                 "rcr{q}\t{1, $dst|$dst, 1}", []>;
-def RCR64ri : RIi8<0xC1, MRM3r, (outs GR64:$dst), (ins GR64:$src, i8imm:$cnt),
-                   "rcr{q}\t{$cnt, $dst|$dst, $cnt}", []>;
-
-let Uses = [CL] in {
-def RCL64rCL : RI<0xD3, MRM2r, (outs GR64:$dst), (ins GR64:$src),
-                  "rcl{q}\t{%cl, $dst|$dst, CL}", []>;
-def RCR64rCL : RI<0xD3, MRM3r, (outs GR64:$dst), (ins GR64:$src),
-                  "rcr{q}\t{%cl, $dst|$dst, CL}", []>;
-}
-} // Constraints = "$src = $dst"
-
-def RCL64m1 : RI<0xD1, MRM2m, (outs), (ins i64mem:$dst),
-                 "rcl{q}\t{1, $dst|$dst, 1}", []>;
-def RCL64mi : RIi8<0xC1, MRM2m, (outs), (ins i64mem:$dst, i8imm:$cnt),
-                   "rcl{q}\t{$cnt, $dst|$dst, $cnt}", []>;
-def RCR64m1 : RI<0xD1, MRM3m, (outs), (ins i64mem:$dst),
-                 "rcr{q}\t{1, $dst|$dst, 1}", []>;
-def RCR64mi : RIi8<0xC1, MRM3m, (outs), (ins i64mem:$dst, i8imm:$cnt),
-                   "rcr{q}\t{$cnt, $dst|$dst, $cnt}", []>;
-
-let Uses = [CL] in {
-def RCL64mCL : RI<0xD3, MRM2m, (outs), (ins i64mem:$dst),
-                  "rcl{q}\t{%cl, $dst|$dst, CL}", []>;
-def RCR64mCL : RI<0xD3, MRM3m, (outs), (ins i64mem:$dst),
-                  "rcr{q}\t{%cl, $dst|$dst, CL}", []>;
-}
-
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in
-def ROL64rCL : RI<0xD3, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
-                  "rol{q}\t{%cl, $dst|$dst, %CL}",
-                  [(set GR64:$dst, (rotl GR64:$src1, CL))]>;
-def ROL64ri  : RIi8<0xC1, MRM0r, (outs GR64:$dst), 
-                    (ins GR64:$src1, i8imm:$src2),
-                    "rol{q}\t{$src2, $dst|$dst, $src2}",
-                    [(set GR64:$dst, (rotl GR64:$src1, (i8 imm:$src2)))]>;
-def ROL64r1  : RI<0xD1, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
-                  "rol{q}\t$dst",
-                  [(set GR64:$dst, (rotl GR64:$src1, (i8 1)))]>;
-} // Constraints = "$src1 = $dst"
-
-let Uses = [CL] in
-def ROL64mCL :  RI<0xD3, MRM0m, (outs), (ins i64mem:$dst),
-                   "rol{q}\t{%cl, $dst|$dst, %CL}",
-                   [(store (rotl (loadi64 addr:$dst), CL), addr:$dst)]>;
-def ROL64mi  : RIi8<0xC1, MRM0m, (outs), (ins i64mem:$dst, i8imm:$src),
-                    "rol{q}\t{$src, $dst|$dst, $src}",
-                [(store (rotl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def ROL64m1  : RI<0xD1, MRM0m, (outs), (ins i64mem:$dst),
-                 "rol{q}\t$dst",
-               [(store (rotl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
-
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in
-def ROR64rCL : RI<0xD3, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
-                  "ror{q}\t{%cl, $dst|$dst, %CL}",
-                  [(set GR64:$dst, (rotr GR64:$src1, CL))]>;
-def ROR64ri  : RIi8<0xC1, MRM1r, (outs GR64:$dst), 
-                    (ins GR64:$src1, i8imm:$src2),
-                    "ror{q}\t{$src2, $dst|$dst, $src2}",
-                    [(set GR64:$dst, (rotr GR64:$src1, (i8 imm:$src2)))]>;
-def ROR64r1  : RI<0xD1, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
-                  "ror{q}\t$dst",
-                  [(set GR64:$dst, (rotr GR64:$src1, (i8 1)))]>;
-} // Constraints = "$src1 = $dst"
-
-let Uses = [CL] in
-def ROR64mCL : RI<0xD3, MRM1m, (outs), (ins i64mem:$dst), 
-                  "ror{q}\t{%cl, $dst|$dst, %CL}",
-                  [(store (rotr (loadi64 addr:$dst), CL), addr:$dst)]>;
-def ROR64mi  : RIi8<0xC1, MRM1m, (outs), (ins i64mem:$dst, i8imm:$src),
-                    "ror{q}\t{$src, $dst|$dst, $src}",
-                [(store (rotr (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def ROR64m1  : RI<0xD1, MRM1m, (outs), (ins i64mem:$dst),
-                 "ror{q}\t$dst",
-               [(store (rotr (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
-
-// Double shift instructions (generalizations of rotate)
-let Constraints = "$src1 = $dst" in {
-let Uses = [CL] in {
-def SHLD64rrCL : RI<0xA5, MRMDestReg, (outs GR64:$dst), 
-                    (ins GR64:$src1, GR64:$src2),
-                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
-                    [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2, CL))]>, 
-                    TB;
-def SHRD64rrCL : RI<0xAD, MRMDestReg, (outs GR64:$dst), 
-                    (ins GR64:$src1, GR64:$src2),
-                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
-                    [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2, CL))]>, 
-                    TB;
-}
-
-let isCommutable = 1 in {  // FIXME: Update X86InstrInfo::commuteInstruction
-def SHLD64rri8 : RIi8<0xA4, MRMDestReg,
-                      (outs GR64:$dst), 
-                      (ins GR64:$src1, GR64:$src2, i8imm:$src3),
-                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                      [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2,
-                                       (i8 imm:$src3)))]>,
-                 TB;
-def SHRD64rri8 : RIi8<0xAC, MRMDestReg,
-                      (outs GR64:$dst), 
-                      (ins GR64:$src1, GR64:$src2, i8imm:$src3),
-                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                      [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2,
-                                       (i8 imm:$src3)))]>,
-                 TB;
-} // isCommutable
-} // Constraints = "$src1 = $dst"
-
-let Uses = [CL] in {
-def SHLD64mrCL : RI<0xA5, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
-                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
-                    [(store (X86shld (loadi64 addr:$dst), GR64:$src2, CL),
-                      addr:$dst)]>, TB;
-def SHRD64mrCL : RI<0xAD, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
-                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
-                    [(store (X86shrd (loadi64 addr:$dst), GR64:$src2, CL),
-                      addr:$dst)]>, TB;
-}
-def SHLD64mri8 : RIi8<0xA4, MRMDestMem,
-                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
-                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                      [(store (X86shld (loadi64 addr:$dst), GR64:$src2,
-                                       (i8 imm:$src3)), addr:$dst)]>,
-                 TB;
-def SHRD64mri8 : RIi8<0xAC, MRMDestMem, 
-                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
-                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                      [(store (X86shrd (loadi64 addr:$dst), GR64:$src2,
-                                       (i8 imm:$src3)), addr:$dst)]>,
-                 TB;
-} // Defs = [EFLAGS]
 
 //===----------------------------------------------------------------------===//
 //  Logical Instructions...
diff --git a/lib/Target/X86/X86InstrShiftRotate.td b/lib/Target/X86/X86InstrShiftRotate.td
index 036f742ac1..e7643bec07 100644
--- a/lib/Target/X86/X86InstrShiftRotate.td
+++ b/lib/Target/X86/X86InstrShiftRotate.td
@@ -26,6 +26,9 @@ def SHL16rCL : I<0xD3, MRM4r, (outs GR16:$dst), (ins GR16:$src1),
 def SHL32rCL : I<0xD3, MRM4r, (outs GR32:$dst), (ins GR32:$src1),
                  "shl{l}\t{%cl, $dst|$dst, CL}",
                  [(set GR32:$dst, (shl GR32:$src1, CL))]>;
+def SHL64rCL : RI<0xD3, MRM4r, (outs GR64:$dst), (ins GR64:$src1),
+                  "shl{q}\t{%cl, $dst|$dst, %CL}",
+                  [(set GR64:$dst, (shl GR64:$src1, CL))]>;
 } // Uses = [CL]
 
 def SHL8ri   : Ii8<0xC0, MRM4r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2),
@@ -39,20 +42,27 @@ def SHL16ri  : Ii8<0xC1, MRM4r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2),
 def SHL32ri  : Ii8<0xC1, MRM4r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2),
                    "shl{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (shl GR32:$src1, (i8 imm:$src2)))]>;
+def SHL64ri  : RIi8<0xC1, MRM4r, (outs GR64:$dst), 
+                    (ins GR64:$src1, i8imm:$src2),
+                    "shl{q}\t{$src2, $dst|$dst, $src2}",
+                    [(set GR64:$dst, (shl GR64:$src1, (i8 imm:$src2)))]>;
 
 // NOTE: We don't include patterns for shifts of a register by one, because
-// 'add reg,reg' is cheaper.
-
+// 'add reg,reg' is cheaper (and we have a Pat pattern for shift-by-one).
 def SHL8r1   : I<0xD0, MRM4r, (outs GR8:$dst), (ins GR8:$src1),
                  "shl{b}\t$dst", []>;
 def SHL16r1  : I<0xD1, MRM4r, (outs GR16:$dst), (ins GR16:$src1),
                  "shl{w}\t$dst", []>, OpSize;
 def SHL32r1  : I<0xD1, MRM4r, (outs GR32:$dst), (ins GR32:$src1),
                  "shl{l}\t$dst", []>;
+def SHL64r1  : RI<0xD1, MRM4r, (outs GR64:$dst), (ins GR64:$src1),
+                 "shl{q}\t$dst", []>;
 } // isConvertibleToThreeAddress = 1
 } // Constraints = "$src = $dst" 
 
 
+// FIXME: Why do we need an explicit "Uses = [CL]" when the instr has a pattern
+// using CL?
 let Uses = [CL] in {
 def SHL8mCL  : I<0xD2, MRM4m, (outs), (ins i8mem :$dst),
                  "shl{b}\t{%cl, $dst|$dst, CL}",
@@ -63,6 +73,9 @@ def SHL16mCL : I<0xD3, MRM4m, (outs), (ins i16mem:$dst),
 def SHL32mCL : I<0xD3, MRM4m, (outs), (ins i32mem:$dst),
                  "shl{l}\t{%cl, $dst|$dst, CL}",
                  [(store (shl (loadi32 addr:$dst), CL), addr:$dst)]>;
+def SHL64mCL : RI<0xD3, MRM4m, (outs), (ins i64mem:$dst),
+                  "shl{q}\t{%cl, $dst|$dst, %CL}",
+                  [(store (shl (loadi64 addr:$dst), CL), addr:$dst)]>;
 }
 def SHL8mi   : Ii8<0xC0, MRM4m, (outs), (ins i8mem :$dst, i8imm:$src),
                    "shl{b}\t{$src, $dst|$dst, $src}",
@@ -74,6 +87,9 @@ def SHL16mi  : Ii8<0xC1, MRM4m, (outs), (ins i16mem:$dst, i8imm:$src),
 def SHL32mi  : Ii8<0xC1, MRM4m, (outs), (ins i32mem:$dst, i8imm:$src),
                    "shl{l}\t{$src, $dst|$dst, $src}",
                [(store (shl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
+def SHL64mi : RIi8<0xC1, MRM4m, (outs), (ins i64mem:$dst, i8imm:$src),
+                  "shl{q}\t{$src, $dst|$dst, $src}",
+                 [(store (shl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
 
 // Shift by 1
 def SHL8m1   : I<0xD0, MRM4m, (outs), (ins i8mem :$dst),
@@ -86,6 +102,9 @@ def SHL16m1  : I<0xD1, MRM4m, (outs), (ins i16mem:$dst),
 def SHL32m1  : I<0xD1, MRM4m, (outs), (ins i32mem:$dst),
                  "shl{l}\t$dst",
                [(store (shl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>;
+def SHL64m1 : RI<0xD1, MRM4m, (outs), (ins i64mem:$dst),
+                  "shl{q}\t$dst",
+                 [(store (shl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
 
 let Constraints = "$src1 = $dst" in {
 let Uses = [CL] in {
@@ -98,6 +117,9 @@ def SHR16rCL : I<0xD3, MRM5r, (outs GR16:$dst), (ins GR16:$src1),
 def SHR32rCL : I<0xD3, MRM5r, (outs GR32:$dst), (ins GR32:$src1),
                  "shr{l}\t{%cl, $dst|$dst, CL}",
                  [(set GR32:$dst, (srl GR32:$src1, CL))]>;
+def SHR64rCL : RI<0xD3, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
+                  "shr{q}\t{%cl, $dst|$dst, %CL}",
+                  [(set GR64:$dst, (srl GR64:$src1, CL))]>;
 }
 
 def SHR8ri   : Ii8<0xC0, MRM5r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$src2),
@@ -109,8 +131,11 @@ def SHR16ri  : Ii8<0xC1, MRM5r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2),
 def SHR32ri  : Ii8<0xC1, MRM5r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2),
                    "shr{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (srl GR32:$src1, (i8 imm:$src2)))]>;
+def SHR64ri : RIi8<0xC1, MRM5r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
+                  "shr{q}\t{$src2, $dst|$dst, $src2}",
+                  [(set GR64:$dst, (srl GR64:$src1, (i8 imm:$src2)))]>;
 
-// Shift by 1
+// Shift right by 1
 def SHR8r1   : I<0xD0, MRM5r, (outs GR8:$dst), (ins GR8:$src1),
                  "shr{b}\t$dst",
                  [(set GR8:$dst, (srl GR8:$src1, (i8 1)))]>;
@@ -120,6 +145,9 @@ def SHR16r1  : I<0xD1, MRM5r, (outs GR16:$dst), (ins GR16:$src1),
 def SHR32r1  : I<0xD1, MRM5r, (outs GR32:$dst), (ins GR32:$src1),
                  "shr{l}\t$dst",
                  [(set GR32:$dst, (srl GR32:$src1, (i8 1)))]>;
+def SHR64r1  : RI<0xD1, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
+                 "shr{q}\t$dst",
+                 [(set GR64:$dst, (srl GR64:$src1, (i8 1)))]>;
 } // Constraints = "$src = $dst"
 
 
@@ -134,6 +162,9 @@ def SHR16mCL : I<0xD3, MRM5m, (outs), (ins i16mem:$dst),
 def SHR32mCL : I<0xD3, MRM5m, (outs), (ins i32mem:$dst),
                  "shr{l}\t{%cl, $dst|$dst, CL}",
                  [(store (srl (loadi32 addr:$dst), CL), addr:$dst)]>;
+def SHR64mCL : RI<0xD3, MRM5m, (outs), (ins i64mem:$dst),
+                  "shr{q}\t{%cl, $dst|$dst, %CL}",
+                  [(store (srl (loadi64 addr:$dst), CL), addr:$dst)]>;
 }
 def SHR8mi   : Ii8<0xC0, MRM5m, (outs), (ins i8mem :$dst, i8imm:$src),
                    "shr{b}\t{$src, $dst|$dst, $src}",
@@ -145,6 +176,9 @@ def SHR16mi  : Ii8<0xC1, MRM5m, (outs), (ins i16mem:$dst, i8imm:$src),
 def SHR32mi  : Ii8<0xC1, MRM5m, (outs), (ins i32mem:$dst, i8imm:$src),
                    "shr{l}\t{$src, $dst|$dst, $src}",
                [(store (srl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
+def SHR64mi : RIi8<0xC1, MRM5m, (outs), (ins i64mem:$dst, i8imm:$src),
+                  "shr{q}\t{$src, $dst|$dst, $src}",
+                 [(store (srl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
 
 // Shift by 1
 def SHR8m1   : I<0xD0, MRM5m, (outs), (ins i8mem :$dst),
@@ -156,6 +190,9 @@ def SHR16m1  : I<0xD1, MRM5m, (outs), (ins i16mem:$dst),
 def SHR32m1  : I<0xD1, MRM5m, (outs), (ins i32mem:$dst),
                  "shr{l}\t$dst",
                [(store (srl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>;
+def SHR64m1 : RI<0xD1, MRM5m, (outs), (ins i64mem:$dst),
+                  "shr{q}\t$dst",
+                 [(store (srl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
 
 let Constraints = "$src1 = $dst" in {
 let Uses = [CL] in {
@@ -168,6 +205,9 @@ def SAR16rCL : I<0xD3, MRM7r, (outs GR16:$dst), (ins GR16:$src1),
 def SAR32rCL : I<0xD3, MRM7r, (outs GR32:$dst), (ins GR32:$src1),
                  "sar{l}\t{%cl, $dst|$dst, CL}",
                  [(set GR32:$dst, (sra GR32:$src1, CL))]>;
+def SAR64rCL : RI<0xD3, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
+                 "sar{q}\t{%cl, $dst|$dst, %CL}",
+                 [(set GR64:$dst, (sra GR64:$src1, CL))]>;
 }
 
 def SAR8ri   : Ii8<0xC0, MRM7r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2),
@@ -180,6 +220,10 @@ def SAR16ri  : Ii8<0xC1, MRM7r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2),
 def SAR32ri  : Ii8<0xC1, MRM7r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2),
                    "sar{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (sra GR32:$src1, (i8 imm:$src2)))]>;
+def SAR64ri  : RIi8<0xC1, MRM7r, (outs GR64:$dst),
+                    (ins GR64:$src1, i8imm:$src2),
+                    "sar{q}\t{$src2, $dst|$dst, $src2}",
+                    [(set GR64:$dst, (sra GR64:$src1, (i8 imm:$src2)))]>;
 
 // Shift by 1
 def SAR8r1   : I<0xD0, MRM7r, (outs GR8 :$dst), (ins GR8 :$src1),
@@ -191,6 +235,9 @@ def SAR16r1  : I<0xD1, MRM7r, (outs GR16:$dst), (ins GR16:$src1),
 def SAR32r1  : I<0xD1, MRM7r, (outs GR32:$dst), (ins GR32:$src1),
                  "sar{l}\t$dst",
                  [(set GR32:$dst, (sra GR32:$src1, (i8 1)))]>;
+def SAR64r1  : RI<0xD1, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
+                 "sar{q}\t$dst",
+                 [(set GR64:$dst, (sra GR64:$src1, (i8 1)))]>;
 } // Constraints = "$src = $dst"
 
 
@@ -204,6 +251,9 @@ def SAR16mCL : I<0xD3, MRM7m, (outs), (ins i16mem:$dst),
 def SAR32mCL : I<0xD3, MRM7m, (outs), (ins i32mem:$dst), 
                  "sar{l}\t{%cl, $dst|$dst, CL}",
                  [(store (sra (loadi32 addr:$dst), CL), addr:$dst)]>;
+def SAR64mCL : RI<0xD3, MRM7m, (outs), (ins i64mem:$dst), 
+                 "sar{q}\t{%cl, $dst|$dst, %CL}",
+                 [(store (sra (loadi64 addr:$dst), CL), addr:$dst)]>;
 }
 def SAR8mi   : Ii8<0xC0, MRM7m, (outs), (ins i8mem :$dst, i8imm:$src),
                    "sar{b}\t{$src, $dst|$dst, $src}",
@@ -215,6 +265,9 @@ def SAR16mi  : Ii8<0xC1, MRM7m, (outs), (ins i16mem:$dst, i8imm:$src),
 def SAR32mi  : Ii8<0xC1, MRM7m, (outs), (ins i32mem:$dst, i8imm:$src),
                    "sar{l}\t{$src, $dst|$dst, $src}",
                [(store (sra (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
+def SAR64mi  : RIi8<0xC1, MRM7m, (outs), (ins i64mem:$dst, i8imm:$src),
+                    "sar{q}\t{$src, $dst|$dst, $src}",
+                 [(store (sra (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
 
 // Shift by 1
 def SAR8m1   : I<0xD0, MRM7m, (outs), (ins i8mem :$dst),
@@ -227,6 +280,9 @@ def SAR16m1  : I<0xD1, MRM7m, (outs), (ins i16mem:$dst),
 def SAR32m1  : I<0xD1, MRM7m, (outs), (ins i32mem:$dst),
                  "sar{l}\t$dst",
                [(store (sra (loadi32 addr:$dst), (i8 1)), addr:$dst)]>;
+def SAR64m1 : RI<0xD1, MRM7m, (outs), (ins i64mem:$dst),
+                  "sar{q}\t$dst",
+                 [(store (sra (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
 
 //===----------------------------------------------------------------------===//
 // Rotate instructions
@@ -235,57 +291,70 @@ def SAR32m1  : I<0xD1, MRM7m, (outs), (ins i32mem:$dst),
 let Constraints = "$src1 = $dst" in {
 def RCL8r1 : I<0xD0, MRM2r, (outs GR8:$dst), (ins GR8:$src1),
                "rcl{b}\t{1, $dst|$dst, 1}", []>;
-let Uses = [CL] in {
-def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src1),
-                "rcl{b}\t{%cl, $dst|$dst, CL}", []>;
-}
 def RCL8ri : Ii8<0xC0, MRM2r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$cnt),
                  "rcl{b}\t{$cnt, $dst|$dst, $cnt}", []>;
+let Uses = [CL] in
+def RCL8rCL : I<0xD2, MRM2r, (outs GR8:$dst), (ins GR8:$src1),
+                "rcl{b}\t{%cl, $dst|$dst, CL}", []>;
   
 def RCL16r1 : I<0xD1, MRM2r, (outs GR16:$dst), (ins GR16:$src1),
                 "rcl{w}\t{1, $dst|$dst, 1}", []>, OpSize;
-let Uses = [CL] in {
-def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src1),
-                 "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
-}
 def RCL16ri : Ii8<0xC1, MRM2r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$cnt),
                   "rcl{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize;
+let Uses = [CL] in
+def RCL16rCL : I<0xD3, MRM2r, (outs GR16:$dst), (ins GR16:$src1),
+                 "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
 
 def RCL32r1 : I<0xD1, MRM2r, (outs GR32:$dst), (ins GR32:$src1),
                 "rcl{l}\t{1, $dst|$dst, 1}", []>;
-let Uses = [CL] in {
-def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src1),
-                 "rcl{l}\t{%cl, $dst|$dst, CL}", []>;
-}
 def RCL32ri : Ii8<0xC1, MRM2r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$cnt),
                   "rcl{l}\t{$cnt, $dst|$dst, $cnt}", []>;
-                  
+let Uses = [CL] in
+def RCL32rCL : I<0xD3, MRM2r, (outs GR32:$dst), (ins GR32:$src1),
+                 "rcl{l}\t{%cl, $dst|$dst, CL}", []>;
+
+
+def RCL64r1 : RI<0xD1, MRM2r, (outs GR64:$dst), (ins GR64:$src1),
+                 "rcl{q}\t{1, $dst|$dst, 1}", []>;
+def RCL64ri : RIi8<0xC1, MRM2r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$cnt),
+                   "rcl{q}\t{$cnt, $dst|$dst, $cnt}", []>;
+let Uses = [CL] in
+def RCL64rCL : RI<0xD3, MRM2r, (outs GR64:$dst), (ins GR64:$src1),
+                  "rcl{q}\t{%cl, $dst|$dst, CL}", []>;
+
+
 def RCR8r1 : I<0xD0, MRM3r, (outs GR8:$dst), (ins GR8:$src1),
                "rcr{b}\t{1, $dst|$dst, 1}", []>;
-let Uses = [CL] in {
-def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src1),
-                "rcr{b}\t{%cl, $dst|$dst, CL}", []>;
-}
 def RCR8ri : Ii8<0xC0, MRM3r, (outs GR8:$dst), (ins GR8:$src1, i8imm:$cnt),
                  "rcr{b}\t{$cnt, $dst|$dst, $cnt}", []>;
+let Uses = [CL] in
+def RCR8rCL : I<0xD2, MRM3r, (outs GR8:$dst), (ins GR8:$src1),
+                "rcr{b}\t{%cl, $dst|$dst, CL}", []>;
   
 def RCR16r1 : I<0xD1, MRM3r, (outs GR16:$dst), (ins GR16:$src1),
                 "rcr{w}\t{1, $dst|$dst, 1}", []>, OpSize;
-let Uses = [CL] in {
-def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src1),
-                 "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
-}
 def RCR16ri : Ii8<0xC1, MRM3r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$cnt),
                   "rcr{w}\t{$cnt, $dst|$dst, $cnt}", []>, OpSize;
+let Uses = [CL] in
+def RCR16rCL : I<0xD3, MRM3r, (outs GR16:$dst), (ins GR16:$src1),
+                 "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
 
 def RCR32r1 : I<0xD1, MRM3r, (outs GR32:$dst), (ins GR32:$src1),
                 "rcr{l}\t{1, $dst|$dst, 1}", []>;
-let Uses = [CL] in {
-def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src1),
-                 "rcr{l}\t{%cl, $dst|$dst, CL}", []>;
-}
 def RCR32ri : Ii8<0xC1, MRM3r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$cnt),
                   "rcr{l}\t{$cnt, $dst|$dst, $cnt}", []>;
+let Uses = [CL] in
+def RCR32rCL : I<0xD3, MRM3r, (outs GR32:$dst), (ins GR32:$src1),
+                 "rcr{l}\t{%cl, $dst|$dst, CL}", []>;
+                 
+def RCR64r1 : RI<0xD1, MRM3r, (outs GR64:$dst), (ins GR64:$src1),
+                 "rcr{q}\t{1, $dst|$dst, 1}", []>;
+def RCR64ri : RIi8<0xC1, MRM3r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$cnt),
+                   "rcr{q}\t{$cnt, $dst|$dst, $cnt}", []>;
+let Uses = [CL] in
+def RCR64rCL : RI<0xD3, MRM3r, (outs GR64:$dst), (ins GR64:$src1),
+                  "rcr{q}\t{%cl, $dst|$dst, CL}", []>;
+
 } // Constraints = "$src = $dst"
 
 def RCL8m1 : I<0xD0, MRM2m, (outs), (ins i8mem:$dst),
@@ -300,6 +369,11 @@ def RCL32m1 : I<0xD1, MRM2m, (outs), (ins i32mem:$dst),
                 "rcl{l}\t{1, $dst|$dst, 1}", []>;
 def RCL32mi : Ii8<0xC1, MRM2m, (outs), (ins i32mem:$dst, i8imm:$cnt),
                   "rcl{l}\t{$cnt, $dst|$dst, $cnt}", []>;
+def RCL64m1 : RI<0xD1, MRM2m, (outs), (ins i64mem:$dst),
+                 "rcl{q}\t{1, $dst|$dst, 1}", []>;
+def RCL64mi : RIi8<0xC1, MRM2m, (outs), (ins i64mem:$dst, i8imm:$cnt),
+                   "rcl{q}\t{$cnt, $dst|$dst, $cnt}", []>;
+
 def RCR8m1 : I<0xD0, MRM3m, (outs), (ins i8mem:$dst),
                "rcr{b}\t{1, $dst|$dst, 1}", []>;
 def RCR8mi : Ii8<0xC0, MRM3m, (outs), (ins i8mem:$dst, i8imm:$cnt),
@@ -312,6 +386,10 @@ def RCR32m1 : I<0xD1, MRM3m, (outs), (ins i32mem:$dst),
                 "rcr{l}\t{1, $dst|$dst, 1}", []>;
 def RCR32mi : Ii8<0xC1, MRM3m, (outs), (ins i32mem:$dst, i8imm:$cnt),
                   "rcr{l}\t{$cnt, $dst|$dst, $cnt}", []>;
+def RCR64m1 : RI<0xD1, MRM3m, (outs), (ins i64mem:$dst),
+                 "rcr{q}\t{1, $dst|$dst, 1}", []>;
+def RCR64mi : RIi8<0xC1, MRM3m, (outs), (ins i64mem:$dst, i8imm:$cnt),
+                   "rcr{q}\t{$cnt, $dst|$dst, $cnt}", []>;
 
 let Uses = [CL] in {
 def RCL8mCL : I<0xD2, MRM2m, (outs), (ins i8mem:$dst),
@@ -320,12 +398,17 @@ def RCL16mCL : I<0xD3, MRM2m, (outs), (ins i16mem:$dst),
                  "rcl{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
 def RCL32mCL : I<0xD3, MRM2m, (outs), (ins i32mem:$dst),
                  "rcl{l}\t{%cl, $dst|$dst, CL}", []>;
+def RCL64mCL : RI<0xD3, MRM2m, (outs), (ins i64mem:$dst),
+                  "rcl{q}\t{%cl, $dst|$dst, CL}", []>;
+
 def RCR8mCL : I<0xD2, MRM3m, (outs), (ins i8mem:$dst),
                 "rcr{b}\t{%cl, $dst|$dst, CL}", []>;
 def RCR16mCL : I<0xD3, MRM3m, (outs), (ins i16mem:$dst),
                  "rcr{w}\t{%cl, $dst|$dst, CL}", []>, OpSize;
 def RCR32mCL : I<0xD3, MRM3m, (outs), (ins i32mem:$dst),
                  "rcr{l}\t{%cl, $dst|$dst, CL}", []>;
+def RCR64mCL : RI<0xD3, MRM3m, (outs), (ins i64mem:$dst),
+                  "rcr{q}\t{%cl, $dst|$dst, CL}", []>;
 }
 
 let Constraints = "$src1 = $dst" in {
@@ -340,6 +423,9 @@ def ROL16rCL : I<0xD3, MRM0r, (outs GR16:$dst), (ins GR16:$src1),
 def ROL32rCL : I<0xD3, MRM0r, (outs GR32:$dst), (ins GR32:$src1),
                  "rol{l}\t{%cl, $dst|$dst, CL}",
                  [(set GR32:$dst, (rotl GR32:$src1, CL))]>;
+def ROL64rCL : RI<0xD3, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
+                  "rol{q}\t{%cl, $dst|$dst, %CL}",
+                  [(set GR64:$dst, (rotl GR64:$src1, CL))]>;
 }
 
 def ROL8ri   : Ii8<0xC0, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2),
@@ -352,6 +438,10 @@ def ROL16ri  : Ii8<0xC1, MRM0r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2),
 def ROL32ri  : Ii8<0xC1, MRM0r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2),
                    "rol{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (rotl GR32:$src1, (i8 imm:$src2)))]>;
+def ROL64ri  : RIi8<0xC1, MRM0r, (outs GR64:$dst), 
+                    (ins GR64:$src1, i8imm:$src2),
+                    "rol{q}\t{$src2, $dst|$dst, $src2}",
+                    [(set GR64:$dst, (rotl GR64:$src1, (i8 imm:$src2)))]>;
 
 // Rotate by 1
 def ROL8r1   : I<0xD0, MRM0r, (outs GR8 :$dst), (ins GR8 :$src1),
@@ -363,6 +453,9 @@ def ROL16r1  : I<0xD1, MRM0r, (outs GR16:$dst), (ins GR16:$src1),
 def ROL32r1  : I<0xD1, MRM0r, (outs GR32:$dst), (ins GR32:$src1),
                  "rol{l}\t$dst",
                  [(set GR32:$dst, (rotl GR32:$src1, (i8 1)))]>;
+def ROL64r1  : RI<0xD1, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
+                  "rol{q}\t$dst",
+                  [(set GR64:$dst, (rotl GR64:$src1, (i8 1)))]>;
 } // Constraints = "$src = $dst"
 
 let Uses = [CL] in {
@@ -375,17 +468,23 @@ def ROL16mCL : I<0xD3, MRM0m, (outs), (ins i16mem:$dst),
 def ROL32mCL : I<0xD3, MRM0m, (outs), (ins i32mem:$dst),
                  "rol{l}\t{%cl, $dst|$dst, CL}",
                  [(store (rotl (loadi32 addr:$dst), CL), addr:$dst)]>;
+def ROL64mCL :  RI<0xD3, MRM0m, (outs), (ins i64mem:$dst),
+                   "rol{q}\t{%cl, $dst|$dst, %CL}",
+                   [(store (rotl (loadi64 addr:$dst), CL), addr:$dst)]>;
 }
-def ROL8mi   : Ii8<0xC0, MRM0m, (outs), (ins i8mem :$dst, i8imm:$src),
-                   "rol{b}\t{$src, $dst|$dst, $src}",
-               [(store (rotl (loadi8 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
-def ROL16mi  : Ii8<0xC1, MRM0m, (outs), (ins i16mem:$dst, i8imm:$src),
-                   "rol{w}\t{$src, $dst|$dst, $src}",
-              [(store (rotl (loadi16 addr:$dst), (i8 imm:$src)), addr:$dst)]>,
+def ROL8mi   : Ii8<0xC0, MRM0m, (outs), (ins i8mem :$dst, i8imm:$src1),
+                   "rol{b}\t{$src1, $dst|$dst, $src1}",
+               [(store (rotl (loadi8 addr:$dst), (i8 imm:$src1)), addr:$dst)]>;
+def ROL16mi  : Ii8<0xC1, MRM0m, (outs), (ins i16mem:$dst, i8imm:$src1),
+                   "rol{w}\t{$src1, $dst|$dst, $src1}",
+              [(store (rotl (loadi16 addr:$dst), (i8 imm:$src1)), addr:$dst)]>,
                    OpSize;
-def ROL32mi  : Ii8<0xC1, MRM0m, (outs), (ins i32mem:$dst, i8imm:$src),
-                   "rol{l}\t{$src, $dst|$dst, $src}",
-              [(store (rotl (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
+def ROL32mi  : Ii8<0xC1, MRM0m, (outs), (ins i32mem:$dst, i8imm:$src1),
+                   "rol{l}\t{$src1, $dst|$dst, $src1}",
+              [(store (rotl (loadi32 addr:$dst), (i8 imm:$src1)), addr:$dst)]>;
+def ROL64mi  : RIi8<0xC1, MRM0m, (outs), (ins i64mem:$dst, i8imm:$src1),
+                    "rol{q}\t{$src1, $dst|$dst, $src1}",
+                [(store (rotl (loadi64 addr:$dst), (i8 imm:$src1)), addr:$dst)]>;
 
 // Rotate by 1
 def ROL8m1   : I<0xD0, MRM0m, (outs), (ins i8mem :$dst),
@@ -398,6 +497,9 @@ def ROL16m1  : I<0xD1, MRM0m, (outs), (ins i16mem:$dst),
 def ROL32m1  : I<0xD1, MRM0m, (outs), (ins i32mem:$dst),
                  "rol{l}\t$dst",
               [(store (rotl (loadi32 addr:$dst), (i8 1)), addr:$dst)]>;
+def ROL64m1  : RI<0xD1, MRM0m, (outs), (ins i64mem:$dst),
+                 "rol{q}\t$dst",
+               [(store (rotl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
 
 let Constraints = "$src1 = $dst" in {
 let Uses = [CL] in {
@@ -410,6 +512,9 @@ def ROR16rCL : I<0xD3, MRM1r, (outs GR16:$dst), (ins GR16:$src1),
 def ROR32rCL : I<0xD3, MRM1r, (outs GR32:$dst), (ins GR32:$src1),
                  "ror{l}\t{%cl, $dst|$dst, CL}",
                  [(set GR32:$dst, (rotr GR32:$src1, CL))]>;
+def ROR64rCL : RI<0xD3, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
+                  "ror{q}\t{%cl, $dst|$dst, %CL}",
+                  [(set GR64:$dst, (rotr GR64:$src1, CL))]>;
 }
 
 def ROR8ri   : Ii8<0xC0, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1, i8imm:$src2),
@@ -422,6 +527,10 @@ def ROR16ri  : Ii8<0xC1, MRM1r, (outs GR16:$dst), (ins GR16:$src1, i8imm:$src2),
 def ROR32ri  : Ii8<0xC1, MRM1r, (outs GR32:$dst), (ins GR32:$src1, i8imm:$src2),
                    "ror{l}\t{$src2, $dst|$dst, $src2}",
                    [(set GR32:$dst, (rotr GR32:$src1, (i8 imm:$src2)))]>;
+def ROR64ri  : RIi8<0xC1, MRM1r, (outs GR64:$dst), 
+                    (ins GR64:$src1, i8imm:$src2),
+                    "ror{q}\t{$src2, $dst|$dst, $src2}",
+                    [(set GR64:$dst, (rotr GR64:$src1, (i8 imm:$src2)))]>;
 
 // Rotate by 1
 def ROR8r1   : I<0xD0, MRM1r, (outs GR8 :$dst), (ins GR8 :$src1),
@@ -433,6 +542,9 @@ def ROR16r1  : I<0xD1, MRM1r, (outs GR16:$dst), (ins GR16:$src1),
 def ROR32r1  : I<0xD1, MRM1r, (outs GR32:$dst), (ins GR32:$src1),
                  "ror{l}\t$dst",
                  [(set GR32:$dst, (rotr GR32:$src1, (i8 1)))]>;
+def ROR64r1  : RI<0xD1, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
+                  "ror{q}\t$dst",
+                  [(set GR64:$dst, (rotr GR64:$src1, (i8 1)))]>;
 } // Constraints = "$src = $dst"
 
 let Uses = [CL] in {
@@ -445,6 +557,9 @@ def ROR16mCL : I<0xD3, MRM1m, (outs), (ins i16mem:$dst),
 def ROR32mCL : I<0xD3, MRM1m, (outs), (ins i32mem:$dst), 
                  "ror{l}\t{%cl, $dst|$dst, CL}",
                  [(store (rotr (loadi32 addr:$dst), CL), addr:$dst)]>;
+def ROR64mCL : RI<0xD3, MRM1m, (outs), (ins i64mem:$dst), 
+                  "ror{q}\t{%cl, $dst|$dst, %CL}",
+                  [(store (rotr (loadi64 addr:$dst), CL), addr:$dst)]>;
 }
 def ROR8mi   : Ii8<0xC0, MRM1m, (outs), (ins i8mem :$dst, i8imm:$src),
                    "ror{b}\t{$src, $dst|$dst, $src}",
@@ -456,6 +571,9 @@ def ROR16mi  : Ii8<0xC1, MRM1m, (outs), (ins i16mem:$dst, i8imm:$src),
 def ROR32mi  : Ii8<0xC1, MRM1m, (outs), (ins i32mem:$dst, i8imm:$src),
                    "ror{l}\t{$src, $dst|$dst, $src}",
               [(store (rotr (loadi32 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
+def ROR64mi  : RIi8<0xC1, MRM1m, (outs), (ins i64mem:$dst, i8imm:$src),
+                    "ror{q}\t{$src, $dst|$dst, $src}",
+                [(store (rotr (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
 
 // Rotate by 1
 def ROR8m1   : I<0xD0, MRM1m, (outs), (ins i8mem :$dst),
@@ -468,6 +586,9 @@ def ROR16m1  : I<0xD1, MRM1m, (outs), (ins i16mem:$dst),
 def ROR32m1  : I<0xD1, MRM1m, (outs), (ins i32mem:$dst),
                  "ror{l}\t$dst",
               [(store (rotr (loadi32 addr:$dst), (i8 1)), addr:$dst)]>;
+def ROR64m1  : RI<0xD1, MRM1m, (outs), (ins i64mem:$dst),
+                 "ror{q}\t$dst",
+               [(store (rotr (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;
 
 
 //===----------------------------------------------------------------------===//
@@ -477,14 +598,6 @@ def ROR32m1  : I<0xD1, MRM1m, (outs), (ins i32mem:$dst),
 let Constraints = "$src1 = $dst" in {
 
 let Uses = [CL] in {
-def SHLD32rrCL : I<0xA5, MRMDestReg, (outs GR32:$dst), 
-                   (ins GR32:$src1, GR32:$src2),
-                   "shld{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
-                   [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2, CL))]>, TB;
-def SHRD32rrCL : I<0xAD, MRMDestReg, (outs GR32:$dst),
-                   (ins GR32:$src1, GR32:$src2),
-                   "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
-                   [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2, CL))]>, TB;
 def SHLD16rrCL : I<0xA5, MRMDestReg, (outs GR16:$dst), 
                    (ins GR16:$src1, GR16:$src2),
                    "shld{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
@@ -495,23 +608,27 @@ def SHRD16rrCL : I<0xAD, MRMDestReg, (outs GR16:$dst),
                    "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
                    [(set GR16:$dst, (X86shrd GR16:$src1, GR16:$src2, CL))]>,
                    TB, OpSize;
+def SHLD32rrCL : I<0xA5, MRMDestReg, (outs GR32:$dst), 
+                   (ins GR32:$src1, GR32:$src2),
+                   "shld{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
+                   [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2, CL))]>, TB;
+def SHRD32rrCL : I<0xAD, MRMDestReg, (outs GR32:$dst),
+                   (ins GR32:$src1, GR32:$src2),
+                   "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
+                   [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2, CL))]>, TB;
+def SHLD64rrCL : RI<0xA5, MRMDestReg, (outs GR64:$dst), 
+                    (ins GR64:$src1, GR64:$src2),
+                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
+                    [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2, CL))]>, 
+                    TB;
+def SHRD64rrCL : RI<0xAD, MRMDestReg, (outs GR64:$dst), 
+                    (ins GR64:$src1, GR64:$src2),
+                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
+                    [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2, CL))]>, 
+                    TB;
 }
 
 let isCommutable = 1 in {  // These instructions commute to each other.
-def SHLD32rri8 : Ii8<0xA4, MRMDestReg,
-                     (outs GR32:$dst), 
-                     (ins GR32:$src1, GR32:$src2, i8imm:$src3),
-                     "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                     [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2,
-                                      (i8 imm:$src3)))]>,
-                 TB;
-def SHRD32rri8 : Ii8<0xAC, MRMDestReg,
-                     (outs GR32:$dst), 
-                     (ins GR32:$src1, GR32:$src2, i8imm:$src3),
-                     "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                     [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2,
-                                      (i8 imm:$src3)))]>,
-                 TB;
 def SHLD16rri8 : Ii8<0xA4, MRMDestReg,
                      (outs GR16:$dst), 
                      (ins GR16:$src1, GR16:$src2, i8imm:$src3),
@@ -526,10 +643,47 @@ def SHRD16rri8 : Ii8<0xAC, MRMDestReg,
                      [(set GR16:$dst, (X86shrd GR16:$src1, GR16:$src2,
                                       (i8 imm:$src3)))]>,
                      TB, OpSize;
+def SHLD32rri8 : Ii8<0xA4, MRMDestReg,
+                     (outs GR32:$dst), 
+                     (ins GR32:$src1, GR32:$src2, i8imm:$src3),
+                     "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                     [(set GR32:$dst, (X86shld GR32:$src1, GR32:$src2,
+                                      (i8 imm:$src3)))]>,
+                 TB;
+def SHRD32rri8 : Ii8<0xAC, MRMDestReg,
+                     (outs GR32:$dst), 
+                     (ins GR32:$src1, GR32:$src2, i8imm:$src3),
+                     "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                     [(set GR32:$dst, (X86shrd GR32:$src1, GR32:$src2,
+                                      (i8 imm:$src3)))]>,
+                 TB;
+def SHLD64rri8 : RIi8<0xA4, MRMDestReg,
+                      (outs GR64:$dst), 
+                      (ins GR64:$src1, GR64:$src2, i8imm:$src3),
+                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                      [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2,
+                                       (i8 imm:$src3)))]>,
+                 TB;
+def SHRD64rri8 : RIi8<0xAC, MRMDestReg,
+                      (outs GR64:$dst), 
+                      (ins GR64:$src1, GR64:$src2, i8imm:$src3),
+                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                      [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2,
+                                       (i8 imm:$src3)))]>,
+                 TB;
 }
 } // Constraints = "$src = $dst"
 
 let Uses = [CL] in {
+def SHLD16mrCL : I<0xA5, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
+                   "shld{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
+                   [(store (X86shld (loadi16 addr:$dst), GR16:$src2, CL),
+                     addr:$dst)]>, TB, OpSize;
+def SHRD16mrCL : I<0xAD, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
+                  "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
+                  [(store (X86shrd (loadi16 addr:$dst), GR16:$src2, CL),
+                    addr:$dst)]>, TB, OpSize;
+
 def SHLD32mrCL : I<0xA5, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
                    "shld{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
                    [(store (X86shld (loadi32 addr:$dst), GR32:$src2, CL),
@@ -538,30 +692,17 @@ def SHRD32mrCL : I<0xAD, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
                   "shrd{l}\t{%cl, $src2, $dst|$dst, $src2, CL}",
                   [(store (X86shrd (loadi32 addr:$dst), GR32:$src2, CL),
                     addr:$dst)]>, TB;
+                    
+def SHLD64mrCL : RI<0xA5, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
+                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
+                    [(store (X86shld (loadi64 addr:$dst), GR64:$src2, CL),
+                      addr:$dst)]>, TB;
+def SHRD64mrCL : RI<0xAD, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
+                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
+                    [(store (X86shrd (loadi64 addr:$dst), GR64:$src2, CL),
+                      addr:$dst)]>, TB;
 }
-def SHLD32mri8 : Ii8<0xA4, MRMDestMem,
-                    (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3),
-                    "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                    [(store (X86shld (loadi32 addr:$dst), GR32:$src2,
-                                      (i8 imm:$src3)), addr:$dst)]>,
-                    TB;
-def SHRD32mri8 : Ii8<0xAC, MRMDestMem, 
-                     (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3),
-                     "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
-                     [(store (X86shrd (loadi32 addr:$dst), GR32:$src2,
-                                       (i8 imm:$src3)), addr:$dst)]>,
-                     TB;
 
-let Uses = [CL] in {
-def SHLD16mrCL : I<0xA5, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
-                   "shld{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
-                   [(store (X86shld (loadi16 addr:$dst), GR16:$src2, CL),
-                     addr:$dst)]>, TB, OpSize;
-def SHRD16mrCL : I<0xAD, MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
-                  "shrd{w}\t{%cl, $src2, $dst|$dst, $src2, CL}",
-                  [(store (X86shrd (loadi16 addr:$dst), GR16:$src2, CL),
-                    addr:$dst)]>, TB, OpSize;
-}
 def SHLD16mri8 : Ii8<0xA4, MRMDestMem,
                     (outs), (ins i16mem:$dst, GR16:$src2, i8imm:$src3),
                     "shld{w}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
@@ -574,5 +715,32 @@ def SHRD16mri8 : Ii8<0xAC, MRMDestMem,
                     [(store (X86shrd (loadi16 addr:$dst), GR16:$src2,
                                       (i8 imm:$src3)), addr:$dst)]>,
                      TB, OpSize;
+
+def SHLD32mri8 : Ii8<0xA4, MRMDestMem,
+                    (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3),
+                    "shld{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                    [(store (X86shld (loadi32 addr:$dst), GR32:$src2,
+                                      (i8 imm:$src3)), addr:$dst)]>,
+                    TB;
+def SHRD32mri8 : Ii8<0xAC, MRMDestMem, 
+                     (outs), (ins i32mem:$dst, GR32:$src2, i8imm:$src3),
+                     "shrd{l}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                     [(store (X86shrd (loadi32 addr:$dst), GR32:$src2,
+                                       (i8 imm:$src3)), addr:$dst)]>,
+                     TB;
+
+def SHLD64mri8 : RIi8<0xA4, MRMDestMem,
+                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
+                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                      [(store (X86shld (loadi64 addr:$dst), GR64:$src2,
+                                       (i8 imm:$src3)), addr:$dst)]>,
+                 TB;
+def SHRD64mri8 : RIi8<0xAC, MRMDestMem, 
+                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
+                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
+                      [(store (X86shrd (loadi64 addr:$dst), GR64:$src2,
+                                       (i8 imm:$src3)), addr:$dst)]>,
+                 TB;
+
 } // Defs = [EFLAGS]