Index: llvm/trunk/lib/Target/X86/X86InstrInfo.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86InstrInfo.td
+++ llvm/trunk/lib/Target/X86/X86InstrInfo.td
@@ -1994,7 +1994,7 @@
 defm XCHG    : ATOMIC_SWAP<0x86, 0x87, "xchg", "atomic_swap">, NotMemoryFoldable;
 
 // Swap between registers.
-let SchedRW = [WriteALU] in {
+let SchedRW = [WriteXCHG] in {
 let Constraints = "$src1 = $dst1, $src2 = $dst2", hasSideEffects = 0 in {
 def XCHG8rr : I<0x86, MRMSrcReg, (outs GR8:$dst1, GR8:$dst2),
                 (ins GR8:$src1, GR8:$src2),
@@ -2027,7 +2027,7 @@
 } // SchedRW
 
 let hasSideEffects = 0, Constraints = "$src1 = $dst1, $src2 = $dst2",
-    Defs = [EFLAGS], SchedRW = [WriteALU] in {
+    Defs = [EFLAGS], SchedRW = [WriteXCHG] in {
 def XADD8rr : I<0xC0, MRMDestReg, (outs GR8:$dst1, GR8:$dst2),
                 (ins GR8:$src1, GR8:$src2),
                 "xadd{b}\t{$src2, $src1|$src1, $src2}", []>, TB;
Index: llvm/trunk/lib/Target/X86/X86SchedBroadwell.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86SchedBroadwell.td
+++ llvm/trunk/lib/Target/X86/X86SchedBroadwell.td
@@ -121,6 +121,7 @@
 
 defm : X86WriteRes<WriteBSWAP32,   [BWPort15], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64,   [BWPort06, BWPort15], 2, [1, 1], 2>;
+defm : X86WriteRes<WriteXCHG,      [BWPort0156], 2, [3], 3>;
 
 defm : BWWriteResPair<WriteCRC32, [BWPort1],   3>;
 def : WriteRes<WriteIMulH, []> { let Latency = 3; } // Integer multiplication, high part.
@@ -759,15 +760,6 @@
 def: InstRW<[BWWriteResGroup28], (instregex "VPBROADCASTBrr",
                                             "VPBROADCASTWrr")>;
 
-def BWWriteResGroup30 : SchedWriteRes<[BWPort0156]> {
-  let Latency = 2;
-  let NumMicroOps = 3;
-  let ResourceCycles = [3];
-}
-def: InstRW<[BWWriteResGroup30], (instrs XADD8rr, XADD16rr, XADD32rr, XADD64rr,
-                                         XCHG8rr, XCHG16rr, XCHG32rr, XCHG64rr,
-                                         XCHG16ar, XCHG32ar, XCHG64ar)>;
-
 def BWWriteResGroup33 : SchedWriteRes<[BWPort5,BWPort0156]> {
   let Latency = 3;
   let NumMicroOps = 3;
Index: llvm/trunk/lib/Target/X86/X86SchedHaswell.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86SchedHaswell.td
+++ llvm/trunk/lib/Target/X86/X86SchedHaswell.td
@@ -126,6 +126,7 @@
 
 defm : X86WriteRes<WriteBSWAP32,   [HWPort15], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64,   [HWPort06, HWPort15], 2, [1,1], 2>;
+defm : X86WriteRes<WriteXCHG, [HWPort0156], 2, [3], 3>;
 
 def  : WriteRes<WriteIMulH, []> { let Latency = 3; }
 
@@ -1287,15 +1288,6 @@
                                               "VPMOVSXWDYrm",
                                               "VPMOVZXWDYrm")>;
 
-def HWWriteResGroup54 : SchedWriteRes<[HWPort0156]> {
-  let Latency = 2;
-  let NumMicroOps = 3;
-  let ResourceCycles = [3];
-}
-def: InstRW<[HWWriteResGroup54], (instrs XADD8rr, XADD16rr, XADD32rr, XADD64rr,
-                                         XCHG8rr, XCHG16rr, XCHG32rr, XCHG64rr,
-                                         XCHG16ar, XCHG32ar, XCHG64ar)>;
-
 def HWWriteResGroup57 : SchedWriteRes<[HWPort5,HWPort0156]> {
   let Latency = 3;
   let NumMicroOps = 3;
Index: llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td
+++ llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td
@@ -111,6 +111,7 @@
 defm : SBWriteResPair<WriteADC,    [SBPort05,SBPort015], 2, [1,1], 2>;
 defm : SBWriteResPair<WriteIMul,   [SBPort1],   3>;
 defm : SBWriteResPair<WriteIMul64, [SBPort1],   3>;
+defm : X86WriteRes<WriteXCHG,      [SBPort015], 2, [3], 3>;
 
 defm : X86WriteRes<WriteBSWAP32,   [SBPort1], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64,   [SBPort1,SBPort05], 2, [1,1], 2>;
@@ -661,15 +662,6 @@
                                               "SHL(8|16|32|64)rCL",
                                               "SHR(8|16|32|64)rCL")>;
 
-def SBWriteResGroup25 : SchedWriteRes<[SBPort015]> {
-  let Latency = 2;
-  let NumMicroOps = 3;
-  let ResourceCycles = [3];
-}
-def: InstRW<[SBWriteResGroup25], (instrs XADD8rr, XADD16rr, XADD32rr, XADD64rr,
-                                         XCHG8rr, XCHG16rr, XCHG32rr, XCHG64rr,
-                                         XCHG16ar, XCHG32ar, XCHG64ar)>;
-
 def SBWriteResGroup25_1 : SchedWriteRes<[SBPort23,SBPort015]> {
   let Latency = 7;
   let NumMicroOps = 3;
Index: llvm/trunk/lib/Target/X86/X86SchedSkylakeClient.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86SchedSkylakeClient.td
+++ llvm/trunk/lib/Target/X86/X86SchedSkylakeClient.td
@@ -112,6 +112,7 @@
 
 defm : X86WriteRes<WriteBSWAP32,    [SKLPort15], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64,    [SKLPort06, SKLPort15], 2, [1,1], 2>;
+defm : X86WriteRes<WriteXCHG, [SKLPort0156], 2, [3], 3>;
 
 defm : SKLWriteResPair<WriteDiv8,   [SKLPort0, SKLDivider], 25, [1,10], 1, 4>;
 defm : SKLWriteResPair<WriteDiv16,  [SKLPort0, SKLDivider], 25, [1,10], 1, 4>;
@@ -776,15 +777,6 @@
                                              "SHL(8|16|32|64)rCL",
                                              "SHR(8|16|32|64)rCL")>;
 
-def SKLWriteResGroup34 : SchedWriteRes<[SKLPort0156]> {
-  let Latency = 2;
-  let NumMicroOps = 3;
-  let ResourceCycles = [3];
-}
-def: InstRW<[SKLWriteResGroup34], (instrs XADD8rr, XADD16rr, XADD32rr, XADD64rr,
-                                          XCHG8rr, XCHG16rr, XCHG32rr, XCHG64rr,
-                                          XCHG16ar, XCHG32ar, XCHG64ar)>;
-
 def SKLWriteResGroup35 : SchedWriteRes<[SKLPort0,SKLPort5]> {
   let Latency = 3;
   let NumMicroOps = 3;
Index: llvm/trunk/lib/Target/X86/X86SchedSkylakeServer.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86SchedSkylakeServer.td
+++ llvm/trunk/lib/Target/X86/X86SchedSkylakeServer.td
@@ -112,6 +112,7 @@
 
 defm : X86WriteRes<WriteBSWAP32, [SKXPort15], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64, [SKXPort06, SKXPort15], 2, [1,1], 2>;
+defm : X86WriteRes<WriteXCHG,       [SKXPort0156], 2, [3], 3>;
 
 defm : SKXWriteResPair<WriteDiv8,   [SKXPort0, SKXDivider], 25, [1,10], 1, 4>;
 defm : SKXWriteResPair<WriteDiv16,  [SKXPort0, SKXDivider], 25, [1,10], 1, 4>;
@@ -844,15 +845,6 @@
                                              "SHL(8|16|32|64)rCL",
                                              "SHR(8|16|32|64)rCL")>;
 
-def SKXWriteResGroup36 : SchedWriteRes<[SKXPort0156]> {
-  let Latency = 2;
-  let NumMicroOps = 3;
-  let ResourceCycles = [3];
-}
-def: InstRW<[SKXWriteResGroup36], (instrs XADD8rr, XADD16rr, XADD32rr, XADD64rr,
-                                          XCHG8rr, XCHG16rr, XCHG32rr, XCHG64rr,
-                                          XCHG16ar, XCHG32ar, XCHG64ar)>;
-
 def SKXWriteResGroup37 : SchedWriteRes<[SKXPort0,SKXPort5]> {
   let Latency = 3;
   let NumMicroOps = 3;
Index: llvm/trunk/lib/Target/X86/X86Schedule.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86Schedule.td
+++ llvm/trunk/lib/Target/X86/X86Schedule.td
@@ -120,6 +120,7 @@
 
 def  WriteBSWAP32 : SchedWrite; // Byte Order (Endianness) 32-bit Swap.
 def  WriteBSWAP64 : SchedWrite; // Byte Order (Endianness) 64-bit Swap.
+def  WriteXCHG   : SchedWrite;        // Compare+Exchange - TODO RMW support.
 
 // Integer division.
 defm WriteDiv8   : X86SchedWritePair;
Index: llvm/trunk/lib/Target/X86/X86ScheduleAtom.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86ScheduleAtom.td
+++ llvm/trunk/lib/Target/X86/X86ScheduleAtom.td
@@ -81,6 +81,7 @@
 defm : AtomWriteResPair<WriteIMul,   [AtomPort01], [AtomPort01],  7,  7,  [7],  [7]>;
 defm : AtomWriteResPair<WriteIMul64, [AtomPort01], [AtomPort01], 12, 12, [12], [12]>;
 
+defm : X86WriteRes<WriteXCHG,        [AtomPort01], 2, [2], 1>;
 defm : X86WriteRes<WriteBSWAP32,     [AtomPort0], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64,     [AtomPort0], 1, [1], 1>;
 
@@ -565,8 +566,6 @@
                                       SCASB, SCASL, SCASQ, SCASW)>;
 def : InstRW<[AtomWrite01_2], (instregex "BT(C|R|S)(16|32|64)mi8",
                                          "PUSH(CS|DS|ES|FS|GS|SS)(16|32|64)",
-                                         "XADD(8|16|32|64)rr",
-                                         "XCHG(8|16|32|64)(ar|rr)",
                                          "(ST|ISTT)_F(P)?(16|32|64)?(m|rr)",
                                          "MMX_P(ADD|SUB)Qirr",
                                          "MOV(S|Z)X16rr8",
Index: llvm/trunk/lib/Target/X86/X86ScheduleBtVer2.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86ScheduleBtVer2.td
+++ llvm/trunk/lib/Target/X86/X86ScheduleBtVer2.td
@@ -170,6 +170,7 @@
 
 defm : X86WriteRes<WriteBSWAP32, [JALU01], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64, [JALU01], 1, [1], 1>;
+defm : X86WriteRes<WriteXCHG,        [JALU01], 1, [1], 1>;
 
 defm : JWriteResIntPair<WriteDiv8,   [JALU1, JDiv], 12, [1, 12], 1>;
 defm : JWriteResIntPair<WriteDiv16,  [JALU1, JDiv], 17, [1, 17], 2>;
Index: llvm/trunk/lib/Target/X86/X86ScheduleSLM.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86ScheduleSLM.td
+++ llvm/trunk/lib/Target/X86/X86ScheduleSLM.td
@@ -100,6 +100,7 @@
 
 defm : X86WriteRes<WriteBSWAP32, [SLM_IEC_RSV01], 1, [1], 1>;
 defm : X86WriteRes<WriteBSWAP64, [SLM_IEC_RSV01], 1, [1], 1>;
+defm : X86WriteRes<WriteXCHG,       [SLM_IEC_RSV01], 1, [1], 1>;
 
 defm : SLMWriteResPair<WriteShift,  [SLM_IEC_RSV0],  1>;
 
Index: llvm/trunk/lib/Target/X86/X86ScheduleZnver1.td
===================================================================
--- llvm/trunk/lib/Target/X86/X86ScheduleZnver1.td
+++ llvm/trunk/lib/Target/X86/X86ScheduleZnver1.td
@@ -182,6 +182,7 @@
 
 defm : X86WriteRes<WriteBSWAP32, [ZnALU], 1, [4], 1>;
 defm : X86WriteRes<WriteBSWAP64, [ZnALU], 1, [4], 1>;
+defm : X86WriteRes<WriteXCHG, [ZnALU], 1, [2], 2>;
 
 defm : ZnWriteResPair<WriteShift, [ZnALU], 1>;
 
@@ -499,14 +500,6 @@
 def : InstRW<[WriteLoad], (instregex "MOV(S|Z)X32rm(8|16)")>;
 
 // XCHG.
-// r,r.
-def ZnWriteXCHG : SchedWriteRes<[ZnALU]> {
-  let NumMicroOps = 2;
-  let ResourceCycles = [2];
-}
-
-def : InstRW<[ZnWriteXCHG], (instregex "XCHG(8|16|32|64)rr", "XCHG(16|32|64)ar")>;
-
 // r,m.
 def ZnWriteXCHGrm : SchedWriteRes<[ZnAGU, ZnALU]> {
   let Latency = 5;
@@ -807,6 +800,8 @@
 def : InstRW<[WriteMicrocoded], (instregex "STOS(B|L|Q|W)")>;
 
 // XADD.
+def ZnXADD : SchedWriteRes<[ZnALU]>;
+def : InstRW<[ZnXADD], (instregex "XADD(8|16|32|64)rr")>;
 def : InstRW<[WriteMicrocoded], (instregex "XADD(8|16|32|64)rm")>;
 
 //=== Floating Point x87 Instructions ===//