Rewrite ppc code generated for __sync_{bool|val}_compare_and_swap

so that lwarx and stwcx are always executed the same number of times.
This is important for performance, I'm told.

llvm-svn: 55163

Author: Dale Johannesen

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

@@ -4056,20 +4056,20 @@ PPCTargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI,
 
     //  loopMBB:
     //   l[wd]arx dest, ptr
-    //   cmp[wd] dest, oldval
-    //   bne- exitMBB
+    //   cmp[wd] CR1, dest, oldval
     //   st[wd]cx. newval, ptr
+    //   bne- CR1, exitMBB
     //   bne- loopMBB
     //   fallthrough --> exitMBB
     BB = loopMBB;
     BuildMI(BB, TII->get(is64bit ? PPC::LDARX : PPC::LWARX), dest)
       .addReg(ptrA).addReg(ptrB);
-    BuildMI(BB, TII->get(is64bit ? PPC::CMPD : PPC::CMPW), PPC::CR0)
+    BuildMI(BB, TII->get(is64bit ? PPC::CMPD : PPC::CMPW), PPC::CR1)
       .addReg(oldval).addReg(dest);
-    BuildMI(BB, TII->get(PPC::BCC))
-      .addImm(PPC::PRED_NE).addReg(PPC::CR0).addMBB(exitMBB);
     BuildMI(BB, TII->get(is64bit ? PPC::STDCX : PPC::STWCX))
       .addReg(newval).addReg(ptrA).addReg(ptrB);
+    BuildMI(BB, TII->get(PPC::BCC))
+      .addImm(PPC::PRED_NE).addReg(PPC::CR1).addMBB(exitMBB);
     BuildMI(BB, TII->get(PPC::BCC))
       .addImm(PPC::PRED_NE).addReg(PPC::CR0).addMBB(loopMBB);    
     BB->addSuccessor(loopMBB);

llvm/lib/Target/PowerPC/PPCInstr64Bit.td

@@ -123,15 +123,18 @@ let usesCustomDAGSchedInserter = 1 in {
       (outs G8RC:$dst), (ins memrr:$ptr, G8RC:$incr),
       "${:comment} ATOMIC_LOAD_ADD_I64 PSEUDO!",
       [(set G8RC:$dst, (PPCatomic_load_add xoaddr:$ptr, G8RC:$incr))]>;
-    def ATOMIC_CMP_SWAP_I64 : Pseudo<
-      (outs G8RC:$dst), (ins memrr:$ptr, G8RC:$old, G8RC:$new),
-      "${:comment} ATOMIC_CMP_SWAP_I64 PSEUDO!",
-      [(set G8RC:$dst, (PPCatomic_cmp_swap xoaddr:$ptr, G8RC:$old, G8RC:$new))]>;
     def ATOMIC_SWAP_I64 : Pseudo<
       (outs G8RC:$dst), (ins memrr:$ptr, G8RC:$new),
       "${:comment} ATOMIC_SWAP_I64 PSEUDO!",
       [(set G8RC:$dst, (PPCatomic_swap xoaddr:$ptr, G8RC:$new))]>;
   }
+  let Uses = [CR0, CR1] in {
+    def ATOMIC_CMP_SWAP_I64 : Pseudo<
+      (outs G8RC:$dst), (ins memrr:$ptr, G8RC:$old, G8RC:$new),
+      "${:comment} ATOMIC_CMP_SWAP_I64 PSEUDO!",
+      [(set G8RC:$dst, 
+                    (PPCatomic_cmp_swap xoaddr:$ptr, G8RC:$old, G8RC:$new))]>;
+  }
 }
 
 // Instructions to support atomic operations

llvm/lib/Target/PowerPC/PPCInstrInfo.td

@@ -553,15 +553,18 @@ let usesCustomDAGSchedInserter = 1 in {
       (outs GPRC:$dst), (ins memrr:$ptr, GPRC:$incr),
       "${:comment} ATOMIC_LOAD_ADD_I32 PSEUDO!",
       [(set GPRC:$dst, (PPCatomic_load_add xoaddr:$ptr, GPRC:$incr))]>;
-    def ATOMIC_CMP_SWAP_I32 : Pseudo<
-      (outs GPRC:$dst), (ins memrr:$ptr, GPRC:$old, GPRC:$new),
-      "${:comment} ATOMIC_CMP_SWAP_I32 PSEUDO!",
-      [(set GPRC:$dst, (PPCatomic_cmp_swap xoaddr:$ptr, GPRC:$old, GPRC:$new))]>;
     def ATOMIC_SWAP_I32 : Pseudo<
       (outs GPRC:$dst), (ins memrr:$ptr, GPRC:$new),
       "${:comment} ATOMIC_SWAP_I32 PSEUDO!",
       [(set GPRC:$dst, (PPCatomic_swap xoaddr:$ptr, GPRC:$new))]>;
   }
+  let Uses = [CR0, CR1] in {
+    def ATOMIC_CMP_SWAP_I32 : Pseudo<
+      (outs GPRC:$dst), (ins memrr:$ptr, GPRC:$old, GPRC:$new),
+      "${:comment} ATOMIC_CMP_SWAP_I32 PSEUDO!",
+      [(set GPRC:$dst, 
+                    (PPCatomic_cmp_swap xoaddr:$ptr, GPRC:$old, GPRC:$new))]>;
+  }
 }
 
 // Instructions to support atomic operations