[PowerPC] Add PowerPC "__stbcx" builtin and intrinsic for XL compatibility

This patch is in a series of patches to provide builtins for compatibility
with the XL compiler. This patch adds the builtin and intrinsic for "__stbcx".

Reviewed By: nemanjai, #powerpc

Differential revision: https://reviews.llvm.org/D106484

clang/include/clang/Basic/BuiltinsPPC.def

@@ -79,6 +79,7 @@ BUILTIN(__builtin_ppc_lbarx, "UiUcD*", "")
 BUILTIN(__builtin_ppc_stdcx, "iLiD*Li", "")
 BUILTIN(__builtin_ppc_stwcx, "iiD*i", "")
 BUILTIN(__builtin_ppc_sthcx, "isD*s", "")
+BUILTIN(__builtin_ppc_stbcx, "icD*i", "")
 BUILTIN(__builtin_ppc_tdw, "vLLiLLiIUi", "")
 BUILTIN(__builtin_ppc_tw, "viiIUi", "")
 BUILTIN(__builtin_ppc_trap, "vi", "")

clang/lib/Basic/Targets/PPC.cpp

@@ -124,6 +124,7 @@ static void defineXLCompatMacros(MacroBuilder &Builder) {
   Builder.defineMacro("__stdcx", "__builtin_ppc_stdcx");
   Builder.defineMacro("__stwcx", "__builtin_ppc_stwcx");
   Builder.defineMacro("__sthcx", "__builtin_ppc_sthcx");
+  Builder.defineMacro("__stbcx", "__builtin_ppc_stbcx");
   Builder.defineMacro("__tdw", "__builtin_ppc_tdw");
   Builder.defineMacro("__tw", "__builtin_ppc_tw");
   Builder.defineMacro("__trap", "__builtin_ppc_trap");

clang/lib/Sema/SemaChecking.cpp

@@ -3434,9 +3434,8 @@ bool Sema::CheckPPCBuiltinFunctionCall(const TargetInfo &TI, unsigned BuiltinID,
   case PPC::BI__builtin_ppc_rdlam:
     return SemaValueIsRunOfOnes(TheCall, 2);
   case PPC::BI__builtin_ppc_icbt:
-    return SemaFeatureCheck(*this, TheCall, "isa-v207-instructions",
-                            diag::err_ppc_builtin_only_on_arch, "8");
   case PPC::BI__builtin_ppc_sthcx:
+  case PPC::BI__builtin_ppc_stbcx:
   case PPC::BI__builtin_ppc_lharx:
   case PPC::BI__builtin_ppc_lbarx:
     return SemaFeatureCheck(*this, TheCall, "isa-v207-instructions",

clang/test/CodeGen/builtins-ppc-xlcompat-pwr8.c

@@ -15,6 +15,8 @@
 // RUN:   -target-cpu pwr7 -o - 2>&1 | FileCheck %s -check-prefix=CHECK-NOPWR8
 
 extern void *a;
+extern volatile char *c_addr;
+extern char c;
 
 void test_icbt() {
 // CHECK-LABEL: @test_icbt(
@@ -31,3 +33,14 @@ void test_builtin_ppc_icbt() {
 // CHECK-PWR8: call void @llvm.ppc.icbt(i8* %0)
 // CHECK-NOPWR8: error: this builtin is only valid on POWER8 or later CPUs
 }
+
+int test_builtin_ppc_stbcx() {
+// CHECK-PWR8-LABEL: @test_builtin_ppc_stbcx(
+// CHECK-PWR8:         [[TMP0:%.*]] = load i8*, i8** @c_addr, align {{[0-9]+}}
+// CHECK-PWR8-NEXT:    [[TMP1:%.*]] = load i8, i8* @c, align 1
+// CHECK-PWR8-NEXT:    [[TMP2:%.*]] = sext i8 [[TMP1]] to i32
+// CHECK-PWR8-NEXT:    [[TMP3:%.*]] = call i32 @llvm.ppc.stbcx(i8* [[TMP0]], i32 [[TMP2]])
+// CHECK-PWR8-NEXT:    ret i32 [[TMP3]]
+// CHECK-NOPWR8: error: this builtin is only valid on POWER8 or later CPUs
+  return __builtin_ppc_stbcx(c_addr, c);
+}

llvm/include/llvm/IR/IntrinsicsPowerPC.td

@@ -1566,6 +1566,9 @@ let TargetPrefix = "ppc" in {
                                 [IntrWriteMem]>;
   def int_ppc_sthcx
       : Intrinsic<[llvm_i32_ty], [ llvm_ptr_ty, llvm_i32_ty ], [IntrWriteMem]>;
+  def int_ppc_stbcx : GCCBuiltin<"__builtin_ppc_stbcx">,
+                      Intrinsic<[llvm_i32_ty], [llvm_ptr_ty, llvm_i32_ty],
+                                [IntrWriteMem]>;
   def int_ppc_dcbtstt : GCCBuiltin<"__builtin_ppc_dcbtstt">,
                         Intrinsic<[], [llvm_ptr_ty],
                                   [IntrArgMemOnly, NoCapture<ArgIndex<0>>]>;

llvm/lib/Target/PowerPC/PPCInstrInfo.td

@@ -5463,6 +5463,8 @@ def : Pat<(i64 (bitreverse i64:$A)),
 
 def : Pat<(int_ppc_stwcx ForceXForm:$dst, gprc:$A),
           (STWCX gprc:$A, ForceXForm:$dst)>;
+def : Pat<(int_ppc_stbcx ForceXForm:$dst, gprc:$A),
+          (STBCX gprc:$A, ForceXForm:$dst)>;
 def : Pat<(int_ppc_tw gprc:$A, gprc:$B, i32:$IMM),
           (TW $IMM, $A, $B)>;
 def : Pat<(int_ppc_trap gprc:$A),

llvm/test/CodeGen/PowerPC/builtins-ppc-xlcompat-LoadReserve-StoreCond.ll

@@ -74,6 +74,28 @@ entry:
   ret i32 %2
 }
 
+declare i32 @llvm.ppc.stbcx(i8*, i32)
+define signext i32 @test_stbcx(i8* %addr, i8 signext %val) {
+; CHECK-64-LABEL: test_stbcx:
+; CHECK-64:       # %bb.0: # %entry
+; CHECK-64-NEXT:    stbcx. 4, 0, 3
+; CHECK-64-NEXT:    mfocrf 3, 128
+; CHECK-64-NEXT:    srwi 3, 3, 28
+; CHECK-64-NEXT:    extsw 3, 3
+; CHECK-64-NEXT:    blr
+;
+; CHECK-32-LABEL: test_stbcx:
+; CHECK-32:       # %bb.0: # %entry
+; CHECK-32-NEXT:    stbcx. 4, 0, 3
+; CHECK-32-NEXT:    mfocrf 3, 128
+; CHECK-32-NEXT:    srwi 3, 3, 28
+; CHECK-32-NEXT:    blr
+entry:
+  %conv = sext i8 %val to i32
+  %0 = tail call i32 @llvm.ppc.stbcx(i8* %addr, i32 %conv)
+  ret i32 %0
+}
+
 define dso_local signext i16 @test_lharx(i16* %a) {
 ; CHECK-64-LABEL: test_lharx:
 ; CHECK-64:       # %bb.0: # %entry