[AMDGPU] Treat printf as builtin for OpenCL

Author: vikramRH

clang/include/clang/Basic/BuiltinsAMDGPU.def

@@ -21,6 +21,10 @@
 #if defined(BUILTIN) && !defined(TARGET_BUILTIN)
 #   define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE) BUILTIN(ID, TYPE, ATTRS)
 #endif
+
+#if defined(BUILTIN) && !defined(LANGBUILTIN)
+#define LANGBUILTIN(ID, TYPE, ATTRS, BUILTIN_LANG) BUILTIN(ID, TYPE, ATTRS)
+#endif
 //===----------------------------------------------------------------------===//
 // SI+ only builtins.
 //===----------------------------------------------------------------------===//
@@ -498,6 +502,9 @@ TARGET_BUILTIN(__builtin_amdgcn_swmmac_f32_16x16x32_fp8_fp8_w64, "V4fiV2iV4fs",
 TARGET_BUILTIN(__builtin_amdgcn_swmmac_f32_16x16x32_fp8_bf8_w64, "V4fiV2iV4fs", "nc", "gfx12-insts,wavefrontsize64")
 TARGET_BUILTIN(__builtin_amdgcn_swmmac_f32_16x16x32_bf8_fp8_w64, "V4fiV2iV4fs", "nc", "gfx12-insts,wavefrontsize64")
 TARGET_BUILTIN(__builtin_amdgcn_swmmac_f32_16x16x32_bf8_bf8_w64, "V4fiV2iV4fs", "nc", "gfx12-insts,wavefrontsize64")
+// OpenCL
+LANGBUILTIN(printf, "icC*4.", "fp:0:", ALL_OCL_LANGUAGES)
 
 #undef BUILTIN
 #undef TARGET_BUILTIN
+#undef LANGBUILTIN

clang/lib/AST/Decl.cpp

@@ -49,6 +49,7 @@
 #include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Basic/Specifiers.h"
+#include "clang/Basic/TargetBuiltins.h"
 #include "clang/Basic/TargetCXXABI.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/Basic/Visibility.h"
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool ConsiderWrapperFunctions) const {
   if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
     return 0;
 
+  // AMDGCN implementation supports printf as a builtin
+  // for OpenCL
+  if (Context.getTargetInfo().getTriple().isAMDGCN() &&
+      Context.getLangOpts().OpenCL && BuiltinID == AMDGPU::BIprintf)
+    return BuiltinID;
+
   // OpenCL v1.2 s6.9.f - The library functions defined in
   // the C99 standard headers are not available.
   if (Context.getLangOpts().OpenCL &&

clang/lib/Basic/Targets/AMDGPU.cpp

@@ -93,6 +93,8 @@ static constexpr Builtin::Info BuiltinInfo[] = {
   {#ID, TYPE, ATTRS, nullptr, HeaderDesc::NO_HEADER, ALL_LANGUAGES},
 #define TARGET_BUILTIN(ID, TYPE, ATTRS, FEATURE)                               \
   {#ID, TYPE, ATTRS, FEATURE, HeaderDesc::NO_HEADER, ALL_LANGUAGES},
+#define LANGBUILTIN(ID, TYPE, ATTRS, LANG)                                     \
+  {#ID, TYPE, ATTRS, nullptr, HeaderDesc::NO_HEADER, LANG},
 #include "clang/Basic/BuiltinsAMDGPU.def"
 };
 

clang/lib/CodeGen/CGBuiltin.cpp

@@ -2550,6 +2550,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
       &getTarget().getLongDoubleFormat() == &llvm::APFloat::IEEEquad())
     BuiltinID = mutateLongDoubleBuiltin(BuiltinID);
 
+   // Mutate the printf builtin ID so that we use the same CodeGen path for
+   // HIP and OpenCL with AMDGPU targets.
+   if (getTarget().getTriple().isAMDGCN() && BuiltinID == AMDGPU::BIprintf)
+     BuiltinID = Builtin::BIprintf;
+
   // If the builtin has been declared explicitly with an assembler label,
   // disable the specialized emitting below. Ideally we should communicate the
   // rename in IR, or at least avoid generating the intrinsic calls that are