Improve handling of floating point literals in OpenCL to only use double precision if the target supports fp64

https://reviews.llvm.org/D24235

llvm-svn: 281714

clang/lib/Sema/SemaExpr.cpp

@@ -828,8 +828,18 @@ ExprResult Sema::DefaultArgumentPromotion(Expr *E) {
   // double.
   const BuiltinType *BTy = Ty->getAs<BuiltinType>();
   if (BTy && (BTy->getKind() == BuiltinType::Half ||
-              BTy->getKind() == BuiltinType::Float))
+              BTy->getKind() == BuiltinType::Float)) {
+    if (getLangOpts().OpenCL &&
+        !((getLangOpts().OpenCLVersion >= 120 &&
+           Context.getTargetInfo()
+               .getSupportedOpenCLOpts()
+               .cl_khr_fp64) ||
+          getOpenCLOptions().cl_khr_fp64)) {
+        E = ImpCastExprToType(E, Context.FloatTy, CK_FloatingCast).get();
+    } else {
       E = ImpCastExprToType(E, Context.DoubleTy, CK_FloatingCast).get();
+    }
+  }
 
   // C++ performs lvalue-to-rvalue conversion as a default argument
   // promotion, even on class types, but note:
@@ -3406,8 +3416,14 @@ ExprResult Sema::ActOnNumericConstant(const Token &Tok, Scope *UDLScope) {
       if (getLangOpts().SinglePrecisionConstants) {
         Res = ImpCastExprToType(Res, Context.FloatTy, CK_FloatingCast).get();
       } else if (getLangOpts().OpenCL &&
-                 !((getLangOpts().OpenCLVersion >= 120) ||
+                 !((getLangOpts().OpenCLVersion >= 120 &&
+                    Context.getTargetInfo()
+                        .getSupportedOpenCLOpts()
+                        .cl_khr_fp64) ||
                    getOpenCLOptions().cl_khr_fp64)) {
+        // Impose single-precision float type when:
+        //  - in CL 1.2 or above and cl_khr_fp64 is not supported, or
+        //  - in CL 1.1 or below and cl_khr_fp64 is not enabled.
         Diag(Tok.getLocation(), diag::warn_double_const_requires_fp64);
         Res = ImpCastExprToType(Res, Context.FloatTy, CK_FloatingCast).get();
       }

clang/lib/Sema/SemaType.cpp

@@ -1401,7 +1401,8 @@ static QualType ConvertDeclSpecToType(TypeProcessingState &state) {
       Result = Context.DoubleTy;
 
     if (S.getLangOpts().OpenCL &&
-        !((S.getLangOpts().OpenCLVersion >= 120) ||
+        !((S.getLangOpts().OpenCLVersion >= 120 
+           && S.Context.getTargetInfo().getSupportedOpenCLOpts().cl_khr_fp64) ||
           S.getOpenCLOptions().cl_khr_fp64)) {
       S.Diag(DS.getTypeSpecTypeLoc(), diag::err_type_requires_extension)
           << Result << "cl_khr_fp64";

clang/test/CodeGenOpenCL/fpmath.cl

@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown | FileCheck --check-prefix=CHECK --check-prefix=NODIVOPT %s
 // RUN: %clang_cc1 %s -emit-llvm -o - -triple spir-unknown-unknown -cl-fp32-correctly-rounded-divide-sqrt | FileCheck --check-prefix=CHECK --check-prefix=DIVOPT %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -DNOFP64 -cl-std=CL1.1 -triple r600-unknown-unknown -target-cpu r600 -pedantic | FileCheck --check-prefix=CHECK-DBL %s
 
 typedef __attribute__(( ext_vector_type(4) )) float float4;
 
@@ -21,14 +22,26 @@ float4 spvectordiv(float4 a, float4 b) {
   return a / b;
 }
 
-#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+void printf(constant char* fmt, ...);
 
+#ifndef NOFP64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+#endif
+void testdbllit(long *val) {
+  // CHECK-DBL: float 2.000000e+01
+  // CHECK: double 2.000000e+01
+  printf("%f", 20.0);
+}
+
+#ifndef NOFP64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
 double dpscalardiv(double a, double b) {
   // CHECK: @dpscalardiv
   // CHECK: #[[ATTR]]
   // CHECK-NOT: !fpmath
   return a / b;
 }
+#endif
 
 // CHECK: attributes #[[ATTR]] = {
 // NODIVOPT: "correctly-rounded-divide-sqrt-fp-math"="false"

clang/test/SemaOpenCL/extensions.cl

@@ -1,13 +1,16 @@
 // RUN: %clang_cc1 %s -triple spir-unknown-unknown -verify -pedantic -fsyntax-only
 // RUN: %clang_cc1 %s -triple spir-unknown-unknown -verify -pedantic -fsyntax-only -cl-std=CL1.1
+// RUN: %clang_cc1 %s -triple spir-unknown-unknown -verify -pedantic -fsyntax-only -cl-std=CL1.2 -DFP64
 
 // Test with a target not supporting fp64.
 // RUN: %clang_cc1 %s -triple r600-unknown-unknown -target-cpu r600 -verify -pedantic -fsyntax-only -DNOFP64
 
+#if __OPENCL_C_VERSION__ < 120
 void f1(double da) { // expected-error {{type 'double' requires cl_khr_fp64 extension}}
   double d; // expected-error {{type 'double' requires cl_khr_fp64 extension}}
   (void) 1.0; // expected-warning {{double precision constant requires cl_khr_fp64}}
 }
+#endif
 
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
 #ifdef NOFP64
@@ -21,8 +24,12 @@ void f2(void) {
 #endif
 
   (void) 1.0;
+#ifdef FP64
+// expected-no-diagnostics
+#endif
+
 #ifdef NOFP64
-// expected-warning@-2{{double precision constant requires cl_khr_fp64, casting to single precision}}
+// expected-warning@-6{{double precision constant requires cl_khr_fp64, casting to single precision}}
 #endif
 }
 
@@ -31,6 +38,8 @@ void f2(void) {
 // expected-warning@-2{{unsupported OpenCL extension 'cl_khr_fp64' - ignoring}}
 #endif
 
+#if __OPENCL_C_VERSION__ < 120
 void f3(void) {
   double d; // expected-error {{type 'double' requires cl_khr_fp64 extension}}
 }
+#endif