[OpenCL] Added implicit conversion rank for overloading functions with vector data...

Summary: I added a new rank to ImplicitConversionRank enum to resolve the function overload ambiguity with vector types. Rank of scalar types conversion is lower than vector splat. So, we can choose which function should we call. See test for more details.

Reviewers: Anastasia, cfe-commits

Reviewed By: Anastasia

Subscribers: bader, yaxunl

Differential Revision: https://reviews.llvm.org/D30816

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@298366 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Sema/Overload.h b/include/clang/Sema/Overload.h
index 5220d987302289d6a609a4322185d4698539e9a5..941b772b78801e86ff0c2ed25050bcce29baafec 100644 (file)
--- a/include/clang/Sema/Overload.h
+++ b/include/clang/Sema/Overload.h
@@ -98,6 +98,7 @@ namespace clang {
     ICR_Exact_Match = 0,         ///< Exact Match
     ICR_Promotion,               ///< Promotion
     ICR_Conversion,              ///< Conversion
+    ICR_OCL_Scalar_Widening,     ///< OpenCL Scalar Widening
     ICR_Complex_Real_Conversion, ///< Complex <-> Real conversion
     ICR_Writeback_Conversion,    ///< ObjC ARC writeback conversion
     ICR_C_Conversion,            ///< Conversion only allowed in the C standard.

diff --git a/lib/Sema/SemaOverload.cpp b/lib/Sema/SemaOverload.cpp
index 8b53258803638dd888b44e7f016393e1f3eae363..7f94bf26d8b30fea2a02f1f93222a27da35fefac 100644 (file)
--- a/lib/Sema/SemaOverload.cpp
+++ b/lib/Sema/SemaOverload.cpp
@@ -131,7 +131,7 @@ ImplicitConversionRank clang::GetConversionRank(ImplicitConversionKind Kind) {
     ICR_Conversion,
     ICR_Conversion,
     ICR_Conversion,
-    ICR_Conversion,
+    ICR_OCL_Scalar_Widening,
     ICR_Complex_Real_Conversion,
     ICR_Conversion,
     ICR_Conversion,

diff --git a/test/CodeGenOpenCL/overload.cl b/test/CodeGenOpenCL/overload.cl
new file mode 100644 (file)
index 0000000..f182cb5
--- /dev/null
+++ b/test/CodeGenOpenCL/overload.cl
@@ -0,0 +1,46 @@
+// RUN: %clang_cc1 -cl-std=CL2.0 -emit-llvm -o - -triple spir-unknown-unknown %s | FileCheck %s
+
+typedef short short4 __attribute__((ext_vector_type(4)));
+
+// CHECK-DAG: declare spir_func <4 x i16> @_Z5clampDv4_sS_S_(<4 x i16>, <4 x i16>, <4 x i16>)
+short4 __attribute__ ((overloadable)) clamp(short4 x, short4 minval, short4 maxval);
+// CHECK-DAG: declare spir_func <4 x i16> @_Z5clampDv4_sss(<4 x i16>, i16 signext, i16 signext)
+short4 __attribute__ ((overloadable)) clamp(short4 x, short minval, short maxval);
+void __attribute__((overloadable)) foo(global int *a, global int *b);
+void __attribute__((overloadable)) foo(generic int *a, generic int *b);
+void __attribute__((overloadable)) bar(generic int *global *a, generic int *global *b);
+void __attribute__((overloadable)) bar(generic int *generic *a, generic int *generic *b);
+
+// Checking address space resolution
+void kernel test1() {
+  global int *a;
+  global int *b;
+  generic int *c;
+  local int *d;
+  generic int *generic *gengen;
+  generic int *local *genloc;
+  generic int *global *genglob;
+  // CHECK-DAG: call spir_func void @_Z3fooPU3AS1iS0_(i32 addrspace(1)* undef, i32 addrspace(1)* undef)
+  foo(a, b);
+  // CHECK-DAG: call spir_func void @_Z3fooPU3AS4iS0_(i32 addrspace(4)* undef, i32 addrspace(4)* undef)
+  foo(b, c);
+  // CHECK-DAG: call spir_func void @_Z3fooPU3AS4iS0_(i32 addrspace(4)* undef, i32 addrspace(4)* undef)
+  foo(a, d);
+
+  // CHECK-DAG: call spir_func void @_Z3barPU3AS4PU3AS4iS2_(i32 addrspace(4)* addrspace(4)* undef, i32 addrspace(4)* addrspace(4)* undef)
+  bar(gengen, genloc);
+  // CHECK-DAG: call spir_func void @_Z3barPU3AS4PU3AS4iS2_(i32 addrspace(4)* addrspace(4)* undef, i32 addrspace(4)* addrspace(4)* undef)
+  bar(gengen, genglob);
+  // CHECK-DAG: call spir_func void @_Z3barPU3AS1PU3AS4iS2_(i32 addrspace(4)* addrspace(1)* undef, i32 addrspace(4)* addrspace(1)* undef)
+  bar(genglob, genglob);
+}
+
+// Checking vector vs scalar resolution
+void kernel test2() {
+  short4 e0=0;
+
+  // CHECK-DAG: call spir_func <4 x i16> @_Z5clampDv4_sss(<4 x i16> zeroinitializer, i16 signext 0, i16 signext 255)
+  clamp(e0, 0, 255);
+  // CHECK-DAG: call spir_func <4 x i16> @_Z5clampDv4_sS_S_(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, <4 x i16> zeroinitializer)
+  clamp(e0, e0, e0);
+}

diff --git a/test/SemaOpenCL/overload_addrspace_resolution.cl b/test/SemaOpenCL/overload_addrspace_resolution.cl
deleted file mode 100644 (file)
index c7cf5fc..0000000
--- a/test/SemaOpenCL/overload_addrspace_resolution.cl
+++ /dev/null
@@ -1,29 +0,0 @@
-// RUN: %clang_cc1 -cl-std=CL2.0 -emit-llvm -o - -triple x86_64-unknown-unknown %s | FileCheck %s
-
-void __attribute__((overloadable)) foo(global int *a, global int *b);
-void __attribute__((overloadable)) foo(generic int *a, generic int *b);
-void __attribute__((overloadable)) bar(generic int *global *a, generic int *global *b);
-void __attribute__((overloadable)) bar(generic int *generic *a, generic int *generic *b);
-
-void kernel ker() {
-  global int *a;
-  global int *b;
-  generic int *c;
-  local int *d;
-  generic int *generic *gengen;
-  generic int *local *genloc;
-  generic int *global *genglob;
-  // CHECK: call void @_Z3fooPU8CLglobaliS0_(i32* undef, i32* undef)
-  foo(a, b);
-  // CHECK: call void @_Z3fooPU9CLgenericiS0_(i32* undef, i32* undef)
-  foo(b, c);
-  // CHECK: call void @_Z3fooPU9CLgenericiS0_(i32* undef, i32* undef)
-  foo(a, d);
-
-  // CHECK: call void @_Z3barPU9CLgenericPU9CLgenericiS2_(i32** undef, i32** undef)
-  bar(gengen, genloc);
-  // CHECK: call void @_Z3barPU9CLgenericPU9CLgenericiS2_(i32** undef, i32** undef)
-  bar(gengen, genglob);
-  // CHECK: call void @_Z3barPU8CLglobalPU9CLgenericiS2_(i32** undef, i32** undef)
-  bar(genglob, genglob);
-}