From c217f37cb663b90c1371c767804b21bef9ce577b Mon Sep 17 00:00:00 2001 From: Egor Churaev Date: Tue, 21 Mar 2017 12:55:55 +0000 Subject: [PATCH] [OpenCL] Added implicit conversion rank for overloading functions with vector data type in OpenCL 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 llvm-svn: 298366 --- clang/include/clang/Sema/Overload.h | 1 + clang/lib/Sema/SemaOverload.cpp | 2 +- clang/test/CodeGenOpenCL/overload.cl | 46 +++++++++++++++++++ .../overload_addrspace_resolution.cl | 29 ------------ 4 files changed, 48 insertions(+), 30 deletions(-) create mode 100644 clang/test/CodeGenOpenCL/overload.cl delete mode 100644 clang/test/SemaOpenCL/overload_addrspace_resolution.cl diff --git a/clang/include/clang/Sema/Overload.h b/clang/include/clang/Sema/Overload.h index 5220d9873022..941b772b7880 100644 --- a/clang/include/clang/Sema/Overload.h +++ b/clang/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/clang/lib/Sema/SemaOverload.cpp b/clang/lib/Sema/SemaOverload.cpp index 8b5325880363..7f94bf26d8b3 100644 --- a/clang/lib/Sema/SemaOverload.cpp +++ b/clang/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/clang/test/CodeGenOpenCL/overload.cl b/clang/test/CodeGenOpenCL/overload.cl new file mode 100644 index 000000000000..f182cb5fd2af --- /dev/null +++ b/clang/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/clang/test/SemaOpenCL/overload_addrspace_resolution.cl b/clang/test/SemaOpenCL/overload_addrspace_resolution.cl deleted file mode 100644 index c7cf5fcb8d84..000000000000 --- a/clang/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); -}