maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[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
This commit is contained in:
Egor Churaev 2017-03-21 12:55:55 +00:00
parent f60ad58dad
commit c217f37cb6
4 changed files with 48 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
clang/include/clang/Sema/Overload.h
View File

@ -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.

2
clang/lib/Sema/SemaOverload.cpp
View File

@ -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,

46
clang/test/CodeGenOpenCL/overload.cl Normal file
View File

@ -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);
}

29
clang/test/SemaOpenCL/overload_addrspace_resolution.cl
View File

@ -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);
}