Anastasia created this revision.
Anastasia added reviewers: rjmccall, rsmith, mantognini.
Herald added subscribers: ebevhan, yaxunl.
I am recreating the review from https://reviews.llvm.org/D59426 that seem to
get lost somehow.
The idea is to be able to allow creating vector literals from other vectors.
Example from reported bug `PR41010`
kernel void test(__global float4 *out)
{
float4 a = (float4)(1.0f, 2.0f, 3.0f, 4.0f);
float4 v = (float4)(a.s23, a.s01);
*out = v;
}
The primary use case is OpenCL but it can be used for vector extensions in
plain C++ too.
https://reviews.llvm.org/D65286
Files:
lib/Sema/SemaInit.cpp
test/CodeGenOpenCL/vector_literals_valid.cl
Index: test/CodeGenOpenCL/vector_literals_valid.cl
===================================================================
--- test/CodeGenOpenCL/vector_literals_valid.cl
+++ test/CodeGenOpenCL/vector_literals_valid.cl
@@ -1,22 +1,61 @@
-// RUN: %clang_cc1 -emit-llvm %s -o %t
+// RUN: %clang_cc1 -emit-llvm %s -o - -O0 | FileCheck %s
+// RUN: %clang_cc1 -emit-llvm %s -o - -cl-std=clc++ -O0 | FileCheck %s
-typedef __attribute__(( ext_vector_type(2) )) int int2;
-typedef __attribute__(( ext_vector_type(3) )) int int3;
-typedef __attribute__(( ext_vector_type(4) )) int int4;
-typedef __attribute__(( ext_vector_type(8) )) int int8;
-typedef __attribute__(( ext_vector_type(4) )) float float4;
+typedef __attribute__((ext_vector_type(2))) int int2;
+typedef __attribute__((ext_vector_type(3))) int int3;
+typedef __attribute__((ext_vector_type(4))) int int4;
+typedef __attribute__((ext_vector_type(8))) int int8;
+typedef __attribute__((ext_vector_type(4))) float float4;
void vector_literals_valid() {
- int4 a_1_1_1_1 = (int4)(1,2,3,4);
- int4 a_2_1_1 = (int4)((int2)(1,2),3,4);
- int4 a_1_2_1 = (int4)(1,(int2)(2,3),4);
- int4 a_1_1_2 = (int4)(1,2,(int2)(3,4));
- int4 a_2_2 = (int4)((int2)(1,2),(int2)(3,4));
- int4 a_3_1 = (int4)((int3)(1,2,3),4);
- int4 a_1_3 = (int4)(1,(int3)(2,3,4));
+ //CHECK: store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>*
+
+ int4 a_1_1_1_1 = (int4)(1, 2, 3, 4);
+
+ //CHECK: store <2 x i32> <i32 1, i32 2>, <2 x i32>*
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: shufflevector <4 x i32> %{{.+}}, <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: insertelement <4 x i32> %{{.+}}, i32 3, i32 2
+ //CHECK: insertelement <4 x i32> %{{.+}}, i32 4, i32 3
+ int4 a_2_1_1 = (int4)((int2)(1, 2), 3, 4);
+
+ //CHECK: store <2 x i32> <i32 2, i32 3>, <2 x i32>*
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: shufflevector <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>, <4 x i32> %{{.+}}, <4 x i32> <i32 0, i32 4, i32 5, i32 undef>
+ //CHECK: insertelement <4 x i32> %{{.+}}, i32 4, i32 3
+ int4 a_1_2_1 = (int4)(1, (int2)(2, 3), 4);
+
+ //CHECK: store <2 x i32> <i32 3, i32 4>, <2 x i32>*
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: shufflevector <4 x i32> <i32 1, i32 2, i32 undef, i32 undef>, <4 x i32> %{{.+}}, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+ int4 a_1_1_2 = (int4)(1, 2, (int2)(3, 4));
+
+ //CHECK: store <2 x i32> <i32 1, i32 2>, <2 x i32>*
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: shufflevector <4 x i32> %{{.+}}, <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: store <2 x i32> <i32 3, i32 4>, <2 x i32>*
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+ //CHECK: shufflevector <4 x i32> %{{.+}}, <4 x i32> %{{.+}}, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+ int4 a_2_2 = (int4)((int2)(1, 2), (int2)(3, 4));
+
+ //CHECK: store <4 x i32> <i32 2, i32 3, i32 4, i32 undef>, <4 x i32>*
+ //CHECK: shufflevector <4 x i32> %{{.+}}, <4 x i32> undef, <3 x i32> <i32 0, i32 1, i32 2>
+ //CHECK: shufflevector <3 x i32> %{{.+}}, <3 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
+ //CHECK: shufflevector <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>, <4 x i32> %{{.+}}, <4 x i32> <i32 0, i32 4, i32 5, i32 6>
+ int4 a_1_3 = (int4)(1, (int3)(2, 3, 4));
+
+ //CHECK: store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32>* %a
int4 a = (int4)(1);
- int8 b = (int8)(1,2,a.xy,a);
- float4 V2 = (float4) (1);
-}
+ //CHECK: load <4 x i32>, <4 x i32>* %a, align 16
+ //CHECK: shufflevector <4 x i32> %{{[0-9]+}}, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
+ //CHECK: shufflevector <2 x i32> %{{[0-9]+}}, <2 x i32> undef, <8 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+ //CHECK: shufflevector <8 x i32> <i32 1, i32 2, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>, <8 x i32> %{{.+}}, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 undef, i32 undef, i32 undef, i32 undef>
+ //CHECK: load <4 x i32>, <4 x i32>* %a, align 16
+ //CHECK: shufflevector <4 x i32> %{{[0-9]+}}, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
+ //CHECK: shufflevector <8 x i32> %{{.+}}, <8 x i32> %{{.+}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
+ int8 b = (int8)(1, 2, a.xy, a);
+ //CHECK: store <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, <4 x float>* %V2
+ float4 V2 = (float4)(1);
+}
Index: lib/Sema/SemaInit.cpp
===================================================================
--- lib/Sema/SemaInit.cpp
+++ lib/Sema/SemaInit.cpp
@@ -1289,7 +1289,16 @@
// FIXME: Better EqualLoc?
InitializationKind Kind =
InitializationKind::CreateCopy(expr->getBeginLoc(), SourceLocation());
- InitializationSequence Seq(SemaRef, Entity, Kind, expr,
+
+ // Vector elements can be initialized from other vectors in which case
+ // we need initialization entity with a type of a vector (and not a vector
+ // element!) initializing multiple vector elements.
+ auto TmpEntity =
+ (ElemType->isExtVectorType() && !Entity.getType()->isExtVectorType())
+ ? InitializedEntity::InitializeTemporary(ElemType)
+ : Entity;
+
+ InitializationSequence Seq(SemaRef, TmpEntity, Kind, expr,
/*TopLevelOfInitList*/ true);
// C++14 [dcl.init.aggr]p13:
@@ -1300,8 +1309,7 @@
// assignment-expression.
if (Seq || isa<InitListExpr>(expr)) {
if (!VerifyOnly) {
- ExprResult Result =
- Seq.Perform(SemaRef, Entity, Kind, expr);
+ ExprResult Result = Seq.Perform(SemaRef, TmpEntity, Kind, expr);
if (Result.isInvalid())
hadError = true;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
