[Bugfix] Fix ICE on constexpr vector splat.
In {CG,}ExprConstant.cpp, we weren't treating vector splats properly.
This patch makes us treat splats more properly.
Additionally, this patch adds a new cast kind which allows a bool->int
cast to result in -1 or 0, instead of 1 or 0 (for true and false,
respectively), so we can sanely model OpenCL bool->int casts in the AST.
Differential Revision: http://reviews.llvm.org/D14877
llvm-svn: 257559
diff --git a/clang/test/CodeGenCXX/builtins-systemz-zvector.cpp b/clang/test/CodeGenCXX/builtins-systemz-zvector.cpp
new file mode 100644
index 0000000..aedb30f
--- /dev/null
+++ b/clang/test/CodeGenCXX/builtins-systemz-zvector.cpp
@@ -0,0 +1,50 @@
+// REQUIRES: systemz-registered-target
+// RUN: %clang_cc1 -target-cpu z13 -triple s390x-linux-gnu \
+// RUN: -fzvector -fno-lax-vector-conversions -std=c++11 \
+// RUN: -Wall -Wno-unused -Werror -emit-llvm %s -o - | FileCheck %s
+
+bool gb;
+
+// There was an issue where we weren't properly converting constexprs to
+// vectors with elements of the appropriate width. (e.g.
+// (vector signed short)0 would be lowered as [4 x i32] in some cases)
+
+// CHECK-LABEL: @_Z8testIntsDv4_i
+void testInts(vector int VI) {
+ constexpr vector int CI1 = (vector int)0LL;
+ // CHECK: icmp
+ gb = (VI == CI1)[0];
+
+ // Likewise for float inits.
+ constexpr vector int CI2 = (vector int)char(0);
+ // CHECK: icmp
+ gb = (VI == CI2)[0];
+
+ constexpr vector int CF1 = (vector int)0.0;
+ // CHECK: icmp
+ gb = (VI == CF1)[0];
+
+ constexpr vector int CF2 = (vector int)0.0f;
+ // CHECK: icmp
+ gb = (VI == CF2)[0];
+}
+
+// CHECK-LABEL: @_Z10testFloatsDv2_d
+void testFloats(vector double VD) {
+ constexpr vector double CI1 = (vector double)0LL;
+ // CHECK: fcmp
+ gb = (VD == CI1)[0];
+
+ // Likewise for float inits.
+ constexpr vector double CI2 = (vector double)char(0);
+ // CHECK: fcmp
+ gb = (VD == CI2)[0];
+
+ constexpr vector double CF1 = (vector double)0.0;
+ // CHECK: fcmp
+ gb = (VD == CF1)[0];
+
+ constexpr vector double CF2 = (vector double)0.0f;
+ // CHECK: fcmp
+ gb = (VD == CF2)[0];
+}
diff --git a/clang/test/CodeGenCXX/vector-splat-conversion.cpp b/clang/test/CodeGenCXX/vector-splat-conversion.cpp
index 410df3d..805f9f5 100644
--- a/clang/test/CodeGenCXX/vector-splat-conversion.cpp
+++ b/clang/test/CodeGenCXX/vector-splat-conversion.cpp
@@ -1,19 +1,51 @@
// RUN: %clang_cc1 %s -triple arm64-apple-ios8.1.0 -std=c++11 -emit-llvm -o - | FileCheck %s
-// rdar://20000762
typedef __attribute__((__ext_vector_type__(8))) float vector_float8;
typedef vector_float8 float8;
-void MandelbrotPolyCalcSIMD8()
-{
- constexpr float8 v4 = 4.0; // value to compare against abs(z)^2, to see if bounded
- float8 vABS;
- auto vLT = vABS < v4;
+// rdar://20000762
+// CHECK-LABEL: define void @_Z23MandelbrotPolyCalcSIMD8v
+void MandelbrotPolyCalcSIMD8() {
+ constexpr float8 v4 = 4.0; // value to compare against abs(z)^2, to see if bounded
+ float8 vABS;
+ auto vLT = vABS < v4;
+ // CHECK: store <8 x float>
+ // CHECK: [[ZERO:%.*]] = load <8 x float>, <8 x float>* [[VARBS:%.*]]
+ // CHECK: [[CMP:%.*]] = fcmp olt <8 x float> [[ZERO]]
+ // CHECK: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
+ // CHECK: store <8 x i32> [[SEXT]], <8 x i32>* [[VLT:%.*]]
}
-// CHECK: store <8 x float>
-// CHECK: [[ZERO:%.*]] = load <8 x float>, <8 x float>* [[VARBS:%.*]]
-// CHECK: [[CMP:%.*]] = fcmp olt <8 x float> [[ZERO]]
-// CHECK: [[SEXT:%.*]] = sext <8 x i1> [[CMP]] to <8 x i32>
-// CHECK: store <8 x i32> [[SEXT]], <8 x i32>* [[VLT:%.*]]
+typedef __attribute__((__ext_vector_type__(4))) int int4;
+typedef __attribute__((__ext_vector_type__(4))) float float4;
+typedef __attribute__((__ext_vector_type__(4))) __int128 bigint4;
+
+// CHECK-LABEL: define void @_Z14BoolConversionv
+void BoolConversion() {
+ // CHECK: store <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
+ int4 intsT = (int4)true;
+ // CHECK: store <4 x i32> zeroinitializer
+ int4 intsF = (int4)false;
+ // CHECK: store <4 x float> <float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00>
+ float4 floatsT = (float4)true;
+ // CHECK: store <4 x float> zeroinitializer
+ float4 floatsF = (float4)false;
+ // CHECK: store <4 x i128> <i128 -1, i128 -1, i128 -1, i128 -1>
+ bigint4 bigintsT = (bigint4)true;
+ // CHECK: store <4 x i128> zeroinitializer
+ bigint4 bigintsF = (bigint4)false;
+
+ // CHECK: store <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
+ constexpr int4 cIntsT = (int4)true;
+ // CHECK: store <4 x i32> zeroinitializer
+ constexpr int4 cIntsF = (int4)false;
+ // CHECK: store <4 x float> <float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00>
+ constexpr float4 cFloatsT = (float4)true;
+ // CHECK: store <4 x float> zeroinitializer
+ constexpr float4 cFloatsF = (float4)false;
+ // CHECK: store <4 x i128> <i128 -1, i128 -1, i128 -1, i128 -1>
+ constexpr bigint4 cBigintsT = (bigint4)true;
+ // CHECK: store <4 x i128> zeroinitializer
+ constexpr bigint4 cBigintsF = (bigint4)false;
+}
diff --git a/clang/test/CodeGenOpenCL/bool_cast.cl b/clang/test/CodeGenOpenCL/bool_cast.cl
index d63431b..8c86b06 100644
--- a/clang/test/CodeGenOpenCL/bool_cast.cl
+++ b/clang/test/CodeGenOpenCL/bool_cast.cl
@@ -2,7 +2,9 @@
typedef unsigned char uchar4 __attribute((ext_vector_type(4)));
typedef unsigned int int4 __attribute((ext_vector_type(4)));
+typedef float float4 __attribute((ext_vector_type(4)));
+// CHECK-LABEL: define void @ker()
void kernel ker() {
bool t = true;
int4 vec4 = (int4)t;
@@ -24,4 +26,8 @@
unsigned char c;
c = (unsigned char)true;
// CHECK: store i8 1, i8* %c, align 1
+
+ float4 vf;
+ vf = (float4)true;
+// CHECK: store <4 x float> <float -1.000000e+00, float -1.000000e+00, float -1.000000e+00, float -1.000000e+00>
}