This lowers vcombine intrinsics to a GIMPLE vector constructor, which enables
better optimisation during GIMPLE passes.
gcc/
* config/aarch64/aarch64-builtins.c
(aarch64_general_gimple_fold_builtin): Add combine.
gcc/testsuite/
* gcc.target/aarch64/advsimd-intrinsics/combine.c:
New test.
diff --git a/gcc/config/aarch64/aarch64-builtins.cc
b/gcc/config/aarch64/aarch64-builtins.cc
index
5753988a9964967c27a03aca5fddb9025fd8ed6e..a25756cfed5fab3a98ebf3e2ee29a5e117cbd2aa
100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -2857,6 +2857,28 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode,
gcall *stmt,
gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
break;
+ BUILTIN_VDC (BINOP, combine, 0, AUTO_FP)
+ BUILTIN_VD_I (BINOPU, combine, 0, NONE)
+ BUILTIN_VDC_P (BINOPP, combine, 0, NONE)
+ {
+ tree first_part, second_part;
+ if (BYTES_BIG_ENDIAN)
+ {
+ second_part = args[0];
+ first_part = args[1];
+ }
+ else
+ {
+ first_part = args[0];
+ second_part = args[1];
+ }
+ tree ret_type = TREE_TYPE (gimple_call_lhs (stmt));
+ tree ctor = build_constructor_va (ret_type, 2, NULL_TREE, first_part,
+ NULL_TREE, second_part);
+ new_stmt = gimple_build_assign (gimple_call_lhs (stmt), ctor);
+ }
+ break;
+
/*lower store and load neon builtins to gimple. */
BUILTIN_VALL_F16 (LOAD1, ld1, 0, LOAD)
BUILTIN_VDQ_I (LOAD1_U, ld1, 0, LOAD)
diff --git a/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c
b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c
new file mode 100644
index
0000000000000000000000000000000000000000..d08faf7a4a160a1e83428ed9b270731bbf7b8c8a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/combine.c
@@ -0,0 +1,18 @@
+/* { dg-do compile { target { aarch64*-*-* } } } */
+/* { dg-final { check-function-bodies "**" "" {-O[^0]} } } */
+/* { dg-skip-if "" { *-*-* } { "-fno-fat-lto-objects" } } */
+
+#include <arm_neon.h>
+
+/*
+** foo:
+** umov w0, v1\.s\[1\]
+** ret
+*/
+
+int32_t foo (int32x2_t a, int32x2_t b)
+{
+ int32x4_t c = vcombine_s32(a, b);
+ return vgetq_lane_s32(c, 3);
+}
+
