GCC 14 adds the header file arm_neon_sve_bridge.h to help interface
SVE and Advanced SIMD code. One of the defined idioms is:
svset_neonq (svundef_TYPE (), advsimd_vector)
which simply reinterprets advsimd_vector as an SVE vector without
regard for what's in the upper bits.
GCC was failing to recognise this idiom, which was likely to
significantly hamper adoption.
There is (AFAIK) no good way of representing an extension with
undefined bits in gimple. We could add an internal-only builtin
to represent it, but the current framework makes that somewhat
awkward. It also doesn't seem very forward-looking.
This patch instead goes for the simpler approach of recognising
undefined arguments at expansion time.
Tested on aarch64-linux-gnu & pushed.
Richard
gcc/
PR target/114577
* config/aarch64/aarch64-sve-builtins.h (aarch64_sve::lookup_fndecl):
Declare.
* config/aarch64/aarch64-sve-builtins.cc (aarch64_sve::lookup_fndecl):
New function.
* config/aarch64/aarch64-sve-builtins-base.cc (is_undef): Likewise.
(svset_neonq_impl::expand): Optimise expansions whose first argument
is undefined.
gcc/testsuite/
PR target/114577
* gcc.target/aarch64/sve/acle/general/pr114577_1.c: New test.
* gcc.target/aarch64/sve/acle/general/pr114577_2.c: Likewise.
---
.../aarch64/aarch64-sve-builtins-base.cc | 27 ++++++
gcc/config/aarch64/aarch64-sve-builtins.cc | 16 ++++
gcc/config/aarch64/aarch64-sve-builtins.h | 1 +
.../aarch64/sve/acle/general/pr114577_1.c | 94 +++++++++++++++++++
.../aarch64/sve/acle/general/pr114577_2.c | 46 +++++++++
5 files changed, 184 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr114577_1.c
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr114577_2.c
@@ -47,11 +47,31 @@
#include "aarch64-builtins.h"
#include "ssa.h"
#include "gimple-fold.h"
+#include "tree-ssa.h"
using namespace aarch64_sve;
namespace {
+/* Return true if VAL is an undefined value. */
+static bool
+is_undef (tree val)
+{
+ if (TREE_CODE (val) == SSA_NAME)
+ {
+ if (ssa_undefined_value_p (val, false))
+ return true;
+
+ gimple *def = SSA_NAME_DEF_STMT (val);
+ if (gcall *call = dyn_cast<gcall *> (def))
+ if (tree fndecl = gimple_call_fndecl (call))
+ if (const function_instance *instance = lookup_fndecl (fndecl))
+ if (instance->base == functions::svundef)
+ return true;
+ }
+ return false;
+}
+
/* Return the UNSPEC_CMLA* unspec for rotation amount ROT. */
static int
unspec_cmla (int rot)
@@ -1142,6 +1162,13 @@ public:
expand (function_expander &e) const override
{
machine_mode mode = e.vector_mode (0);
+
+ /* If the SVE argument is undefined, we just need to reinterpret the
+ Advanced SIMD argument as an SVE vector. */
+ if (!BYTES_BIG_ENDIAN
+ && is_undef (CALL_EXPR_ARG (e.call_expr, 0)))
+ return simplify_gen_subreg (mode, e.args[1], GET_MODE (e.args[1]), 0);
+
rtx_vector_builder builder (VNx16BImode, 16, 2);
for (unsigned int i = 0; i < 16; i++)
builder.quick_push (CONST1_RTX (BImode));
@@ -1055,6 +1055,22 @@ get_vector_type (sve_type type)
return acle_vector_types[type.num_vectors - 1][vector_type];
}
+/* If FNDECL is an SVE builtin, return its function instance, otherwise
+ return null. */
+const function_instance *
+lookup_fndecl (tree fndecl)
+{
+ if (!fndecl_built_in_p (fndecl, BUILT_IN_MD))
+ return nullptr;
+
+ unsigned int code = DECL_MD_FUNCTION_CODE (fndecl);
+ if ((code & AARCH64_BUILTIN_CLASS) != AARCH64_BUILTIN_SVE)
+ return nullptr;
+
+ unsigned int subcode = code >> AARCH64_BUILTIN_SHIFT;
+ return &(*registered_functions)[subcode]->instance;
+}
+
/* Report an error against LOCATION that the user has tried to use
function FNDECL when extension EXTENSION is disabled. */
static void
@@ -810,6 +810,7 @@ extern tree acle_svprfop;
bool vector_cst_all_same (tree, unsigned int);
bool is_ptrue (tree, unsigned int);
+const function_instance *lookup_fndecl (tree);
/* Try to find a mode with the given mode_suffix_info fields. Return the
mode on success or MODE_none on failure. */
new file mode 100644
@@ -0,0 +1,94 @@
+/* { dg-options "-O" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include <arm_neon_sve_bridge.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+svint32_t svundef_foo ();
+
+/*
+** f1: { target aarch64_little_endian }
+** ldr q0, \[x0\]
+** ret
+*/
+svint32_t
+f1 (int *a)
+{
+ return svset_neonq (svundef_s32 (), vld1q_s32 (a));
+}
+
+/*
+** f2: { target aarch64_little_endian }
+** ldr q0, \[x0\]
+** ret
+*/
+svint32_t
+f2 (int *a)
+{
+ svint32_t undef;
+ return svset_neonq (undef, vld1q_s32 (a));
+}
+
+/*
+** f3: { target aarch64_little_endian }
+** mov [vz]0.[^\n]+, [vz]1.[^\n]+
+** ret
+*/
+svint32_t
+f3 (int32x4_t v0, int32x4_t v1)
+{
+ return svset_neonq (svundef_s32 (), v1);
+}
+
+/*
+** f4: { target aarch64_little_endian }
+** uzp1 z([0-9]+)\.s, z0\.s, z1\.s
+** ldr q([0-9]+), \[x0\]
+** ptrue p([0-7])\.s, vl4
+** sel z0\.s, p\3, z\2\.s, z\1\.s
+** ret
+*/
+svint32_t
+f4 (int *a, svint32_t x, svint32_t y)
+{
+ x = svuzp1 (x, y);
+ int32x4_t z = vld1q_s32 (a);
+ return svset_neonq (x, z);
+}
+
+/*
+** f5:
+** ...
+** bl svundef_foo
+** ...
+** sel z0\.s, [^\n]+
+** ...
+** ret
+*/
+svint32_t
+f5 (int *a)
+{
+ return svset_neonq (svundef_foo (), vld1q_s32 (a));
+}
+
+/*
+** f6:
+** ...
+** blr x[0-9]+
+** ...
+** sel z0\.s, [^\n]+
+** ...
+** ret
+*/
+svint32_t
+f6 (int *a, svint32_t (*svundef_s32) ())
+{
+ return svset_neonq (svundef_s32 (), vld1q_s32 (a));
+}
+
+#ifdef __cplusplus
+}
+#endif
new file mode 100644
@@ -0,0 +1,46 @@
+/* { dg-options "-O -msve-vector-bits=256" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include <arm_neon_sve_bridge.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+** f1: { target aarch64_little_endian }
+** ldr q0, \[x0\]
+** ret
+*/
+svint32_t
+f1 (int *a)
+{
+ return svset_neonq (svundef_s32 (), vld1q_s32 (a));
+}
+
+/*
+** f2: { target aarch64_little_endian }
+** ldr q0, \[x0\]
+** ret
+*/
+svint32_t
+f2 (int *a)
+{
+ svint32_t undef;
+ return svset_neonq (undef, vld1q_s32 (a));
+}
+
+/*
+** f3: { target aarch64_little_endian }
+** mov [vz]0.[^\n]+, [vz]1.[^\n]+
+** ret
+*/
+svint32_t
+f3 (int32x4_t v0, int32x4_t v1)
+{
+ return svset_neonq (svundef_s32 (), v1);
+}
+
+#ifdef __cplusplus
+}
+#endif