During code review, it was discovered that the implementation of
__builtin_altivec_lvx_v1ti is not complete. The constant
ALTIVEC_BUILTINLVX_V1TI is introduced and is bound to the function
__builtin_altivec_lvx_v1ti. However, this function's implementation is
incomplete because there is no call to the def_builtin function for this
binding.
This patch provides the missing pieces to add support for this function.
Additionally, this patch introduces four new __int128-based prototypes
of the overloaded __builtin_vec_ld function. This is the function that
implements the vec_ld () macro expansion. A new test case has been
provided to exercise each of these prototypes.
This patch has been bootstrapped and tested without regressions on both
powerpc64le-unknown-linux (P8) and on powerpc-linux (P7 big-endian, with
both -m32 and -m64 target options).
Is this patch ok for trunk?
gcc/ChangeLog:
2018-03-14 Kelvin Nilsen <kel...@gcc.gnu.org>
* config/rs6000/rs6000-c.c (altivec_overloaded_builtins): Add
entries for V1TI variants of __builtin_altivec_ld builtin.
* config/rs6000/rs6000.c (altivec_expand_lv_builtin): Add test and
handling of V1TI variant of LVX icode pattern.
(altivec_expand_builtin): Add case for ALTIVEC_BUILTIN_LVX_V1TI.
(rs6000_gimple_fold_builtin): Likewise.
(altivec_init_builtins): Add code to define
__builtin_altivec_lvx_v1ti function.
* doc/extend.texi: Add four new prototypes for vec_ld.
gcc/testsuite/ChangeLog:
2018-03-14 Kelvin Nilsen <kel...@gcc.gnu.org>
* gcc.target/powerpc/altivec-ld-1.c: New test.
Index: gcc/config/rs6000/rs6000-c.c
===================================================================
--- gcc/config/rs6000/rs6000-c.c (revision 258341)
+++ gcc/config/rs6000/rs6000-c.c (working copy)
@@ -1562,6 +1562,15 @@ const struct altivec_builtin_types altivec_overloa
{ VSX_BUILTIN_VEC_FLOATO, VSX_BUILTIN_UNS_FLOATO_V2DI,
RS6000_BTI_V4SF, RS6000_BTI_unsigned_V2DI, 0, 0 },
+ { ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V1TI,
+ RS6000_BTI_V1TI, RS6000_BTI_INTSI, ~RS6000_BTI_V1TI, 0 },
+ { ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V1TI,
+ RS6000_BTI_unsigned_V1TI, RS6000_BTI_INTSI, ~RS6000_BTI_unsigned_V1TI, 0 },
+ { ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V1TI,
+ RS6000_BTI_V1TI, RS6000_BTI_INTSI, ~RS6000_BTI_INTTI, 0 },
+ { ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V1TI,
+ RS6000_BTI_unsigned_V1TI, RS6000_BTI_INTSI, ~RS6000_BTI_UINTTI, 0 },
+
{ ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V2DF,
RS6000_BTI_V2DF, RS6000_BTI_INTSI, ~RS6000_BTI_V2DF, 0 },
{ ALTIVEC_BUILTIN_VEC_LD, ALTIVEC_BUILTIN_LVX_V2DI,
Index: gcc/config/rs6000/rs6000.c
===================================================================
--- gcc/config/rs6000/rs6000.c (revision 258341)
+++ gcc/config/rs6000/rs6000.c (working copy)
@@ -14452,6 +14452,7 @@ altivec_expand_lv_builtin (enum insn_code icode, t
LVXL and LVE*X expand to use UNSPECs to hide their special behavior,
so the raw address is fine. */
if (icode == CODE_FOR_altivec_lvx_v2df_2op
+ || icode == CODE_FOR_altivec_lvx_v1ti_2op
|| icode == CODE_FOR_altivec_lvx_v2di_2op
|| icode == CODE_FOR_altivec_lvx_v4sf_2op
|| icode == CODE_FOR_altivec_lvx_v4si_2op
@@ -15811,6 +15812,9 @@ altivec_expand_builtin (tree exp, rtx target, bool
case ALTIVEC_BUILTIN_LVX_V2DI:
return altivec_expand_lv_builtin (CODE_FOR_altivec_lvx_v2di_2op,
exp, target, false);
+ case ALTIVEC_BUILTIN_LVX_V1TI:
+ return altivec_expand_lv_builtin (CODE_FOR_altivec_lvx_v1ti_2op,
+ exp, target, false);
case ALTIVEC_BUILTIN_LVX_V4SF:
return altivec_expand_lv_builtin (CODE_FOR_altivec_lvx_v4sf_2op,
exp, target, false);
@@ -16542,6 +16546,7 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *
case ALTIVEC_BUILTIN_LVX_V4SF:
case ALTIVEC_BUILTIN_LVX_V2DI:
case ALTIVEC_BUILTIN_LVX_V2DF:
+ case ALTIVEC_BUILTIN_LVX_V1TI:
{
arg0 = gimple_call_arg (stmt, 0); // offset
arg1 = gimple_call_arg (stmt, 1); // address
@@ -17443,6 +17448,10 @@ altivec_init_builtins (void)
= build_function_type_list (V2DI_type_node,
long_integer_type_node, pcvoid_type_node,
NULL_TREE);
+ tree v1ti_ftype_long_pcvoid
+ = build_function_type_list (V1TI_type_node,
+ long_integer_type_node, pcvoid_type_node,
+ NULL_TREE);
tree void_ftype_opaque_long_pvoid
= build_function_type_list (void_type_node,
@@ -17540,6 +17549,8 @@ altivec_init_builtins (void)
def_builtin ("__builtin_altivec_lvx", v4si_ftype_long_pcvoid,
ALTIVEC_BUILTIN_LVX);
def_builtin ("__builtin_altivec_lvx_v2df", v2df_ftype_long_pcvoid,
ALTIVEC_BUILTIN_LVX_V2DF);
+ def_builtin ("__builtin_altivec_lvx_v1ti", v1ti_ftype_long_pcvoid,
+ ALTIVEC_BUILTIN_LVX_V1TI);
def_builtin ("__builtin_altivec_lvx_v2di", v2di_ftype_long_pcvoid,
ALTIVEC_BUILTIN_LVX_V2DI);
def_builtin ("__builtin_altivec_lvx_v4sf", v4sf_ftype_long_pcvoid,
Index: gcc/doc/extend.texi
===================================================================
--- gcc/doc/extend.texi (revision 258341)
+++ gcc/doc/extend.texi (working copy)
@@ -18396,6 +18396,10 @@ vector double vec_div (vector double, vector doubl
vector long vec_div (vector long, vector long);
vector unsigned long vec_div (vector unsigned long, vector unsigned long);
vector double vec_floor (vector double);
+vector __int128 vec_ld (int, const vector __int128 *);
+vector unsigned __int128 vec_ld (int, const vector unsigned __int128 *);
+vector __int128 vec_ld (int, const __int128 *);
+vector unsigned __int128 vec_ld (int, const unsigned __int128 *);
vector double vec_ld (int, const vector double *);
vector double vec_ld (int, const double *);
vector double vec_ldl (int, const vector double *);
Index: gcc/testsuite/gcc.target/powerpc/altivec-ld-1.c
===================================================================
--- gcc/testsuite/gcc.target/powerpc/altivec-ld-1.c (nonexistent)
+++ gcc/testsuite/gcc.target/powerpc/altivec-ld-1.c (working copy)
@@ -0,0 +1,67 @@
+/* { dg-do run { target powerpc*-*-* } } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-maltivec -O0 -Wall -Wno-deprecated" } */
+
+#include <altivec.h>
+#include <stdlib.h>
+
+static __vector __int128 v;
+static __vector __int128 *pv;
+
+static __vector unsigned __int128 uv;
+static __vector unsigned __int128 *puv;
+
+static __int128 i128;
+static __int128 *pi128;
+
+static unsigned __int128 u128;
+static unsigned __int128 *pu128;
+
+
+void
+doInitialization ()
+{
+ v[0] = -1;
+ pv = &v;
+
+ uv[0] = 0xcafebabe;
+ puv = &uv;
+
+ i128 = 0xfabeabe;
+ pi128 = &i128;
+
+ u128 = 0xabefabe;
+ pu128 = &u128;
+}
+
+int
+main (int argc, char *argv[])
+{
+ __vector __int128 loaded_v;
+ __vector unsigned __int128 loaded_uv;
+
+ /* Usage:
+ * <Type> result = vec_ld (int index, __vector <Type> v)
+ * is equivalent to:
+ * result = v [index];
+ */
+ doInitialization ();
+ loaded_v = vec_ld (0, pv);
+ if (loaded_v[0] != -1)
+ abort ();
+
+ loaded_uv = vec_ld (0, puv);
+ if (loaded_uv[0] != 0xcafebabe)
+ abort ();
+
+ loaded_v = vec_ld (0, pi128);
+ if (loaded_v[0] != 0xfabeabe)
+ abort ();
+
+ loaded_uv = vec_ld (0, pu128);
+ if (loaded_uv[0] != 0xabefabe)
+ abort ();
+
+ return 0;
+}
