This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[PATCH, rs6000] gimple folding support for vec_pack and vec_unpack
- From: Will Schmidt <will_schmidt at vnet dot ibm dot com>
- To: Richard Biener <richard dot guenther at gmail dot com>, Segher Boessenkool <segher at kernel dot crashing dot org>, Bill Schmidt <wschmidt at linux dot vnet dot ibm dot com>, David Edelsohn <dje dot gcc at gmail dot com>
- Cc: GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: Mon, 09 Jul 2018 14:08:37 -0500
- Subject: [PATCH, rs6000] gimple folding support for vec_pack and vec_unpack
- Reply-to: will_schmidt at vnet dot ibm dot com
Hi,
Add support for gimple folding for vec_pack(), vec_unpackh() and
vec_unpackl().
Testcases for vec_pack are already in tree. Tests for vec_unpack
have been posted separately.
OK for trunk?
Thanks,
-Will
[gcc]
2018-07-09 Will Schmidt <will_schmidt@vnet.ibm.com>
* config/rs6000/rs6000.c (rs6000_gimple_fold_builtin):
Add support for gimple-folding of vec_pack() and vec_unpack()
intrinsics.
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 774c60a..1335661 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -16100,10 +16100,65 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
case VSX_BUILTIN_XXMRGHW_4SI:
case ALTIVEC_BUILTIN_VMRGHB:
case VSX_BUILTIN_VEC_MERGEH_V2DI:
fold_mergehl_helper (gsi, stmt, 0);
return true;
+
+ /* d = vec_pack (a, b) */
+ case P8V_BUILTIN_VPKUDUM:
+ case ALTIVEC_BUILTIN_VPKUHUM:
+ case ALTIVEC_BUILTIN_VPKUWUM:
+ {
+ arg0 = gimple_call_arg (stmt, 0);
+ arg1 = gimple_call_arg (stmt, 1);
+ lhs = gimple_call_lhs (stmt);
+ gimple *g = gimple_build_assign (lhs, VEC_PACK_TRUNC_EXPR, arg0, arg1);
+ gimple_set_location (g, gimple_location (stmt));
+ gsi_replace (gsi, g, true);
+ return true;
+ }
+
+ /* d = vec_unpackh (a) */
+ /* Note that the UNPACK_{HI,LO}_EXPR used in the gimple_build_assign call
+ in this code is sensitive to endian-ness, and needs to be inverted to
+ handle both LE and BE targets. */
+ case ALTIVEC_BUILTIN_VUPKHSB:
+ case ALTIVEC_BUILTIN_VUPKHSH:
+ case P8V_BUILTIN_VUPKHSW:
+ {
+ arg0 = gimple_call_arg (stmt, 0);
+ lhs = gimple_call_lhs (stmt);
+ if (BYTES_BIG_ENDIAN)
+ g = gimple_build_assign (lhs, VEC_UNPACK_HI_EXPR, arg0);
+ else
+ g = gimple_build_assign (lhs, VEC_UNPACK_LO_EXPR, arg0);
+ gimple_set_location (g, gimple_location (stmt));
+ gsi_replace (gsi, g, true);
+ return true;
+ }
+ /* d = vec_unpackl (a) */
+ case ALTIVEC_BUILTIN_VUPKLSB:
+ case ALTIVEC_BUILTIN_VUPKLSH:
+ case P8V_BUILTIN_VUPKLSW:
+ {
+ arg0 = gimple_call_arg (stmt, 0);
+ lhs = gimple_call_lhs (stmt);
+ if (BYTES_BIG_ENDIAN)
+ g = gimple_build_assign (lhs, VEC_UNPACK_LO_EXPR, arg0);
+ else
+ g = gimple_build_assign (lhs, VEC_UNPACK_HI_EXPR, arg0);
+ gimple_set_location (g, gimple_location (stmt));
+ gsi_replace (gsi, g, true);
+ return true;
+ }
+ /* There is no gimple type corresponding with pixel, so just return. */
+ case ALTIVEC_BUILTIN_VUPKHPX:
+ case ALTIVEC_BUILTIN_VUPKLPX:
+ {
+ return false;
+ }
+
default:
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "gimple builtin intrinsic not matched:%d %s %s\n",
fn_code, fn_name1, fn_name2);
break;