Hi,
Add support for gimple folding of splat_u{8,16,32}.
Testcase coverage is primarily handled by existing tests
testsuite/gcc.target/powerpc/fold-vec-splat_*.c
One new test added to verify we continue to receive
an 'invalid argument, must be a 5-bit immediate' error
when we try to splat a non-constant value.
V2 updates include..
Use the gimple_convert() helper.
Use the build_vector_from_val() helper.
whitespace fix-ups.
Those changes actually simplify the code here significantly, which is good. :-)
Per comments from last iteration, regarding the early exit for
arg0 != INTEGER_CST, if I remove the early exit when arg0 is not constant,
the code appears to handle things OK, and the generated code looks
reasonable, but this is a behavior change with respect to when folding is
disabled, which is to error out with an ("argument 1 must be a 5-bit signed
literal") error. For that reason, I'm planning to leave that check in place.
I'll defer to Bill/Segher/David, etc on whether it would be appropriate to
change that behavior.
This intrinsic only takes INTegral types, so no need to check for FLOAT_CST.
(The other vec_splat* intrinsics will deal more with floats, those are later
in my queue).
Regtests across assorted power systems look clean.
OK for trunk?
Thanks,
-Will
[gcc]
2017-12-08 Will Schmidt <will_schm...@vnet.ibm.com>
* config/rs6000/rs6000.c (rs6000_gimple_fold_builtin): Add support for
early folding of splat_u{8,16,32}.
[testsuite]
2017-12-08 Will Schmidt <will_schm...@vnet.ibm.com>
* gcc.target/powerpc/fold-vec-splat-misc-invalid.c: New.
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 045a014..8972d80 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -16614,10 +16614,32 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
case VSX_BUILTIN_CMPLE_2DI:
case VSX_BUILTIN_CMPLE_U2DI:
fold_compare_helper (gsi, LE_EXPR, stmt);
return true;
+ /* flavors of vec_splat_[us]{8,16,32}. */
+ case ALTIVEC_BUILTIN_VSPLTISB:
+ case ALTIVEC_BUILTIN_VSPLTISH:
+ case ALTIVEC_BUILTIN_VSPLTISW:
+ {
+ arg0 = gimple_call_arg (stmt, 0);
+ lhs = gimple_call_lhs (stmt);
+ /* Only fold the vec_splat_*() if arg0 is constant. */
+ if (TREE_CODE (arg0) != INTEGER_CST)
+ return false;
+ gimple_seq stmts = NULL;
+ location_t loc = gimple_location (stmt);
+ tree splat_value = gimple_convert (&stmts, loc,
+ TREE_TYPE (TREE_TYPE (lhs)), arg0);
+ gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
+ tree splat_tree = build_vector_from_val (TREE_TYPE (lhs), splat_value);
+ g = gimple_build_assign (lhs, splat_tree);
+ gimple_set_location (g, gimple_location (stmt));
+ gsi_replace (gsi, g, true);
+ return true;
+ }
+
default:
if (TARGET_DEBUG_BUILTIN)
fprintf (stderr, "gimple builtin intrinsic not matched:%d %s %s\n",
fn_code, fn_name1, fn_name2);
break;
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-splat-misc-invalid.c
b/gcc/testsuite/gcc.target/powerpc/fold-vec-splat-misc-invalid.c
new file mode 100644
index 0000000..20f5b05
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-splat-misc-invalid.c
@@ -0,0 +1,33 @@
+/* Verify that overloaded built-ins for vec_splat_s8 and vec_splat_s16
+ generate errors as expected when we attempt to use invalid inputs. */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-mvsx -O2" } */
+
+#include <altivec.h>
+
+vector signed short
+testss_1 (unsigned int ui)
+{
+ return vec_splat_s16 (ui);/* { dg-error "argument 1 must be a 5-bit signed
literal" } */
+}
+
+vector unsigned short
+testss_2 (signed int si)
+{
+ return vec_splat_u16 (si);/* { dg-error "argument 1 must be a 5-bit signed
literal" } */
+}
+
+vector signed char
+testsc_1 (unsigned int ui)
+{
+ return vec_splat_s8 (ui); /* { dg-error "argument 1 must be a 5-bit signed
literal" } */
+}
+
+vector unsigned char
+testsc_2 (signed int si)
+{
+ return vec_splat_u8 (si);/* { dg-error "argument 1 must be a 5-bit signed
literal" } */
+}
+
