https://gcc.gnu.org/g:1e7022f2b9e09fa3bf98d4cc7333d5cfab89ba42
commit 1e7022f2b9e09fa3bf98d4cc7333d5cfab89ba42
Author: Michael Meissner <meiss...@linux.ibm.com>
Date: Wed Aug 14 02:58:03 2024 -0400
Optimize splat of a V2DF/V2DI extract with constant element
2024-08-14 Michael Meissner <meiss...@linux.ibm.com>
gcc/
* config/rs6000/vsx.md (vsx_splat_extract_<mode>): New insn.
gcc/testsuite/
* gcc.target/powerpc/pr99293.c: New test.
Diff:
---
gcc/config/rs6000/vsx.md | 18 ++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/pr99293.c | 22 ++++++++++++++++++++++
2 files changed, 40 insertions(+)
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 7892477fa922..6e8cd041f3b8 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -4797,6 +4797,24 @@
"lxvdsx %x0,%y1"
[(set_attr "type" "vecload")])
+;; Optimize SPLAT of an extract from a V2DF/V2DI vector with a constant element
+(define_insn "*vsx_splat_extract_<mode>"
+ [(set (match_operand:VSX_D 0 "vsx_register_operand" "=wa")
+ (vec_duplicate:VSX_D
+ (vec_select:<VEC_base>
+ (match_operand:VSX_D 1 "vsx_register_operand" "wa")
+ (parallel [(match_operand 2 "const_0_to_1_operand" "n")]))))]
+ "VECTOR_MEM_VSX_P (<MODE>mode)"
+{
+ int which_word = INTVAL (operands[2]);
+ if (!BYTES_BIG_ENDIAN)
+ which_word = 1 - which_word;
+
+ operands[3] = GEN_INT (which_word ? 3 : 0);
+ return "xxpermdi %x0,%x1,%x1,%3";
+}
+ [(set_attr "type" "vecperm")])
+
;; V4SI splat support
(define_insn "vsx_splat_v4si"
[(set (match_operand:V4SI 0 "vsx_register_operand" "=wa,wa")
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99293.c
b/gcc/testsuite/gcc.target/powerpc/pr99293.c
new file mode 100644
index 000000000000..20adc1f27f65
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr99293.c
@@ -0,0 +1,22 @@
+/* { dg-do compile { target powerpc*-*-* } } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx" } */
+
+/* Test for PR 99263, which wants to do:
+ __builtin_vec_splats (__builtin_vec_extract (v, n))
+
+ where v is a V2DF or V2DI vector and n is either 0 or 1. Previously the
+ compiler would do a direct move to the GPR registers to select the item and
a
+ direct move from the GPR registers to do the splat. */
+
+vector long long splat_dup_l_0 (vector long long v)
+{
+ return __builtin_vec_splats (__builtin_vec_extract (v, 0));
+}
+
+vector long long splat_dup_l_1 (vector long long v)
+{
+ return __builtin_vec_splats (__builtin_vec_extract (v, 1));
+}
+
+/* { dg-final { scan-assembler-times "xxpermdi" 2 } } */
