PR 99293: Optimize splat of vec_extract for V2DI/V2DF.
We had optimizations for splat of a vector extract for the other vector
types, but we missed having one for V2DI and V2DF. This patch adds a
combiner insn to do this optimization.
In looking at the source, we had similar optimizations for V4SI and V4SF
extract and splats, but we missed doing V2DI/V2DF.
Without the patch for the code:
vector long long splat_dup_l_0 (vector long long v)
{
return __builtin_vec_splats (__builtin_vec_extract (v, 0));
}
the compiler generates (on a little endian power9):
splat_dup_l_0:
mfvsrld 9,34
mtvsrdd 34,9,9
blr
Now it generates:
splat_dup_l_0:
xxpermdi 34,34,34,3
blr
I have tested this on:
* Little endian power9 running Linux using --with-code=power9
* Big endian power8 running Linux using --with-code=power8
* Little endian power10 running Linux using --with-code=power10
There were no regressions in the test suites (including 32-bit on big endian).
Can I check this into the master branch?
Can I check this into the open branches (GCC-11, GCC-10) after a soak-in period
if there were no errors during the soak-in period?
gcc/
2021-06-04 Michael Meissner <meiss...@linux.ibm.com>
PR target/99293
* config/rs6000/vsx.md (vsx_splat_extract_<mode): New insn.
gcc/testsuite/
2021-06-04 Michael Meissner <meiss...@linux.ibm.com>
PR target/99293
* gcc.target/powerpc/pr99293.c: New test.
---
gcc/config/rs6000/vsx.md | 18 ++++++++++++++++++
gcc/testsuite/gcc.target/powerpc/pr99293.c | 22 ++++++++++++++++++++++
2 files changed, 40 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/powerpc/pr99293.c
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index b49d5b44573..ecad45a43d1 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -5020,6 +5020,24 @@ (define_insn "vsx_splat_<mode>_mem"
"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:<VS_scalar>
+ (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" "=we,we")
diff --git a/gcc/testsuite/gcc.target/powerpc/pr99293.c
b/gcc/testsuite/gcc.target/powerpc/pr99293.c
new file mode 100644
index 00000000000..20adc1f27f6
--- /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 } } */
--
2.31.1
--
Michael Meissner, IBM
IBM, M/S 2506R, 550 King Street, Littleton, MA 01460-6245, USA
email: meiss...@linux.ibm.com, phone: +1 (978) 899-4797
