i386: Add combiner splitter to optimize V2SImode memory rotation [PR96166]

Since the x86 backend enabled V2SImode vectorization (with
TARGET_MMX_WITH_SSE), slp vectorization can kick in and emit
        movq    (%rdi), %xmm1
        pshufd  $225, %xmm1, %xmm0
        movq    %xmm0, (%rdi)
instead of
        rolq    $32, (%rdi)
we used to emit (or emit when slp vectorization is disabled).
I think the rotate is both smaller and faster, so this patch adds
a combiner splitter to optimize that back.

2021-02-13  Jakub Jelinek  <jakub@redhat.com>

	PR target/96166
	* config/i386/mmx.md (*mmx_pshufd_1): Add a combine splitter for
	swap of V2SImode elements in memory into DImode memory rotate by 32.

	* gcc.target/i386/pr96166.c: New test.

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 9e5a4d1f2834b969929049967d1b6b139e0138fd..0f51e616755dffe6550e2ddc602ef48f489dba7b 100644 (file)
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -2076,6 +2076,17 @@
    (set_attr "length_immediate" "1")
    (set_attr "mode" "TI")])
 
+;; Optimize V2SImode load from memory, swapping the elements and
+;; storing back into the memory into DImode rotate of the memory by 32.
+(define_split
+  [(set (match_operand:V2SI 0 "memory_operand")
+       (vec_select:V2SI (match_dup 0)
+         (parallel [(const_int 1) (const_int 0)])))]
+  "TARGET_64BIT && (TARGET_READ_MODIFY_WRITE || optimize_insn_for_size_p ())"
+  [(set (match_dup 0)
+       (rotate:DI (match_dup 0) (const_int 32)))]
+  "operands[0] = adjust_address (operands[0], DImode, 0);")
+
 (define_insn "mmx_pswapdv2si2"
   [(set (match_operand:V2SI 0 "register_operand" "=y,Yv")
        (vec_select:V2SI

diff --git a/gcc/testsuite/gcc.target/i386/pr96166.c b/gcc/testsuite/gcc.target/i386/pr96166.c
new file mode 100644 (file)
index 0000000..4d02022
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr96166.c
@@ -0,0 +1,21 @@
+/* PR target/96166 */
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O3 -mtune=generic -masm=att" } */
+/* { dg-final { scan-assembler "rolq\\s\\\$32, \\\(%\[re]di\\\)" } } */
+
+static inline void
+swap (int *x, int *y)
+{
+  int tmp = *x;
+  *x = *y;
+  *y = tmp;
+}
+
+void
+bar (int (*x)[2])
+{
+  int y[2];
+  __builtin_memcpy (&y, x, sizeof *x);
+  swap (&y[0], &y[1]);
+  __builtin_memcpy (x, &y, sizeof *x);
+}