i386: Add variable vec_set for 32bit vectors [PR97194]

To generate sane code a SSE4.1 variable PBLENDV instruction is needed.

Also enable variable vec_set through vec_setm_operand predicate
for TARGET_SSE4_1 instead of TARGET_AVX2.  ix86_expand_vector_init_duplicate
is able to emulate vpbroadcast{b,w} with pxor/pshufb.

2021-07-06  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/97194
	* config/i386/predicates.md (vec_setm_operand): Enable
	register_operand for TARGET_SSE4_1.
	* config/i386/mmx.md (vec_setv2hi): Use vec_setm_operand
	as operand 2 predicate.  Call ix86_expand_vector_set_var
	for non-constant index operand.
	(vec_setv4qi): Use vec_setm_mmx_operand as operand 2 predicate.
	Call ix86_expand_vector_set_var for non-constant index operand.

gcc/testsuite/

	PR target/97194
	* gcc.target/i386/sse4_1-vec-set-1a.c: New test.
	* gcc.target/i386/sse4_1-vec-set-2a.c: Ditto.

4 files changed, 77 insertions, 7 deletions

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 4ead8be..7e83b64 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -3534,11 +3534,14 @@
 (define_expand "vec_setv2hi"
   [(match_operand:V2HI 0 "register_operand")
    (match_operand:HI 1 "register_operand")
-   (match_operand 2 "const_int_operand")]
+   (match_operand 2 "vec_setm_operand")]
   "TARGET_SSE2"
 {
-  ix86_expand_vector_set (false, operands[0], operands[1],
-			  INTVAL (operands[2]));
+  if (CONST_INT_P (operands[2]))
+    ix86_expand_vector_set (false, operands[0], operands[1],
+			    INTVAL (operands[2]));
+  else
+    ix86_expand_vector_set_var (operands[0], operands[1], operands[2]);
   DONE;
 })
 
@@ -3556,11 +3559,14 @@
 (define_expand "vec_setv4qi"
   [(match_operand:V4QI 0 "register_operand")
    (match_operand:QI 1 "register_operand")
-   (match_operand 2 "const_int_operand")]
+   (match_operand 2 "vec_setm_mmx_operand")]
   "TARGET_SSE4_1"
 {
-  ix86_expand_vector_set (false, operands[0], operands[1],
-			  INTVAL (operands[2]));
+  if (CONST_INT_P (operands[2]))
+    ix86_expand_vector_set (false, operands[0], operands[1],
+			    INTVAL (operands[2]));
+  else
+    ix86_expand_vector_set_var (operands[0], operands[1], operands[2]);
   DONE;
 })
 
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index c4b35c8..9488632 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -1023,7 +1023,7 @@
 ;; True for registers, or const_int_operand, used to vec_setm expander.
 (define_predicate "vec_setm_operand"
   (ior (and (match_operand 0 "register_operand")
-	    (match_test "TARGET_AVX2"))
+	    (match_test "TARGET_SSE4_1"))
        (match_code "const_int")))
 
 (define_predicate "vec_setm_mmx_operand"
diff --git a/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-1a.c b/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-1a.c
new file mode 100644
index 0000000..e2a67a6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-1a.c
@@ -0,0 +1,20 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-msse4.1 -O2" } */
+/* { dg-final { scan-assembler-times {(?n)v?pcmpeq[bwd]} 2 } } */
+/* { dg-final { scan-assembler-times {(?n)v?p?blendv} 2 } } */
+
+typedef char v4qi __attribute__ ((vector_size (4)));
+typedef short v2hi __attribute__ ((vector_size (4)));
+
+#define FOO(VTYPE, TYPE)			\
+  VTYPE						\
+  __attribute__ ((noipa))			\
+  foo_##VTYPE (VTYPE a, TYPE b, unsigned int c)	\
+  {						\
+    a[c] = b;					\
+    return a;					\
+  }						\
+
+FOO (v4qi, char);
+
+FOO (v2hi, short);
diff --git a/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-2a.c b/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-2a.c
new file mode 100644
index 0000000..5a945be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/sse4_1-vec-set-2a.c
@@ -0,0 +1,44 @@
+/* { dg-do run { target { ! ia32 } } } */
+/* { dg-require-effective-target sse4 } */
+/* { dg-options "-O2 -msse4.1" } */
+
+
+#ifndef CHECK
+#define CHECK "sse4_1-check.h"
+#endif
+
+#ifndef TEST
+#define TEST sse4_1_test
+#endif
+
+#include CHECK
+
+#include "sse4_1-vec-set-1a.c"
+
+#define CALC_TEST(vtype, type, N, idx)				\
+do								\
+  {								\
+    int i,val = idx * idx - idx * 3 + 16;			\
+    type res[N],exp[N];						\
+    vtype resv;							\
+    for (i = 0; i < N; i++)					\
+      {								\
+	res[i] = i * i - i * 3 + 15;				\
+	exp[i] = res[i];					\
+      }								\
+    exp[idx] = val;						\
+    resv = foo_##vtype (*(vtype *)&res[0], val, idx);		\
+    for (i = 0; i < N; i++)					\
+      {								\
+	if (resv[i] != exp[i])					\
+	  abort ();						\
+      }								\
+  }								\
+while (0)
+
+static void
+TEST (void)
+{
+  CALC_TEST (v4qi, char, 4, 2);
+  CALC_TEST (v2hi, short, 2, 1);
+}