i386: Add insert and extract patterns for 4-byte vectors [PR100637]

The patch introduces insert and extract patterns for 4-byte vectors.
It effectively only emits PINSR and PEXTR instructions when available,
otherwise falls back to generic code that emulates these instructions
via inserts, extracts, logic operations and shifts in integer registers.

Please note that generic fallback produces better code than the current
approach of constructing new vector in memory (due to store forwarding stall)
so also enable QImode 8-byte vector inserts only with TARGET_SSE4_1.

2021-06-03  Uroš Bizjak  <ubizjak@gmail.com>

gcc/
	PR target/100637
	* config/i386/i386-expand.c (ix86_expand_vector_set):
	Handle V2HI and V4QI modes.
	(ix86_expand_vector_extract): Ditto.
	* config/i386/mmx.md (*pinsrw): New insn pattern.
	(*pinsrb): Ditto.
	(*pextrw): Ditto.
	(*pextrw_zext): Ditto.
	(*pextrb): Ditto.
	(*pextrb_zext): Ditto.
	(vec_setv2hi): New expander.
	(vec_extractv2hihi): Ditto.
	(vec_setv4qi): Ditto.
	(vec_extractv4qiqi): Ditto.

	(vec_setv8qi): Enable only for TARGET_SSE4_1.
	(vec_extractv8qiqi): Ditto.

gcc/testsuite/

	PR target/100637
	* gcc.target/i386/vperm-v2hi.c: New test.
	* gcc.target/i386/vperm-v4qi.c: Ditto.

4 files changed, 268 insertions, 2 deletions

diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index 4185f58..eb7cdb0 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -14968,6 +14968,7 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
       return;
 
     case E_V8HImode:
+    case E_V2HImode:
       use_vec_merge = TARGET_SSE2;
       break;
     case E_V4HImode:
@@ -14975,6 +14976,7 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
       break;
 
     case E_V16QImode:
+    case E_V4QImode:
       use_vec_merge = TARGET_SSE4_1;
       break;
 
@@ -15274,6 +15276,7 @@ ix86_expand_vector_extract (bool mmx_ok, rtx target, rtx vec, int elt)
       break;
 
     case E_V8HImode:
+    case E_V2HImode:
       use_vec_extr = TARGET_SSE2;
       break;
     case E_V4HImode:
@@ -15294,6 +15297,9 @@ ix86_expand_vector_extract (bool mmx_ok, rtx target, rtx vec, int elt)
 	  return;
 	}
       break;
+    case E_V4QImode:
+      use_vec_extr = TARGET_SSE4_1;
+      break;
 
     case E_V8SFmode:
       if (TARGET_AVX)
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index f39e062..914e5e9 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -3092,7 +3092,7 @@
   [(match_operand:V8QI 0 "register_operand")
    (match_operand:QI 1 "register_operand")
    (match_operand 2 "const_int_operand")]
-  "TARGET_MMX || TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE"
 {
   ix86_expand_vector_set (TARGET_MMX_WITH_SSE, operands[0], operands[1],
 			  INTVAL (operands[2]));
@@ -3103,7 +3103,7 @@
   [(match_operand:QI 0 "register_operand")
    (match_operand:V8QI 1 "register_operand")
    (match_operand 2 "const_int_operand")]
-  "TARGET_MMX || TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE"
 {
   ix86_expand_vector_extract (TARGET_MMX_WITH_SSE, operands[0],
 			      operands[1], INTVAL (operands[2]));
@@ -3120,6 +3120,178 @@
   DONE;
 })
 
+(define_insn "*pinsrw"
+  [(set (match_operand:V2HI 0 "register_operand" "=x,YW")
+        (vec_merge:V2HI
+          (vec_duplicate:V2HI
+            (match_operand:HI 2 "nonimmediate_operand" "rm,rm"))
+	  (match_operand:V2HI 1 "register_operand" "0,YW")
+          (match_operand:SI 3 "const_int_operand")))]
+  "TARGET_SSE2
+   && ((unsigned) exact_log2 (INTVAL (operands[3]))
+       < GET_MODE_NUNITS (V2HImode))"
+{
+  operands[3] = GEN_INT (exact_log2 (INTVAL (operands[3])));
+  switch (which_alternative)
+    {
+    case 1:
+      if (MEM_P (operands[2]))
+	return "vpinsrw\t{%3, %2, %1, %0|%0, %1, %2, %3}";
+      else
+	return "vpinsrw\t{%3, %k2, %1, %0|%0, %1, %k2, %3}";
+    case 0:
+      if (MEM_P (operands[2]))
+	return "pinsrw\t{%3, %2, %0|%0, %2, %3}";
+      else
+	return "pinsrw\t{%3, %k2, %0|%0, %k2, %3}";
+    default:
+      gcc_unreachable ();
+    }
+}
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sselog")
+   (set_attr "length_immediate" "1")
+   (set_attr "mode" "TI")])
+
+(define_insn "*pinsrb"
+  [(set (match_operand:V4QI 0 "register_operand" "=x,YW")
+        (vec_merge:V4QI
+          (vec_duplicate:V4QI
+            (match_operand:QI 2 "nonimmediate_operand" "rm,rm"))
+	  (match_operand:V4QI 1 "register_operand" "0,YW")
+          (match_operand:SI 3 "const_int_operand")))]
+  "TARGET_SSE4_1
+   && ((unsigned) exact_log2 (INTVAL (operands[3]))
+       < GET_MODE_NUNITS (V4QImode))"
+{
+  operands[3] = GEN_INT (exact_log2 (INTVAL (operands[3])));
+  switch (which_alternative)
+    {
+    case 1:
+      if (MEM_P (operands[2]))
+	return "vpinsrb\t{%3, %2, %1, %0|%0, %1, %2, %3}";
+      else
+	return "vpinsrb\t{%3, %k2, %1, %0|%0, %1, %k2, %3}";
+    case 0:
+      if (MEM_P (operands[2]))
+	return "pinsrb\t{%3, %2, %0|%0, %2, %3}";
+      else
+	return "pinsrb\t{%3, %k2, %0|%0, %k2, %3}";
+    default:
+      gcc_unreachable ();
+    }
+}
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sselog")
+   (set_attr "prefix_data16" "1")
+   (set_attr "prefix_extra" "1")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "orig,vex")
+   (set_attr "mode" "TI")])
+
+(define_insn "*pextrw"
+  [(set (match_operand:HI 0 "register_sse4nonimm_operand" "=r,m")
+	(vec_select:HI
+	  (match_operand:V2HI 1 "register_operand" "YW,YW")
+	  (parallel [(match_operand:SI 2 "const_0_to_1_operand" "n,n")])))]
+  "TARGET_SSE2"
+  "@
+   %vpextrw\t{%2, %1, %k0|%k0, %1, %2}
+   %vpextrw\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,sse4")
+   (set_attr "type" "sselog1")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "TI")])
+
+(define_insn "*pextrw_zext"
+  [(set (match_operand:SWI48 0 "register_operand" "=r")
+	(zero_extend:SWI48
+	  (vec_select:HI
+	    (match_operand:V2HI 1 "register_operand" "YW")
+	    (parallel [(match_operand:SI 2 "const_0_to_1_operand" "n")]))))]
+  "TARGET_SSE2"
+  "%vpextrw\t{%2, %1, %k0|%k0, %1, %2}"
+  [(set_attr "type" "sselog1")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "TI")])
+
+(define_insn "*pextrb"
+  [(set (match_operand:QI 0 "nonimmediate_operand" "=r,m")
+	(vec_select:QI
+	  (match_operand:V4QI 1 "register_operand" "YW,YW")
+	  (parallel [(match_operand:SI 2 "const_0_to_3_operand" "n,n")])))]
+  "TARGET_SSE4_1"
+  "@
+   %vpextrb\t{%2, %1, %k0|%k0, %1, %2}
+   %vpextrb\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "type" "sselog1")
+   (set_attr "prefix_data16" "1")
+   (set_attr "prefix_extra" "1")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "TI")])
+
+(define_insn "*pextrb_zext"
+  [(set (match_operand:SWI248 0 "register_operand" "=r")
+	(zero_extend:SWI248
+	  (vec_select:QI
+	    (match_operand:V4QI 1 "register_operand" "YW")
+	    (parallel [(match_operand:SI 2 "const_0_to_3_operand" "n")]))))]
+  "TARGET_SSE4_1"
+  "%vpextrb\t{%2, %1, %k0|%k0, %1, %2}"
+  [(set_attr "type" "sselog1")
+   (set_attr "prefix_data16" "1")
+   (set_attr "prefix_extra" "1")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "TI")])
+
+(define_expand "vec_setv2hi"
+  [(match_operand:V2HI 0 "register_operand")
+   (match_operand:HI 1 "register_operand")
+   (match_operand 2 "const_int_operand")]
+  "TARGET_SSE2"
+{
+  ix86_expand_vector_set (false, operands[0], operands[1],
+			  INTVAL (operands[2]));
+  DONE;
+})
+
+(define_expand "vec_extractv2hihi"
+  [(match_operand:HI 0 "register_operand")
+   (match_operand:V2HI 1 "register_operand")
+   (match_operand 2 "const_int_operand")]
+  "TARGET_SSE2"
+{
+  ix86_expand_vector_extract (false, operands[0],
+			      operands[1], INTVAL (operands[2]));
+  DONE;
+})
+
+(define_expand "vec_setv4qi"
+  [(match_operand:V4QI 0 "register_operand")
+   (match_operand:QI 1 "register_operand")
+   (match_operand 2 "const_int_operand")]
+  "TARGET_SSE4_1"
+{
+  ix86_expand_vector_set (false, operands[0], operands[1],
+			  INTVAL (operands[2]));
+  DONE;
+})
+
+(define_expand "vec_extractv4qiqi"
+  [(match_operand:QI 0 "register_operand")
+   (match_operand:V4QI 1 "register_operand")
+   (match_operand 2 "const_int_operand")]
+  "TARGET_SSE4_1"
+{
+  ix86_expand_vector_extract (false, operands[0],
+			      operands[1], INTVAL (operands[2]));
+  DONE;
+})
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
 ;; Miscellaneous
diff --git a/gcc/testsuite/gcc.target/i386/vperm-v2hi.c b/gcc/testsuite/gcc.target/i386/vperm-v2hi.c
new file mode 100644
index 0000000..0af94f2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vperm-v2hi.c
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+/* { dg-options "-O -msse2" } */
+/* { dg-require-effective-target sse2 } */
+
+#include "isa-check.h"
+#include "sse-os-support.h"
+
+typedef short S;
+typedef short V __attribute__((vector_size(4)));
+typedef short IV __attribute__((vector_size(4)));
+typedef union { S s[2]; V v; } U;
+
+static U i[2], b, c;
+
+extern int memcmp (const void *, const void *, __SIZE_TYPE__);
+#define assert(T) ((T) || (__builtin_trap (), 0))
+
+#define TEST(E0, E1) \
+  b.v = __builtin_shuffle (i[0].v, i[1].v, (IV){E0, E1}); \
+  c.s[0] = i[0].s[E0]; \
+  c.s[1] = i[0].s[E1]; \
+  __asm__("" : : : "memory"); \
+  assert (memcmp (&b, &c, sizeof(c)) == 0);
+
+#include "vperm-2-2.inc"
+
+int main()
+{
+  check_isa ();
+
+  if (!sse_os_support ())
+    exit (0);
+
+  i[0].s[0] = 0;
+  i[0].s[1] = 1;
+  i[0].s[2] = 2;
+  i[0].s[3] = 3;
+
+  check();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/i386/vperm-v4qi.c b/gcc/testsuite/gcc.target/i386/vperm-v4qi.c
new file mode 100644
index 0000000..57fa547
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vperm-v4qi.c
@@ -0,0 +1,47 @@
+/* { dg-do run } */
+/* { dg-options "-O -msse2" } */
+/* { dg-require-effective-target sse2 } */
+
+#include "isa-check.h"
+#include "sse-os-support.h"
+
+typedef char S;
+typedef char V __attribute__((vector_size(4)));
+typedef char IV __attribute__((vector_size(4)));
+typedef union { S s[4]; V v; } U;
+
+static U i[2], b, c;
+
+extern int memcmp (const void *, const void *, __SIZE_TYPE__);
+#define assert(T) ((T) || (__builtin_trap (), 0))
+
+#define TEST(E0, E1, E2, E3) \
+  b.v = __builtin_shuffle (i[0].v, i[1].v, (IV){E0, E1, E2, E3}); \
+  c.s[0] = i[0].s[E0]; \
+  c.s[1] = i[0].s[E1]; \
+  c.s[2] = i[0].s[E2]; \
+  c.s[3] = i[0].s[E3]; \
+  __asm__("" : : : "memory"); \
+  assert (memcmp (&b, &c, sizeof(c)) == 0);
+
+#include "vperm-4-2.inc"
+
+int main()
+{
+  check_isa ();
+
+  if (!sse_os_support ())
+    exit (0);
+
+  i[0].s[0] = 0;
+  i[0].s[1] = 1;
+  i[0].s[2] = 2;
+  i[0].s[3] = 3;
+  i[0].s[4] = 4;
+  i[0].s[5] = 5;
+  i[0].s[6] = 6;
+  i[0].s[7] = 7;
+
+  check();
+  return 0;
+}