[PATCH] Add VEC_UNPACK_{HI,LO}_EXPR support for V{32QI,16HI,8SI} with AVX2

[Jakub Jelinek]

Hi!

This patch allows to vectorize
char a[1024], c[1024];
long long b[1024];
void
foo (void)
{
  int i;
  for (i = 0; i < 1024; i++)
    b[i] = a[i] + 3 * c[i];
}
using 32-byte vectors with -mavx2.  Bootstrapped/regtested
on x86_64-linux and i686-linux, ok for trunk?

2011-10-12  Jakub Jelinek  <ja...@redhat.com>

        * config/i386/sse.md (vec_unpacks_lo_<mode>,
        vec_unpacks_hi_<mode>, vec_unpacku_lo_<mode>,
        vec_unpacku_hi_<mode>): Change VI124_128 mode to
        VI124_AVX2.
        * config/i386/i386.c (ix86_expand_sse_unpack): Handle
        V32QImode, V16HImode and V8SImode for TARGET_AVX2.

--- gcc/config/i386/sse.md.jj   2011-10-12 15:42:12.000000000 +0200
+++ gcc/config/i386/sse.md      2011-10-12 16:16:49.000000000 +0200
@@ -7536,25 +7536,25 @@ (define_insn "vec_concatv2di"
 
 (define_expand "vec_unpacks_lo_<mode>"
   [(match_operand:<sseunpackmode> 0 "register_operand" "")
-   (match_operand:VI124_128 1 "register_operand" "")]
+   (match_operand:VI124_AVX2 1 "register_operand" "")]
   "TARGET_SSE2"
   "ix86_expand_sse_unpack (operands, false, false); DONE;")
 
 (define_expand "vec_unpacks_hi_<mode>"
   [(match_operand:<sseunpackmode> 0 "register_operand" "")
-   (match_operand:VI124_128 1 "register_operand" "")]
+   (match_operand:VI124_AVX2 1 "register_operand" "")]
   "TARGET_SSE2"
   "ix86_expand_sse_unpack (operands, false, true); DONE;")
 
 (define_expand "vec_unpacku_lo_<mode>"
   [(match_operand:<sseunpackmode> 0 "register_operand" "")
-   (match_operand:VI124_128 1 "register_operand" "")]
+   (match_operand:VI124_AVX2 1 "register_operand" "")]
   "TARGET_SSE2"
   "ix86_expand_sse_unpack (operands, true, false); DONE;")
 
 (define_expand "vec_unpacku_hi_<mode>"
   [(match_operand:<sseunpackmode> 0 "register_operand" "")
-   (match_operand:VI124_128 1 "register_operand" "")]
+   (match_operand:VI124_AVX2 1 "register_operand" "")]
   "TARGET_SSE2"
   "ix86_expand_sse_unpack (operands, true, true); DONE;")
 
--- gcc/config/i386/i386.c.jj   2011-10-12 14:19:26.000000000 +0200
+++ gcc/config/i386/i386.c      2011-10-12 16:15:50.000000000 +0200
@@ -19658,9 +19658,38 @@ ix86_expand_sse_unpack (rtx operands[2],
   if (TARGET_SSE4_1)
     {
       rtx (*unpack)(rtx, rtx);
+      rtx (*extract)(rtx, rtx) = NULL;
+      enum machine_mode halfmode = BLKmode;
 
       switch (imode)
        {
+       case V32QImode:
+         if (unsigned_p)
+           unpack = gen_avx2_zero_extendv16qiv16hi2;
+         else
+           unpack = gen_avx2_sign_extendv16qiv16hi2;
+         halfmode = V16QImode;
+         extract
+           = high_p ? gen_vec_extract_hi_v32qi : gen_vec_extract_lo_v32qi;
+         break;
+       case V16HImode:
+         if (unsigned_p)
+           unpack = gen_avx2_zero_extendv8hiv8si2;
+         else
+           unpack = gen_avx2_sign_extendv8hiv8si2;
+         halfmode = V8HImode;
+         extract
+           = high_p ? gen_vec_extract_hi_v16hi : gen_vec_extract_lo_v16hi;
+         break;
+       case V8SImode:
+         if (unsigned_p)
+           unpack = gen_avx2_zero_extendv4siv4di2;
+         else
+           unpack = gen_avx2_sign_extendv4siv4di2;
+         halfmode = V4SImode;
+         extract
+           = high_p ? gen_vec_extract_hi_v8si : gen_vec_extract_lo_v8si;
+         break;
        case V16QImode:
          if (unsigned_p)
            unpack = gen_sse4_1_zero_extendv8qiv8hi2;
@@ -19683,7 +19712,12 @@ ix86_expand_sse_unpack (rtx operands[2],
          gcc_unreachable ();
        }
 
-      if (high_p)
+      if (GET_MODE_SIZE (imode) == 32)
+       {
+         tmp = gen_reg_rtx (halfmode);
+         emit_insn (extract (tmp, operands[1]));
+       }
+      else if (high_p)
        {
          /* Shift higher 8 bytes to lower 8 bytes.  */
          tmp = gen_reg_rtx (imode);

        Jakub