[COMMITTED] i386: Account for the memory read in V*QImode multiplication sequences

[Uros Bizjak via Gcc-patches]

Add the cost of a memory read to the cost of V*QImode vector mult sequences.

gcc/ChangeLog:

    * config/i386/i386.cc (ix86_multiplication_cost): Add
    the cost of a memory read to the cost of V?QImode sequences.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Uros.

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 6a4b3326219..a36e625342d 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -20463,27 +20463,42 @@ ix86_multiplication_cost (const struct 
processor_costs *cost,
       {
       case V4QImode:
       case V8QImode:
-       /* Partial V*QImode is emulated with 4-5 insns.  */
-       if ((TARGET_AVX512BW && TARGET_AVX512VL) || TARGET_XOP)
+       /* Partial V*QImode is emulated with 4-6 insns.  */
+       if (TARGET_AVX512BW && TARGET_AVX512VL)
          return ix86_vec_cost (mode, cost->mulss + cost->sse_op * 3);
+       else if (TARGET_AVX2)
+         return ix86_vec_cost (mode, cost->mulss + cost->sse_op * 5);
+       else if (TARGET_XOP)
+         return (ix86_vec_cost (mode, cost->mulss + cost->sse_op * 3)
+                 + cost->sse_load[2]);
        else
-         return ix86_vec_cost (mode, cost->mulss + cost->sse_op * 4);
+         return (ix86_vec_cost (mode, cost->mulss + cost->sse_op * 4)
+                 + cost->sse_load[2]);
 
       case V16QImode:
        /* V*QImode is emulated with 4-11 insns.  */
        if (TARGET_AVX512BW && TARGET_AVX512VL)
          return ix86_vec_cost (mode, cost->mulss + cost->sse_op * 3);
+       else if (TARGET_AVX2)
+         return ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 8);
        else if (TARGET_XOP)
-         return ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 5);
-       /* FALLTHRU */
+         return (ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 5)
+                 + cost->sse_load[2]);
+       else
+         return (ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 7)
+                 + cost->sse_load[2]);
+
       case V32QImode:
-       if (TARGET_AVX512BW && mode == V32QImode)
+       if (TARGET_AVX512BW)
          return ix86_vec_cost (mode, cost->mulss + cost->sse_op * 3);
        else
-         return ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 7);
+         return (ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 7)
+                 + cost->sse_load[3] * 2);
 
       case V64QImode:
-       return ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 9);
+       return (ix86_vec_cost (mode, cost->mulss * 2 + cost->sse_op * 9)
+               + cost->sse_load[3] * 2
+               + cost->sse_load[4] * 2);
 
       case V4SImode:
        /* pmulld is used in this case. No emulation is needed.  */