i386: Emulate MMX ssse3_ph<plusminus_mnemonic>dv2si3 with SSE

Emulate MMX ssse3_ph<plusminus_mnemonic>dv2si3 with SSE by moving bits
64:95 to bits 32:63 in SSE register.  Only SSE register source operand
is allowed.

	PR target/89021
	* config/i386/sse.md (ssse3_ph<plusminus_mnemonic>dv2si3):
	Changed to define_insn_and_split to support SSE emulation.

From-SVN: r271242

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index c0861717ca1aa3b04c4574851799e55b05d32302..80b83ccf35671305fccc9675af7ccafb44782c46 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2019-05-15  H.J. Lu  <hongjiu.lu@intel.com>
+
+       PR target/89021
+       * config/i386/sse.md (ssse3_ph<plusminus_mnemonic>dv2si3):
+       Changed to define_insn_and_split to support SSE emulation.
+
 2019-05-15  H.J. Lu  <hongjiu.lu@intel.com>
 
        PR target/89021

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index bcdd8f9a6b59b7c29e02a449b82d6b520f5e8842..0a0b8a4f028c87b5c82f621716365edc10a67063 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -15814,26 +15814,44 @@
    (set_attr "prefix" "orig,vex")
    (set_attr "mode" "TI")])
 
-(define_insn "ssse3_ph<plusminus_mnemonic>dv2si3"
-  [(set (match_operand:V2SI 0 "register_operand" "=y")
+(define_insn_and_split "ssse3_ph<plusminus_mnemonic>dv2si3"
+  [(set (match_operand:V2SI 0 "register_operand" "=y,x,Yv")
        (vec_concat:V2SI
          (plusminus:SI
            (vec_select:SI
-             (match_operand:V2SI 1 "register_operand" "0")
+             (match_operand:V2SI 1 "register_operand" "0,0,Yv")
              (parallel [(const_int 0)]))
            (vec_select:SI (match_dup 1) (parallel [(const_int 1)])))
          (plusminus:SI
            (vec_select:SI
-             (match_operand:V2SI 2 "nonimmediate_operand" "ym")
+             (match_operand:V2SI 2 "register_mmxmem_operand" "ym,x,Yv")
              (parallel [(const_int 0)]))
            (vec_select:SI (match_dup 2) (parallel [(const_int 1)])))))]
-  "TARGET_SSSE3"
-  "ph<plusminus_mnemonic>d\t{%2, %0|%0, %2}"
-  [(set_attr "type" "sseiadd")
+  "(TARGET_MMX || TARGET_MMX_WITH_SSE) && TARGET_SSSE3"
+  "@
+   ph<plusminus_mnemonic>d\t{%2, %0|%0, %2}
+   #
+   #"
+  "TARGET_MMX_WITH_SSE && reload_completed"
+  [(const_int 0)]
+{
+  /* Generate SSE version of the operation.  */
+  rtx op0 = lowpart_subreg (V4SImode, operands[0],
+                           GET_MODE (operands[0]));
+  rtx op1 = lowpart_subreg (V4SImode, operands[1],
+                           GET_MODE (operands[1]));
+  rtx op2 = lowpart_subreg (V4SImode, operands[2],
+                           GET_MODE (operands[2]));
+  emit_insn (gen_ssse3_ph<plusminus_mnemonic>dv4si3 (op0, op1, op2));
+  ix86_move_vector_high_sse_to_mmx (op0);
+  DONE;
+}
+  [(set_attr "mmx_isa" "native,x64_noavx,x64_avx")
+   (set_attr "type" "sseiadd")
    (set_attr "atom_unit" "complex")
    (set_attr "prefix_extra" "1")
    (set (attr "prefix_rex") (symbol_ref "x86_extended_reg_mentioned_p (insn)"))
-   (set_attr "mode" "DI")])
+   (set_attr "mode" "DI,TI,TI")])
 
 (define_insn "avx2_pmaddubsw256"
   [(set (match_operand:V16HI 0 "register_operand" "=x,v")