[PATCH 32/46] i386: Emulate MMX ssse3_pmaddubsw with SSE

[H.J. Lu]

Emulate MMX ssse3_pmaddubsw with SSE.  Only SSE register source operand
is allowed.

        PR target/89021
        * config/i386/sse.md (ssse3_pmaddubsw): Add SSE emulation.
---
 gcc/config/i386/sse.md | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index b06e105e379..7c066a2cdc5 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -15658,17 +15658,17 @@
    (set_attr "mode" "TI")])
 
 (define_insn "ssse3_pmaddubsw"
-  [(set (match_operand:V4HI 0 "register_operand" "=y")
+  [(set (match_operand:V4HI 0 "register_operand" "=y,Yx,Yy")
        (ss_plus:V4HI
          (mult:V4HI
            (zero_extend:V4HI
              (vec_select:V4QI
-               (match_operand:V8QI 1 "register_operand" "0")
+               (match_operand:V8QI 1 "register_operand" "0,0,Yy")
                (parallel [(const_int 0) (const_int 2)
                           (const_int 4) (const_int 6)])))
            (sign_extend:V4HI
              (vec_select:V4QI
-               (match_operand:V8QI 2 "nonimmediate_operand" "ym")
+               (match_operand:V8QI 2 "nonimmediate_operand" "ym,Yx,Yy")
                (parallel [(const_int 0) (const_int 2)
                           (const_int 4) (const_int 6)]))))
          (mult:V4HI
@@ -15681,12 +15681,16 @@
                (parallel [(const_int 1) (const_int 3)
                           (const_int 5) (const_int 7)]))))))]
   "TARGET_SSSE3"
-  "pmaddubsw\t{%2, %0|%0, %2}"
-  [(set_attr "type" "sseiadd")
+  "@
+   pmaddubsw\t{%2, %0|%0, %2}
+   pmaddubsw\t{%2, %0|%0, %2}
+   vpmaddubsw\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "*,noavx,avx")
+   (set_attr "type" "sseiadd")
    (set_attr "atom_unit" "simul")
    (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_mode_iterator PMULHRSW
   [V4HI V8HI (V16HI "TARGET_AVX2")])
-- 
2.20.1