Hi!

The following patch adds =*k, *km alternatives to the various
zero_extend?i?i2 patterns, because kmov* instructions actually zero extend
the destination to 64-bits.  I've kept * for the alternatives because that
is what is used e.g. in *mov[sd]i_internal patterns (probably to make it
less likely that RA chooses to perform arithmetics unrelated to masks in
the mask registers).

Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?

2018-12-12  Jakub Jelinek  <ja...@redhat.com>

        PR target/88461
        * config/i386/i386.md (*zero_extendsidi2, zero_extend<mode>di2,
        *zero_extend<mode>si2, *zero_extendqihi2): Add =*k, *km alternatives.

--- gcc/config/i386/i386.md.jj  2018-12-11 15:49:52.919342538 +0100
+++ gcc/config/i386/i386.md     2018-12-12 15:51:42.232521901 +0100
@@ -3751,10 +3751,10 @@ (define_expand "zero_extendsidi2"
 
 (define_insn "*zero_extendsidi2"
   [(set (match_operand:DI 0 "nonimmediate_operand"
-               "=r,?r,?o,r   ,o,?*y,?!*y,$r,$v,$x,*x,*v,*r")
+               "=r,?r,?o,r   ,o,?*y,?!*y,$r,$v,$x,*x,*v,*r,*k")
        (zero_extend:DI
         (match_operand:SI 1 "x86_64_zext_operand"
-               "0 ,rm,r ,rmWz,0,r  ,m   ,v ,r ,m ,*x,*v,*k")))]
+               "0 ,rm,r ,rmWz,0,r  ,m   ,v ,r ,m ,*x,*v,*k,*km")))]
   ""
 {
   switch (get_attr_type (insn))
@@ -3806,6 +3806,8 @@ (define_insn "*zero_extendsidi2"
              (const_string "avx512f")
            (eq_attr "alternative" "12")
              (const_string "x64_avx512bw")
+           (eq_attr "alternative" "13")
+             (const_string "avx512bw")
           ]
           (const_string "*")))
    (set (attr "type")
@@ -3819,7 +3821,7 @@ (define_insn "*zero_extendsidi2"
                (const_string "multi"))
            (eq_attr "alternative" "8,9,10,11")
              (const_string "ssemov")
-           (eq_attr "alternative" "12")
+           (eq_attr "alternative" "12,13")
              (const_string "mskmov")
           ]
           (const_string "imovx")))
@@ -3881,16 +3883,17 @@ (define_mode_attr kmov_isa
   [(QI "avx512dq") (HI "avx512f") (SI "avx512bw") (DI "avx512bw")])
 
 (define_insn "zero_extend<mode>di2"
-  [(set (match_operand:DI 0 "register_operand" "=r,*r")
+  [(set (match_operand:DI 0 "register_operand" "=r,*r,*k")
        (zero_extend:DI
-        (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k")))]
+        (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k,*km")))]
   "TARGET_64BIT"
   "@
    movz{<imodesuffix>l|x}\t{%1, %k0|%k0, %1}
+   kmov<mskmodesuffix>\t{%1, %k0|%k0, %1}
    kmov<mskmodesuffix>\t{%1, %k0|%k0, %1}"
-  [(set_attr "isa" "*,<kmov_isa>")
-   (set_attr "type" "imovx,mskmov")
-   (set_attr "mode" "SI,<MODE>")])
+  [(set_attr "isa" "*,<kmov_isa>,<kmov_isa>")
+   (set_attr "type" "imovx,mskmov,mskmov")
+   (set_attr "mode" "SI,<MODE>,<MODE>")])
 
 (define_expand "zero_extend<mode>si2"
   [(set (match_operand:SI 0 "register_operand")
@@ -3933,16 +3936,17 @@ (define_insn_and_split "zero_extend<mode
    (set_attr "mode" "SI")])
 
 (define_insn "*zero_extend<mode>si2"
-  [(set (match_operand:SI 0 "register_operand" "=r,*r")
+  [(set (match_operand:SI 0 "register_operand" "=r,*r,*k")
        (zero_extend:SI
-         (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k")))]
+         (match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k,*km")))]
   "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
   "@
    movz{<imodesuffix>l|x}\t{%1, %0|%0, %1}
+   kmov<mskmodesuffix>\t{%1, %0|%0, %1}
    kmov<mskmodesuffix>\t{%1, %0|%0, %1}"
-  [(set_attr "isa" "*,<kmov_isa>")
-   (set_attr "type" "imovx,mskmov")
-   (set_attr "mode" "SI,<MODE>")])
+  [(set_attr "isa" "*,<kmov_isa>,<kmov_isa>")
+   (set_attr "type" "imovx,mskmov,mskmov")
+   (set_attr "mode" "SI,<MODE>,<MODE>")])
 
 (define_expand "zero_extendqihi2"
   [(set (match_operand:HI 0 "register_operand")
@@ -3985,15 +3989,16 @@ (define_insn_and_split "zero_extendqihi2
 
 ; zero extend to SImode to avoid partial register stalls
 (define_insn "*zero_extendqihi2"
-  [(set (match_operand:HI 0 "register_operand" "=r,*r")
-       (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand" "qm,*k")))]
+  [(set (match_operand:HI 0 "register_operand" "=r,*r,*k")
+       (zero_extend:HI (match_operand:QI 1 "nonimmediate_operand" 
"qm,*k,*km")))]
   "!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
   "@
    movz{bl|x}\t{%1, %k0|%k0, %1}
-   kmovb\t{%1, %k0|%k0, %1}"
-  [(set_attr "isa" "*,avx512dq")
-   (set_attr "type" "imovx,mskmov")
-   (set_attr "mode" "SI,QI")])
+   kmovb\t{%1, %k0|%k0, %1}
+   kmovb\t{%1, %0|%0, %1}"
+  [(set_attr "isa" "*,avx512dq,avx512dq")
+   (set_attr "type" "imovx,mskmov,mskmov")
+   (set_attr "mode" "SI,QI,QI")])
 
 (define_insn_and_split "*zext<mode>_doubleword_and"
   [(set (match_operand:DI 0 "register_operand" "=&<r>")

        Jakub

Reply via email to