[PATCH] x86: make better use of VBROADCASTSS / VPBROADCASTD

[Jan Beulich <jbeulich@suse.com>]

... in vec_dupv4sf / *vec_dupv4si. The respective broadcast insns are
never longer (yet sometimes shorter) than the corresponding VSHUFPS /
VPSHUFD, due to the immediate operand of the shuffle insns balancing the
need for VEX3 in the broadcast ones. When EVEX encoding is required the
broadcast insns are always shorter.

Add two new alternatives each, one covering the AVX2 case and one
covering AVX512.

gcc/

	* config/i386/sse.md (vec_dupv4sf): New AVX2 and AVX512F
	alternatives using vbroadcastss.
	(*vec_dupv4si): New AVX2 and AVX512F alternatives using
	vpbroadcastd.
---
I'm working from the assumption that the isa attributes to the original
1st and 2nd alternatives don't need further restricting (to sse2_noavx2
or avx_noavx2 as applicable), as the new earlier alternatives cover all
operand forms already when at least AVX2 is enabled.

Isn't prefix_extra use bogus here? What extra prefix does vbroadcastss
use? (Same further down in *vec_dupv4si and avx2_vbroadcasti128_<mode>
and elsewhere.)

Is use of Yv for the source operand really necessary in *vec_dupv4si?
I.e. would scalar integer values be put in XMM{16...31} when AVX512VL
isn't enabled? If so (*movsi_internal / *movdi_internal suggest they
might), wouldn't *vec_dupv2di need to use Yv as well in its 3rd
alternative (or just m, as Yv is already covered by the 2nd one)?

--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -25798,38 +25798,42 @@
 	(const_int 1)))])
 
 (define_insn "vec_dupv4sf"
-  [(set (match_operand:V4SF 0 "register_operand" "=v,v,x")
+  [(set (match_operand:V4SF 0 "register_operand" "=Yv,v,v,v,x")
 	(vec_duplicate:V4SF
-	  (match_operand:SF 1 "nonimmediate_operand" "Yv,m,0")))]
+	  (match_operand:SF 1 "nonimmediate_operand" "v,vm,Yv,m,0")))]
   "TARGET_SSE"
   "@
+   vbroadcastss\t{%1, %0|%0, %1}
+   vbroadcastss\t{%1, %g0|%g0, %1}
    vshufps\t{$0, %1, %1, %0|%0, %1, %1, 0}
    vbroadcastss\t{%1, %0|%0, %1}
    shufps\t{$0, %0, %0|%0, %0, 0}"
-  [(set_attr "isa" "avx,avx,noavx")
-   (set_attr "type" "sseshuf1,ssemov,sseshuf1")
-   (set_attr "length_immediate" "1,0,1")
-   (set_attr "prefix_extra" "0,1,*")
-   (set_attr "prefix" "maybe_evex,maybe_evex,orig")
-   (set_attr "mode" "V4SF")])
+  [(set_attr "isa" "avx2,avx512f,avx,avx,noavx")
+   (set_attr "type" "ssemov,ssemov,sseshuf1,ssemov,sseshuf1")
+   (set_attr "length_immediate" "0,0,1,0,1")
+   (set_attr "prefix_extra" "*,*,0,1,*")
+   (set_attr "prefix" "maybe_evex,evex,maybe_evex,maybe_evex,orig")
+   (set_attr "mode" "V4SF,V16SF,V4SF,V4SF,V4SF")])
 
 (define_insn "*vec_dupv4si"
-  [(set (match_operand:V4SI 0 "register_operand"     "=v,v,x")
+  [(set (match_operand:V4SI 0 "register_operand"     "=Yv,v,v,v,x")
 	(vec_duplicate:V4SI
-	  (match_operand:SI 1 "nonimmediate_operand" "Yv,m,0")))]
+	  (match_operand:SI 1 "nonimmediate_operand" "vm,vm,Yv,m,0")))]
   "TARGET_SSE"
   "@
+   vpbroadcastd\t{%1, %0|%0, %1}
+   vpbroadcastd\t{%1, %g0|%g0, %1}
    %vpshufd\t{$0, %1, %0|%0, %1, 0}
    vbroadcastss\t{%1, %0|%0, %1}
    shufps\t{$0, %0, %0|%0, %0, 0}"
-  [(set_attr "isa" "sse2,avx,noavx")
-   (set_attr "type" "sselog1,ssemov,sselog1")
-   (set_attr "length_immediate" "1,0,1")
-   (set_attr "prefix_extra" "0,1,*")
-   (set_attr "prefix" "maybe_vex,maybe_evex,orig")
-   (set_attr "mode" "TI,V4SF,V4SF")
+  [(set_attr "isa" "avx2,avx512f,sse2,avx,noavx")
+   (set_attr "type" "ssemov,ssemov,sselog1,ssemov,sselog1")
+   (set_attr "length_immediate" "0,0,1,0,1")
+   (set_attr "prefix_extra" "*,*,0,1,*")
+   (set_attr "prefix" "maybe_evex,evex,maybe_vex,maybe_evex,orig")
+   (set_attr "mode" "TI,XI,TI,V4SF,V4SF")
    (set (attr "preferred_for_speed")
-     (cond [(eq_attr "alternative" "1")
+     (cond [(eq_attr "alternative" "3")
 	      (symbol_ref "!TARGET_INTER_UNIT_MOVES_TO_VEC")
 	   ]
 	   (symbol_ref "true")))])