x86: improve fast bfloat->float conversion

There's nothing AVX512BW-ish in here, so no reason to use Yw as the
constraints for the AVX alternative. Furthermore by using the 512-bit
form of VPSSLD (in a new alternative) all 32 registers can be used
directly by the insn without AVX512VL needing to be enabled.

Also adjust the originally last alternative's "prefix" attribute to
maybe_evex.

gcc/

	* config/i386/i386.md (extendbfsf2_1): Add new AVX512F
	alternative. Adjust original last alternative's "prefix"
	attribute to maybe_evex.

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 844deeae6cb34d9fe1a4c0ee5304e002251db3fa..ef9683491bd54ed888b7aaf3b86c171619f41eae 100644 (file)
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -5247,21 +5247,27 @@
 ;; Don't use float_extend since psrlld doesn't raise
 ;; exceptions and turn a sNaN into a qNaN.
 (define_insn "extendbfsf2_1"
-  [(set (match_operand:SF 0 "register_operand"   "=x,Yw")
+  [(set (match_operand:SF 0 "register_operand"   "=x,Yv,v")
        (unspec:SF
-         [(match_operand:BF 1 "register_operand" " 0,Yw")]
+         [(match_operand:BF 1 "register_operand" " 0,Yv,v")]
          UNSPEC_CVTBFSF))]
  "TARGET_SSE2"
  "@
   pslld\t{$16, %0|%0, 16}
-  vpslld\t{$16, %1, %0|%0, %1, 16}"
-  [(set_attr "isa" "noavx,avx")
+  vpslld\t{$16, %1, %0|%0, %1, 16}
+  vpslld\t{$16, %g1, %g0|%g0, %g1, 16}"
+  [(set_attr "isa" "noavx,avx,*")
    (set_attr "type" "sseishft1")
    (set_attr "length_immediate" "1")
-   (set_attr "prefix_data16" "1,*")
-   (set_attr "prefix" "orig,vex")
-   (set_attr "mode" "TI")
-   (set_attr "memory" "none")])
+   (set_attr "prefix_data16" "1,*,*")
+   (set_attr "prefix" "orig,maybe_evex,evex")
+   (set_attr "mode" "TI,TI,XI")
+   (set_attr "memory" "none")
+   (set (attr "enabled")
+     (if_then_else (eq_attr "alternative" "2")
+       (symbol_ref "TARGET_AVX512F && !TARGET_AVX512VL
+                   && !TARGET_PREFER_AVX256")
+       (const_string "*")))])
 
 (define_expand "extend<mode>xf2"
   [(set (match_operand:XF 0 "nonimmediate_operand")