Re: [PATCH, i386]: Implement usadv64qi

[Kirill Yukhin]

Hello Uroš,
On 09 мая 13:07, Uros Bizjak wrote:
> This patch adds usadv64qi expander, so the compiler is able to
> vectorize with 512bit vpsadbw insn.
> 
> 2017-05-09  Uros Bizjak  
> 
> PR target/85693
> * config/i386/sse.md (usadv64qi): New expander.
> 
> Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.
> 
> OK for mainline?
Patch is OK.
> 
> Uros.

--
Thanks, K

[PATCH, i386]: Implement usadv64qi

[Uros Bizjak]

This patch adds usadv64qi expander, so the compiler is able to
vectorize with 512bit vpsadbw insn.

2017-05-09  Uros Bizjak  

PR target/85693
* config/i386/sse.md (usadv64qi): New expander.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

OK for mainline?

Uros.
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index ae6294e559c..0e625a4cc58 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -10878,6 +10878,21 @@
   DONE;
 })
 
+(define_expand "usadv64qi"
+  [(match_operand:V16SI 0 "register_operand")
+   (match_operand:V64QI 1 "register_operand")
+   (match_operand:V64QI 2 "nonimmediate_operand")
+   (match_operand:V16SI 3 "nonimmediate_operand")]
+  "TARGET_AVX512BW"
+{
+  rtx t1 = gen_reg_rtx (V8DImode);
+  rtx t2 = gen_reg_rtx (V16SImode);
+  emit_insn (gen_avx512f_psadbw (t1, operands[1], operands[2]));
+  convert_move (t2, t1, 0);
+  emit_insn (gen_addv16si3 (operands[0], t2, operands[3]));
+  DONE;
+})
+
 (define_insn "ashr3"
   [(set (match_operand:VI248_AVX512BW_1 0 "register_operand" "=v,v")
(ashiftrt:VI248_AVX512BW_1