From: Alexander Ivchenko <alexander.ivchenko@intel.com>
Date: Thu, 16 Oct 2014 05:41:51 +0000 (+0000)
Subject: AVX-512. 76/n. Extend int 2 float conversions.
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=2fa9ee8fe709332458ce086676c885d83c6ea7d2;p=gcc.git

AVX-512. 76/n. Extend int 2 float conversions.

gcc/
	* config/i386/sse.md
	(define_expand "floatuns<sseintvecmodelower><mode>2"): Extend to
	support AVX-512VL instructions.

Co-Authored-By: Andrey Turetskiy <andrey.turetskiy@intel.com>
Co-Authored-By: Anna Tikhonova <anna.tikhonova@intel.com>
Co-Authored-By: Ilya Tocar <ilya.tocar@intel.com>
Co-Authored-By: Ilya Verbin <ilya.verbin@intel.com>
Co-Authored-By: Kirill Yukhin <kirill.yukhin@intel.com>
Co-Authored-By: Maxim Kuznetsov <maxim.kuznetsov@intel.com>
Co-Authored-By: Michael Zolotukhin <michael.v.zolotukhin@intel.com>

From-SVN: r216297
---

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a936c016811..349b3037d0d 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2014-10-16  Alexander Ivchenko  <alexander.ivchenko@intel.com>
+	    Maxim Kuznetsov  <maxim.kuznetsov@intel.com>
+	    Anna Tikhonova  <anna.tikhonova@intel.com>
+	    Ilya Tocar  <ilya.tocar@intel.com>
+	    Andrey Turetskiy  <andrey.turetskiy@intel.com>
+	    Ilya Verbin  <ilya.verbin@intel.com>
+	    Kirill Yukhin  <kirill.yukhin@intel.com>
+	    Michael Zolotukhin  <michael.v.zolotukhin@intel.com>
+
+	* config/i386/sse.md
+	(define_expand "floatuns<sseintvecmodelower><mode>2"): Extend to
+	support AVX-512VL instructions.
+
 2014-10-16  DJ Delorie  <dj@redhat.com>
 
 	* tree-core.h: Fix comment to not assume pointers are multiples of
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index a6cf3639576..dcb53dfa897 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -4013,6 +4013,14 @@
 {
   if (<MODE>mode == V16SFmode)
     emit_insn (gen_ufloatv16siv16sf2 (operands[0], operands[1]));
+  else
+    if (TARGET_AVX512VL)
+      {
+	if (<MODE>mode == V4SFmode)
+	  emit_insn (gen_ufloatv4siv4sf2 (operands[0], operands[1]));
+	else
+	  emit_insn (gen_ufloatv8siv8sf2 (operands[0], operands[1]));
+      }
   else
     ix86_expand_vector_convert_uns_vsivsf (operands[0], operands[1]);