re PR tree-optimization/89386 (Generation of vectorized MULHRS (Multiply High…

re PR tree-optimization/89386 (Generation of vectorized MULHRS (Multiply High with Round and Scale) instruction)

	PR tree-optimization/89386
	* config/i386/sse.md (smulhrs<mode>3): New expander.
	(smulhrsv4hi3): Ditto.

testsuite/ChangeLog:

	PR tree-optimization/89386
	* gcc.target/i386/pr89386.c: New test.
	* gcc.target/i386/pr89386-1.c: Ditto.

From-SVN: r275689

gcc/ChangeLog

+2019-09-12  Uroš Bizjak  <ubizjak@gmail.com>
+
+	PR tree-optimization/89386
+	* config/i386/sse.md (smulhrs<mode>3): New expander.
+	(smulhrsv4hi3): Ditto.
+
 2019-09-12  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/91750
@@ -27,15 +33,6 @@
 	* tree-vect-patterns.c (vect_recog_mulhs_pattern): New pattern
 	function.
 	(vect_vect_recog_func_ptrs): Add it.
-	* testsuite/gcc.target/aarch64/sve2/mulhrs_1.c: New test.
-	* testsuite/gcc.dg/vect/vect-mulhrs-1.c: As above.
-	* testsuite/gcc.dg/vect/vect-mulhrs-2.c: As above.
-	* testsuite/gcc.dg/vect/vect-mulhrs-3.c: As above.
-	* testsuite/gcc.dg/vect/vect-mulhrs-4.c: As above.
-	* doc/sourcebuild.texi (vect_mulhrs_hi): Document new target selector.
-	* testsuite/lib/target-supports.exp
-	(check_effective_target_vect_mulhrs_hi): Return true for AArch64
-	with SVE2.
 
 2019-09-11  Michael Meissner  <meissner@linux.ibm.com>
 

gcc/config/i386/sse.md

@@ -16475,6 +16475,26 @@
   ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);
 })
 
+(define_expand "smulhrs<mode>3"
+  [(set (match_operand:VI2_AVX2 0 "register_operand")
+	(truncate:VI2_AVX2
+	  (lshiftrt:<ssedoublemode>
+	    (plus:<ssedoublemode>
+	      (lshiftrt:<ssedoublemode>
+		(mult:<ssedoublemode>
+		  (sign_extend:<ssedoublemode>
+		    (match_operand:VI2_AVX2 1 "nonimmediate_operand"))
+		  (sign_extend:<ssedoublemode>
+		    (match_operand:VI2_AVX2 2 "nonimmediate_operand")))
+		(const_int 14))
+	      (match_dup 3))
+	    (const_int 1))))]
+  "TARGET_SSSE3"
+{
+  operands[3] = CONST1_RTX(<MODE>mode);
+  ix86_fixup_binary_operands_no_copy (MULT, <MODE>mode, operands);
+})
+
 (define_insn "*<ssse3_avx2>_pmulhrsw<mode>3<mask_name>"
   [(set (match_operand:VI2_AVX2 0 "register_operand" "=x,x,v")
 	(truncate:VI2_AVX2
@@ -16502,6 +16522,26 @@
    (set_attr "prefix" "orig,maybe_evex,evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_expand "smulhrsv4hi3"
+  [(set (match_operand:V4HI 0 "register_operand")
+	(truncate:V4HI
+	  (lshiftrt:V4SI
+	    (plus:V4SI
+	      (lshiftrt:V4SI
+		(mult:V4SI
+		  (sign_extend:V4SI
+		    (match_operand:V4HI 1 "register_operand"))
+		  (sign_extend:V4SI
+		    (match_operand:V4HI 2 "register_operand")))
+		(const_int 14))
+	      (match_dup 3))
+	    (const_int 1))))]
+  "TARGET_MMX_WITH_SSE && TARGET_SSSE3"
+{
+  operands[3] = CONST1_RTX(V4HImode);
+  ix86_fixup_binary_operands_no_copy (MULT, V4HImode, operands);
+})
+
 (define_expand "ssse3_pmulhrswv4hi3"
   [(set (match_operand:V4HI 0 "register_operand")
 	(truncate:V4HI

gcc/testsuite/ChangeLog

+2019-09-12  Uroš Bizjak  <ubizjak@gmail.com>
+
+	PR tree-optimization/89386
+	* gcc.target/i386/pr89386.c: New test.
+	* gcc.target/i386/pr89386-1.c: Ditto.
+
 2019-09-12  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/91750
 	* gcc.dg/vect/pr91750.c: New testcase.
 
+2019-09-12  Yuliang Wang  <yuliang.wang@arm.com>
+
+	PR tree-optimization/89386
+	* testsuite/gcc.target/aarch64/sve2/mulhrs_1.c: New test.
+	* testsuite/gcc.dg/vect/vect-mulhrs-1.c: As above.
+	* testsuite/gcc.dg/vect/vect-mulhrs-2.c: As above.
+	* testsuite/gcc.dg/vect/vect-mulhrs-3.c: As above.
+	* testsuite/gcc.dg/vect/vect-mulhrs-4.c: As above.
+	* doc/sourcebuild.texi (vect_mulhrs_hi): Document new target selector.
+	* testsuite/lib/target-supports.exp
+	(check_effective_target_vect_mulhrs_hi): Return true for AArch64
+	with SVE2.
+
 2019-09-11  Sandra Loosemore  <sandra@codesourcery.com>
 
 	PR testsuite/83889

gcc/testsuite/gcc.target/i386/pr89386-1.c

+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-mssse3 -O2 -ftree-vectorize" } */
+
+#define N 4
+
+short a[N], b[N], c[N];
+
+int foo (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    a[i] = ((((int) b[i] * (int) c[i]) >> 14) + 1) >> 1;
+}
+
+/* { dg-final { scan-assembler "pmulhrsw" } } */

gcc/testsuite/gcc.target/i386/pr89386.c

+/* { dg-do compile } */
+/* { dg-options "-mssse3 -O2 -ftree-vectorize" } */
+
+#define N 1024
+
+short a[N], b[N], c[N];
+
+int foo (void)
+{
+  int i;
+
+  for (i = 0; i < N; i++)
+    a[i] = ((((int) b[i] * (int) c[i]) >> 14) + 1) >> 1;
+}
+
+/* { dg-final { scan-assembler "pmulhrsw" } } */