[PATCH, i386]: Fix PR85950, Unsafe-math-optimizations regresses optimization using SSE4.1 roundss

[Uros Bizjak]

Hello!

Attached patch enables l<rounding_insn><MODEF:mode><SWI48:mode>2 for
TARGET_SSE4.1, and while there, also corrects operand 1 predicate of
rounds{s,d} instruction.

2018-05-29  Uros Bizjak  <ubizjak@gmail.com>

    PR target/85950
    * config/i386/i386.md (l<rounding_insn><MODEF:mode><SWI48:mode>2):
    Enable for TARGET_SSE4_1 and generate rounds{s,d} and cvtts{s,d}2si{,q}
    sequence.
    (sse4_1_round<mode>2): Use nonimmediate_operand
    for operand 1 predicate.

testsuite/ChangeLog:

2018-05-29  Uros Bizjak  <ubizjak@gmail.com>

    PR target/85950
    * gcc.target/i386/pr85950.c: New test.

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

Committed to mainline SVN.

Uros.
-------------- next part --------------
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md	(revision 260850)
+++ config/i386/i386.md	(working copy)
@@ -16655,7 +16655,7 @@
 
 (define_insn "sse4_1_round<mode>2"
   [(set (match_operand:MODEF 0 "register_operand" "=x,v")
-	(unspec:MODEF [(match_operand:MODEF 1 "register_operand" "x,v")
+	(unspec:MODEF [(match_operand:MODEF 1 "nonimmediate_operand" "xm,vm")
 		       (match_operand:SI 2 "const_0_to_15_operand" "n,n")]
 		      UNSPEC_ROUND))]
   "TARGET_SSE4_1"
@@ -17251,12 +17251,19 @@
 				 FIST_ROUNDING))
 	      (clobber (reg:CC FLAGS_REG))])]
   "SSE_FLOAT_MODE_P (<MODEF:MODE>mode) && TARGET_SSE_MATH
-   && !flag_trapping_math"
+   && (TARGET_SSE4_1 || !flag_trapping_math)"
 {
-  if (TARGET_64BIT && optimize_insn_for_size_p ())
-    FAIL;
+  if (TARGET_SSE4_1)
+    {
+      rtx tmp = gen_reg_rtx (<MODEF:MODE>mode);
 
-  if (ROUND_<ROUNDING> == ROUND_FLOOR)
+      emit_insn (gen_sse4_1_round<mode>2
+		 (tmp, operands[1], GEN_INT (ROUND_<ROUNDING>
+					     | ROUND_NO_EXC)));
+      emit_insn (gen_fix_trunc<MODEF:mode><SWI48:mode>2
+		 (operands[0], tmp));
+    }
+  else if (ROUND_<ROUNDING> == ROUND_FLOOR)
     ix86_expand_lfloorceil (operands[0], operands[1], true);
   else if (ROUND_<ROUNDING> == ROUND_CEIL)
     ix86_expand_lfloorceil (operands[0], operands[1], false);
Index: testsuite/gcc.target/i386/pr85950.c
===================================================================
--- testsuite/gcc.target/i386/pr85950.c	(nonexistent)
+++ testsuite/gcc.target/i386/pr85950.c	(working copy)
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse4.1 -mfpmath=sse" } */
+
+double floor (double);
+double ceil (double);
+
+int ifloor (double x) { return floor (x); }
+int iceil (double x) { return ceil (x); }
+
+#ifdef __x86_64__
+long long llfloor (double x) { return floor (x); }
+long long llceil (double x) { return ceil (x); }
+#endif
+  
+/* { dg-final { scan-assembler-times "roundsd" 2 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "roundsd" 4 { target { ! ia32 } } } } */