i386: Do not sanitize upper part of V2SFmode reg with -fno-trapping-math [PR110832]

Also introduce -m[no-]partial-vector-fp-math option to disable trapping
V2SF named patterns in order to avoid generation of partial vector V4SFmode
trapping instructions.

The new option is enabled by default, because even with sanitization,
a small but consistent speed up of 2 to 3% with Polyhedron capacita
benchmark can be achieved vs. scalar code.

Using -fno-trapping-math improves Polyhedron capacita runtime 8 to 9%
vs. scalar code.  This is what clang does by default, as it defaults
to -fno-trapping-math.

	PR target/110832

gcc/ChangeLog:

	* config/i386/i386.opt (mpartial-vector-fp-math): New option.
	* config/i386/mmx.md (movq_<mode>_to_sse): Do not sanitize
	upper part of V2SFmode register with -fno-trapping-math.
	(<plusminusmult:insn>v2sf3): Enable for ix86_partial_vec_fp_math.
	(divv2sf3): Ditto.
	(<smaxmin:code>v2sf3): Ditto.
	(sqrtv2sf2): Ditto.
	(*mmx_haddv2sf3_low): Ditto.
	(*mmx_hsubv2sf3_low): Ditto.
	(vec_addsubv2sf3): Ditto.
	(vec_cmpv2sfv2si): Ditto.
	(vcond<V2FI:mode>v2sf): Ditto.
	(fmav2sf4): Ditto.
	(fmsv2sf4): Ditto.
	(fnmav2sf4): Ditto.
	(fnmsv2sf4): Ditto.
	(fix_truncv2sfv2si2): Ditto.
	(fixuns_truncv2sfv2si2): Ditto.
	(floatv2siv2sf2): Ditto.
	(floatunsv2siv2sf2): Ditto.
	(nearbyintv2sf2): Ditto.
	(rintv2sf2): Ditto.
	(lrintv2sfv2si2): Ditto.
	(ceilv2sf2): Ditto.
	(lceilv2sfv2si2): Ditto.
	(floorv2sf2): Ditto.
	(lfloorv2sfv2si2): Ditto.
	(btruncv2sf2): Ditto.
	(roundv2sf2): Ditto.
	(lroundv2sfv2si2): Ditto.
	* doc/invoke.texi (x86 Options): Document
	-mpartial-vector-fp-math option.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr110832-1.c: New test.
	* gcc.target/i386/pr110832-2.c: New test.
	* gcc.target/i386/pr110832-3.c: New test.

6 files changed, 103 insertions, 32 deletions

diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index 1cc8563..ddb7f11 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -632,6 +632,10 @@ Enum(prefer_vector_width) String(256) Value(PVW_AVX256)
 EnumValue
 Enum(prefer_vector_width) String(512) Value(PVW_AVX512)
 
+mpartial-vector-fp-math
+Target Var(ix86_partial_vec_fp_math) Init(1)
+Enable floating-point status flags setting SSE vector operations on partial vectors
+
 mmove-max=
 Target RejectNegative Joined Var(ix86_move_max) Enum(prefer_vector_width) Init(PVW_NONE) Save
 Maximum number of bits that can be moved from memory to memory efficiently.
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index b49554e..d51b3b9 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -595,7 +595,18 @@
 	  (match_operand:V2FI_V4HF 1 "nonimmediate_operand")
 	  (match_dup 2)))]
   "TARGET_SSE2"
-  "operands[2] = CONST0_RTX (<MODE>mode);")
+{
+  if (<MODE>mode == V2SFmode
+      && !flag_trapping_math)
+    {
+      rtx op1 = force_reg (<MODE>mode, operands[1]);
+      emit_move_insn (operands[0], lowpart_subreg (<mmxdoublevecmode>mode,
+						   op1, <MODE>mode));
+      DONE;
+    }
+
+  operands[2] = CONST0_RTX (<MODE>mode);
+})
 
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
@@ -648,7 +659,7 @@
 	(plusminusmult:V2SF
 	  (match_operand:V2SF 1 "nonimmediate_operand")
 	  (match_operand:V2SF 2 "nonimmediate_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op2 = gen_reg_rtx (V4SFmode);
   rtx op1 = gen_reg_rtx (V4SFmode);
@@ -726,7 +737,7 @@
   [(set (match_operand:V2SF 0 "register_operand")
 	(div:V2SF (match_operand:V2SF 1 "register_operand")
 		  (match_operand:V2SF 2 "register_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op2 = gen_reg_rtx (V4SFmode);
   rtx op1 = gen_reg_rtx (V4SFmode);
@@ -748,7 +759,7 @@
         (smaxmin:V2SF
 	  (match_operand:V2SF 1 "register_operand")
 	  (match_operand:V2SF 2 "register_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op2 = gen_reg_rtx (V4SFmode);
   rtx op1 = gen_reg_rtx (V4SFmode);
@@ -850,7 +861,7 @@
 (define_expand "sqrtv2sf2"
   [(set (match_operand:V2SF 0 "register_operand")
 	(sqrt:V2SF (match_operand:V2SF 1 "nonimmediate_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -931,7 +942,7 @@
 	  (vec_select:SF
 	    (match_dup 1)
 	    (parallel [(match_operand:SI 3 "const_0_to_1_operand")]))))]
-  "TARGET_SSE3 && TARGET_MMX_WITH_SSE
+  "TARGET_SSE3 && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math
    && INTVAL (operands[2]) != INTVAL (operands[3])
    && ix86_pre_reload_split ()"
   "#"
@@ -977,7 +988,7 @@
 	  (vec_select:SF
 	    (match_dup 1)
 	    (parallel [(const_int 1)]))))]
-  "TARGET_SSE3 && TARGET_MMX_WITH_SSE
+  "TARGET_SSE3 && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math
    && ix86_pre_reload_split ()"
   "#"
   "&& 1"
@@ -1039,7 +1050,7 @@
 	    (match_operand:V2SF 2 "nonimmediate_operand"))
 	  (plus:V2SF (match_dup 1) (match_dup 2))
 	  (const_int 1)))]
-  "TARGET_SSE3 && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE3 && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op2 = gen_reg_rtx (V4SFmode);
   rtx op1 = gen_reg_rtx (V4SFmode);
@@ -1102,7 +1113,7 @@
 	(match_operator:V2SI 1 ""
 	  [(match_operand:V2SF 2 "nonimmediate_operand")
 	   (match_operand:V2SF 3 "nonimmediate_operand")]))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx ops[4];
   ops[3] = gen_reg_rtx (V4SFmode);
@@ -1128,7 +1139,7 @@
 	     (match_operand:V2SF 5 "nonimmediate_operand")])
 	  (match_operand:V2FI 1 "general_operand")
 	  (match_operand:V2FI 2 "general_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx ops[6];
   ops[5] = gen_reg_rtx (V4SFmode);
@@ -1318,7 +1329,7 @@
 	  (match_operand:V2SF 2 "nonimmediate_operand")
 	  (match_operand:V2SF 3 "nonimmediate_operand")))]
   "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512VL)
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op3 = gen_reg_rtx (V4SFmode);
   rtx op2 = gen_reg_rtx (V4SFmode);
@@ -1343,7 +1354,7 @@
 	  (neg:V2SF
 	    (match_operand:V2SF 3 "nonimmediate_operand"))))]
   "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512VL)
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op3 = gen_reg_rtx (V4SFmode);
   rtx op2 = gen_reg_rtx (V4SFmode);
@@ -1368,7 +1379,7 @@
 	  (match_operand:V2SF   2 "nonimmediate_operand")
 	  (match_operand:V2SF   3 "nonimmediate_operand")))]
   "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512VL)
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op3 = gen_reg_rtx (V4SFmode);
   rtx op2 = gen_reg_rtx (V4SFmode);
@@ -1394,7 +1405,7 @@
 	  (neg:V2SF
 	    (match_operand:V2SF 3 "nonimmediate_operand"))))]
   "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512VL)
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op3 = gen_reg_rtx (V4SFmode);
   rtx op2 = gen_reg_rtx (V4SFmode);
@@ -1420,7 +1431,7 @@
 (define_expand "fix_truncv2sfv2si2"
   [(set (match_operand:V2SI 0 "register_operand")
 	(fix:V2SI (match_operand:V2SF 1 "nonimmediate_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
@@ -1436,7 +1447,7 @@
 (define_expand "fixuns_truncv2sfv2si2"
   [(set (match_operand:V2SI 0 "register_operand")
 	(unsigned_fix:V2SI (match_operand:V2SF 1 "nonimmediate_operand")))]
-  "TARGET_AVX512VL && TARGET_MMX_WITH_SSE"
+  "TARGET_AVX512VL && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
@@ -1461,7 +1472,7 @@
 (define_expand "floatv2siv2sf2"
   [(set (match_operand:V2SF 0 "register_operand")
 	(float:V2SF (match_operand:V2SI 1 "nonimmediate_operand")))]
-  "TARGET_MMX_WITH_SSE"
+  "TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SImode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1477,7 +1488,7 @@
 (define_expand "floatunsv2siv2sf2"
   [(set (match_operand:V2SF 0 "register_operand")
 	(unsigned_float:V2SF (match_operand:V2SI 1 "nonimmediate_operand")))]
-  "TARGET_AVX512VL && TARGET_MMX_WITH_SSE"
+  "TARGET_AVX512VL && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SImode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1754,7 +1765,7 @@
 (define_expand "nearbyintv2sf2"
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
-  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1770,7 +1781,7 @@
 (define_expand "rintv2sf2"
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
-  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1786,8 +1797,8 @@
 (define_expand "lrintv2sfv2si2"
   [(match_operand:V2SI 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
- "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && !flag_trapping_math
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
@@ -1804,7 +1815,7 @@
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
   "TARGET_SSE4_1 && !flag_trapping_math
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1820,8 +1831,8 @@
 (define_expand "lceilv2sfv2si2"
   [(match_operand:V2SI 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
- "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && !flag_trapping_math
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
@@ -1838,7 +1849,7 @@
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
   "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1854,8 +1865,8 @@
 (define_expand "lfloorv2sfv2si2"
   [(match_operand:V2SI 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
- "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && !flag_trapping_math
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
@@ -1872,7 +1883,7 @@
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
   "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1889,7 +1900,7 @@
   [(match_operand:V2SF 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
   "TARGET_SSE4_1 && !flag_trapping_math
-   && TARGET_MMX_WITH_SSE"
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SFmode);
@@ -1905,8 +1916,8 @@
 (define_expand "lroundv2sfv2si2"
   [(match_operand:V2SI 0 "register_operand")
    (match_operand:V2SF 1 "nonimmediate_operand")]
- "TARGET_SSE4_1 && !flag_trapping_math
-  && TARGET_MMX_WITH_SSE"
+  "TARGET_SSE4_1 && !flag_trapping_math
+   && TARGET_MMX_WITH_SSE && ix86_partial_vec_fp_math"
 {
   rtx op1 = gen_reg_rtx (V4SFmode);
   rtx op0 = gen_reg_rtx (V4SImode);
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 674f956..38c9b4e 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -1419,6 +1419,7 @@ See RS/6000 and PowerPC Options.
 -mcld  -mcx16  -msahf  -mmovbe  -mcrc32 -mmwait
 -mrecip  -mrecip=@var{opt}
 -mvzeroupper  -mprefer-avx128  -mprefer-vector-width=@var{opt}
+-mpartial-vector-fp-math
 -mmove-max=@var{bits} -mstore-max=@var{bits}
 -mmmx  -msse  -msse2  -msse3  -mssse3  -msse4.1  -msse4.2  -msse4  -mavx
 -mavx2  -mavx512f  -mavx512pf  -mavx512er  -mavx512cd  -mavx512vl
@@ -33754,6 +33755,23 @@ This option instructs GCC to use 128-bit AVX instructions instead of
 This option instructs GCC to use @var{opt}-bit vector width in instructions
 instead of default on the selected platform.
 
+@opindex mpartial-vector-fp-math
+@item -mpartial-vector-fp-math
+This option enables GCC to generate floating-point operations that might
+affect the set of floating-point status flags on partial vectors, where
+vector elements reside in the low part of the 128-bit SSE register.  Unless
+@option{-fno-trapping-math} is specified, the compiler guarantees correct
+behavior by sanitizing all input operands to have zeroes in the unused
+upper part of the vector register.  Note that by using built-in functions
+or inline assembly with partial vector arguments, NaNs, denormal or invalid
+values can leak into the upper part of the vector, causing possible
+performance issues when @option{-fno-trapping-math} is in effect.  These
+issues can be mitigated by manually sanitizing the upper part of the partial
+vector argument register or by using @option{-mdaz-ftz} to set
+denormals-are-zero (DAZ) flag in the MXCSR register.
+
+This option is enabled by default.
+
 @opindex mmove-max
 @item -mmove-max=@var{bits}
 This option instructs GCC to set the maximum number of bits can be
diff --git a/gcc/testsuite/gcc.target/i386/pr110832-1.c b/gcc/testsuite/gcc.target/i386/pr110832-1.c
new file mode 100644
index 0000000..f473e40
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110832-1.c
@@ -0,0 +1,12 @@
+/* PR target/110832 */
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -msse2 -mno-partial-vector-fp-math" } */
+
+typedef float __attribute__((vector_size(8))) v2sf;
+
+v2sf test (v2sf a, v2sf b)
+{
+  return a + b;
+}
+
+/* { dg-final { scan-assembler-not "addps" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110832-2.c b/gcc/testsuite/gcc.target/i386/pr110832-2.c
new file mode 100644
index 0000000..59cf8f9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110832-2.c
@@ -0,0 +1,13 @@
+/* PR target/110832 */
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -ftrapping-math -msse2 -mpartial-vector-fp-math -dp" } */
+
+typedef float __attribute__((vector_size(8))) v2sf;
+
+v2sf test (v2sf a, v2sf b)
+{
+  return a + b;
+}
+
+/* { dg-final { scan-assembler "addps" } } */
+/* { dg-final { scan-assembler-times "\\*vec_concatv4sf_0" 2 } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr110832-3.c b/gcc/testsuite/gcc.target/i386/pr110832-3.c
new file mode 100644
index 0000000..19e219e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr110832-3.c
@@ -0,0 +1,13 @@
+/* PR target/110832 */
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -fno-trapping-math -msse2 -mpartial-vector-fp-math -dp" } */
+
+typedef float __attribute__((vector_size(8))) v2sf;
+
+v2sf test (v2sf a, v2sf b)
+{
+  return a + b;
+}
+
+/* { dg-final { scan-assembler "addps" } } */
+/* { dg-final { scan-assembler-not "\\*vec_concatv4sf_0" } } */