i386: Generate standard floating point scalar operation patterns

Standard floating point scalar operation patterns for combiner, which
preserve the rest of the vector, look like

     (vec_merge:V2DF
       (vec_duplicate:V2DF (reg:DF 87))
       (reg/v:V2DF 85 [ x ])
       (const_int 1 [0x1])]))

and

     (vec_merge:V2DF
       (vec_duplicate:V2DF
         (op:DF (vec_select:DF (reg/v:V2DF 85 [ x ])
                (parallel [ (const_int 0 [0])]))
         (reg:DF 87))
       (reg/v:V2DF 85 [ x ])
       (const_int 1 [0x1])]))

This patch adds and generates such standard floating point scalar
operation patterns for +, -, *, /, > and <.

Tested on x86-64.

gcc/

	PR target/54855
	* config/i386/i386-expand.c (ix86_expand_vector_set): Generate
	standard scalar operation pattern for V2DF.
	* config/i386/sse.md (*<sse>_vm<plusminus_insn><mode>3): New.
	(*<sse>_vm<multdiv_mnemonic><mode>3): Likewise.
	(*ieee_<ieee_maxmin><mode>3): Likewise.
	(vec_setv2df_0): Likewise.

gcc/testsuite/

	PR target/54855
	* gcc.target/i386/pr54855-1.c: New test.
	* gcc.target/i386/pr54855-2.c: Likewise.
	* gcc.target/i386/pr54855-3.c: Likewise.
	* gcc.target/i386/pr54855-4.c: Likewise.
	* gcc.target/i386/pr54855-5.c: Likewise.
	* gcc.target/i386/pr54855-6.c: Likewise.
	* gcc.target/i386/pr54855-7.c: Likewise.
	* gcc.target/i386/pr54855-8.c: Likewise.
	* gcc.target/i386/pr54855-9.c: Likewise.
	* gcc.target/i386/pr54855-10.c: Likewise.

From-SVN: r272511

gcc/ChangeLog

+2019-06-20  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/54855
+	* config/i386/i386-expand.c (ix86_expand_vector_set): Generate
+	standard scalar operation pattern for V2DF.
+	* config/i386/sse.md (*<sse>_vm<plusminus_insn><mode>3): New.
+	(*<sse>_vm<multdiv_mnemonic><mode>3): Likewise.
+	(*ieee_<ieee_maxmin><mode>3): Likewise.
+	(vec_setv2df_0): Likewise.
+
 2019-06-20  Jan Hubicka  <jh@suse.cz>
 
 	* tree-ssa-alias.c (aliasing_component_refs_p): Remove ref2_is_decl

gcc/config/i386/i386-expand.c

@@ -14214,6 +14214,17 @@ ix86_expand_vector_set (bool mmx_ok, rtx target, rtx val, int elt)
       return;
 
     case E_V2DFmode:
+      /* NB: For ELT == 0, use standard scalar operation patterns which
+	 preserve the rest of the vector for combiner:
+
+	 (vec_merge:V2DF
+	   (vec_duplicate:V2DF (reg:DF))
+	   (reg:V2DF)
+	   (const_int 1))
+       */
+      if (elt == 0)
+	goto do_vec_merge;
+
       {
 	rtx op0, op1;
 
@@ -14511,6 +14522,7 @@ quarter:
     }
   else if (use_vec_merge)
     {
+do_vec_merge:
       tmp = gen_rtx_VEC_DUPLICATE (mode, val);
       tmp = gen_rtx_VEC_MERGE (mode, tmp, target,
 			       GEN_INT (HOST_WIDE_INT_1U << elt));

gcc/config/i386/sse.md

@@ -1826,6 +1826,28 @@
    (set_attr "type" "sseadd")
    (set_attr "mode" "<MODE>")])
 
+;; Standard scalar operation patterns which preserve the rest of the
+;; vector for combiner.
+(define_insn "*<sse>_vm<plusminus_insn><mode>3"
+  [(set (match_operand:VF_128 0 "register_operand" "=x,v")
+	(vec_merge:VF_128
+	  (vec_duplicate:VF_128
+	    (plusminus:<ssescalarmode>
+	      (vec_select:<ssescalarmode>
+	        (match_operand:VF_128 1 "register_operand" "0,v")
+		(parallel [(const_int 0)]))
+	      (match_operand:<ssescalarmode> 2 "nonimmediate_operand" "xm,vm")))
+	  (match_dup 1)
+	  (const_int 1)))]
+  "TARGET_SSE"
+  "@
+   <plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %0|%0, %<iptr>2}
+   v<plusminus_mnemonic><ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %<iptr>2}"
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sseadd")
+   (set_attr "prefix" "orig,vex")
+   (set_attr "mode" "<ssescalarmode>")])
+
 (define_insn "<sse>_vm<plusminus_insn><mode>3<mask_scalar_name><round_scalar_name>"
   [(set (match_operand:VF_128 0 "register_operand" "=x,v")
 	(vec_merge:VF_128
@@ -1880,6 +1902,29 @@
    (set_attr "type" "ssemul")
    (set_attr "mode" "<MODE>")])
 
+;; Standard scalar operation patterns which preserve the rest of the
+;; vector for combiner.
+(define_insn "*<sse>_vm<multdiv_mnemonic><mode>3"
+  [(set (match_operand:VF_128 0 "register_operand" "=x,v")
+	(vec_merge:VF_128
+	  (vec_duplicate:VF_128
+	    (multdiv:<ssescalarmode>
+	      (vec_select:<ssescalarmode>
+	        (match_operand:VF_128 1 "register_operand" "0,v")
+		(parallel [(const_int 0)]))
+	      (match_operand:<ssescalarmode> 2 "nonimmediate_operand" "xm,vm")))
+	  (match_dup 1)
+	  (const_int 1)))]
+  "TARGET_SSE"
+  "@
+   <multdiv_mnemonic><ssescalarmodesuffix>\t{%2, %0|%0, %<iptr>2}
+   v<multdiv_mnemonic><ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %<iptr>2}"
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sse<multdiv_mnemonic>")
+   (set_attr "prefix" "orig,vex")
+   (set_attr "btver2_decode" "direct,double")
+   (set_attr "mode" "<ssescalarmode>")])
+
 (define_insn "<sse>_vm<multdiv_mnemonic><mode>3<mask_scalar_name><round_scalar_name>"
   [(set (match_operand:VF_128 0 "register_operand" "=x,v")
 	(vec_merge:VF_128
@@ -2229,6 +2274,30 @@
    (set_attr "prefix" "<mask_prefix3>")
    (set_attr "mode" "<MODE>")])
 
+;; Standard scalar operation patterns which preserve the rest of the
+;; vector for combiner.
+(define_insn "*ieee_<ieee_maxmin><mode>3"
+  [(set (match_operand:VF_128 0 "register_operand" "=x,v")
+	(vec_merge:VF_128
+	  (vec_duplicate:VF_128
+	    (unspec:<ssescalarmode>
+	      [(vec_select:<ssescalarmode>
+	         (match_operand:VF_128 1 "register_operand" "0,v")
+		 (parallel [(const_int 0)]))
+	       (match_operand:<ssescalarmode> 2 "nonimmediate_operand" "xm,vm")]
+	       IEEE_MAXMIN))
+	  (match_dup 1)
+	  (const_int 1)))]
+  "TARGET_SSE"
+  "@
+   <ieee_maxmin><ssescalarmodesuffix>\t{%2, %0|%0, %2}
+   v<ieee_maxmin><ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "noavx,avx")
+   (set_attr "type" "sseadd")
+   (set_attr "btver2_sse_attr" "maxmin")
+   (set_attr "prefix" "orig,vex")
+   (set_attr "mode" "<ssescalarmode>")])
+
 (define_insn "<sse>_vm<code><mode>3<mask_scalar_name><round_saeonly_scalar_name>"
   [(set (match_operand:VF_128 0 "register_operand" "=x,v")
 	(vec_merge:VF_128
@@ -7911,6 +7980,25 @@
   [(set (match_dup 0) (match_dup 1))]
   "operands[0] = adjust_address (operands[0], <ssescalarmode>mode, 0);")
 
+;; Standard scalar operation patterns which preserve the rest of the
+;; vector for combiner.
+(define_insn "vec_setv2df_0"
+  [(set (match_operand:V2DF 0 "register_operand"       "=x,v,x,v")
+	(vec_merge:V2DF
+	  (vec_duplicate:V2DF
+	    (match_operand:DF 2 "nonimmediate_operand" " x,v,m,m"))
+	  (match_operand:V2DF 1 "register_operand"     " 0,v,0,v")
+	  (const_int 1)))]
+  "TARGET_SSE2"
+  "@
+   movsd\t{%2, %0|%0, %2}
+   vmovsd\t{%2, %1, %0|%0, %1, %2}
+   movlpd\t{%2, %0|%0, %2}
+   vmovlpd\t{%2, %1, %0|%0, %1, %2}"
+  [(set_attr "isa" "noavx,avx,noavx,avx")
+   (set_attr "type" "ssemov")
+   (set_attr "mode" "DF")])
+
 (define_expand "vec_set<mode>"
   [(match_operand:V 0 "register_operand")
    (match_operand:<ssescalarmode> 1 "register_operand")

gcc/testsuite/ChangeLog

+2019-06-20  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR target/54855
+	* gcc.target/i386/pr54855-1.c: New test.
+	* gcc.target/i386/pr54855-2.c: Likewise.
+	* gcc.target/i386/pr54855-3.c: Likewise.
+	* gcc.target/i386/pr54855-4.c: Likewise.
+	* gcc.target/i386/pr54855-5.c: Likewise.
+	* gcc.target/i386/pr54855-6.c: Likewise.
+	* gcc.target/i386/pr54855-7.c: Likewise.
+	* gcc.target/i386/pr54855-8.c: Likewise.
+	* gcc.target/i386/pr54855-9.c: Likewise.
+	* gcc.target/i386/pr54855-10.c: Likewise.
+
 2019-06-20  Jan Hubicka  <jh@suse.cz>
 
 	* gcc.c-torture/execute/alias-access-path-1.c: New testcase.

gcc/testsuite/gcc.target/i386/pr54855-1.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "addsd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double __v2df __attribute__ ((__vector_size__ (16)));
+typedef double __m128d __attribute__ ((__vector_size__ (16), __may_alias__));
+
+__m128d
+_mm_add_sd (__m128d x, __m128d y)
+{
+  __m128d z =  __extension__ (__m128d)(__v2df)
+    { (((__v2df) x)[0] + ((__v2df) y)[0]), ((__v2df) x)[1] };
+  return z;
+}

gcc/testsuite/gcc.target/i386/pr54855-10.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "movlpd" 1 } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x, double *a)
+{
+  x[0] = *a;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-2.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "mulsd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double __v2df __attribute__ ((__vector_size__ (16)));
+
+__v2df
+_mm_mul_sd (__v2df x, __v2df y)
+{
+  __v2df z = x;
+  z[0] = x[0] * y[0];
+  return z;
+}

gcc/testsuite/gcc.target/i386/pr54855-3.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "subsd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x)
+{
+  x[0] -= 1.;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-4.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "subsd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x, double a)
+{
+  x[0] -= a;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-5.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "subsd" 1 } } */
+/* { dg-final { scan-assembler-times "mulpd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double __v2df __attribute__ ((__vector_size__ (16)));
+
+__v2df
+foo (__v2df x, __v2df y)
+{
+  x[0] -= y[0];
+  x *= y;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-6.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "divss" 1 } } */
+/* { dg-final { scan-assembler-not "movaps" } } */
+/* { dg-final { scan-assembler-not "movss" } } */
+
+typedef float vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x, float f)
+{
+  x[0] /= f;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-7.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "divss" 1 } } */
+/* { dg-final { scan-assembler-not "movaps" } } */
+/* { dg-final { scan-assembler-not "movss" } } */
+
+typedef float vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x)
+{
+  x[0] /= 2.1f;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-8.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "maxsd" 1 } } */
+/* { dg-final { scan-assembler-not "movapd" } } */
+/* { dg-final { scan-assembler-not "movsd" } } */
+
+typedef double vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x, double a)
+{
+  x[0] = x[0] > a ? x[0] : a;
+  return x;
+}

gcc/testsuite/gcc.target/i386/pr54855-9.c

+/* { dg-do compile } */
+/* { dg-options "-O2 -msse2 -mfpmath=sse" } */
+/* { dg-final { scan-assembler-times "minss" 1 } } */
+/* { dg-final { scan-assembler-not "movaps" } } */
+/* { dg-final { scan-assembler-not "movss" } } */
+
+typedef float vec __attribute__((vector_size(16)));
+
+vec
+foo (vec x, float a)
+{
+  x[0] = x[0] < a ? x[0] : a;
+  return x;
+}