re PR target/53512 (SH Target: Allow fsca and fsrra for non-SH4A)

	PR target/53512
	* sh.opt (mfsca, mfsrra): New options.
	* sh.md (rsqrtsf2): Use TARGET_FPU_ANY and TARGET_FSRRA	condition.
	(fsca): Use TARGET_FPU_ANY and TARGET_FSCA condition.
	(sinssf2, cossf2): Fold expanders to ...
	(sincossf3): ... this new expander.  Use TARGET_FPU_ANY and
	TARGET_FSCA condition.
	* sh.c (sh_option_override): Handle TARGET_FSRRA and TARGET_FSCA.
	* doc/invoke.texi (SH Options): Add descriptions for -mfsca,
	-mno-fsca, -mfsrra, -mno-fsrra.

	PR target/53512
	* gcc.target/sh/pr53512-1.c: New.
	* gcc.target/sh/pr53512-2.c: New.
	* gcc.target/sh/pr53512-3.c: New.
	* gcc.target/sh/pr53512-4.c: New.

From-SVN: r188149

10 files changed, 173 insertions, 35 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 46ef309..0e10272 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2012-06-03  Oleg Endo  <olegendo@gcc.gnu.org>
+
+	PR target/53512
+	* sh.opt (mfsca, mfsrra): New options.
+	* sh.md (rsqrtsf2): Use TARGET_FPU_ANY and TARGET_FSRRA	condition.
+	(fsca): Use TARGET_FPU_ANY and TARGET_FSCA condition.
+	(sinssf2, cossf2): Fold expanders to ...
+	(sincossf3): ... this new expander.  Use TARGET_FPU_ANY and
+	TARGET_FSCA condition.
+	* sh.c (sh_option_override): Handle TARGET_FSRRA and TARGET_FSCA.
+	* doc/invoke.texi (SH Options): Add descriptions for -mfsca,
+	-mno-fsca, -mfsrra, -mno-fsrra.
+
 2012-06-03  Matt Turner  <mattst88@gmail.com>
 
 	* config/mips/4600.md (r4700_imul_si): New.
@@ -18,7 +31,7 @@
 	* config/sparc/sparc-protos.h (sparc_initial_elimination_offset):
 	Prototype it.
 
-2012-06-2  Kenneth Zadeck <zadeck@naturalbridge.com>
+2012-06-02  Kenneth Zadeck <zadeck@naturalbridge.com>
 
 	* expmed.c (expand_mult, choose_multiplier): Change "2 *
 	HOST_BITS_PER_WIDE_INT" to "HOST_BITS_PER_DOUBLE_INT".
diff --git a/gcc/config/sh/sh.c b/gcc/config/sh/sh.c
index 20e67c6..d5071c8 100644
--- a/gcc/config/sh/sh.c
+++ b/gcc/config/sh/sh.c
@@ -876,12 +876,29 @@ sh_option_override (void)
 	align_functions = min_align;
     }
 
-  /* Enable fmac insn for "a * b + c" SFmode calculations when -ffast-math
-     is enabled and -mno-fused-madd is not specified by the user.
-     The fmac insn can't be enabled by default due to the implied
-     FMA semantics.   See also PR target/29100.  */
-  if (global_options_set.x_TARGET_FMAC == 0 && flag_unsafe_math_optimizations)
-    TARGET_FMAC = 1;
+  if (flag_unsafe_math_optimizations)
+    {
+      /* Enable fmac insn for "a * b + c" SFmode calculations when -ffast-math
+	 is enabled and -mno-fused-madd is not specified by the user.
+	 The fmac insn can't be enabled by default due to the implied
+	 FMA semantics.   See also PR target/29100.  */
+      if (global_options_set.x_TARGET_FMAC == 0)
+	TARGET_FMAC = 1;
+
+      /* Enable fsca insn for SH4A if not otherwise specified by the user.  */
+      if (global_options_set.x_TARGET_FSCA == 0 && TARGET_SH4A_FP)
+	TARGET_FSCA = 1;
+
+      /* Enable fsrra insn for SH4A if not otherwise specified by the user.  */
+      if (global_options_set.x_TARGET_FSRRA == 0 && TARGET_SH4A_FP)
+	TARGET_FSRRA = 1;
+    }
+
+  /*  Allow fsrra insn only if -funsafe-math-optimizations and
+      -ffinite-math-only is enabled.  */
+  TARGET_FSRRA = TARGET_FSRRA
+		 && flag_unsafe_math_optimizations
+		 && flag_finite_math_only;
 
   if (sh_fixed_range_str)
     sh_fix_range (sh_fixed_range_str);
@@ -896,7 +913,6 @@ sh_option_override (void)
     error ("-msoft-atomic and -mhard-atomic cannot be used at the same time");
   if (TARGET_HARD_ATOMIC && ! TARGET_SH4A_ARCH)
     error ("-mhard-atomic is only available for SH4A targets");
-
 }
 
 /* Print the operand address in x to the stream.  */
diff --git a/gcc/config/sh/sh.md b/gcc/config/sh/sh.md
index 99d4c62..3bb14e8 100644
--- a/gcc/config/sh/sh.md
+++ b/gcc/config/sh/sh.md
@@ -10689,7 +10689,7 @@ label:
 	(div:SF (match_operand:SF 1 "immediate_operand" "i")
 		(sqrt:SF (match_operand:SF 2 "register_operand" "0"))))
    (use (match_operand:PSI 3 "fpscr_operand" "c"))]
-  "TARGET_SH4A_FP && flag_unsafe_math_optimizations
+  "TARGET_FPU_ANY && TARGET_FSRRA
    && operands[1] == CONST1_RTX (SFmode)"
   "fsrra	%0"
   [(set_attr "type" "fsrra")
@@ -10705,47 +10705,35 @@ label:
 	 (unspec:SF [(mult:SF (float:SF (match_dup 1)) (match_dup 2))
 		    ] UNSPEC_FCOSA)))
    (use (match_operand:PSI 3 "fpscr_operand" "c"))]
-  "TARGET_SH4A_FP && flag_unsafe_math_optimizations
+  "TARGET_FPU_ANY && TARGET_FSCA
    && operands[2] == sh_fsca_int2sf ()"
   "fsca	fpul,%d0"
   [(set_attr "type" "fsca")
    (set_attr "fp_mode" "single")])
 
-(define_expand "sinsf2"
+;; When the sincos pattern is defined, the builtin functions sin and cos
+;; will be expanded to the sincos pattern and one of the output values will
+;; remain unused.
+(define_expand "sincossf3"
   [(set (match_operand:SF 0 "nonimmediate_operand" "")
-	(unspec:SF [(match_operand:SF 1 "fp_arith_reg_operand" "")]
-		   UNSPEC_FSINA))]
-  "TARGET_SH4A_FP && flag_unsafe_math_optimizations"
+	(unspec:SF [(match_operand:SF 2 "fp_arith_reg_operand" "")]
+		   UNSPEC_FSINA))
+   (set (match_operand:SF 1 "nonimmediate_operand" "")
+	(unspec:SF [(match_dup 2)] UNSPEC_FCOSA))]
+  "TARGET_FPU_ANY && TARGET_FSCA"
 {
   rtx scaled = gen_reg_rtx (SFmode);
   rtx truncated = gen_reg_rtx (SImode);
   rtx fsca = gen_reg_rtx (V2SFmode);
   rtx scale_reg = force_reg (SFmode, sh_fsca_sf2int ());
 
-  emit_sf_insn (gen_mulsf3 (scaled, operands[1], scale_reg));
+  emit_sf_insn (gen_mulsf3 (scaled, operands[2], scale_reg));
   emit_sf_insn (gen_fix_truncsfsi2 (truncated, scaled));
   emit_sf_insn (gen_fsca (fsca, truncated, sh_fsca_int2sf (),
 			  get_fpscr_rtx ()));
-  emit_move_insn (operands[0], gen_rtx_SUBREG (SFmode, fsca, 0));
-  DONE;
-})
-
-(define_expand "cossf2"
-  [(set (match_operand:SF 0 "nonimmediate_operand" "")
-	(unspec:SF [(match_operand:SF 1 "fp_arith_reg_operand" "")]
-		   UNSPEC_FCOSA))]
-  "TARGET_SH4A_FP && flag_unsafe_math_optimizations"
-{
-  rtx scaled = gen_reg_rtx (SFmode);
-  rtx truncated = gen_reg_rtx (SImode);
-  rtx fsca = gen_reg_rtx (V2SFmode);
-  rtx scale_reg = force_reg (SFmode, sh_fsca_sf2int ());
 
-  emit_sf_insn (gen_mulsf3 (scaled, operands[1], scale_reg));
-  emit_sf_insn (gen_fix_truncsfsi2 (truncated, scaled));
-  emit_sf_insn (gen_fsca (fsca, truncated, sh_fsca_int2sf (),
-			  get_fpscr_rtx ()));
-  emit_move_insn (operands[0], gen_rtx_SUBREG (SFmode, fsca, 4));
+  emit_move_insn (operands[0], gen_rtx_SUBREG (SFmode, fsca, 0));
+  emit_move_insn (operands[1], gen_rtx_SUBREG (SFmode, fsca, 4));
   DONE;
 })
 
diff --git a/gcc/config/sh/sh.opt b/gcc/config/sh/sh.opt
index 6a78d04..be315d7 100644
--- a/gcc/config/sh/sh.opt
+++ b/gcc/config/sh/sh.opt
@@ -348,3 +348,12 @@ Don't generate privileged-mode only code; implies -mno-inline-ic_invalidate if t
 mpretend-cmove
 Target Var(TARGET_PRETEND_CMOVE)
 Pretend a branch-around-a-move is a conditional move.
+
+mfsca
+Target Var(TARGET_FSCA)
+Enable the use of the fsca instruction
+
+mfsrra
+Target Var(TARGET_FSRRA)
+Enable the use of the fsrra instruction
+
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index eb582b3..d4f22e8 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -886,7 +886,7 @@ See RS/6000 and PowerPC Options.
 -mindexed-addressing -mgettrcost=@var{number} -mpt-fixed @gol
 -maccumulate-outgoing-args -minvalid-symbols -msoft-atomic -mhard-atomic @gol
 -mbranch-cost=@var{num} -mcbranchdi -mcmpeqdi -mfused-madd -mno-fused-madd @gol
--mpretend-cmove -menable-tas}
+-mfsca -mno-fsca -mfsrra -mno-fsrra -mpretend-cmove -menable-tas}
 
 @emph{Solaris 2 Options}
 @gccoptlist{-mimpure-text  -mno-impure-text @gol
@@ -18302,6 +18302,28 @@ arithmetic.  @code{-mfused-madd} is enabled by default by option
 disallow the usage of the @code{fmac} instruction for regular calculations
 even if @option{-funsafe-math-optimizations} is in effect.
 
+@item -mfsca
+@itemx -mno-fsca
+@opindex mfsca
+@opindex mno-fsca
+Allow or disallow the compiler to emit the @code{fsca} instruction for sine
+and cosine approximations.  The option @code{-mfsca} must be used in
+combination with @code{-funsafe-math-optimizations}.  It is enabled by default
+when generating code for SH4A.  Using @code{-mno-fsca} disables sine and cosine
+approximations even if @code{-funsafe-math-optimizations} is in effect.
+
+@item -mfsrra
+@itemx -mno-fsrra
+@opindex mfsrra
+@opindex mno-fsrra
+Allow or disallow the compiler to emit the @code{fsrra} instruction for
+reciprocal square root approximations.  The option @code{-mfsrra} must be used
+in combination with @code{-funsafe-math-optimizations} and
+@code{-ffinite-math-only}.  It is enabled by default when generating code for
+SH4A.  Using @code{-mno-fsrra} disables reciprocal square root approximations
+even if @code{-funsafe-math-optimizations} and @code{-ffinite-math-only} are
+in effect.
+
 @item -mpretend-cmove
 @opindex mpretend-cmove
 Prefer zero-displacement conditional branches for conditional move instruction
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 3d0b249..946fb3f 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,11 @@
+2012-06-03  Oleg Endo  <olegendo@gcc.gnu.org>
+
+	PR target/53512
+	* gcc.target/sh/pr53512-1.c: New.
+	* gcc.target/sh/pr53512-2.c: New.
+	* gcc.target/sh/pr53512-3.c: New.
+	* gcc.target/sh/pr53512-4.c: New.
+
 2012-06-01  Jason Merrill  <jason@redhat.com>
 
 	PR c++/52973
diff --git a/gcc/testsuite/gcc.target/sh/pr53512-1.c b/gcc/testsuite/gcc.target/sh/pr53512-1.c
new file mode 100644
index 0000000..b46db65
--- /dev/null
+++ b/gcc/testsuite/gcc.target/sh/pr53512-1.c
@@ -0,0 +1,26 @@
+/* Verify that the fsca insn is used when specifying -mfsca and
+  -funsafe-math-optimizations.  */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-O1 -mfsca -funsafe-math-optimizations" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m1" "-m2*" "-m4al" "*nofpu" "-m4-340*" "-m4-400*" "-m4-500*" "-m5*" } { "" } }  */
+/* { dg-final { scan-assembler-times "fsca" 3 } } */
+
+#include <math.h>
+
+float
+test_func_00 (float x)
+{
+  return sinf (x) + cosf (x);
+}
+
+float
+test_func_01 (float x)
+{
+  return sinf (x);
+}
+
+float
+test_func_02 (float x)
+{
+  return cosf (x);
+}
diff --git a/gcc/testsuite/gcc.target/sh/pr53512-2.c b/gcc/testsuite/gcc.target/sh/pr53512-2.c
new file mode 100644
index 0000000..d629ee7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/sh/pr53512-2.c
@@ -0,0 +1,26 @@
+/* Verify that the fsca insn is not used when specifying -mno-fsca and
+  -funsafe-math-optimizations.  */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-O1 -mno-fsca -funsafe-math-optimizations" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m1" "-m2*" "-m4al" "*nofpu" "-m4-340*" "-m4-400*" "-m4-500*" "-m5*" } { "" } }  */
+/* { dg-final { scan-assembler-not "fsca" } } */
+
+#include <math.h>
+
+float
+test_func_00 (float x)
+{
+  return sinf (x) + cosf (x);
+}
+
+float
+test_func_01 (float x)
+{
+  return sinf (x);
+}
+
+float
+test_func_02 (float x)
+{
+  return cosf (x);
+}
diff --git a/gcc/testsuite/gcc.target/sh/pr53512-3.c b/gcc/testsuite/gcc.target/sh/pr53512-3.c
new file mode 100644
index 0000000..b8e6ada
--- /dev/null
+++ b/gcc/testsuite/gcc.target/sh/pr53512-3.c
@@ -0,0 +1,15 @@
+/* Verify that the fsrra insn is used when specifying -mfsrra and
+  -funsafe-math-optimizations and -ffinite-math-only.  */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-O1 -mfsrra -funsafe-math-optimizations -ffinite-math-only" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m1" "-m2*" "-m4al" "*nofpu" "-m4-340*" "-m4-400*" "-m4-500*" "-m5*" } { "" } }  */
+/* { dg-final { scan-assembler "fsrra" } } */
+
+#include <math.h>
+
+float
+test_func_00 (float x)
+{
+  return 1 / sqrtf (x);
+}
+
diff --git a/gcc/testsuite/gcc.target/sh/pr53512-4.c b/gcc/testsuite/gcc.target/sh/pr53512-4.c
new file mode 100644
index 0000000..9ddad38
--- /dev/null
+++ b/gcc/testsuite/gcc.target/sh/pr53512-4.c
@@ -0,0 +1,15 @@
+/* Verify that the fsrra insn is not used when specifying -mno-fsrra and
+  -funsafe-math-optimizations and -ffinite-math-only.  */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-O1 -mno-fsrra -funsafe-math-optimizations -ffinite-math-only" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m1" "-m2*" "-m4al" "*nofpu" "-m4-340*" "-m4-400*" "-m4-500*" "-m5*" } { "" } }  */
+/* { dg-final { scan-assembler-not "fsrra" } } */
+
+#include <math.h>
+
+float
+test_func_00 (float x)
+{
+  return 1 / sqrtf (x);
+}
+