Patchwork [PATCHv5] rs6000: Add 2 built-ins to read the Time Base Register on PowerPC

login
register
mail settings
Submitter Tulio Magno Quites Machado Filho
Date Sept. 19, 2012, 6:18 p.m.
Message ID <1348078684-9380-1-git-send-email-tuliom@linux.vnet.ibm.com>
Download mbox | patch
Permalink /patch/185130/
State New
Headers show

Comments

Tulio Magno Quites Machado Filho - Sept. 19, 2012, 6:18 p.m.
Changes since v4:
- Changed the condition register mode to CC;
- Fixed some style issues (removed spaces between operands in asm, included
  spaces after function names in the testcases and before sentences in the
  manual)

-- >8 --

Add __builtin_ppc_get_timebase and __builtin_ppc_mftb to read the Time
Base Register on PowerPC.
They are required by applications that measure time at high frequencies
with high precision that can't afford a syscall.
__builtin_ppc_get_timebase returns the 64 bits of the Time Base Register
while __builtin_ppc_mftb generates only 1 instruction and returns the
least significant word on 32-bit environments and the whole Time Base value
on 64-bit.

[gcc]
2012-09-19 Tulio Magno Quites Machado Filho <tuliom@linux.vnet.ibm.com>

	* config/rs6000/rs6000-builtin.def: Add __builtin_ppc_get_timebase
	and __builtin_ppc_mftb.
	* config/rs6000/rs6000.c (rs6000_expand_zeroop_builtin): New
	function to expand an expression that calls a built-in without
	arguments.
	(rs6000_expand_builtin): Add __builtin_ppc_get_timebase and
	__builtin_ppc_mftb.
	(rs6000_init_builtins): Likewise.
	* config/rs6000/rs6000.md: Likewise.
	* doc/extend.texi (PowerPC Built-in Functions): New section.
	(PowerPC AltiVec/VSX Built-in Functions):
	Move some built-ins unrelated to Altivec/VSX to the new section.

[gcc/testsuite]
2012-09-19 Tulio Magno Quites Machado Filho <tuliom@linux.vnet.ibm.com>

	* gcc.target/powerpc/ppc-get-timebase.c: New file.
	* gcc.target/powerpc/ppc-mftb.c: New file.
---
 gcc/config/rs6000/rs6000-builtin.def               |    6 ++
 gcc/config/rs6000/rs6000.c                         |   46 ++++++++++++++
 gcc/config/rs6000/rs6000.md                        |   66 ++++++++++++++++++++
 gcc/doc/extend.texi                                |   51 ++++++++++-----
 .../gcc.target/powerpc/ppc-get-timebase.c          |   20 ++++++
 gcc/testsuite/gcc.target/powerpc/ppc-mftb.c        |   18 +++++
 6 files changed, 189 insertions(+), 18 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/ppc-get-timebase.c
 create mode 100644 gcc/testsuite/gcc.target/powerpc/ppc-mftb.c

Patch

diff --git a/gcc/config/rs6000/rs6000-builtin.def b/gcc/config/rs6000/rs6000-builtin.def
index c8f8f86..9fa3a0f 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -1429,6 +1429,12 @@  BU_SPECIAL_X (RS6000_BUILTIN_RSQRT, "__builtin_rsqrt", RS6000_BTM_FRSQRTE,
 BU_SPECIAL_X (RS6000_BUILTIN_RSQRTF, "__builtin_rsqrtf", RS6000_BTM_FRSQRTES,
 	      RS6000_BTC_FP)
 
+BU_SPECIAL_X (RS6000_BUILTIN_GET_TB, "__builtin_ppc_get_timebase",
+	     RS6000_BTM_ALWAYS, RS6000_BTC_MISC)
+
+BU_SPECIAL_X (RS6000_BUILTIN_MFTB, "__builtin_ppc_mftb",
+	     RS6000_BTM_ALWAYS, RS6000_BTC_MISC)
+
 /* Darwin CfString builtin.  */
 BU_SPECIAL_X (RS6000_BUILTIN_CFSTRING, "__builtin_cfstring", RS6000_BTM_ALWAYS,
 	      RS6000_BTC_MISC)
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index a5a3848..c3bece1 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -9748,6 +9748,30 @@  rs6000_overloaded_builtin_p (enum rs6000_builtins fncode)
   return (rs6000_builtin_info[(int)fncode].attr & RS6000_BTC_OVERLOADED) != 0;
 }
 
+/* Expand an expression EXP that calls a builtin without arguments.  */
+static rtx
+rs6000_expand_zeroop_builtin (enum insn_code icode, rtx target)
+{
+  rtx pat;
+  enum machine_mode tmode = insn_data[icode].operand[0].mode;
+
+  if (icode == CODE_FOR_nothing)
+    /* Builtin not supported on this processor.  */
+    return 0;
+
+  if (target == 0
+      || GET_MODE (target) != tmode
+      || ! (*insn_data[icode].operand[0].predicate) (target, tmode))
+    target = gen_reg_rtx (tmode);
+
+  pat = GEN_FCN (icode) (target);
+  if (! pat)
+    return 0;
+  emit_insn (pat);
+
+  return target;
+}
+
 
 static rtx
 rs6000_expand_unop_builtin (enum insn_code icode, tree exp, rtx target)
@@ -11337,6 +11361,16 @@  rs6000_expand_builtin (tree exp, rtx target, rtx subtarget ATTRIBUTE_UNUSED,
 					   ? CODE_FOR_bpermd_di
 					   : CODE_FOR_bpermd_si), exp, target);
 
+    case RS6000_BUILTIN_GET_TB:
+      return rs6000_expand_zeroop_builtin (CODE_FOR_rs6000_get_timebase,
+					   target);
+
+    case RS6000_BUILTIN_MFTB:
+      return rs6000_expand_zeroop_builtin (((TARGET_64BIT)
+					    ? CODE_FOR_rs6000_mftb_di
+					    : CODE_FOR_rs6000_mftb_si),
+					   target);
+
     case ALTIVEC_BUILTIN_MASK_FOR_LOAD:
     case ALTIVEC_BUILTIN_MASK_FOR_STORE:
       {
@@ -11621,6 +11655,18 @@  rs6000_init_builtins (void)
 				 POWER7_BUILTIN_BPERMD, "__builtin_bpermd");
   def_builtin ("__builtin_bpermd", ftype, POWER7_BUILTIN_BPERMD);
 
+  ftype = build_function_type_list (unsigned_intDI_type_node,
+				    NULL_TREE);
+  def_builtin ("__builtin_ppc_get_timebase", ftype, RS6000_BUILTIN_GET_TB);
+
+  if (TARGET_64BIT)
+    ftype = build_function_type_list (unsigned_intDI_type_node,
+				      NULL_TREE);
+  else
+    ftype = build_function_type_list (unsigned_intSI_type_node,
+				      NULL_TREE);
+  def_builtin ("__builtin_ppc_mftb", ftype, RS6000_BUILTIN_MFTB);
+
 #if TARGET_XCOFF
   /* AIX libm provides clog as __clog.  */
   if ((tdecl = builtin_decl_explicit (BUILT_IN_CLOG)) != NULL_TREE)
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index f2bc15f..c499156 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -136,6 +136,7 @@ 
    UNSPECV_PROBE_STACK_RANGE	; probe range of stack addresses
    UNSPECV_EH_RR		; eh_reg_restore
    UNSPECV_ISYNC		; isync instruction
+   UNSPECV_MFTB			; move from time base
   ])
 
 
@@ -14103,6 +14104,71 @@ 
   ""
   "")
 
+(define_expand "rs6000_get_timebase"
+  [(use (match_operand:DI 0 "gpc_reg_operand" ""))]
+  ""
+{
+  if (TARGET_POWERPC64)
+    emit_insn (gen_rs6000_mftb_di (operands[0]));
+  else
+    emit_insn (gen_rs6000_get_timebase_ppc32 (operands[0]));
+  DONE;
+})
+
+(define_insn "rs6000_get_timebase_ppc32"
+  [(set (match_operand:DI 0 "gpc_reg_operand" "=r")
+        (unspec_volatile:DI [(const_int 0)] UNSPECV_MFTB))
+   (clobber (match_scratch:SI 1 "=r"))
+   (clobber (match_scratch:CC 2 "=y"))]
+  "!TARGET_POWERPC64"
+{
+  if (WORDS_BIG_ENDIAN)
+    if (TARGET_MFCRF)
+      {
+        return "mfspr %0,269\;"
+	       "mfspr %L0,268\;"
+	       "mfspr %1,269\;"
+	       "cmpw %2,%0, %1\;"
+	       "bne- %2,$-16";
+      }
+    else
+      {
+        return "mftbu %0\;"
+	       "mftb %L0\;"
+	       "mftbu %1\;"
+	       "cmpw %2,%0,%1\;"
+	       "bne- %2,$-16";
+      }
+  else
+    if (TARGET_MFCRF)
+      {
+        return "mfspr %L0,269\;"
+	       "mfspr %0,268\;"
+	       "mfspr %1,269\;"
+	       "cmpw %2,%L0,%1\;"
+	       "bne- %2,$-16";
+      }
+    else
+      {
+        return "mftbu %L0\;"
+	       "mftb %0\;"
+	       "mftbu %1\;"
+	       "cmpw %2,%L0,%1\;"
+	       "bne- %2,$-16";
+      }
+})
+
+(define_insn "rs6000_mftb_<mode>"
+  [(set (match_operand:P 0 "gpc_reg_operand" "=r")
+        (unspec_volatile:P [(const_int 0)] UNSPECV_MFTB))]
+  ""
+{
+  if (TARGET_MFCRF)
+    return "mfspr %0,268";
+  else
+    return "mftb %0";
+})
+
 
 
 (include "sync.md")
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
index e850266..5a75d45 100644
--- a/gcc/doc/extend.texi
+++ b/gcc/doc/extend.texi
@@ -8647,6 +8647,7 @@  instructions, but allow the compiler to schedule those calls.
 * MIPS Loongson Built-in Functions::
 * Other MIPS Built-in Functions::
 * picoChip Built-in Functions::
+* PowerPC Built-in Functions::
 * PowerPC AltiVec/VSX Built-in Functions::
 * RX Built-in Functions::
 * SPARC VIS Built-in Functions::
@@ -11596,6 +11597,38 @@  GCC defines the preprocessor macro @code{___GCC_HAVE_BUILTIN_MIPS_CACHE}
 when this function is available.
 @end table
 
+@node PowerPC Built-in Functions
+@subsection PowerPC Built-in Functions
+
+These built-in functions are available for the PowerPC family of
+processors:
+@smallexample
+float __builtin_recipdivf (float, float);
+float __builtin_rsqrtf (float);
+double __builtin_recipdiv (double, double);
+double __builtin_rsqrt (double);
+long __builtin_bpermd (long, long);
+uint64_t __builtin_ppc_get_timebase ();
+unsigned long __builtin_ppc_mftb ();
+@end smallexample
+
+The @code{vec_rsqrt}, @code{__builtin_rsqrt}, and
+@code{__builtin_rsqrtf} functions generate multiple instructions to
+implement the reciprocal sqrt functionality using reciprocal sqrt
+estimate instructions.
+
+The @code{__builtin_recipdiv}, and @code{__builtin_recipdivf}
+functions generate multiple instructions to implement division using
+the reciprocal estimate instructions.
+
+The @code{__builtin_ppc_get_timebase} and @code{__builtin_ppc_mftb}
+functions generate instructions to read the Time Base Register.  The
+@code{__builtin_ppc_get_timebase} function may generate multiple
+instructions and always returns the 64 bits of the Time Base Register.
+The @code{__builtin_ppc_mftb} function always generates one instruction and
+returns the Time Base Register value as an unsigned long, throwing away
+the most significant word on 32-bit environments.
+
 @node PowerPC AltiVec/VSX Built-in Functions
 @subsection PowerPC AltiVec Built-in Functions
 
@@ -13653,24 +13686,6 @@  if the VSX instruction set is available.  The @samp{vec_vsx_ld} and
 @samp{vec_vsx_st} builtins will always generate the VSX @samp{LXVD2X},
 @samp{LXVW4X}, @samp{STXVD2X}, and @samp{STXVW4X} instructions.
 
-GCC provides a few other builtins on Powerpc to access certain instructions:
-@smallexample
-float __builtin_recipdivf (float, float);
-float __builtin_rsqrtf (float);
-double __builtin_recipdiv (double, double);
-double __builtin_rsqrt (double);
-long __builtin_bpermd (long, long);
-@end smallexample
-
-The @code{vec_rsqrt}, @code{__builtin_rsqrt}, and
-@code{__builtin_rsqrtf} functions generate multiple instructions to
-implement the reciprocal sqrt functionality using reciprocal sqrt
-estimate instructions.
-
-The @code{__builtin_recipdiv}, and @code{__builtin_recipdivf}
-functions generate multiple instructions to implement division using
-the reciprocal estimate instructions.
-
 @node RX Built-in Functions
 @subsection RX Built-in Functions
 GCC supports some of the RX instructions which cannot be expressed in
diff --git a/gcc/testsuite/gcc.target/powerpc/ppc-get-timebase.c b/gcc/testsuite/gcc.target/powerpc/ppc-get-timebase.c
new file mode 100644
index 0000000..9de8929
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/ppc-get-timebase.c
@@ -0,0 +1,20 @@ 
+/* { dg-do run { target { powerpc*-*-* } } } */
+
+/* Test if __builtin_ppc_get_timebase () is compatible with the current
+   processor and if it's changing between reads.  A read failure might indicate
+   a Power ISA or binutils change.  */
+
+#include <inttypes.h>
+
+int
+main (void)
+{
+  uint64_t t = __builtin_ppc_get_timebase ();
+  int j;
+
+  for (j = 0; j < 1000000; j++)
+    if (t != __builtin_ppc_get_timebase ())
+      return 0;
+
+  return 1;
+}
diff --git a/gcc/testsuite/gcc.target/powerpc/ppc-mftb.c b/gcc/testsuite/gcc.target/powerpc/ppc-mftb.c
new file mode 100644
index 0000000..f64e45d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/ppc-mftb.c
@@ -0,0 +1,18 @@ 
+/* { dg-do run { target { powerpc*-*-* } } } */
+
+/* Test if __builtin_ppc_mftb () is compatible with the current processor and
+   if it's changing between reads.  A read failure might indicate a Power
+   ISA or binutils change.  */
+
+int
+main (void)
+{
+  unsigned long t = __builtin_ppc_mftb ();
+  int j;
+
+  for (j = 0; j < 1000000; j++)
+    if (t != __builtin_ppc_mftb ())
+      return 0;
+
+  return 1;
+}