rs6000: Consider inline asm as safe if no assembler complains [PR111828]

As discussed in PR111828, rs6000_update_ipa_fn_target_info
is much conservative, currently for any non-empty inline
asm, without any parsing, it would take inline asm could
have HTM insns.  It means for one function attributed with
power8 having inline asm, even if it has no HTM insns, we
don't make a function attributed with power10 inline it.

Peter pointed out an inline asm parser can be a slippery
slope, and noticed that the current gnu assembler still
allows HTM insns even with power10 machine type, so he
suggested that we can aggressively ignore the handling on
inline asm, this patch goes for this suggestion.

Considering that there are a few assembler alternatives
and assembler can update its behaviors (complaining HTM
insns at power10 and later cpus sounds reasonable from a
certain point of view), this patch also checks assembler
complains on HTM insns at power10 or not.  For a case that
a caller attributed power10 calls a callee attributed
power8 having inline asm with HTM insn, without inlining
at least the compilation succeeds, but if assembler
complains HTM insns at power10, after inlining the
compilation would fail.

The two associated test cases are fine without and with
this patch (effective target takes effect or not).

	PR target/111828

gcc/ChangeLog:

	* config.in: Regenerate.
	* config/rs6000/rs6000.cc (rs6000_update_ipa_fn_target_info): Guard
	inline asm handling under !HAVE_AS_POWER10_HTM.
	* configure: Regenerate.
	* configure.ac: Detect assembler support for HTM insns at power10.

gcc/testsuite/ChangeLog:

	* lib/target-supports.exp
	(check_effective_target_powerpc_as_p10_htm): New proc.
	* g++.target/powerpc/pr111828-1.C: New test.
	* g++.target/powerpc/pr111828-2.C: New test.

diff --git a/gcc/config.in b/gcc/config.in
index 03faee1c6ac1e81a8cf5ec5dac6d48e5c1107090..0509ba7e6a799df7cc649dff2d82317e88f99b14 100644 (file)
--- a/gcc/config.in
+++ b/gcc/config.in
@@ -701,6 +701,12 @@
 #endif
 
 
+/* Define if your assembler supports htm insns on power10. */
+#ifndef USED_FOR_TARGET
+#undef HAVE_AS_POWER10_HTM
+#endif
+
+
 /* Define if your assembler supports .ref */
 #ifndef USED_FOR_TARGET
 #undef HAVE_AS_REF

diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 9f750674e53b516a8ecd6a06fd58761abdedea7e..5f56c3ed85b5b759f5e02058efcde31249737499 100644 (file)
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -25682,6 +25682,7 @@ rs6000_need_ipa_fn_target_info (const_tree decl,
 static bool
 rs6000_update_ipa_fn_target_info (unsigned int &info, const gimple *stmt)
 {
+#ifndef HAVE_AS_POWER10_HTM
   /* Assume inline asm can use any instruction features.  */
   if (gimple_code (stmt) == GIMPLE_ASM)
     {
@@ -25693,7 +25694,9 @@ rs6000_update_ipa_fn_target_info (unsigned int &info, const gimple *stmt)
        info |= RS6000_FN_TARGET_INFO_HTM;
       return false;
     }
-  else if (gimple_code (stmt) == GIMPLE_CALL)
+#endif
+
+  if (gimple_code (stmt) == GIMPLE_CALL)
     {
       tree fndecl = gimple_call_fndecl (stmt);
       if (fndecl && fndecl_built_in_p (fndecl, BUILT_IN_MD))

diff --git a/gcc/configure b/gcc/configure
index d4ad988000f02d641fddeb47e38a5e9e8cecbc8f..4d0357cbc28f55efb2bd0b25776e9bd5436bc86e 100755 (executable)
--- a/gcc/configure
+++ b/gcc/configure
@@ -28408,6 +28408,49 @@ if test $gcc_cv_as_powerpc_mfcrf = yes; then
 
 $as_echo "#define HAVE_AS_MFCRF 1" >>confdefs.h
 
+fi
+
+
+    case $target in
+      *-*-aix*) conftest_s='   .machine "pwr10"
+       .csect .text[PR]
+       tend. 0';;
+      *-*-darwin*) conftest_s='        .text
+       tend. 0';;
+      *) conftest_s='  .machine power10
+       .text
+       tend. 0';;
+    esac
+
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking assembler for htm support on Power10" >&5
+$as_echo_n "checking assembler for htm support on Power10... " >&6; }
+if ${gcc_cv_as_power10_htm+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  gcc_cv_as_power10_htm=no
+  if test x$gcc_cv_as != x; then
+    $as_echo "$conftest_s" > conftest.s
+    if { ac_try='$gcc_cv_as $gcc_cv_as_flags  -o conftest.o conftest.s >&5'
+  { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_try\""; } >&5
+  (eval $ac_try) 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; }
+    then
+       gcc_cv_as_power10_htm=yes
+    else
+      echo "configure: failed program was" >&5
+      cat conftest.s >&5
+    fi
+    rm -f conftest.o conftest.s
+  fi
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $gcc_cv_as_power10_htm" >&5
+$as_echo "$gcc_cv_as_power10_htm" >&6; }
+if test $gcc_cv_as_power10_htm = yes; then
+
+$as_echo "#define HAVE_AS_POWER10_HTM 1" >>confdefs.h
+
 fi
 
 

diff --git a/gcc/configure.ac b/gcc/configure.ac
index dc8cb6a33de23f9e6a33a316b62e71eaa8d9b5c3..764a33f0b0446d59ffa7ff7321c9cc9f53c349f7 100644 (file)
--- a/gcc/configure.ac
+++ b/gcc/configure.ac
@@ -5132,6 +5132,23 @@ gd:
       [AC_DEFINE(HAVE_AS_MFCRF, 1,
          [Define if your assembler supports mfcr field.])])
 
+    case $target in
+      *-*-aix*) conftest_s='   .machine "pwr10"
+       .csect .text[[PR]]
+       tend. 0';;
+      *-*-darwin*) conftest_s='        .text
+       tend. 0';;
+      *) conftest_s='  .machine power10
+       .text
+       tend. 0';;
+    esac
+
+    gcc_GAS_CHECK_FEATURE([htm support on Power10],
+      gcc_cv_as_power10_htm,,
+      [$conftest_s],,
+      [AC_DEFINE(HAVE_AS_POWER10_HTM, 1,
+         [Define if your assembler supports htm insns on power10.])])
+
     case $target in
       *-*-aix*) conftest_s='   .csect .text[[PR]]
 LCF..0:

diff --git a/gcc/testsuite/g++.target/powerpc/pr111828-1.C b/gcc/testsuite/g++.target/powerpc/pr111828-1.C
new file mode 100644 (file)
index 0000000..d76a084
--- /dev/null
+++ b/gcc/testsuite/g++.target/powerpc/pr111828-1.C
@@ -0,0 +1,49 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_as_p10_htm } */
+/* Use -Wno-attributes to suppress the possible warning on always_inline.  */
+/* { dg-options "-O2 -mdejagnu-cpu=power9 -Wno-attributes" } */
+
+/* Verify it doesn't emit any error messages.  */
+
+#include <stddef.h>
+#define HWY_PRAGMA(tokens) _Pragma (#tokens)
+#define HWY_PUSH_ATTRIBUTES(targets_str) HWY_PRAGMA (GCC target targets_str)
+__attribute__ ((always_inline)) void
+PreventElision (int output)
+{
+  asm("nop" : "+r"(output) : : "memory");
+}
+#define HWY_BEFORE_NAMESPACE() HWY_PUSH_ATTRIBUTES (",cpu=power10")
+HWY_BEFORE_NAMESPACE () namespace detail
+{
+  template <typename, size_t, int> struct CappedTagChecker
+  {
+  };
+}
+template <typename T, size_t kLimit, int kPow2 = 0>
+using CappedTag = detail::CappedTagChecker<T, kLimit, kPow2>;
+template <typename, size_t, size_t kMinArg, class Test> struct ForeachCappedR
+{
+  static void Do (size_t, size_t)
+  {
+    CappedTag<int, kMinArg> d;
+    Test () (int(), d);
+  }
+};
+template <class Test> struct ForPartialVectors
+{
+  template <typename T> void operator() (T)
+  {
+    ForeachCappedR<T, 1, 1, Test>::Do (1, 1);
+  }
+};
+struct TestFloorLog2
+{
+  template <class T, class DF> void operator() (T, DF) { PreventElision (0x10); }
+};
+void
+TestAllFloorLog2 ()
+{
+  ForPartialVectors<TestFloorLog2> () (float());
+}
+

diff --git a/gcc/testsuite/g++.target/powerpc/pr111828-2.C b/gcc/testsuite/g++.target/powerpc/pr111828-2.C
new file mode 100644 (file)
index 0000000..0b73316
--- /dev/null
+++ b/gcc/testsuite/g++.target/powerpc/pr111828-2.C
@@ -0,0 +1,52 @@
+/* { dg-do compile } */
+/* { dg-skip-if "HTM inline asm supported" { powerpc_as_p10_htm } } */
+/* Use -Wno-attributes to suppress the possible warning on always_inline.  */
+/* { dg-options "-O2 -mdejagnu-cpu=power9 -Wno-attributes" } */
+
+/* Verify it emits error messages on non-empty inline asm.  */
+
+#include <stddef.h>
+#define HWY_PRAGMA(tokens) _Pragma (#tokens)
+#define HWY_PUSH_ATTRIBUTES(targets_str) HWY_PRAGMA (GCC target targets_str)
+__attribute__ ((always_inline)) void
+PreventElision (int output) /* { dg-error "inlining failed in call to .* target specific option mismatch" } */
+{
+  asm("nop" : "+r"(output) : : "memory");
+}
+#define HWY_BEFORE_NAMESPACE() HWY_PUSH_ATTRIBUTES (",cpu=power10")
+HWY_BEFORE_NAMESPACE () namespace detail
+{
+  template <typename, size_t, int> struct CappedTagChecker
+  {
+  };
+}
+template <typename T, size_t kLimit, int kPow2 = 0>
+using CappedTag = detail::CappedTagChecker<T, kLimit, kPow2>;
+template <typename, size_t, size_t kMinArg, class Test> struct ForeachCappedR
+{
+  static void Do (size_t, size_t)
+  {
+    CappedTag<int, kMinArg> d;
+    Test () (int(), d);
+  }
+};
+template <class Test> struct ForPartialVectors
+{
+  template <typename T> void operator() (T)
+  {
+    ForeachCappedR<T, 1, 1, Test>::Do (1, 1);
+  }
+};
+struct TestFloorLog2
+{
+  template <class T, class DF> void operator() (T, DF)
+  {
+    PreventElision (0x10); /* { dg-message "called from here" } */
+  }
+};
+void
+TestAllFloorLog2 ()
+{
+  ForPartialVectors<TestFloorLog2> () (float());
+}
+

diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index bc93f6e158bb36606b60afe4ae3fe072ab481f2f..024939ee2e785f89caa88783749d0c95e6ae364b 100644 (file)
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -12901,6 +12901,46 @@ proc check_effective_target_o_flag_in_section { } {
     }]
 }
 
+# Return 1 if the given assembler supports hardware transactional memory
+# instructions with machine type Power10, 0 otherwise.  Cache the result.
+
+proc check_effective_target_powerpc_as_p10_htm { } {
+    global tool
+    global GCC_UNDER_TEST
+
+    # Need auto-host.h to check linker support.
+    if { ![file exists ../../auto-host.h ] } {
+       return 0
+    }
+
+    return [check_cached_effective_target powerpc_as_p10_htm {
+
+       set src pie[pid].c
+       set obj pie[pid].o
+
+       set f [open $src "w"]
+       puts $f "#include \"../../auto-host.h\""
+       puts $f "#if HAVE_AS_POWER10_HTM == 0"
+       puts $f "# error Assembler does not support htm insns with power10."
+       puts $f "#endif"
+       close $f
+
+       verbose "check_effective_target_powerpc_as_p10_htm compiling testfile $src" 2
+       set lines [${tool}_target_compile $src $obj object ""]
+
+       file delete $src
+       file delete $obj
+
+       if [string match "" $lines] then {
+           verbose "check_effective_target_powerpc_as_p10_htm testfile compilation passed" 2
+           return 1
+       } else {
+           verbose "check_effective_target_powerpc_as_p10_htm testfile compilation failed" 2
+           return 0
+       }
+    }]
+}
+
 # return 1 if LRA is supported.
 
 proc check_effective_target_lra { } {