File gcc48-ibm-power8-other.diff of Package cross-ia64-gcc48-icecream-backend

Overview Repositories Revisions Requests Users Attributes Meta

File gcc48-ibm-power8-other.diff of Package cross-ia64-gcc48-icecream-backend (Revision 5b8b5574b4320271965e204f41440dfd)

Currently displaying revision 5b8b5574b4320271965e204f41440dfd , Show latest

Also contains backports of not strictly required

2013-11-14  Ulrich Weigand  <Ulrich.Weigand@de.ibm.com>
            Alan Modra  <amodra@gmail.com>

* function.c (assign_parms): Use all.reg_parm_stack_space instead
        of re-evaluating REG_PARM_STACK_SPACE target macro.
        (locate_and_pad_parm): New parameter REG_PARM_STACK_SPACE.  Use it
        instead of evaluating target macro REG_PARM_STACK_SPACE every time.
        (assign_parm_find_entry_rtl): Update call.
        * calls.c (initialize_argument_information): Update call.
        (emit_library_call_value_1): Likewise.
        * expr.h (locate_and_pad_parm): Update prototype.

2013-08-19  Peter Bergner  <bergner@vnet.ibm.com>
            Jakub Jelinek  <jakub@redhat.com>

* builtins.def (BUILT_IN_FABSD32): New DFP ABS builtin.
        (BUILT_IN_FABSD64): Likewise.
        (BUILT_IN_FABSD128): Likewise.
        * builtins.c (expand_builtin): Add support for new DFP ABS builtins.
        (fold_builtin_1): Likewise.
        * config/rs6000/dfp.md (*negtd2_fpr): Handle non-overlapping
        destination and source operands.
        (*abstd2_fpr): Likewise.
        (*nabstd2_fpr): Likewise.

Index: libstdc++-v3/scripts/extract_symvers.in
===================================================================
--- libstdc++-v3/scripts/extract_symvers.in	(revision 206404)
+++ libstdc++-v3/scripts/extract_symvers.in	(working copy)
@@ -53,6 +53,7 @@
   # present on Solaris.
   ${readelf} ${lib} |\
   sed -e 's/ \[<other>: [A-Fa-f0-9]*\] //' -e '/\.dynsym/,/^$/p;d' |\
+  sed -e 's/ \[<localentry>: [0-9]*\] //' |\
   egrep -v ' (LOCAL|UND) ' |\
   egrep -v ' (_DYNAMIC|_GLOBAL_OFFSET_TABLE_|_PROCEDURE_LINKAGE_TABLE_|_edata|_end|_etext)$' |\
   sed -e 's/ <processor specific>: / <processor_specific>:_/g' |\
Index: gcc/doc/extend.texi
===================================================================
--- gcc/doc/extend.texi	(revision 206404)
+++ gcc/doc/extend.texi	(working copy)
@@ -8804,6 +8804,7 @@
 * picoChip Built-in Functions::
 * PowerPC Built-in Functions::
 * PowerPC AltiVec/VSX Built-in Functions::
+* PowerPC Hardware Transactional Memory Built-in Functions::
 * RX Built-in Functions::
 * S/390 System z Built-in Functions::
 * SH Built-in Functions::
@@ -13931,6 +13932,531 @@
 @samp{vec_vsx_st} built-in functions always generate the VSX @samp{LXVD2X},
 @samp{LXVW4X}, @samp{STXVD2X}, and @samp{STXVW4X} instructions.
 
+If the ISA 2.07 additions to the vector/scalar (power8-vector)
+instruction set is available, the following additional functions are
+available for both 32-bit and 64-bit targets.  For 64-bit targets, you
+can use @var{vector long} instead of @var{vector long long},
+@var{vector bool long} instead of @var{vector bool long long}, and
+@var{vector unsigned long} instead of @var{vector unsigned long long}.
+
+@smallexample
+vector long long vec_abs (vector long long);
+
+vector long long vec_add (vector long long, vector long long);
+vector unsigned long long vec_add (vector unsigned long long,
+                                   vector unsigned long long);
+
+int vec_all_eq (vector long long, vector long long);
+int vec_all_ge (vector long long, vector long long);
+int vec_all_gt (vector long long, vector long long);
+int vec_all_le (vector long long, vector long long);
+int vec_all_lt (vector long long, vector long long);
+int vec_all_ne (vector long long, vector long long);
+int vec_any_eq (vector long long, vector long long);
+int vec_any_ge (vector long long, vector long long);
+int vec_any_gt (vector long long, vector long long);
+int vec_any_le (vector long long, vector long long);
+int vec_any_lt (vector long long, vector long long);
+int vec_any_ne (vector long long, vector long long);
+
+vector long long vec_eqv (vector long long, vector long long);
+vector long long vec_eqv (vector bool long long, vector long long);
+vector long long vec_eqv (vector long long, vector bool long long);
+vector unsigned long long vec_eqv (vector unsigned long long,
+                                   vector unsigned long long);
+vector unsigned long long vec_eqv (vector bool long long,
+                                   vector unsigned long long);
+vector unsigned long long vec_eqv (vector unsigned long long,
+                                   vector bool long long);
+vector int vec_eqv (vector int, vector int);
+vector int vec_eqv (vector bool int, vector int);
+vector int vec_eqv (vector int, vector bool int);
+vector unsigned int vec_eqv (vector unsigned int, vector unsigned int);
+vector unsigned int vec_eqv (vector bool unsigned int,
+                             vector unsigned int);
+vector unsigned int vec_eqv (vector unsigned int,
+                             vector bool unsigned int);
+vector short vec_eqv (vector short, vector short);
+vector short vec_eqv (vector bool short, vector short);
+vector short vec_eqv (vector short, vector bool short);
+vector unsigned short vec_eqv (vector unsigned short, vector unsigned short);
+vector unsigned short vec_eqv (vector bool unsigned short,
+                               vector unsigned short);
+vector unsigned short vec_eqv (vector unsigned short,
+                               vector bool unsigned short);
+vector signed char vec_eqv (vector signed char, vector signed char);
+vector signed char vec_eqv (vector bool signed char, vector signed char);
+vector signed char vec_eqv (vector signed char, vector bool signed char);
+vector unsigned char vec_eqv (vector unsigned char, vector unsigned char);
+vector unsigned char vec_eqv (vector bool unsigned char, vector unsigned char);
+vector unsigned char vec_eqv (vector unsigned char, vector bool unsigned char);
+
+vector long long vec_max (vector long long, vector long long);
+vector unsigned long long vec_max (vector unsigned long long,
+                                   vector unsigned long long);
+
+vector long long vec_min (vector long long, vector long long);
+vector unsigned long long vec_min (vector unsigned long long,
+                                   vector unsigned long long);
+
+vector long long vec_nand (vector long long, vector long long);
+vector long long vec_nand (vector bool long long, vector long long);
+vector long long vec_nand (vector long long, vector bool long long);
+vector unsigned long long vec_nand (vector unsigned long long,
+                                    vector unsigned long long);
+vector unsigned long long vec_nand (vector bool long long,
+                                   vector unsigned long long);
+vector unsigned long long vec_nand (vector unsigned long long,
+                                    vector bool long long);
+vector int vec_nand (vector int, vector int);
+vector int vec_nand (vector bool int, vector int);
+vector int vec_nand (vector int, vector bool int);
+vector unsigned int vec_nand (vector unsigned int, vector unsigned int);
+vector unsigned int vec_nand (vector bool unsigned int,
+                              vector unsigned int);
+vector unsigned int vec_nand (vector unsigned int,
+                              vector bool unsigned int);
+vector short vec_nand (vector short, vector short);
+vector short vec_nand (vector bool short, vector short);
+vector short vec_nand (vector short, vector bool short);
+vector unsigned short vec_nand (vector unsigned short, vector unsigned short);
+vector unsigned short vec_nand (vector bool unsigned short,
+                                vector unsigned short);
+vector unsigned short vec_nand (vector unsigned short,
+                                vector bool unsigned short);
+vector signed char vec_nand (vector signed char, vector signed char);
+vector signed char vec_nand (vector bool signed char, vector signed char);
+vector signed char vec_nand (vector signed char, vector bool signed char);
+vector unsigned char vec_nand (vector unsigned char, vector unsigned char);
+vector unsigned char vec_nand (vector bool unsigned char, vector unsigned char);
+vector unsigned char vec_nand (vector unsigned char, vector bool unsigned char);
+
+vector long long vec_orc (vector long long, vector long long);
+vector long long vec_orc (vector bool long long, vector long long);
+vector long long vec_orc (vector long long, vector bool long long);
+vector unsigned long long vec_orc (vector unsigned long long,
+                                   vector unsigned long long);
+vector unsigned long long vec_orc (vector bool long long,
+                                   vector unsigned long long);
+vector unsigned long long vec_orc (vector unsigned long long,
+                                   vector bool long long);
+vector int vec_orc (vector int, vector int);
+vector int vec_orc (vector bool int, vector int);
+vector int vec_orc (vector int, vector bool int);
+vector unsigned int vec_orc (vector unsigned int, vector unsigned int);
+vector unsigned int vec_orc (vector bool unsigned int,
+                             vector unsigned int);
+vector unsigned int vec_orc (vector unsigned int,
+                             vector bool unsigned int);
+vector short vec_orc (vector short, vector short);
+vector short vec_orc (vector bool short, vector short);
+vector short vec_orc (vector short, vector bool short);
+vector unsigned short vec_orc (vector unsigned short, vector unsigned short);
+vector unsigned short vec_orc (vector bool unsigned short,
+                               vector unsigned short);
+vector unsigned short vec_orc (vector unsigned short,
+                               vector bool unsigned short);
+vector signed char vec_orc (vector signed char, vector signed char);
+vector signed char vec_orc (vector bool signed char, vector signed char);
+vector signed char vec_orc (vector signed char, vector bool signed char);
+vector unsigned char vec_orc (vector unsigned char, vector unsigned char);
+vector unsigned char vec_orc (vector bool unsigned char, vector unsigned char);
+vector unsigned char vec_orc (vector unsigned char, vector bool unsigned char);
+
+vector int vec_pack (vector long long, vector long long);
+vector unsigned int vec_pack (vector unsigned long long,
+                              vector unsigned long long);
+vector bool int vec_pack (vector bool long long, vector bool long long);
+
+vector int vec_packs (vector long long, vector long long);
+vector unsigned int vec_packs (vector unsigned long long,
+                               vector unsigned long long);
+
+vector unsigned int vec_packsu (vector long long, vector long long);
+
+vector long long vec_rl (vector long long,
+                         vector unsigned long long);
+vector long long vec_rl (vector unsigned long long,
+                         vector unsigned long long);
+
+vector long long vec_sl (vector long long, vector unsigned long long);
+vector long long vec_sl (vector unsigned long long,
+                         vector unsigned long long);
+
+vector long long vec_sr (vector long long, vector unsigned long long);
+vector unsigned long long char vec_sr (vector unsigned long long,
+                                       vector unsigned long long);
+
+vector long long vec_sra (vector long long, vector unsigned long long);
+vector unsigned long long vec_sra (vector unsigned long long,
+                                   vector unsigned long long);
+
+vector long long vec_sub (vector long long, vector long long);
+vector unsigned long long vec_sub (vector unsigned long long,
+                                   vector unsigned long long);
+
+vector long long vec_unpackh (vector int);
+vector unsigned long long vec_unpackh (vector unsigned int);
+
+vector long long vec_unpackl (vector int);
+vector unsigned long long vec_unpackl (vector unsigned int);
+
+vector long long vec_vaddudm (vector long long, vector long long);
+vector long long vec_vaddudm (vector bool long long, vector long long);
+vector long long vec_vaddudm (vector long long, vector bool long long);
+vector unsigned long long vec_vaddudm (vector unsigned long long,
+                                       vector unsigned long long);
+vector unsigned long long vec_vaddudm (vector bool unsigned long long,
+                                       vector unsigned long long);
+vector unsigned long long vec_vaddudm (vector unsigned long long,
+                                       vector bool unsigned long long);
+
+vector long long vec_vclz (vector long long);
+vector unsigned long long vec_vclz (vector unsigned long long);
+vector int vec_vclz (vector int);
+vector unsigned int vec_vclz (vector int);
+vector short vec_vclz (vector short);
+vector unsigned short vec_vclz (vector unsigned short);
+vector signed char vec_vclz (vector signed char);
+vector unsigned char vec_vclz (vector unsigned char);
+
+vector signed char vec_vclzb (vector signed char);
+vector unsigned char vec_vclzb (vector unsigned char);
+
+vector long long vec_vclzd (vector long long);
+vector unsigned long long vec_vclzd (vector unsigned long long);
+
+vector short vec_vclzh (vector short);
+vector unsigned short vec_vclzh (vector unsigned short);
+
+vector int vec_vclzw (vector int);
+vector unsigned int vec_vclzw (vector int);
+
+vector long long vec_vmaxsd (vector long long, vector long long);
+
+vector unsigned long long vec_vmaxud (vector unsigned long long,
+                                      unsigned vector long long);
+
+vector long long vec_vminsd (vector long long, vector long long);
+
+vector unsigned long long vec_vminud (vector long long,
+                                      vector long long);
+
+vector int vec_vpksdss (vector long long, vector long long);
+vector unsigned int vec_vpksdss (vector long long, vector long long);
+
+vector unsigned int vec_vpkudus (vector unsigned long long,
+                                 vector unsigned long long);
+
+vector int vec_vpkudum (vector long long, vector long long);
+vector unsigned int vec_vpkudum (vector unsigned long long,
+                                 vector unsigned long long);
+vector bool int vec_vpkudum (vector bool long long, vector bool long long);
+
+vector long long vec_vpopcnt (vector long long);
+vector unsigned long long vec_vpopcnt (vector unsigned long long);
+vector int vec_vpopcnt (vector int);
+vector unsigned int vec_vpopcnt (vector int);
+vector short vec_vpopcnt (vector short);
+vector unsigned short vec_vpopcnt (vector unsigned short);
+vector signed char vec_vpopcnt (vector signed char);
+vector unsigned char vec_vpopcnt (vector unsigned char);
+
+vector signed char vec_vpopcntb (vector signed char);
+vector unsigned char vec_vpopcntb (vector unsigned char);
+
+vector long long vec_vpopcntd (vector long long);
+vector unsigned long long vec_vpopcntd (vector unsigned long long);
+
+vector short vec_vpopcnth (vector short);
+vector unsigned short vec_vpopcnth (vector unsigned short);
+
+vector int vec_vpopcntw (vector int);
+vector unsigned int vec_vpopcntw (vector int);
+
+vector long long vec_vrld (vector long long, vector unsigned long long);
+vector unsigned long long vec_vrld (vector unsigned long long,
+                                    vector unsigned long long);
+
+vector long long vec_vsld (vector long long, vector unsigned long long);
+vector long long vec_vsld (vector unsigned long long,
+                           vector unsigned long long);
+
+vector long long vec_vsrad (vector long long, vector unsigned long long);
+vector unsigned long long vec_vsrad (vector unsigned long long,
+                                     vector unsigned long long);
+
+vector long long vec_vsrd (vector long long, vector unsigned long long);
+vector unsigned long long char vec_vsrd (vector unsigned long long,
+                                         vector unsigned long long);
+
+vector long long vec_vsubudm (vector long long, vector long long);
+vector long long vec_vsubudm (vector bool long long, vector long long);
+vector long long vec_vsubudm (vector long long, vector bool long long);
+vector unsigned long long vec_vsubudm (vector unsigned long long,
+                                       vector unsigned long long);
+vector unsigned long long vec_vsubudm (vector bool long long,
+                                       vector unsigned long long);
+vector unsigned long long vec_vsubudm (vector unsigned long long,
+                                       vector bool long long);
+
+vector long long vec_vupkhsw (vector int);
+vector unsigned long long vec_vupkhsw (vector unsigned int);
+
+vector long long vec_vupklsw (vector int);
+vector unsigned long long vec_vupklsw (vector int);
+@end smallexample
+
+If the cryptographic instructions are enabled (@option{-mcrypto} or
+@option{-mcpu=power8}), the following builtins are enabled.
+
+@smallexample
+vector unsigned long long __builtin_crypto_vsbox (vector unsigned long long);
+
+vector unsigned long long __builtin_crypto_vcipher (vector unsigned long long,
+                                                    vector unsigned long long);
+
+vector unsigned long long __builtin_crypto_vcipherlast
+                                     (vector unsigned long long,
+                                      vector unsigned long long);
+
+vector unsigned long long __builtin_crypto_vncipher (vector unsigned long long,
+                                                     vector unsigned long long);
+
+vector unsigned long long __builtin_crypto_vncipherlast
+                                     (vector unsigned long long,
+                                      vector unsigned long long);
+
+vector unsigned char __builtin_crypto_vpermxor (vector unsigned char,
+                                                vector unsigned char,
+                                                vector unsigned char);
+
+vector unsigned short __builtin_crypto_vpermxor (vector unsigned short,
+                                                 vector unsigned short,
+                                                 vector unsigned short);
+
+vector unsigned int __builtin_crypto_vpermxor (vector unsigned int,
+                                               vector unsigned int,
+                                               vector unsigned int);
+
+vector unsigned long long __builtin_crypto_vpermxor (vector unsigned long long,
+                                                     vector unsigned long long,
+                                                     vector unsigned long long);
+
+vector unsigned char __builtin_crypto_vpmsumb (vector unsigned char,
+                                               vector unsigned char);
+
+vector unsigned short __builtin_crypto_vpmsumb (vector unsigned short,
+                                                vector unsigned short);
+
+vector unsigned int __builtin_crypto_vpmsumb (vector unsigned int,
+                                              vector unsigned int);
+
+vector unsigned long long __builtin_crypto_vpmsumb (vector unsigned long long,
+                                                    vector unsigned long long);
+
+vector unsigned long long __builtin_crypto_vshasigmad
+                               (vector unsigned long long, int, int);
+
+vector unsigned int __builtin_crypto_vshasigmaw (vector unsigned int,
+                                                 int, int);
+@end smallexample
+
+The second argument to the @var{__builtin_crypto_vshasigmad} and
+@var{__builtin_crypto_vshasigmaw} builtin functions must be a constant
+integer that is 0 or 1.  The third argument to these builtin functions
+must be a constant integer in the range of 0 to 15.
+
+@node PowerPC Hardware Transactional Memory Built-in Functions
+@subsection PowerPC Hardware Transactional Memory Built-in Functions
+GCC provides two interfaces for accessing the Hardware Transactional
+Memory (HTM) instructions available on some of the PowerPC family
+of prcoessors (eg, POWER8).  The two interfaces come in a low level
+interface, consisting of built-in functions specific to PowerPC and a
+higher level interface consisting of inline functions that are common
+between PowerPC and S/390.
+
+@subsubsection PowerPC HTM Low Level Built-in Functions
+
+The following low level built-in functions are available with
+@option{-mhtm} or @option{-mcpu=CPU} where CPU is `power8' or later.
+They all generate the machine instruction that is part of the name.
+
+The HTM built-ins return true or false depending on their success and
+their arguments match exactly the type and order of the associated
+hardware instruction's operands.  Refer to the ISA manual for a
+description of each instruction's operands.
+
+@smallexample
+unsigned int __builtin_tbegin (unsigned int)
+unsigned int __builtin_tend (unsigned int)
+
+unsigned int __builtin_tabort (unsigned int)
+unsigned int __builtin_tabortdc (unsigned int, unsigned int, unsigned int)
+unsigned int __builtin_tabortdci (unsigned int, unsigned int, int)
+unsigned int __builtin_tabortwc (unsigned int, unsigned int, unsigned int)
+unsigned int __builtin_tabortwci (unsigned int, unsigned int, int)
+
+unsigned int __builtin_tcheck (unsigned int)
+unsigned int __builtin_treclaim (unsigned int)
+unsigned int __builtin_trechkpt (void)
+unsigned int __builtin_tsr (unsigned int)
+@end smallexample
+
+In addition to the above HTM built-ins, we have added built-ins for
+some common extended mnemonics of the HTM instructions:
+
+@smallexample
+unsigned int __builtin_tendall (void)
+unsigned int __builtin_tresume (void)
+unsigned int __builtin_tsuspend (void)
+@end smallexample
+
+The following set of built-in functions are available to gain access
+to the HTM specific special purpose registers.
+
+@smallexample
+unsigned long __builtin_get_texasr (void)
+unsigned long __builtin_get_texasru (void)
+unsigned long __builtin_get_tfhar (void)
+unsigned long __builtin_get_tfiar (void)
+
+void __builtin_set_texasr (unsigned long);
+void __builtin_set_texasru (unsigned long);
+void __builtin_set_tfhar (unsigned long);
+void __builtin_set_tfiar (unsigned long);
+@end smallexample
+
+Example usage of these low level built-in functions may look like:
+
+@smallexample
+#include <htmintrin.h>
+
+int num_retries = 10;
+
+while (1)
+  @{
+    if (__builtin_tbegin (0))
+      @{
+        /* Transaction State Initiated.  */
+        if (is_locked (lock))
+          __builtin_tabort (0);
+        ... transaction code...
+        __builtin_tend (0);
+        break;
+      @}
+    else
+      @{
+        /* Transaction State Failed.  Use locks if the transaction
+           failure is "persistent" or we've tried too many times.  */
+        if (num_retries-- <= 0
+            || _TEXASRU_FAILURE_PERSISTENT (__builtin_get_texasru ()))
+          @{
+            acquire_lock (lock);
+            ... non transactional fallback path...
+            release_lock (lock);
+            break;
+          @}
+      @}
+  @}
+@end smallexample
+
+One final built-in function has been added that returns the value of
+the 2-bit Transaction State field of the Machine Status Register (MSR)
+as stored in @code{CR0}.
+
+@smallexample
+unsigned long __builtin_ttest (void)
+@end smallexample
+
+This built-in can be used to determine the current transaction state
+using the following code example:
+
+@smallexample
+#include <htmintrin.h>
+
+unsigned char tx_state = _HTM_STATE (__builtin_ttest ());
+
+if (tx_state == _HTM_TRANSACTIONAL)
+  @{
+    /* Code to use in transactional state.  */
+  @}
+else if (tx_state == _HTM_NONTRANSACTIONAL)
+  @{
+    /* Code to use in non-transactional state.  */
+  @}
+else if (tx_state == _HTM_SUSPENDED)
+  @{
+    /* Code to use in transaction suspended state.  */
+  @}
+@end smallexample
+
+@subsubsection PowerPC HTM High Level Inline Functions
+
+The following high level HTM interface is made available by including
+@code{<htmxlintrin.h>} and using @option{-mhtm} or @option{-mcpu=CPU}
+where CPU is `power8' or later.  This interface is common between PowerPC
+and S/390, allowing users to write one HTM source implementation that
+can be compiled and executed on either system.
+
+@smallexample
+long __TM_simple_begin (void)
+long __TM_begin (void* const TM_buff)
+long __TM_end (void)
+void __TM_abort (void)
+void __TM_named_abort (unsigned char const code)
+void __TM_resume (void)
+void __TM_suspend (void)
+
+long __TM_is_user_abort (void* const TM_buff)
+long __TM_is_named_user_abort (void* const TM_buff, unsigned char *code)
+long __TM_is_illegal (void* const TM_buff)
+long __TM_is_footprint_exceeded (void* const TM_buff)
+long __TM_nesting_depth (void* const TM_buff)
+long __TM_is_nested_too_deep(void* const TM_buff)
+long __TM_is_conflict(void* const TM_buff)
+long __TM_is_failure_persistent(void* const TM_buff)
+long __TM_failure_address(void* const TM_buff)
+long long __TM_failure_code(void* const TM_buff)
+@end smallexample
+
+Using these common set of HTM inline functions, we can create
+a more portable version of the HTM example in the previous
+section that will work on either PowerPC or S/390:
+
+@smallexample
+#include <htmxlintrin.h>
+
+int num_retries = 10;
+TM_buff_type TM_buff;
+
+while (1)
+  @{
+    if (__TM_begin (TM_buff))
+      @{
+        /* Transaction State Initiated.  */
+        if (is_locked (lock))
+          __TM_abort ();
+        ... transaction code...
+        __TM_end ();
+        break;
+      @}
+    else
+      @{
+        /* Transaction State Failed.  Use locks if the transaction
+           failure is "persistent" or we've tried too many times.  */
+        if (num_retries-- <= 0
+            || __TM_is_failure_persistent (TM_buff))
+          @{
+            acquire_lock (lock);
+            ... non transactional fallback path...
+            release_lock (lock);
+            break;
+          @}
+      @}
+  @}
+@end smallexample
+
 @node RX Built-in Functions
 @subsection RX Built-in Functions
 GCC supports some of the RX instructions which cannot be expressed in
Index: gcc/doc/invoke.texi
===================================================================
--- gcc/doc/invoke.texi	(revision 206404)
+++ gcc/doc/invoke.texi	(working copy)
@@ -855,7 +855,10 @@
 -mno-recip-precision @gol
 -mveclibabi=@var{type} -mfriz -mno-friz @gol
 -mpointers-to-nested-functions -mno-pointers-to-nested-functions @gol
--msave-toc-indirect -mno-save-toc-indirect}
+-msave-toc-indirect -mno-save-toc-indirect @gol
+-mpower8-fusion -mno-mpower8-fusion -mpower8-vector -mno-power8-vector @gol
+-mcrypto -mno-crypto -mdirect-move -mno-direct-move @gol
+-mquad-memory -mno-quad-memory}
 
 @emph{RX Options}
 @gccoptlist{-m64bit-doubles  -m32bit-doubles  -fpu  -nofpu@gol
@@ -17237,7 +17240,9 @@
 @gccoptlist{-maltivec  -mfprnd  -mhard-float  -mmfcrf  -mmultiple @gol
 -mpopcntb -mpopcntd  -mpowerpc64 @gol
 -mpowerpc-gpopt  -mpowerpc-gfxopt  -msingle-float -mdouble-float @gol
--msimple-fpu -mstring  -mmulhw  -mdlmzb  -mmfpgpr -mvsx}
+-msimple-fpu -mstring  -mmulhw  -mdlmzb  -mmfpgpr -mvsx @gol
+-mcrypto -mdirect-move -mpower8-fusion -mpower8-vector -mquad-memory @gol
+-mcompat-align-parm -mno-compat-align-parm}
 
 The particular options set for any particular CPU varies between
 compiler versions, depending on what setting seems to produce optimal
@@ -17355,6 +17360,47 @@
 instructions, and also enable the use of built-in functions that allow
 more direct access to the VSX instruction set.
 
+@item -mcrypto
+@itemx -mno-crypto
+@opindex mcrypto
+@opindex mno-crypto
+Enable the use (disable) of the built-in functions that allow direct
+access to the cryptographic instructions that were added in version
+2.07 of the PowerPC ISA.
+
+@item -mdirect-move
+@itemx -mno-direct-move
+@opindex mdirect-move
+@opindex mno-direct-move
+Generate code that uses (does not use) the instructions to move data
+between the general purpose registers and the vector/scalar (VSX)
+registers that were added in version 2.07 of the PowerPC ISA.
+
+@item -mpower8-fusion
+@itemx -mno-power8-fusion
+@opindex mpower8-fusion
+@opindex mno-power8-fusion
+Generate code that keeps (does not keeps) some integer operations
+adjacent so that the instructions can be fused together on power8 and
+later processors.
+
+@item -mpower8-vector
+@itemx -mno-power8-vector
+@opindex mpower8-vector
+@opindex mno-power8-vector
+Generate code that uses (does not use) the vector and scalar
+instructions that were added in version 2.07 of the PowerPC ISA.  Also
+enable the use of built-in functions that allow more direct access to
+the vector instructions.
+
+@item -mquad-memory
+@itemx -mno-quad-memory
+@opindex mquad-memory
+@opindex mno-quad-memory
+Generate code that uses (does not use) the quad word memory
+instructions.  The @option{-mquad-memory} option requires use of
+64-bit mode.
+
 @item -mfloat-gprs=@var{yes/single/double/no}
 @itemx -mfloat-gprs
 @opindex mfloat-gprs
@@ -17774,7 +17820,8 @@
 @opindex mabi
 Extend the current ABI with a particular extension, or remove such extension.
 Valid values are @var{altivec}, @var{no-altivec}, @var{spe},
-@var{no-spe}, @var{ibmlongdouble}, @var{ieeelongdouble}@.
+@var{no-spe}, @var{ibmlongdouble}, @var{ieeelongdouble},
+@var{elfv1}, @var{elfv2}@.
 
 @item -mabi=spe
 @opindex mabi=spe
@@ -17796,6 +17843,20 @@
 Change the current ABI to use IEEE extended-precision long double.
 This is a PowerPC 32-bit Linux ABI option.
 
+@item -mabi=elfv1
+@opindex mabi=elfv1
+Change the current ABI to use the ELFv1 ABI.
+This is the default ABI for big-endian PowerPC 64-bit Linux.
+Overriding the default ABI requires special system support and is
+likely to fail in spectacular ways.
+
+@item -mabi=elfv2
+@opindex mabi=elfv2
+Change the current ABI to use the ELFv2 ABI.
+This is the default ABI for little-endian PowerPC 64-bit Linux.
+Overriding the default ABI requires special system support and is
+likely to fail in spectacular ways.
+
 @item -mprototype
 @itemx -mno-prototype
 @opindex mprototype
@@ -18081,6 +18142,23 @@
 a pointer on AIX and 64-bit Linux systems.  If the TOC value is not
 saved in the prologue, it is saved just before the call through the
 pointer.  The @option{-mno-save-toc-indirect} option is the default.
+
+@item -mcompat-align-parm
+@itemx -mno-compat-align-parm
+@opindex mcompat-align-parm
+Generate (do not generate) code to pass structure parameters with a
+maximum alignment of 64 bits, for compatibility with older versions
+of GCC.
+
+Older versions of GCC (prior to 4.9.0) incorrectly did not align a
+structure parameter on a 128-bit boundary when that structure contained
+a member requiring 128-bit alignment.  This is corrected in more
+recent versions of GCC.  This option may be used to generate code
+that is compatible with functions compiled with older versions of
+GCC.
+
+In this version of the compiler, the @option{-mcompat-align-parm}
+is the default, except when using the Linux ELFv2 ABI.
 @end table
 
 @node RX Options
Index: gcc/doc/md.texi
===================================================================
--- gcc/doc/md.texi	(revision 206404)
+++ gcc/doc/md.texi	(working copy)
@@ -2055,7 +2055,7 @@
 
 @end table
 
-@item PowerPC and IBM RS6000---@file{config/rs6000/rs6000.h}
+@item PowerPC and IBM RS6000---@file{config/rs6000/constraints.md}
 @table @code
 @item b
 Address base register
@@ -2069,18 +2069,58 @@
 @item v
 Altivec vector register
 
+@item wa
+Any VSX register if the -mvsx option was used or NO_REGS.
+
 @item wd
-VSX vector register to hold vector double data
+VSX vector register to hold vector double data or NO_REGS.
 
 @item wf
-VSX vector register to hold vector float data
+VSX vector register to hold vector float data or NO_REGS.
 
+@item wg
+If @option{-mmfpgpr} was used, a floating point register or NO_REGS.
+
+@item wl
+Floating point register if the LFIWAX instruction is enabled or NO_REGS.
+
+@item wm
+VSX register if direct move instructions are enabled, or NO_REGS.
+
+@item wn
+No register (NO_REGS).
+
+@item wr
+General purpose register if 64-bit instructions are enabled or NO_REGS.
+
 @item ws
-VSX vector register to hold scalar float data
+VSX vector register to hold scalar double values or NO_REGS.
 
-@item wa
-Any VSX register
+@item wt
+VSX vector register to hold 128 bit integer or NO_REGS.
 
+@item wu
+Altivec register to use for float/32-bit int loads/stores  or NO_REGS.
+
+@item wv
+Altivec register to use for double loads/stores  or NO_REGS.
+
+@item ww
+FP or VSX register to perform float operations under @option{-mvsx} or NO_REGS.
+
+@item wx
+Floating point register if the STFIWX instruction is enabled or NO_REGS.
+
+@item wy
+VSX vector register to hold scalar float values or NO_REGS.
+
+@item wz
+Floating point register if the LFIWZX instruction is enabled or NO_REGS.
+
+@item wQ
+A memory address that will work with the @code{lq} and @code{stq}
+instructions.
+
 @item h
 @samp{MQ}, @samp{CTR}, or @samp{LINK} register
 
Index: gcc/builtins.c
===================================================================
--- gcc/builtins.c	(revision 206404)
+++ gcc/builtins.c	(working copy)
@@ -5850,6 +5850,9 @@
   switch (fcode)
     {
     CASE_FLT_FN (BUILT_IN_FABS):
+    case BUILT_IN_FABSD32:
+    case BUILT_IN_FABSD64:
+    case BUILT_IN_FABSD128:
       target = expand_builtin_fabs (exp, target, subtarget);
       if (target)
 	return target;
@@ -10302,6 +10305,9 @@
       return fold_builtin_strlen (loc, type, arg0);
 
     CASE_FLT_FN (BUILT_IN_FABS):
+    case BUILT_IN_FABSD32:
+    case BUILT_IN_FABSD64:
+    case BUILT_IN_FABSD128:
       return fold_builtin_fabs (loc, arg0, type);
 
     case BUILT_IN_ABS:
Index: gcc/builtins.def
===================================================================
--- gcc/builtins.def	(revision 206404)
+++ gcc/builtins.def	(working copy)
@@ -252,6 +252,9 @@
 DEF_LIB_BUILTIN        (BUILT_IN_FABS, "fabs", BT_FN_DOUBLE_DOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_C90RES_BUILTIN (BUILT_IN_FABSF, "fabsf", BT_FN_FLOAT_FLOAT, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_C90RES_BUILTIN (BUILT_IN_FABSL, "fabsl", BT_FN_LONGDOUBLE_LONGDOUBLE, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD32, "fabsd32", BT_FN_DFLOAT32_DFLOAT32, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD64, "fabsd64", BT_FN_DFLOAT64_DFLOAT64, ATTR_CONST_NOTHROW_LEAF_LIST)
+DEF_GCC_BUILTIN        (BUILT_IN_FABSD128, "fabsd128", BT_FN_DFLOAT128_DFLOAT128, ATTR_CONST_NOTHROW_LEAF_LIST)
 DEF_C99_BUILTIN        (BUILT_IN_FDIM, "fdim", BT_FN_DOUBLE_DOUBLE_DOUBLE, ATTR_MATHFN_FPROUNDING_ERRNO)
 DEF_C99_BUILTIN        (BUILT_IN_FDIMF, "fdimf", BT_FN_FLOAT_FLOAT_FLOAT, ATTR_MATHFN_FPROUNDING_ERRNO)
 DEF_C99_BUILTIN        (BUILT_IN_FDIML, "fdiml", BT_FN_LONGDOUBLE_LONGDOUBLE_LONGDOUBLE, ATTR_MATHFN_FPROUNDING_ERRNO)
Index: gcc/expr.h
===================================================================
--- gcc/expr.h	(revision 206404)
+++ gcc/expr.h	(working copy)
@@ -521,8 +521,8 @@
 			  rtx, int);
 #endif
 
-extern void locate_and_pad_parm (enum machine_mode, tree, int, int, tree,
-				 struct args_size *,
+extern void locate_and_pad_parm (enum machine_mode, tree, int, int, int,
+				 tree, struct args_size *,
 				 struct locate_and_pad_arg_data *);
 
 /* Return the CODE_LABEL rtx for a LABEL_DECL, creating it if necessary.  */
Index: gcc/function.c
===================================================================
--- gcc/function.c	(revision 206404)
+++ gcc/function.c	(working copy)
@@ -2507,6 +2507,7 @@
     }
 
   locate_and_pad_parm (data->promoted_mode, data->passed_type, in_regs,
+		       all->reg_parm_stack_space,
 		       entry_parm ? data->partial : 0, current_function_decl,
 		       &all->stack_args_size, &data->locate);
 
@@ -3485,11 +3486,7 @@
   /* Adjust function incoming argument size for alignment and
      minimum length.  */
 
-#ifdef REG_PARM_STACK_SPACE
-  crtl->args.size = MAX (crtl->args.size,
-				    REG_PARM_STACK_SPACE (fndecl));
-#endif
-
+  crtl->args.size = MAX (crtl->args.size, all.reg_parm_stack_space);
   crtl->args.size = CEIL_ROUND (crtl->args.size,
 					   PARM_BOUNDARY / BITS_PER_UNIT);
 
@@ -3693,6 +3690,9 @@
    IN_REGS is nonzero if the argument will be passed in registers.  It will
    never be set if REG_PARM_STACK_SPACE is not defined.
 
+   REG_PARM_STACK_SPACE is the number of bytes of stack space reserved
+   for arguments which are passed in registers.
+
    FNDECL is the function in which the argument was defined.
 
    There are two types of rounding that are done.  The first, controlled by
@@ -3713,19 +3713,16 @@
 
 void
 locate_and_pad_parm (enum machine_mode passed_mode, tree type, int in_regs,
-		     int partial, tree fndecl ATTRIBUTE_UNUSED,
+		     int reg_parm_stack_space, int partial,
+		     tree fndecl ATTRIBUTE_UNUSED,
 		     struct args_size *initial_offset_ptr,
 		     struct locate_and_pad_arg_data *locate)
 {
   tree sizetree;
   enum direction where_pad;
   unsigned int boundary, round_boundary;
-  int reg_parm_stack_space = 0;
   int part_size_in_regs;
 
-#ifdef REG_PARM_STACK_SPACE
-  reg_parm_stack_space = REG_PARM_STACK_SPACE (fndecl);
-
   /* If we have found a stack parm before we reach the end of the
      area reserved for registers, skip that area.  */
   if (! in_regs)
@@ -3743,7 +3740,6 @@
 	    initial_offset_ptr->constant = reg_parm_stack_space;
 	}
     }
-#endif /* REG_PARM_STACK_SPACE */
 
   part_size_in_regs = (reg_parm_stack_space == 0 ? partial : 0);
 
@@ -3806,11 +3802,7 @@
 
   locate->slot_offset.constant += part_size_in_regs;
 
-  if (!in_regs
-#ifdef REG_PARM_STACK_SPACE
-      || REG_PARM_STACK_SPACE (fndecl) > 0
-#endif
-     )
+  if (!in_regs || reg_parm_stack_space > 0)
     pad_to_arg_alignment (&locate->slot_offset, boundary,
 			  &locate->alignment_pad);
 
@@ -3830,11 +3822,7 @@
     pad_below (&locate->offset, passed_mode, sizetree);
 
 #else /* !ARGS_GROW_DOWNWARD */
-  if (!in_regs
-#ifdef REG_PARM_STACK_SPACE
-      || REG_PARM_STACK_SPACE (fndecl) > 0
-#endif
-      )
+  if (!in_regs || reg_parm_stack_space > 0)
     pad_to_arg_alignment (initial_offset_ptr, boundary,
 			  &locate->alignment_pad);
   locate->slot_offset = *initial_offset_ptr;
@@ -5093,6 +5081,7 @@
 	     amount.  BLKmode results are handled using the group load/store
 	     machinery.  */
 	  if (TYPE_MODE (TREE_TYPE (decl_result)) != BLKmode
+	      && REG_P (real_decl_rtl)
 	      && targetm.calls.return_in_msb (TREE_TYPE (decl_result)))
 	    {
 	      emit_move_insn (gen_rtx_REG (GET_MODE (decl_rtl),
Index: gcc/calls.c
===================================================================
--- gcc/calls.c	(revision 206404)
+++ gcc/calls.c	(working copy)
@@ -983,6 +983,7 @@
 
   for (i = 0; i < num_actuals; i++)
     if (args[i].reg != 0 && ! args[i].pass_on_stack
+	&& GET_CODE (args[i].reg) != PARALLEL
 	&& args[i].mode == BLKmode
 	&& MEM_P (args[i].value)
 	&& (MEM_ALIGN (args[i].value)
@@ -1327,6 +1328,7 @@
 #else
 			     args[i].reg != 0,
 #endif
+			     reg_parm_stack_space,
 			     args[i].pass_on_stack ? 0 : args[i].partial,
 			     fndecl, args_size, &args[i].locate);
 #ifdef BLOCK_REG_PADDING
@@ -3171,7 +3173,9 @@
 	 group load/store machinery below.  */
       if (!structure_value_addr
 	  && !pcc_struct_value
+	  && TYPE_MODE (rettype) != VOIDmode
 	  && TYPE_MODE (rettype) != BLKmode
+	  && REG_P (valreg)
 	  && targetm.calls.return_in_msb (rettype))
 	{
 	  if (shift_return_value (TYPE_MODE (rettype), false, valreg))
@@ -3734,7 +3738,8 @@
 #else
 			   argvec[count].reg != 0,
 #endif
-			   0, NULL_TREE, &args_size, &argvec[count].locate);
+			   reg_parm_stack_space, 0,
+			   NULL_TREE, &args_size, &argvec[count].locate);
 
       if (argvec[count].reg == 0 || argvec[count].partial != 0
 	  || reg_parm_stack_space > 0)
@@ -3821,7 +3826,7 @@
 #else
 			       argvec[count].reg != 0,
 #endif
-			       argvec[count].partial,
+			       reg_parm_stack_space, argvec[count].partial,
 			       NULL_TREE, &args_size, &argvec[count].locate);
 	  args_size.constant += argvec[count].locate.size.constant;
 	  gcc_assert (!argvec[count].locate.size.var);
Index: libffi/src/types.c
===================================================================
--- libffi/src/types.c	(revision 206404)
+++ libffi/src/types.c	(working copy)
@@ -44,6 +44,17 @@
   id, NULL					\
 }
 
+#define FFI_NONCONST_TYPEDEF(name, type, id)	\
+struct struct_align_##name {			\
+  char c;					\
+  type x;					\
+};						\
+ffi_type ffi_type_##name = {			\
+  sizeof(type),					\
+  offsetof(struct struct_align_##name, x),	\
+  id, NULL					\
+}
+
 /* Size and alignment are fake here. They must not be 0. */
 const ffi_type ffi_type_void = {
   1, 1, FFI_TYPE_VOID, NULL
@@ -73,5 +84,9 @@
 # endif
 const ffi_type ffi_type_longdouble = { 16, 16, 4, NULL };
 #elif FFI_TYPE_LONGDOUBLE != FFI_TYPE_DOUBLE
+# if HAVE_LONG_DOUBLE_VARIANT
+FFI_NONCONST_TYPEDEF(longdouble, long double, FFI_TYPE_LONGDOUBLE);
+# else
 FFI_TYPEDEF(longdouble, long double, FFI_TYPE_LONGDOUBLE);
+# endif
 #endif
Index: libffi/src/prep_cif.c
===================================================================
--- libffi/src/prep_cif.c	(revision 206404)
+++ libffi/src/prep_cif.c	(working copy)
@@ -126,6 +126,10 @@
 
   cif->flags = 0;
 
+#if HAVE_LONG_DOUBLE_VARIANT
+  ffi_prep_types (abi);
+#endif
+
   /* Initialize the return type if necessary */
   if ((cif->rtype->size == 0) && (initialize_aggregate(cif->rtype) != FFI_OK))
     return FFI_BAD_TYPEDEF;
Index: libffi/doc/libffi.texi
===================================================================
--- libffi/doc/libffi.texi	(revision 206404)
+++ libffi/doc/libffi.texi	(working copy)
@@ -184,11 +184,11 @@
 
 @var{rvalue} is a pointer to a chunk of memory that will hold the
 result of the function call.  This must be large enough to hold the
-result and must be suitably aligned; it is the caller's responsibility
+result, no smaller than the system register size (generally 32 or 64
+bits), and must be suitably aligned; it is the caller's responsibility
 to ensure this.  If @var{cif} declares that the function returns
 @code{void} (using @code{ffi_type_void}), then @var{rvalue} is
-ignored.  If @var{rvalue} is @samp{NULL}, then the return value is
-discarded.
+ignored.
 
 @var{avalues} is a vector of @code{void *} pointers that point to the
 memory locations holding the argument values for a call.  If @var{cif}
@@ -214,7 +214,7 @@
   ffi_type *args[1];
   void *values[1];
   char *s;
-  int rc;
+  ffi_arg rc;
   
   /* Initialize the argument info vectors */    
   args[0] = &ffi_type_pointer;
@@ -222,7 +222,7 @@
   
   /* Initialize the cif */
   if (ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 1, 
-		       &ffi_type_uint, args) == FFI_OK)
+		       &ffi_type_sint, args) == FFI_OK)
     @{
       s = "Hello World!";
       ffi_call(&cif, puts, &rc, values);
@@ -360,7 +360,7 @@
 new @code{ffi_type} object for it.
 
 @tindex ffi_type
-@deftp ffi_type
+@deftp {Data type} ffi_type
 The @code{ffi_type} has the following members:
 @table @code
 @item size_t size
@@ -414,6 +414,7 @@
       int i;
 
       tm_type.size = tm_type.alignment = 0;
+      tm_type.type = FFI_TYPE_STRUCT;
       tm_type.elements = &tm_type_elements;
     
       for (i = 0; i < 9; i++)
@@ -540,21 +541,23 @@
 #include <ffi.h>
 
 /* Acts like puts with the file given at time of enclosure. */
-void puts_binding(ffi_cif *cif, unsigned int *ret, void* args[], 
-                  FILE *stream)
+void puts_binding(ffi_cif *cif, void *ret, void* args[],
+                  void *stream)
 @{
-  *ret = fputs(*(char **)args[0], stream);
+  *(ffi_arg *)ret = fputs(*(char **)args[0], (FILE *)stream);
 @}
 
+typedef int (*puts_t)(char *);
+
 int main()
 @{
   ffi_cif cif;
   ffi_type *args[1];
   ffi_closure *closure;
 
-  int (*bound_puts)(char *);
+  void *bound_puts;
   int rc;
-  
+
   /* Allocate closure and bound_puts */
   closure = ffi_closure_alloc(sizeof(ffi_closure), &bound_puts);
 
@@ -565,13 +568,13 @@
 
       /* Initialize the cif */
       if (ffi_prep_cif(&cif, FFI_DEFAULT_ABI, 1,
-                       &ffi_type_uint, args) == FFI_OK)
+                       &ffi_type_sint, args) == FFI_OK)
         @{
           /* Initialize the closure, setting stream to stdout */
-          if (ffi_prep_closure_loc(closure, &cif, puts_binding, 
+          if (ffi_prep_closure_loc(closure, &cif, puts_binding,
                                    stdout, bound_puts) == FFI_OK)
             @{
-              rc = bound_puts("Hello World!");
+              rc = ((puts_t)bound_puts)("Hello World!");
               /* rc now holds the result of the call to fputs */
             @}
         @}
Index: libcpp/lex.c
===================================================================
--- libcpp/lex.c	(revision 206404)
+++ libcpp/lex.c	(working copy)
@@ -559,8 +559,13 @@
      beginning with all ones and shifting in zeros according to the
      mis-alignment.  The LVSR instruction pulls the exact shift we
      want from the address.  */
+#ifdef __BIG_ENDIAN__
   mask = __builtin_vec_lvsr(0, s);
   mask = __builtin_vec_perm(zero, ones, mask);
+#else
+  mask = __builtin_vec_lvsl(0, s);
+  mask = __builtin_vec_perm(ones, zero, mask);
+#endif
   data &= mask;
 
   /* While altivec loads mask addresses, we still need to align S so
@@ -624,7 +629,11 @@
     /* L now contains 0xff in bytes for which we matched one of the
        relevant characters.  We can find the byte index by finding
        its bit index and dividing by 8.  */
+#ifdef __BIG_ENDIAN__
     l = __builtin_clzl(l) >> 3;
+#else
+    l = __builtin_ctzl(l) >> 3;
+#endif
     return s + l;
 
 #undef N

Places

File gcc48-ibm-power8-other.diff of Package cross-ia64-gcc48-icecream-backend (Revision 5b8b5574b4320271965e204f41440dfd)

Places