- support -mcld option (generate cld instruction in fn. prologue).

Changed files:
    gcc-explicit_cld.patch -> 1.1

diff --git a/gcc-explicit_cld.patch b/gcc-explicit_cld.patch
new file mode 100644 (file)
index 0000000..7d3a25c
--- /dev/null
+++ b/gcc-explicit_cld.patch
@@ -0,0 +1,175 @@
+This patch adds back generation of cld instructions when stringops are
+used in the function. cld insn is emitted as unspec volatile at the
+end of function prologue. Currently, patched gcc emits cld when
+"-mcld" is added to compile flags.
+
+2008-03-06  Uros Bizjak  <ubizjak@gmail.com>
+
+       * config/i386/i386.h (TARGET_CLD): New define.
+       (struct machine_function): Add needs_cld field.
+       (ix86_current_function_needs_cld): New define.
+       * config/i386/i386.md (UNSPEC_CLD): New unspec volatile constant.
+       ("cld"): New isns pattern.
+       ("strmov_singleop"): Set ix86_current_function_needs_cld flag.
+       ("rep_mov"): Ditto.
+       ("strset_singleop"): Ditto.
+       ("rep_stos"): Ditto.
+       ("cmpstrnqi_nz_1"): Ditto.
+       ("cmpstrnqi_1"): Ditto.
+       ("strlenqi_1"): Ditto.
+       * config/i386/i386.opt (mcld): New option.
+       * config/i386/i386.c (ix86_expand_prologue): Emit cld insn for
+       TARGET_CLD when ix86_current_function_needs_cld is set.
+
+Index: gcc/config/i386/i386.h
+===================================================================
+--- gcc/config/i386/i386.h     (revision 132966)
++++ gcc/config/i386/i386.h     (working copy)
+@@ -388,6 +388,7 @@ extern unsigned int ix86_arch_features[X
+ 
+ extern int x86_prefetch_sse;
+ 
++#define TARGET_CLD            x86_cld
+ #define TARGET_ABM            x86_abm
+ #define TARGET_CMPXCHG16B     x86_cmpxchg16b
+ #define TARGET_POPCNT         x86_popcnt
+@@ -2446,8 +2447,9 @@ struct machine_function GTY(())
+   int save_varrargs_registers;
+   int accesses_prev_frame;
+   int optimize_mode_switching[MAX_386_ENTITIES];
+-  /* Set by ix86_compute_frame_layout and used by prologue/epilogue expander to
+-     determine the style used.  */
++  int needs_cld;
++  /* Set by ix86_compute_frame_layout and used by prologue/epilogue
++     expander to determine the style used.  */
+   int use_fast_prologue_epilogue;
+   /* Number of saved registers USE_FAST_PROLOGUE_EPILOGUE has been computed
+      for.  */
+@@ -2467,6 +2469,7 @@ struct machine_function GTY(())
+ #define ix86_stack_locals (cfun->machine->stack_locals)
+ #define ix86_save_varrargs_registers (cfun->machine->save_varrargs_registers)
+ #define ix86_optimize_mode_switching (cfun->machine->optimize_mode_switching)
++#define ix86_current_function_needs_cld (cfun->machine->needs_cld)
+ #define ix86_tls_descriptor_calls_expanded_in_cfun \
+   (cfun->machine->tls_descriptor_call_expanded_p)
+ /* Since tls_descriptor_call_expanded is not cleared, even if all TLS
+Index: gcc/config/i386/i386.md
+===================================================================
+--- gcc/config/i386/i386.md    (revision 132966)
++++ gcc/config/i386/i386.md    (working copy)
+@@ -205,6 +205,7 @@
+    (UNSPECV_XCHG              12)
+    (UNSPECV_LOCK              13)
+    (UNSPECV_PROLOGUE_USE      14)
++   (UNSPECV_CLD                       15)
+   ])
+ 
+ ;; Constants to represent pcomtrue/pcomfalse variants
+@@ -18519,6 +18520,14 @@
+ \f
+ ;; Block operation instructions
+ 
++(define_insn "cld"
++  [(unspec_volatile [(const_int 0)] UNSPECV_CLD)]
++  ""
++  "cld"
++  [(set_attr "length" "1")
++   (set_attr "length_immediate" "0")
++   (set_attr "modrm" "0")])
++
+ (define_expand "movmemsi"
+   [(use (match_operand:BLK 0 "memory_operand" ""))
+    (use (match_operand:BLK 1 "memory_operand" ""))
+@@ -18591,7 +18600,7 @@
+             (set (match_operand 2 "register_operand" "")
+                  (match_operand 5 "" ""))])]
+   "TARGET_SINGLE_STRINGOP || optimize_size"
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*strmovdi_rex_1"
+   [(set (mem:DI (match_operand:DI 2 "register_operand" "0"))
+@@ -18708,7 +18717,7 @@
+                  (match_operand 3 "memory_operand" ""))
+             (use (match_dup 4))])]
+   ""
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*rep_movdi_rex64"
+   [(set (match_operand:DI 2 "register_operand" "=c") (const_int 0))
+@@ -18868,7 +18877,7 @@
+             (set (match_operand 0 "register_operand" "")
+                  (match_operand 3 "" ""))])]
+   "TARGET_SINGLE_STRINGOP || optimize_size"
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*strsetdi_rex_1"
+   [(set (mem:DI (match_operand:DI 1 "register_operand" "0"))
+@@ -18962,7 +18971,7 @@
+             (use (match_operand 3 "register_operand" ""))
+             (use (match_dup 1))])]
+   ""
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*rep_stosdi_rex64"
+   [(set (match_operand:DI 1 "register_operand" "=c") (const_int 0))
+@@ -19138,7 +19147,7 @@
+             (clobber (match_operand 1 "register_operand" ""))
+             (clobber (match_dup 2))])]
+   ""
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*cmpstrnqi_nz_1"
+   [(set (reg:CC FLAGS_REG)
+@@ -19185,7 +19194,7 @@
+             (clobber (match_operand 1 "register_operand" ""))
+             (clobber (match_dup 2))])]
+   ""
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*cmpstrnqi_1"
+   [(set (reg:CC FLAGS_REG)
+@@ -19254,7 +19263,7 @@
+             (clobber (match_operand 1 "register_operand" ""))
+             (clobber (reg:CC FLAGS_REG))])]
+   ""
+-  "")
++  "ix86_current_function_needs_cld = 1;")
+ 
+ (define_insn "*strlenqi_1"
+   [(set (match_operand:SI 0 "register_operand" "=&c")
+Index: gcc/config/i386/i386.opt
+===================================================================
+--- gcc/config/i386/i386.opt   (revision 132966)
++++ gcc/config/i386/i386.opt   (working copy)
+@@ -250,6 +250,10 @@ Support SSE5 built-in functions and code
+ 
+ ;; Instruction support
+ 
++mcld
++Target Report RejectNegative Var(x86_cld)
++Generate cld instruction in the function prologue.
++
+ mabm
+ Target Report RejectNegative Var(x86_abm)
+ Support code generation of Advanced Bit Manipulation (ABM) instructions.
+Index: gcc/config/i386/i386.c
+===================================================================
+--- gcc/config/i386/i386.c     (revision 132966)
++++ gcc/config/i386/i386.c     (working copy)
+@@ -6498,6 +6498,10 @@ ix86_expand_prologue (void)
+       emit_insn (gen_prologue_use (pic_offset_table_rtx));
+       emit_insn (gen_blockage ());
+     }
++
++  /* Emit cld instruction if stringops are used in the function.  */
++  if (TARGET_CLD && ix86_current_function_needs_cld)
++    emit_insn (gen_cld ());
+ }
+ 
+ /* Emit code to restore saved registers using MOV insns.  First register