On Sat, Mar 17, 2012 at 11:20 AM, Uros Bizjak <ubiz...@gmail.com> wrote:
> On Sat, Mar 17, 2012 at 7:18 PM, H.J. Lu <hjl.to...@gmail.com> wrote:
>
>>>> Since we must use reg64 in %fs:(%reg) memory operand like
>>>>
>>>> movq x@gottpoff(%rip),%reg64;
>>>> mov %fs:(%reg64),%reg
>>>>
>>>> this patch optimizes x32 TLS IE load and store by wrapping
>>>> %reg64 inside of UNSPEC when Pmode == SImode. OK for
>>>> trunk?
>>>>
>>>> Thanks.
>>>>
>>>> --
>>>> H.J.
>>>> ---
>>>> 2012-03-11 H.J. Lu <hongjiu...@intel.com>
>>>>
>>>> * config/i386/i386.md (*tls_initial_exec_x32_load): New.
>>>> (*tls_initial_exec_x32_store): Likewise.
>>>
>>> Can you implement this with define_insn_and_split, like i.e.
>>> *tls_dynamic_gnu2_combine_32 ?
>>>
>>
>> I will give it a try again. Last time when I tried it, GCC didn't
>> like memory operand in DImode when Pmode == SImode.
>
> You should remove mode for tls_symbolic_operand predicate.
>
I am testing this patch. OK for trunk if it passes all tests?
Thanks.
--
H.J.
2012-03-17 H.J. Lu <hongjiu...@intel.com>
* config/i386/i386-protos.h (ix86_split_tls_initial_exec_x32): New.
* config/i386/i386.c (ix86_split_tls_initial_exec_x32): Likewise.
* config/i386/i386.md (*tls_initial_exec_x32_load): New.
(*tls_initial_exec_x32_store): Likewise.
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 630112f..2c4f1ed 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -213,6 +213,7 @@ extern unsigned int ix86_get_callcvt (const_tree);
#endif
extern rtx ix86_tls_module_base (void);
+extern void ix86_split_tls_initial_exec_x32 (rtx [], enum machine_mode, bool);
extern void ix86_expand_vector_init (bool, rtx, rtx);
extern void ix86_expand_vector_set (bool, rtx, rtx, int);
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 78a366e..5a9c673 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -12754,6 +12754,28 @@ legitimize_tls_address (rtx x, enum tls_model model,
bool for_mov)
return dest;
}
+/* Split x32 TLS IE access in MODE. Split load if LOAD is TRUE,
+ otherwise split store. */
+
+void
+ix86_split_tls_initial_exec_x32 (rtx operands[],
+ enum machine_mode mode, bool load)
+{
+ rtx base, mem;
+ rtx off = load ? operands[1] : operands[0];
+ off = gen_rtx_UNSPEC (DImode, gen_rtvec (1, off), UNSPEC_GOTNTPOFF);
+ off = gen_rtx_CONST (DImode, off);
+ off = gen_const_mem (DImode, off);
+ set_mem_alias_set (off, ix86_GOT_alias_set ());
+ base = gen_rtx_UNSPEC (DImode, gen_rtvec (1, const0_rtx), UNSPEC_TP);
+ off = gen_rtx_PLUS (DImode, base, force_reg (DImode, off));
+ mem = gen_rtx_MEM (mode, off);
+ if (load)
+ emit_move_insn (operands[0], mem);
+ else
+ emit_move_insn (mem, operands[1]);
+}
+
/* Create or return the unique __imp_DECL dllimport symbol corresponding
to symbol DECL. */
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index eae26ae..78faeec 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -12858,6 +12858,32 @@
}
[(set_attr "type" "multi")])
+(define_insn_and_split "*tls_initial_exec_x32_load"
+ [(set (match_operand:SWI1248x 0 "register_operand" "=r")
+ (mem:SWI1248x
+ (unspec:SI
+ [(match_operand 1 "tls_symbolic_operand" "")]
+ UNSPEC_TLS_IE_X32)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_X32"
+ "#"
+ ""
+ [(const_int 0)]
+ "ix86_split_tls_initial_exec_x32 (operands, <MODE>mode, TRUE); DONE;")
+
+(define_insn_and_split "*tls_initial_exec_x32_store"
+ [(set (mem:SWI1248x
+ (unspec:SI
+ [(match_operand 0 "tls_symbolic_operand" "")]
+ UNSPEC_TLS_IE_X32))
+ (match_operand:SWI1248x 1 "register_operand" "r"))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_X32"
+ "#"
+ ""
+ [(const_int 0)]
+ "ix86_split_tls_initial_exec_x32 (operands, <MODE>mode, FALSE); DONE;")
+
;; GNU2 TLS patterns can be split.
(define_expand "tls_dynamic_gnu2_32"
