This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
stfiwx for rs6000
- From: gkeating at apple dot com (Geoffrey Keating)
- To: gcc-patches at gcc dot gnu dot org
- Date: Fri, 25 Mar 2005 11:49:34 -0800 (PST)
- Subject: stfiwx for rs6000
This patch adds minimal support for the 'stfiwx' instruction to the
rs6000 backend. I say 'minimal' because even though it is used, the
benefit of it is only that 4 bytes are saved on the stack per
temporary, rather than what you'd really like, which is that it will
store directory into a variable in memory if that's more efficient. I
couldn't work out how to make it store into user memory, after trying
several possibilities; combine won't do it, and when I tried to just say
that "this instruction requires a memory operand", reload would fail.
But, 4 bytes is 4 bytes. In fact, sometimes it's hundreds of bytes if
there are many temporaries.
Bootstrapped & tested on powerpc-darwin8.
--
- Geoffrey Keating <geoffk@apple.com>
===File ~/patches/rs6000-stfiwx-2.patch=====================
2005-03-24 Geoffrey Keating <geoffk@apple.com>
* config/rs6000/rs6000.md (UNSPEC constants): Add UNSPEC_STFIWX.
(fix_truncdfsi2): Allow registers or memory as destination.
When TARGET_PPC_GFXOPT, generate simplified pattern.
(fix_truncdfsi2_internal): Use define_insn_and_split.
(fix_truncdfsi2_internal_gfxopt): New.
(fctiwz): Don't confuse register allocation by giving it no choices.
(stfiwx): New.
* config/rs6000/rs6000.h (EXTRA_CONSTRAINT): Add 'Z'.
(EXTRA_MEMORY_CONSTRAINT): Likewise.
* config/rs6000/rs6000.c (indexed_or_indirect_operand): New.
* config/rs6000/rs6000-protos.h (indexed_or_indirect_operand): New.
Index: testsuite/ChangeLog
2005-03-25 Geoffrey Keating <geoffk@apple.com>
* gcc.dg/ppc-stfiwx.c: New.
Index: config/rs6000/rs6000-protos.h
===================================================================
RCS file: /cvs/gcc/gcc/gcc/config/rs6000/rs6000-protos.h,v
retrieving revision 1.96
diff -u -p -u -p -r1.96 rs6000-protos.h
--- config/rs6000/rs6000-protos.h 14 Mar 2005 07:24:24 -0000 1.96
+++ config/rs6000/rs6000-protos.h 25 Mar 2005 19:44:38 -0000
@@ -49,6 +49,7 @@ extern bool rs6000_legitimate_offset_add
extern rtx rs6000_got_register (rtx);
extern rtx find_addr_reg (rtx);
extern int word_offset_memref_operand (rtx, enum machine_mode);
+extern int indexed_or_indirect_operand (rtx, enum machine_mode);
extern rtx gen_easy_vector_constant_add_self (rtx);
extern const char *output_vec_const_move (rtx *);
extern void build_mask64_2_operands (rtx, rtx *);
Index: config/rs6000/rs6000.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/config/rs6000/rs6000.c,v
retrieving revision 1.796
diff -u -p -u -p -r1.796 rs6000.c
--- config/rs6000/rs6000.c 20 Mar 2005 23:25:14 -0000 1.796
+++ config/rs6000/rs6000.c 25 Mar 2005 19:44:38 -0000
@@ -2297,6 +2297,25 @@ word_offset_memref_operand (rtx op, enum
return (off % 4) == 0;
}
+/* Return true if the operand is an indirect or indexed memory operand. */
+
+int
+indexed_or_indirect_operand (rtx op, enum machine_mode mode ATTRIBUTE_UNUSED)
+{
+ rtx addr;
+ if (!memory_operand (op, mode))
+ return 0;
+
+ addr = XEXP (op, 0);
+ if (GET_CODE (addr) == REG)
+ return 1;
+ if (GET_CODE (addr) == PLUS
+ && GET_CODE (XEXP (addr, 0)) == REG
+ && GET_CODE (XEXP (addr, 1)) == REG)
+ return 1;
+ return 0;
+}
+
/* Return true if either operand is a general purpose register. */
bool
Index: config/rs6000/rs6000.h
===================================================================
RCS file: /cvs/gcc/gcc/gcc/config/rs6000/rs6000.h,v
retrieving revision 1.357
diff -u -p -u -p -r1.357 rs6000.h
--- config/rs6000/rs6000.h 14 Mar 2005 07:24:29 -0000 1.357
+++ config/rs6000/rs6000.h 25 Mar 2005 19:44:40 -0000
@@ -1357,6 +1357,7 @@ enum reg_class
'U' is for V.4 small data references.
'W' is a vector constant that can be easily generated (no mem refs).
'Y' is a indexed or word-aligned displacement memory operand.
+ 'Z' is an indexed or indirect memory operand.
't' is for AND masks that can be performed by two rldic{l,r} insns. */
#define EXTRA_CONSTRAINT(OP, C) \
@@ -1372,6 +1373,7 @@ enum reg_class
&& !mask64_operand (OP, DImode)) \
: (C) == 'W' ? (easy_vector_constant (OP, GET_MODE (OP))) \
: (C) == 'Y' ? (word_offset_memref_operand (OP, GET_MODE (OP))) \
+ : (C) == 'Z' ? (indexed_or_indirect_operand (OP, GET_MODE (OP))) \
: 0)
/* Define which constraints are memory constraints. Tell reload
@@ -1379,7 +1381,7 @@ enum reg_class
memory address into a base register if required. */
#define EXTRA_MEMORY_CONSTRAINT(C, STR) \
- ((C) == 'Q' || (C) == 'Y')
+ ((C) == 'Q' || (C) == 'Y' || (C) == 'Z')
/* Given an rtx X being reloaded into a reg required to be
in class CLASS, return the class of reg to actually use.
Index: config/rs6000/rs6000.md
===================================================================
RCS file: /cvs/gcc/gcc/gcc/config/rs6000/rs6000.md,v
retrieving revision 1.355
diff -u -p -u -p -r1.355 rs6000.md
--- config/rs6000/rs6000.md 16 Mar 2005 18:29:26 -0000 1.355
+++ config/rs6000/rs6000.md 25 Mar 2005 19:44:40 -0000
@@ -51,6 +51,7 @@
(UNSPEC_TLSTLS 29)
(UNSPEC_FIX_TRUNC_TF 30) ; fadd, rounding towards zero
(UNSPEC_MV_CR_GT 31) ; move_from_CR_eq_bit
+ (UNSPEC_STFIWX 32)
])
;;
@@ -5272,7 +5273,7 @@
}")
(define_expand "fix_truncdfsi2"
- [(parallel [(set (match_operand:SI 0 "gpc_reg_operand" "")
+ [(parallel [(set (match_operand:SI 0 "reg_or_mem_operand" "")
(fix:SI (match_operand:DF 1 "gpc_reg_operand" "")))
(clobber (match_dup 2))
(clobber (match_dup 3))])]
@@ -5286,28 +5287,29 @@
DONE;
}
operands[2] = gen_reg_rtx (DImode);
+ if (TARGET_PPC_GFXOPT)
+ {
+ rtx orig_dest = operands[0];
+ if (GET_CODE (orig_dest) != MEM)
+ operands[0] = assign_stack_temp (SImode, GET_MODE_SIZE (SImode), 0);
+ emit_insn (gen_fix_truncdfsi2_internal_gfxopt (operands[0], operands[1],
+ operands[2]));
+ if (operands[0] != orig_dest)
+ emit_move_insn (orig_dest, operands[0]);
+ DONE;
+ }
operands[3] = assign_stack_temp (DImode, GET_MODE_SIZE (DImode), 0);
}")
-(define_insn "*fix_truncdfsi2_internal"
+(define_insn_and_split "*fix_truncdfsi2_internal"
[(set (match_operand:SI 0 "gpc_reg_operand" "=r")
(fix:SI (match_operand:DF 1 "gpc_reg_operand" "f")))
(clobber (match_operand:DI 2 "gpc_reg_operand" "=f"))
(clobber (match_operand:DI 3 "memory_operand" "=o"))]
"(TARGET_POWER2 || TARGET_POWERPC) && TARGET_HARD_FLOAT && TARGET_FPRS"
"#"
- [(set_attr "length" "16")])
-
-(define_split
- [(set (match_operand:SI 0 "gpc_reg_operand" "")
- (fix:SI (match_operand:DF 1 "gpc_reg_operand" "")))
- (clobber (match_operand:DI 2 "gpc_reg_operand" ""))
- (clobber (match_operand:DI 3 "offsettable_mem_operand" ""))]
- "(TARGET_POWER2 || TARGET_POWERPC) && TARGET_HARD_FLOAT && TARGET_FPRS"
- [(set (match_operand:SI 0 "gpc_reg_operand" "")
- (fix:SI (match_operand:DF 1 "gpc_reg_operand" "")))
- (clobber (match_operand:DI 2 "gpc_reg_operand" ""))
- (clobber (match_operand:DI 3 "offsettable_mem_operand" ""))]
+ "&& 1"
+ [(pc)]
"
{
rtx lowword;
@@ -5321,20 +5323,47 @@
emit_move_insn (operands[3], operands[2]);
emit_move_insn (operands[0], gen_rtx_MEM (SImode, lowword));
DONE;
-}")
+}"
+ [(set_attr "length" "16")])
+
+(define_insn_and_split "fix_truncdfsi2_internal_gfxopt"
+ [(set (match_operand:SI 0 "memory_operand" "=Z")
+ (fix:SI (match_operand:DF 1 "gpc_reg_operand" "f")))
+ (clobber (match_operand:DI 2 "gpc_reg_operand" "=f"))]
+ "(TARGET_POWER2 || TARGET_POWERPC) && TARGET_HARD_FLOAT && TARGET_FPRS
+ && TARGET_PPC_GFXOPT"
+ "#"
+ "&& 1"
+ [(pc)]
+ "
+{
+ emit_insn (gen_fctiwz (operands[2], operands[1]));
+ emit_insn (gen_stfiwx (operands[0], operands[2]));
+ DONE;
+}"
+ [(set_attr "length" "16")])
; Here, we use (set (reg) (unspec:DI [(fix:SI ...)] UNSPEC_FCTIWZ))
; rather than (set (subreg:SI (reg)) (fix:SI ...))
; because the first makes it clear that operand 0 is not live
; before the instruction.
(define_insn "fctiwz"
- [(set (match_operand:DI 0 "gpc_reg_operand" "=*f")
+ [(set (match_operand:DI 0 "gpc_reg_operand" "=f")
(unspec:DI [(fix:SI (match_operand:DF 1 "gpc_reg_operand" "f"))]
UNSPEC_FCTIWZ))]
"(TARGET_POWER2 || TARGET_POWERPC) && TARGET_HARD_FLOAT && TARGET_FPRS"
"{fcirz|fctiwz} %0,%1"
[(set_attr "type" "fp")])
+; An UNSPEC is used so we don't have to support SImode in FP registers.
+(define_insn "stfiwx"
+ [(set (match_operand:SI 0 "memory_operand" "=Z")
+ (unspec:SI [(match_operand:DI 1 "gpc_reg_operand" "f")]
+ UNSPEC_STFIWX))]
+ "TARGET_PPC_GFXOPT"
+ "stfiwx %1,%y0"
+ [(set_attr "type" "fpstore")])
+
(define_expand "floatsisf2"
[(set (match_operand:SF 0 "gpc_reg_operand" "")
(float:SF (match_operand:SI 1 "gpc_reg_operand" "")))]
Index: testsuite/gcc.dg/ppc-stfiwx.c
===================================================================
RCS file: testsuite/gcc.dg/ppc-stfiwx.c
diff -N testsuite/gcc.dg/ppc-stfiwx.c
--- /dev/null 1 Jan 1970 00:00:00 -0000
+++ testsuite/gcc.dg/ppc-stfiwx.c 25 Mar 2005 19:44:43 -0000
@@ -0,0 +1,8 @@
+/* { dg-do compile { target powerpc*-*-* } } */
+/* { dg-options "-mpowerpc-gfxopt" } */
+/* { dg-final { scan-assembler "stfiwx" } } */
+
+int foo (double x)
+{
+ return x;
+}
============================================================