Hi Suwa-san,
On Fri, Oct 14, 2022 at 4:19 AM Takayuki 'January June' Suwa
<jjsuwa_sys3175@yahoo.co.jp> wrote:
> This patch provides the first step in the transition from Reload to LRA
> in Xtensa.
>
> gcc/ChangeLog:
>
> * config/xtensa/xtensa-proto.h (xtensa_split1_is_finished_p):
> New prototype.
> * config/xtensa/xtensa.cc
> (xtensa_split1_is_finished_p, xtensa_lra_p): New functions.
> (TARGET_LRA_P): Replace the dummy hook with xtensa_lra_p.
> (xt_true_regnum): Rework.
> * gcc/config/xtensa/xtensa.h (CALL_REALLY_USED_REGISTERS):
> Rename from CALL_USED_REGISTERS, and remove what correspond to
> FIXED_REGISTERS.
> * gcc/config/xtensa/constraints.md (Y):
> Use !xtensa_split1_is_finished_p() instead of can_create_pseudo_p().
> * gcc/config/xtensa/predicates.md (move_operand): Ditto.
> * gcc/config/xtensa/xtensa.md:
> Add new split pattern that puts out-of-constraint integer constants
> into the constant pool.
> * gcc/config/xtensa/xtensa.opt (-mlra): New target-specific option
> for testing purpose.
> ---
> gcc/config/xtensa/constraints.md | 2 +-
> gcc/config/xtensa/predicates.md | 2 +-
> gcc/config/xtensa/xtensa-protos.h | 1 +
> gcc/config/xtensa/xtensa.cc | 48 ++++++++++++++++++++++++-------
> gcc/config/xtensa/xtensa.h | 6 ++--
> gcc/config/xtensa/xtensa.md | 12 ++++++++
> gcc/config/xtensa/xtensa.opt | 4 +++
> 7 files changed, 60 insertions(+), 15 deletions(-)
Thank you for doing this, I couldn't find time to get back to it since 2020 ):
This change results in a few new regressions in the following tests
caused by ICE even when running without -mlra option:
+FAIL: gcc.c-torture/execute/pr92904.c -O1 (internal compiler
error: in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -O2 (internal compiler
error: in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -O3 -fomit-frame-pointer
-funroll-loops -fpeel-loops -ftracer -finline-functions (internal
compiler error: in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -O3 -g (internal compiler
error: in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -Os (internal compiler
error: in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -O2 -flto
-fno-use-linker-plugin -flto-partition=none (internal compiler error:
in extract_insn, at recog.cc:2791)
+FAIL: gcc.c-torture/execute/pr92904.c -O2 -flto -fuse-linker-plugin
-fno-fat-lto-objects (internal compiler error: in extract_insn, at
recog.cc:2791)
+FAIL: g++.dg/torture/vshuf-v2si.C -O3 -g (internal compiler error:
in extract_insn, at recog.cc:2791)
+FAIL: g++.dg/torture/vshuf-v8qi.C -O3 -g (internal compiler error:
in extract_insn, at recog.cc:2791)
The backtraces look like this in all of them:
gcc/gcc/testsuite/gcc.c-torture/execute/pr92904.c:395:1: error:
unrecognizable insn:
(insn 10501 7 10502 2 (set (reg:SI 5913)
(const_int 1431655765 [0x55555555]))
"gcc/gcc/testsuite/gcc.c-torture/execute/pr92904.c":239:9 -1
(nil))
during RTL pass: subreg3
gcc/gcc/testsuite/gcc.c-torture/execute/pr92904.c:395:1: internal
compiler error: in extract_insn, at recog.cc:2791
0x6b17f7 _fatal_insn(char const*, rtx_def const*, char const*, int, char const*)
gcc/gcc/rtl-error.cc:108
0x6b187a _fatal_insn_not_found(rtx_def const*, char const*, int, char const*)
gcc/gcc/rtl-error.cc:116
0x6a2aa4 extract_insn(rtx_insn*)
gcc/gcc/recog.cc:2791
0x179e94d decompose_multiword_subregs
gcc/gcc/lower-subreg.cc:1678
0x179ebdd execute
gcc/gcc/lower-subreg.cc:1820
There's also the following runtime failures, but only on
call0 configuration:
+FAIL: gcc.c-torture/execute/20010122-1.c -O1 execution test
+FAIL: gcc.c-torture/execute/20010122-1.c -O2 execution test
+FAIL: gcc.c-torture/execute/20010122-1.c -O3 -g execution test
+FAIL: gcc.c-torture/execute/20010122-1.c -Os execution test
+FAIL: gcc.c-torture/execute/20010122-1.c -O2 -flto
-fno-use-linker-plugin -flto-partition=none execution test
@@ -121,7 +121,7 @@
(ior (and (match_code "const_int,const_double,const,symbol_ref,label_ref")
(match_test "TARGET_AUTO_LITPOOLS"))
(and (match_code "const_int")
- (match_test "can_create_pseudo_p ()"))))
+ (match_test "! xtensa_split1_is_finished_p ()"))))
;; Memory constraints. Do not use define_memory_constraint here. Doing so
;; causes reload to force some constants into the constant pool, but since
@@ -149,7 +149,7 @@
(ior (and (match_code "const_int")
(match_test "(GET_MODE_CLASS (mode) == MODE_INT
&& xtensa_simm12b (INTVAL (op)))
- || can_create_pseudo_p ()"))
+ || ! xtensa_split1_is_finished_p ()"))
(and (match_code "const_int,const_double,const,symbol_ref,label_ref")
(match_test "(TARGET_CONST16 || TARGET_AUTO_LITPOOLS)
&& CONSTANT_P (op)
@@ -58,6 +58,7 @@ extern char *xtensa_emit_call (int, rtx *);
extern char *xtensa_emit_sibcall (int, rtx *);
extern bool xtensa_tls_referenced_p (rtx);
extern enum rtx_code xtensa_shlrd_which_direction (rtx, rtx);
+extern bool xtensa_split1_is_finished_p (void);
#ifdef TREE_CODE
extern void init_cumulative_args (CUMULATIVE_ARGS *, int);
@@ -56,6 +56,7 @@ along with GCC; see the file COPYING3. If not see
#include "hw-doloop.h"
#include "rtl-iter.h"
#include "insn-attr.h"
+#include "tree-pass.h"
/* This file should be included last. */
#include "target-def.h"
@@ -199,6 +200,7 @@ static void xtensa_output_mi_thunk (FILE *file, tree thunk ATTRIBUTE_UNUSED,
HOST_WIDE_INT delta,
HOST_WIDE_INT vcall_offset,
tree function);
+static bool xtensa_lra_p (void);
static rtx xtensa_delegitimize_address (rtx);
@@ -295,7 +297,7 @@ static rtx xtensa_delegitimize_address (rtx);
#define TARGET_CANNOT_FORCE_CONST_MEM xtensa_cannot_force_const_mem
#undef TARGET_LRA_P
-#define TARGET_LRA_P hook_bool_void_false
+#define TARGET_LRA_P xtensa_lra_p
#undef TARGET_LEGITIMATE_ADDRESS_P
#define TARGET_LEGITIMATE_ADDRESS_P xtensa_legitimate_address_p
@@ -492,21 +494,30 @@ xtensa_mask_immediate (HOST_WIDE_INT v)
int
xt_true_regnum (rtx x)
{
- if (GET_CODE (x) == REG)
+ if (REG_P (x))
{
- if (reg_renumber
- && REGNO (x) >= FIRST_PSEUDO_REGISTER
- && reg_renumber[REGNO (x)] >= 0)
+ if (HARD_REGISTER_P (x)
+ && reg_renumber
+ && (lra_in_progress || reg_renumber[REGNO (x)] >= 0))
return reg_renumber[REGNO (x)];
return REGNO (x);
}
- if (GET_CODE (x) == SUBREG)
+ if (SUBREG_P (x))
{
int base = xt_true_regnum (SUBREG_REG (x));
- if (base >= 0 && base < FIRST_PSEUDO_REGISTER)
- return base + subreg_regno_offset (REGNO (SUBREG_REG (x)),
- GET_MODE (SUBREG_REG (x)),
- SUBREG_BYTE (x), GET_MODE (x));
+
+ if (base >= 0
+ && HARD_REGISTER_NUM_P (base))
+ {
+ struct subreg_info info;
+
+ subreg_get_info (lra_in_progress
+ ? (unsigned) base : REGNO (SUBREG_REG (x)),
+ GET_MODE (SUBREG_REG (x)),
+ SUBREG_BYTE (x), GET_MODE (x), &info);
+ if (info.representable_p)
+ return base + info.offset;
+ }
}
return -1;
}
@@ -2477,6 +2488,15 @@ xtensa_shlrd_which_direction (rtx op0, rtx op1)
}
+/* Return true after "split1" pass is finished. */
+
+bool
+xtensa_split1_is_finished_p (void)
+{
+ return cfun && (cfun->curr_properties & PROP_rtl_split_insns);
+}
+
+
/* Implement TARGET_CANNOT_FORCE_CONST_MEM. */
static bool
@@ -5119,4 +5139,12 @@ xtensa_delegitimize_address (rtx op)
return op;
}
+/* Implement TARGET_LRA_P. */
+
+static bool
+xtensa_lra_p (void)
+{
+ return TARGET_LRA;
+}
+
#include "gt-xtensa.h"
@@ -242,10 +242,10 @@ along with GCC; see the file COPYING3. If not see
Proper values are computed in TARGET_CONDITIONAL_REGISTER_USAGE. */
-#define CALL_USED_REGISTERS \
+#define CALL_REALLY_USED_REGISTERS \
{ \
- 1, 1, 4, 4, 4, 4, 4, 4, 1, 1, 1, 1, 2, 2, 2, 2, \
- 1, 1, 1, \
+ 0, 0, 4, 4, 4, 4, 4, 4, 1, 1, 1, 1, 2, 2, 2, 2, \
+ 0, 0, 1, \
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, \
1, \
}
@@ -1017,6 +1017,18 @@
(set_attr "mode" "SI")
(set_attr "length" "2,2,2,2,2,2,3,3,3,3,6,3,3,3,3,3")])
+(define_split
+ [(set (match_operand:SI 0 "register_operand")
+ (match_operand:SI 1 "const_int_operand"))]
+ "!TARGET_CONST16 && !TARGET_AUTO_LITPOOLS
+ && ! xtensa_split1_is_finished_p ()
+ && ! xtensa_simm12b (INTVAL (operands[1]))"
+ [(set (match_dup 0)
+ (match_dup 1))]
+{
+ operands[1] = force_const_mem (SImode, operands[1]);
+})
+
(define_split
[(set (match_operand:SI 0 "register_operand")
(match_operand:SI 1 "constantpool_operand"))]
@@ -34,6 +34,10 @@ mextra-l32r-costs=
Target RejectNegative Joined UInteger Var(xtensa_extra_l32r_costs) Init(0)
Set extra memory access cost for L32R instruction, in clock-cycle units.
+mlra
+Target Mask(LRA)
+Use LRA instead of reload (transitional).
+
mtarget-align
Target
Automatically align branch targets to reduce branch penalties.