packages/gcc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
gcc/LoongArch-Optimize-immediate-load.patch
ticat_fp 7e7be47bfd LoongArch: Sync patch from gcc upstream 
Signed-off-by: ticat_fp <fanpeng@loongson.cn>
2024-03-27 09:22:13 +08:00

339 lines
11 KiB
Diff
Raw Blame History

From b533b615ae47b97d51eeb83e1a63f7c72407430f Mon Sep 17 00:00:00 2001
From: Lulu Cheng <chenglulu@loongson.cn>
Date: Thu, 17 Nov 2022 17:08:36 +0800
Subject: [PATCH 032/124] LoongArch: Optimize immediate load.
The immediate number is split in the Split pass, not in the expand pass.
Because loop2_invariant pass will extract the instructions that do not change
in the loop out of the loop, some instructions will not meet the extraction
conditions if the machine performs immediate decomposition while expand pass,
so the immediate decomposition will be transferred to the split process.
gcc/ChangeLog:
* config/loongarch/loongarch.cc (enum loongarch_load_imm_method):
Remove the member METHOD_INSV that is not currently used.
(struct loongarch_integer_op): Define a new member curr_value,
that records the value of the number stored in the destination
register immediately after the current instruction has run.
(loongarch_build_integer): Assign a value to the curr_value member variable.
(loongarch_move_integer): Adds information for the immediate load instruction.
* config/loongarch/loongarch.md (*movdi_32bit): Redefine as define_insn_and_split.
(*movdi_64bit): Likewise.
(*movsi_internal): Likewise.
(*movhi_internal): Likewise.
* config/loongarch/predicates.md: Return true as long as it is CONST_INT, ensure
that the immediate number is not optimized by decomposition during expand
optimization loop.
gcc/testsuite/ChangeLog:
* gcc.target/loongarch/imm-load.c: New test.
* gcc.target/loongarch/imm-load1.c: New test.
Signed-off-by: Peng Fan <fanpeng@loongson.cn>
Signed-off-by: ticat_fp <fanpeng@loongson.cn>
---
gcc/config/loongarch/loongarch.cc | 62 ++++++++++---------
gcc/config/loongarch/loongarch.md | 44 +++++++++++--
gcc/config/loongarch/predicates.md | 2 +-
gcc/testsuite/gcc.target/loongarch/imm-load.c | 10 +++
.../gcc.target/loongarch/imm-load1.c | 26 ++++++++
5 files changed, 110 insertions(+), 34 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/loongarch/imm-load.c
create mode 100644 gcc/testsuite/gcc.target/loongarch/imm-load1.c
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index 622c9435b..f45a49f90 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -139,22 +139,21 @@ struct loongarch_address_info
METHOD_LU52I:
Load 52-63 bit of the immediate number.
-
- METHOD_INSV:
- immediate like 0xfff00000fffffxxx
- */
+*/
enum loongarch_load_imm_method
{
METHOD_NORMAL,
METHOD_LU32I,
- METHOD_LU52I,
- METHOD_INSV
+ METHOD_LU52I
};
struct loongarch_integer_op
{
enum rtx_code code;
HOST_WIDE_INT value;
+ /* Represent the result of the immediate count of the load instruction at
+ each step. */
+ HOST_WIDE_INT curr_value;
enum loongarch_load_imm_method method;
};
@@ -1474,24 +1473,27 @@ loongarch_build_integer (struct loongarch_integer_op *codes,
{
/* The value of the lower 32 bit be loaded with one instruction.
lu12i.w. */
- codes[0].code = UNKNOWN;
- codes[0].method = METHOD_NORMAL;
- codes[0].value = low_part;
+ codes[cost].code = UNKNOWN;
+ codes[cost].method = METHOD_NORMAL;
+ codes[cost].value = low_part;
+ codes[cost].curr_value = low_part;
cost++;
}
else
{
/* lu12i.w + ior. */
- codes[0].code = UNKNOWN;
- codes[0].method = METHOD_NORMAL;
- codes[0].value = low_part & ~(IMM_REACH - 1);
+ codes[cost].code = UNKNOWN;
+ codes[cost].method = METHOD_NORMAL;
+ codes[cost].value = low_part & ~(IMM_REACH - 1);
+ codes[cost].curr_value = codes[cost].value;
cost++;
HOST_WIDE_INT iorv = low_part & (IMM_REACH - 1);
if (iorv != 0)
{
- codes[1].code = IOR;
- codes[1].method = METHOD_NORMAL;
- codes[1].value = iorv;
+ codes[cost].code = IOR;
+ codes[cost].method = METHOD_NORMAL;
+ codes[cost].value = iorv;
+ codes[cost].curr_value = low_part;
cost++;
}
}
@@ -1514,11 +1516,14 @@ loongarch_build_integer (struct loongarch_integer_op *codes,
{
codes[cost].method = METHOD_LU52I;
codes[cost].value = value & LU52I_B;
+ codes[cost].curr_value = value;
return cost + 1;
}
codes[cost].method = METHOD_LU32I;
codes[cost].value = (value & LU32I_B) | (sign51 ? LU52I_B : 0);
+ codes[cost].curr_value = (value & 0xfffffffffffff)
+ | (sign51 ? LU52I_B : 0);
cost++;
/* Determine whether the 52-61 bits are sign-extended from the low order,
@@ -1527,6 +1532,7 @@ loongarch_build_integer (struct loongarch_integer_op *codes,
{
codes[cost].method = METHOD_LU52I;
codes[cost].value = value & LU52I_B;
+ codes[cost].curr_value = value;
cost++;
}
}
@@ -2910,6 +2916,9 @@ loongarch_move_integer (rtx temp, rtx dest, unsigned HOST_WIDE_INT value)
else
x = force_reg (mode, x);
+ set_unique_reg_note (get_last_insn (), REG_EQUAL,
+ GEN_INT (codes[i-1].curr_value));
+
switch (codes[i].method)
{
case METHOD_NORMAL:
@@ -2917,22 +2926,17 @@ loongarch_move_integer (rtx temp, rtx dest, unsigned HOST_WIDE_INT value)
GEN_INT (codes[i].value));
break;
case METHOD_LU32I:
- emit_insn (
- gen_rtx_SET (x,
- gen_rtx_IOR (DImode,
- gen_rtx_ZERO_EXTEND (
- DImode, gen_rtx_SUBREG (SImode, x, 0)),
- GEN_INT (codes[i].value))));
+ gcc_assert (mode == DImode);
+ x = gen_rtx_IOR (DImode,
+ gen_rtx_ZERO_EXTEND (DImode,
+ gen_rtx_SUBREG (SImode, x, 0)),
+ GEN_INT (codes[i].value));
break;
case METHOD_LU52I:
- emit_insn (gen_lu52i_d (x, x, GEN_INT (0xfffffffffffff),
- GEN_INT (codes[i].value)));
- break;
- case METHOD_INSV:
- emit_insn (
- gen_rtx_SET (gen_rtx_ZERO_EXTRACT (DImode, x, GEN_INT (20),
- GEN_INT (32)),
- gen_rtx_REG (DImode, 0)));
+ gcc_assert (mode == DImode);
+ x = gen_rtx_IOR (DImode,
+ gen_rtx_AND (DImode, x, GEN_INT (0xfffffffffffff)),
+ GEN_INT (codes[i].value));
break;
default:
gcc_unreachable ();
diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index 2fda53819..f61db66d5 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -1718,23 +1718,41 @@
DONE;
})
-(define_insn "*movdi_32bit"
+(define_insn_and_split "*movdi_32bit"
[(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,w,*f,*f,*r,*m")
(match_operand:DI 1 "move_operand" "r,i,w,r,*J*r,*m,*f,*f"))]
"!TARGET_64BIT
&& (register_operand (operands[0], DImode)
|| reg_or_0_operand (operands[1], DImode))"
{ return loongarch_output_move (operands[0], operands[1]); }
+ "CONST_INT_P (operands[1]) && REG_P (operands[0]) && GP_REG_P (REGNO
+ (operands[0]))"
+ [(const_int 0)]
+ "
+{
+ loongarch_move_integer (operands[0], operands[0], INTVAL (operands[1]));
+ DONE;
+}
+ "
[(set_attr "move_type" "move,const,load,store,mgtf,fpload,mftg,fpstore")
(set_attr "mode" "DI")])
-(define_insn "*movdi_64bit"
+(define_insn_and_split "*movdi_64bit"
[(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,w,*f,*f,*r,*m")
(match_operand:DI 1 "move_operand" "r,Yd,w,rJ,*r*J,*m,*f,*f"))]
"TARGET_64BIT
&& (register_operand (operands[0], DImode)
|| reg_or_0_operand (operands[1], DImode))"
{ return loongarch_output_move (operands[0], operands[1]); }
+ "CONST_INT_P (operands[1]) && REG_P (operands[0]) && GP_REG_P (REGNO
+ (operands[0]))"
+ [(const_int 0)]
+ "
+{
+ loongarch_move_integer (operands[0], operands[0], INTVAL (operands[1]));
+ DONE;
+}
+ "
[(set_attr "move_type" "move,const,load,store,mgtf,fpload,mftg,fpstore")
(set_attr "mode" "DI")])
@@ -1749,12 +1767,21 @@
DONE;
})
-(define_insn "*movsi_internal"
+(define_insn_and_split "*movsi_internal"
[(set (match_operand:SI 0 "nonimmediate_operand" "=r,r,r,w,*f,*f,*r,*m,*r,*z")
(match_operand:SI 1 "move_operand" "r,Yd,w,rJ,*r*J,*m,*f,*f,*z,*r"))]
"(register_operand (operands[0], SImode)
|| reg_or_0_operand (operands[1], SImode))"
{ return loongarch_output_move (operands[0], operands[1]); }
+ "CONST_INT_P (operands[1]) && REG_P (operands[0]) && GP_REG_P (REGNO
+ (operands[0]))"
+ [(const_int 0)]
+ "
+{
+ loongarch_move_integer (operands[0], operands[0], INTVAL (operands[1]));
+ DONE;
+}
+ "
[(set_attr "move_type" "move,const,load,store,mgtf,fpload,mftg,fpstore,mftg,mgtf")
(set_attr "mode" "SI")])
@@ -1774,12 +1801,21 @@
DONE;
})
-(define_insn "*movhi_internal"
+(define_insn_and_split "*movhi_internal"
[(set (match_operand:HI 0 "nonimmediate_operand" "=r,r,r,r,m,r,k")
(match_operand:HI 1 "move_operand" "r,Yd,I,m,rJ,k,rJ"))]
"(register_operand (operands[0], HImode)
|| reg_or_0_operand (operands[1], HImode))"
{ return loongarch_output_move (operands[0], operands[1]); }
+ "CONST_INT_P (operands[1]) && REG_P (operands[0]) && GP_REG_P (REGNO
+ (operands[0]))"
+ [(const_int 0)]
+ "
+{
+ loongarch_move_integer (operands[0], operands[0], INTVAL (operands[1]));
+ DONE;
+}
+ "
[(set_attr "move_type" "move,const,const,load,store,load,store")
(set_attr "mode" "HI")])
diff --git a/gcc/config/loongarch/predicates.md b/gcc/config/loongarch/predicates.md
index 8bd0c1376..58c3dc226 100644
--- a/gcc/config/loongarch/predicates.md
+++ b/gcc/config/loongarch/predicates.md
@@ -226,7 +226,7 @@
switch (GET_CODE (op))
{
case CONST_INT:
- return !splittable_const_int_operand (op, mode);
+ return true;
case CONST:
case SYMBOL_REF:
diff --git a/gcc/testsuite/gcc.target/loongarch/imm-load.c b/gcc/testsuite/gcc.target/loongarch/imm-load.c
new file mode 100644
index 000000000..c04ca3399
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/imm-load.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-mabi=lp64d -O2 -fdump-rtl-split1" } */
+
+long int
+test (void)
+{
+ return 0x1234567890abcdef;
+}
+/* { dg-final { scan-rtl-dump-times "scanning new insn with uid" 6 "split1" } } */
+
diff --git a/gcc/testsuite/gcc.target/loongarch/imm-load1.c b/gcc/testsuite/gcc.target/loongarch/imm-load1.c
new file mode 100644
index 000000000..2ff029712
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/imm-load1.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-mabi=lp64d -O2" } */
+/* { dg-final { scan-assembler "test:.*lu52i\.d.*\n\taddi\.w.*\n\.L2:" } } */
+
+
+extern long long b[10];
+static inline long long
+repeat_bytes (void)
+{
+ long long r = 0x0101010101010101;
+
+ return r;
+}
+
+static inline long long
+highbit_mask (long long m)
+{
+ return m & repeat_bytes ();
+}
+
+void test(long long *a)
+{
+ for (int i = 0; i < 10; i++)
+ b[i] = highbit_mask (a[i]);
+
+}
--
2.33.0
Reference in New Issue View Git Blame Copy Permalink