在 2023/12/13 上午2:27, Xi Ruoyao 写道:
fld.s $f1,$r4,0
fld.s $f0,$r4,4
fld.s $f3,$r4,8
fld.s $f2,$r4,12
fcmp.slt.s $fcc1,$f0,$f3
fcmp.sgt.s $fcc0,$f1,$f2
movcf2gr $r13,$fcc1
movcf2gr $r12,$fcc0
or $r12,$r12,$r13
bnez $r12,.L3
fld.s $f4,$r4,16
fld.s $f5,$r4,20
or $r4,$r0,$r0
fcmp.sgt.s $fcc1,$f1,$f5
fcmp.slt.s $fcc0,$f0,$f4
movcf2gr $r12,$fcc1
movcf2gr $r13,$fcc0
or $r12,$r12,$r13
bnez $r12,.L2
fcmp.sgt.s $fcc1,$f3,$f5
fcmp.slt.s $fcc0,$f2,$f4
movcf2gr $r4,$fcc1
movcf2gr $r12,$fcc0
or $r4,$r4,$r12
xori $r4,$r4,1
slli.w $r4,$r4,0
jr $r1
.align 4
.L3:
or $r4,$r0,$r0
.align 4
.L2:
jr $r1
Per my micro-benchmark this is much faster than
LOGICAL_OP_NON_SHORT_CIRCUIT = 0 for randomly generated inputs (i.e.
when the branches are not predictable).
Note that there is a redundant slli.w instruction in the compiled code
and I couldn't find a way to remove it (my trick in the TARGET_64BIT
branch only works for simple examples). We may be able to handle via
the ext_dce pass [1] in the future.
Patches in attachments can remove the remaining symbol extension
directives from
the assembly.
[1]:https://gcc.gnu.org/pipermail/gcc-patches/2023-November/637320.html
>From 01eea237e13056fad9839219ed1aa70037cd3b60 Mon Sep 17 00:00:00 2001
From: Lulu Cheng <chengl...@loongson.cn>
Date: Fri, 8 Dec 2023 10:16:48 +0800
Subject: [PATCH v1] LoongArch: Optimized some of the symbolic expansion
instructions generated during bitwise operations
There are two mode iterators defined in the loongarch.md:
(define_mode_iterator GPR [SI (DI "TARGET_64BIT")])
and
(define_mode_iterator X [(SI "!TARGET_64BIT") (DI "TARGET_64BIT")])
Replace the mode in the bit arithmetic from GPR to X.
Since the bitwise operation instruction does not distinguish between 64-bit,
32-bit, etc., it is necessary to perform symbolic expansion if the bitwise
operation is less than 64 bits.
The original definition would have generated a lot of redundant symbolic
extension instructions. This problem is optimized with reference to the
implementation of RISCV.
gcc/ChangeLog:
* config/loongarch/loongarch.md (one_cmpl<mode>2): Replace GPR with X.
(*nor<mode>3): Likewise.
(nor<mode>3): Likewise.
(*branch_on_bit<X:mode>): Likewise.
(*branch_on_bit_range<X:mode>): Likewise.
(*negsi2_extended): New template.
(*<optab>si3_internal): Likewise.
(*one_cmplsi2_internal): Likewise.
(*norsi3_internal): Likewise.
(*<optab>nsi_internal): Likewise.
(bytepick_w_<bytepick_imm>_extend): Modify this template according to the
modified bit operation to make the optimization work.
* config/loongarch/predicates.md (branch_on_bit_operand): New predicate.
gcc/testsuite/ChangeLog:
* gcc.target/loongarch/sign-extend-1.c: New test.
---
gcc/config/loongarch/loongarch.md | 148 +++++++++++++++---
gcc/config/loongarch/predicates.md | 5 +
.../gcc.target/loongarch/sign-extend-1.c | 21 +++
3 files changed, 151 insertions(+), 23 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/loongarch/sign-extend-1.c
diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index 7a101dd64b7..35788deafc7 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -721,7 +721,7 @@ (define_insn "sub<mode>3"
(define_insn "sub<mode>3"
[(set (match_operand:GPR 0 "register_operand" "=r")
- (minus:GPR (match_operand:GPR 1 "register_operand" "rJ")
+ (minus:GPR (match_operand:GPR 1 "register_operand" "r")
(match_operand:GPR 2 "register_operand" "r")))]
""
"sub.<d>\t%0,%z1,%2"
@@ -1327,13 +1327,13 @@ (define_insn "neg<mode>2"
[(set_attr "alu_type" "sub")
(set_attr "mode" "<MODE>")])
-(define_insn "one_cmpl<mode>2"
- [(set (match_operand:GPR 0 "register_operand" "=r")
- (not:GPR (match_operand:GPR 1 "register_operand" "r")))]
- ""
- "nor\t%0,%.,%1"
- [(set_attr "alu_type" "not")
- (set_attr "mode" "<MODE>")])
+(define_insn "*negsi2_extended"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (sign_extend:DI (neg:SI (match_operand:SI 1 "register_operand" "r"))))]
+ "TARGET_64BIT"
+ "sub.w\t%0,%.,%1"
+ [(set_attr "alu_type" "sub")
+ (set_attr "mode" "SI")])
(define_insn "neg<mode>2"
[(set (match_operand:ANYF 0 "register_operand" "=f")
@@ -1353,14 +1353,39 @@ (define_insn "neg<mode>2"
;;
(define_insn "<optab><mode>3"
- [(set (match_operand:GPR 0 "register_operand" "=r,r")
- (any_bitwise:GPR (match_operand:GPR 1 "register_operand" "%r,r")
- (match_operand:GPR 2 "uns_arith_operand" "r,K")))]
+ [(set (match_operand:X 0 "register_operand" "=r,r")
+ (any_bitwise:X (match_operand:X 1 "register_operand" "%r,r")
+ (match_operand:X 2 "uns_arith_operand" "r,K")))]
""
"<insn>%i2\t%0,%1,%2"
[(set_attr "type" "logical")
(set_attr "mode" "<MODE>")])
+(define_insn "*<optab>si3_internal"
+ [(set (match_operand:SI 0 "register_operand" "=r,r")
+ (any_bitwise:SI (match_operand:SI 1 "register_operand" "%r,r")
+ (match_operand:SI 2 "uns_arith_operand" " r,K")))]
+ "TARGET_64BIT"
+ "<insn>%i2\t%0,%1,%2"
+ [(set_attr "type" "logical")
+ (set_attr "mode" "SI")])
+
+(define_insn "one_cmpl<mode>2"
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (not:X (match_operand:X 1 "register_operand" "r")))]
+ ""
+ "nor\t%0,%.,%1"
+ [(set_attr "alu_type" "not")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "*one_cmplsi2_internal"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (not:SI (match_operand:SI 1 "register_operand" " r")))]
+ "TARGET_64BIT"
+ "nor\t%0,%.,%1"
+ [(set_attr "type" "logical")
+ (set_attr "mode" "SI")])
+
(define_insn "and<mode>3_extended"
[(set (match_operand:GPR 0 "register_operand" "=r")
(and:GPR (match_operand:GPR 1 "nonimmediate_operand" "r")
@@ -1476,25 +1501,43 @@ (define_insn "*iorhi3"
[(set_attr "type" "logical")
(set_attr "mode" "HI")])
-(define_insn "*nor<mode>3"
- [(set (match_operand:GPR 0 "register_operand" "=r")
- (and:GPR (not:GPR (match_operand:GPR 1 "register_operand" "%r"))
- (not:GPR (match_operand:GPR 2 "register_operand" "r"))))]
+(define_insn "nor<mode>3"
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (and:X (not:X (match_operand:X 1 "register_operand" "%r"))
+ (not:X (match_operand:X 2 "register_operand" "r"))))]
""
"nor\t%0,%1,%2"
[(set_attr "type" "logical")
(set_attr "mode" "<MODE>")])
+(define_insn "*norsi3_internal"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (and:SI (not:SI (match_operand:SI 1 "register_operand" "%r"))
+ (not:SI (match_operand:SI 2 "register_operand" "r"))))]
+ "TARGET_64BIT"
+ "nor\t%0,%1,%2"
+ [(set_attr "type" "logical")
+ (set_attr "mode" "SI")])
+
(define_insn "<optab>n<mode>"
- [(set (match_operand:GPR 0 "register_operand" "=r")
- (neg_bitwise:GPR
- (not:GPR (match_operand:GPR 1 "register_operand" "r"))
- (match_operand:GPR 2 "register_operand" "r")))]
+ [(set (match_operand:X 0 "register_operand" "=r")
+ (neg_bitwise:X
+ (not:X (match_operand:X 1 "register_operand" "r"))
+ (match_operand:X 2 "register_operand" "r")))]
""
"<insn>n\t%0,%2,%1"
[(set_attr "type" "logical")
(set_attr "mode" "<MODE>")])
+(define_insn "*<optab>nsi_internal"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (neg_bitwise:SI
+ (not:SI (match_operand:SI 1 "register_operand" "r"))
+ (match_operand:SI 2 "register_operand" "r")))]
+ "TARGET_64BIT"
+ "<insn>n\t%0,%2,%1"
+ [(set_attr "type" "logical")
+ (set_attr "mode" "SI")])
;;
;; ....................
@@ -2976,6 +3019,62 @@ (define_expand "condjump"
(label_ref (match_operand 1))
(pc)))])
+(define_insn_and_split "*branch_on_bit<X:mode>"
+ [(set (pc)
+ (if_then_else
+ (match_operator 0 "equality_operator"
+ [(zero_extract:X (match_operand:X 2 "register_operand" "r")
+ (const_int 1)
+ (match_operand 3 "branch_on_bit_operand"))
+ (const_int 0)])
+ (label_ref (match_operand 1))
+ (pc)))
+ (clobber (match_scratch:X 4 "=&r"))]
+ ""
+ "#"
+ "reload_completed"
+ [(set (match_dup 4)
+ (ashift:X (match_dup 2) (match_dup 3)))
+ (set (pc)
+ (if_then_else
+ (match_op_dup 0 [(match_dup 4) (const_int 0)])
+ (label_ref (match_operand 1))
+ (pc)))]
+{
+ int shift = GET_MODE_BITSIZE (<MODE>mode) - 1 - INTVAL (operands[3]);
+ operands[3] = GEN_INT (shift);
+
+ if (GET_CODE (operands[0]) == EQ)
+ operands[0] = gen_rtx_GE (<MODE>mode, operands[4], const0_rtx);
+ else
+ operands[0] = gen_rtx_LT (<MODE>mode, operands[4], const0_rtx);
+})
+
+(define_insn_and_split "*branch_on_bit_range<X:mode>"
+ [(set (pc)
+ (if_then_else
+ (match_operator 0 "equality_operator"
+ [(zero_extract:X (match_operand:X 2 "register_operand" "r")
+ (match_operand 3 "branch_on_bit_operand")
+ (const_int 0))
+ (const_int 0)])
+ (label_ref (match_operand 1))
+ (pc)))
+ (clobber (match_scratch:X 4 "=&r"))]
+ ""
+ "#"
+ "reload_completed"
+ [(set (match_dup 4)
+ (ashift:X (match_dup 2) (match_dup 3)))
+ (set (pc)
+ (if_then_else
+ (match_op_dup 0 [(match_dup 4) (const_int 0)])
+ (label_ref (match_operand 1))
+ (pc)))]
+{
+ operands[3] = GEN_INT (GET_MODE_BITSIZE (<MODE>mode) - INTVAL (operands[3]));
+})
+
;;
@@ -3762,10 +3861,13 @@ (define_insn "bytepick_w_<bytepick_imm>"
(define_insn "bytepick_w_<bytepick_imm>_extend"
[(set (match_operand:DI 0 "register_operand" "=r")
(sign_extend:DI
- (ior:SI (lshiftrt (match_operand:SI 1 "register_operand" "r")
- (const_int <bytepick_w_lshiftrt_amount>))
- (ashift (match_operand:SI 2 "register_operand" "r")
- (const_int bytepick_w_ashift_amount)))))]
+ (subreg:SI
+ (ior:DI (subreg:DI (lshiftrt
+ (match_operand:SI 1 "register_operand" "r")
+ (const_int <bytepick_w_lshiftrt_amount>)) 0)
+ (subreg:DI (ashift
+ (match_operand:SI 2 "register_operand" "r")
+ (const_int bytepick_w_ashift_amount)) 0)) 0)))]
"TARGET_64BIT"
"bytepick.w\t%0,%1,%2,<bytepick_imm>"
[(set_attr "mode" "SI")])
diff --git a/gcc/config/loongarch/predicates.md b/gcc/config/loongarch/predicates.md
index d02e846cb12..5084752171a 100644
--- a/gcc/config/loongarch/predicates.md
+++ b/gcc/config/loongarch/predicates.md
@@ -67,6 +67,11 @@ (define_predicate "arith_operand"
(ior (match_operand 0 "const_arith_operand")
(match_operand 0 "register_operand")))
+;; Only use branch-on-bit sequences when the mask is not an ANDI immediate.
+(define_predicate "branch_on_bit_operand"
+ (and (match_code "const_int")
+ (match_test "INTVAL (op) >= IMM_BITS - 1")))
+
(define_predicate "plus_di_operand"
(ior (match_operand 0 "arith_operand")
(match_operand 0 "const_dual_imm12_operand")
diff --git a/gcc/testsuite/gcc.target/loongarch/sign-extend-1.c b/gcc/testsuite/gcc.target/loongarch/sign-extend-1.c
new file mode 100644
index 00000000000..c294ba6c407
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/sign-extend-1.c
@@ -0,0 +1,21 @@
+/* { dg-do compile } */
+/* { dg-options "-mabi=lp64d -O2" } */
+/* { dg-final { scan-assembler-not "slli.w" } } */
+
+struct pmop
+{
+ unsigned int op_pmflags;
+ unsigned int op_pmpermflags;
+};
+unsigned int PL_hints;
+
+struct pmop *pmop;
+void
+Perl_newPMOP (int type, int flags)
+{
+ if (PL_hints & 0x00100000)
+ pmop->op_pmpermflags |= 0x0001;
+ if (PL_hints & 0x00000004)
+ pmop->op_pmpermflags |= 0x0800;
+ pmop->op_pmflags = pmop->op_pmpermflags;
+}
--
2.39.3
