1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
|
From eb49bbb886ef374eddb93e866c9c9f5f314c8014 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 18 Jun 2024 12:22:31 +0100
Subject: [PATCH 13/16] aarch64: Add some uses of force_lowpart_subreg
This patch makes more use of force_lowpart_subreg, similarly
to the recent patch for force_subreg. The criteria were:
(1) The code is obviously specific to expand (where new pseudos
can be created).
(2) The value is obviously an rvalue rather than an lvalue.
gcc/
PR target/115464
* config/aarch64/aarch64-builtins.cc (aarch64_expand_fcmla_builtin)
(aarch64_expand_rwsr_builtin): Use force_lowpart_subreg instead of
simplify_gen_subreg and lowpart_subreg.
* config/aarch64/aarch64-sve-builtins-base.cc
(svset_neonq_impl::expand): Likewise.
* config/aarch64/aarch64-sve-builtins-sme.cc
(add_load_store_slice_operand): Likewise.
* config/aarch64/aarch64.cc (aarch64_sve_reinterpret): Likewise.
(aarch64_addti_scratch_regs, aarch64_subvti_scratch_regs): Likewise.
gcc/testsuite/
PR target/115464
* gcc.target/aarch64/sve/acle/general/pr115464_2.c: New test.
(cherry picked from commit 6bd4fbae45d11795a9a6f54b866308d4d7134def)
---
gcc/config/aarch64/aarch64-builtins.cc | 11 +++++------
gcc/config/aarch64/aarch64-sve-builtins-base.cc | 2 +-
gcc/config/aarch64/aarch64-sve-builtins-sme.cc | 2 +-
gcc/config/aarch64/aarch64.cc | 14 +++++---------
.../aarch64/sve/acle/general/pr115464_2.c | 11 +++++++++++
5 files changed, 23 insertions(+), 17 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr115464_2.c
diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index b2e46a073a8..264b9560709 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -2497,8 +2497,7 @@ aarch64_expand_fcmla_builtin (tree exp, rtx target, int fcode)
int lane = INTVAL (lane_idx);
if (lane < nunits / 4)
- op2 = simplify_gen_subreg (d->mode, op2, quadmode,
- subreg_lowpart_offset (d->mode, quadmode));
+ op2 = force_lowpart_subreg (d->mode, op2, quadmode);
else
{
/* Select the upper 64 bits, either a V2SF or V4HF, this however
@@ -2508,8 +2507,7 @@ aarch64_expand_fcmla_builtin (tree exp, rtx target, int fcode)
gen_highpart_mode generates code that isn't optimal. */
rtx temp1 = gen_reg_rtx (d->mode);
rtx temp2 = gen_reg_rtx (DImode);
- temp1 = simplify_gen_subreg (d->mode, op2, quadmode,
- subreg_lowpart_offset (d->mode, quadmode));
+ temp1 = force_lowpart_subreg (d->mode, op2, quadmode);
temp1 = force_subreg (V2DImode, temp1, d->mode, 0);
if (BYTES_BIG_ENDIAN)
emit_insn (gen_aarch64_get_lanev2di (temp2, temp1, const0_rtx));
@@ -2754,7 +2752,7 @@ aarch64_expand_rwsr_builtin (tree exp, rtx target, int fcode)
case AARCH64_WSR64:
case AARCH64_WSRF64:
case AARCH64_WSR128:
- subreg = lowpart_subreg (sysreg_mode, input_val, mode);
+ subreg = force_lowpart_subreg (sysreg_mode, input_val, mode);
break;
case AARCH64_WSRF:
subreg = gen_lowpart_SUBREG (SImode, input_val);
@@ -2789,7 +2787,8 @@ aarch64_expand_rwsr_builtin (tree exp, rtx target, int fcode)
case AARCH64_RSR64:
case AARCH64_RSRF64:
case AARCH64_RSR128:
- return lowpart_subreg (TYPE_MODE (TREE_TYPE (exp)), target, sysreg_mode);
+ return force_lowpart_subreg (TYPE_MODE (TREE_TYPE (exp)),
+ target, sysreg_mode);
case AARCH64_RSRF:
subreg = gen_lowpart_SUBREG (SImode, target);
return gen_lowpart_SUBREG (SFmode, subreg);
diff --git a/gcc/config/aarch64/aarch64-sve-builtins-base.cc b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
index 2c95da79572..3c970e9c5f8 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
@@ -1183,7 +1183,7 @@ public:
if (BYTES_BIG_ENDIAN)
return e.use_exact_insn (code_for_aarch64_sve_set_neonq (mode));
insn_code icode = code_for_vcond_mask (mode, mode);
- e.args[1] = lowpart_subreg (mode, e.args[1], GET_MODE (e.args[1]));
+ e.args[1] = force_lowpart_subreg (mode, e.args[1], GET_MODE (e.args[1]));
e.add_output_operand (icode);
e.add_input_operand (icode, e.args[1]);
e.add_input_operand (icode, e.args[0]);
diff --git a/gcc/config/aarch64/aarch64-sve-builtins-sme.cc b/gcc/config/aarch64/aarch64-sve-builtins-sme.cc
index f4c91bcbb95..b66b35ae60b 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-sme.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-sme.cc
@@ -112,7 +112,7 @@ add_load_store_slice_operand (function_expander &e, insn_code icode,
rtx base = e.args[argno];
if (e.mode_suffix_id == MODE_vnum)
{
- rtx vnum = lowpart_subreg (SImode, e.args[vnum_argno], DImode);
+ rtx vnum = force_lowpart_subreg (SImode, e.args[vnum_argno], DImode);
base = simplify_gen_binary (PLUS, SImode, base, vnum);
}
e.add_input_operand (icode, base);
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 1beec94629d..a064aeecbc0 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -3284,7 +3284,7 @@ aarch64_sve_reinterpret (machine_mode mode, rtx x)
/* can_change_mode_class must only return true if subregs and svreinterprets
have the same semantics. */
if (targetm.can_change_mode_class (GET_MODE (x), mode, FP_REGS))
- return lowpart_subreg (mode, x, GET_MODE (x));
+ return force_lowpart_subreg (mode, x, GET_MODE (x));
rtx res = gen_reg_rtx (mode);
x = force_reg (GET_MODE (x), x);
@@ -26979,9 +26979,8 @@ aarch64_addti_scratch_regs (rtx op1, rtx op2, rtx *low_dest,
rtx *high_in2)
{
*low_dest = gen_reg_rtx (DImode);
- *low_in1 = gen_lowpart (DImode, op1);
- *low_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_lowpart_offset (DImode, TImode));
+ *low_in1 = force_lowpart_subreg (DImode, op1, TImode);
+ *low_in2 = force_lowpart_subreg (DImode, op2, TImode);
*high_dest = gen_reg_rtx (DImode);
*high_in1 = gen_highpart (DImode, op1);
*high_in2 = simplify_gen_subreg (DImode, op2, TImode,
@@ -27013,11 +27012,8 @@ aarch64_subvti_scratch_regs (rtx op1, rtx op2, rtx *low_dest,
rtx *high_in2)
{
*low_dest = gen_reg_rtx (DImode);
- *low_in1 = simplify_gen_subreg (DImode, op1, TImode,
- subreg_lowpart_offset (DImode, TImode));
-
- *low_in2 = simplify_gen_subreg (DImode, op2, TImode,
- subreg_lowpart_offset (DImode, TImode));
+ *low_in1 = force_lowpart_subreg (DImode, op1, TImode);
+ *low_in2 = force_lowpart_subreg (DImode, op2, TImode);
*high_dest = gen_reg_rtx (DImode);
*high_in1 = simplify_gen_subreg (DImode, op1, TImode,
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr115464_2.c b/gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr115464_2.c
new file mode 100644
index 00000000000..f561c34f732
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/acle/general/pr115464_2.c
@@ -0,0 +1,11 @@
+/* { dg-options "-O2" } */
+
+#include <arm_neon.h>
+#include <arm_sve.h>
+#include <arm_neon_sve_bridge.h>
+
+svuint16_t
+convolve4_4_x (uint16x8x2_t permute_tbl, svuint16_t a)
+{
+ return svset_neonq_u16 (a, permute_tbl.val[1]);
+}
--
2.44.2
|
