@@ -2579,8 +2579,7 @@ 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
@@ -2590,8 +2589,7 @@ 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));
@@ -2836,7 +2834,7 @@ 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);
@@ -2871,7 +2869,8 @@ 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);
@@ -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]);
@@ -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);
@@ -3288,7 +3288,7 @@ 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);
@@ -26870,9 +26870,8 @@ 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,
@@ -26904,11 +26903,8 @@ 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,
new file mode 100644
@@ -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]);
+}
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. --- 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