This patch uses the new force_reload_address routine added by the
previous patch to fix PR112906.
gcc/ChangeLog:
PR target/112906
* config/aarch64/aarch64-sve.md (@aarch64_vec_duplicate_vq<mode>_le):
Use force_reload_address to reload addresses that aren't suitable for
ld1rq in the pre-RA splitter.
gcc/testsuite/ChangeLog:
PR target/112906
* gcc.target/aarch64/sve/acle/general/pr112906.c: New test.
{
if (can_create_pseudo_p ()
&& !aarch64_sve_ld1rq_operand (operands[1], <V128>mode))
- {
- rtx addr = force_reg (Pmode, XEXP (operands[1], 0));
- operands[1] = replace_equiv_address (operands[1], addr);
- }
+ operands[1] = force_reload_address (operands[1]);
if (GET_CODE (operands[2]) == SCRATCH)
operands[2] = gen_reg_rtx (VNx16BImode);
emit_move_insn (operands[2], CONSTM1_RTX (VNx16BImode));
--- /dev/null
+/* { dg-do compile } */
+/* { dg-additional-options "-O2" } */
+#include <arm_sve.h>
+unsigned c;
+long d;
+void f() {
+ unsigned char *b;
+ svbool_t x = svptrue_b8();
+ svuint32_t g;
+ svuint8_t h, i;
+ d = 0;
+ for (; (unsigned *)d < &c; d += 16) {
+ h = svld1rq(x, &b[d]);
+ g = svdot_lane(g, i, h, 3);
+ }
+ svst1_vnum(x, &c, 8, g);
+}