move_lo_quad_internal_<mode> and move_lo_quad_internal_be_<mode>
partially duplicate the later aarch64_combinez{,_be}<mode> patterns.
The duplication itself is a regression.
The only substantive differences between the two are:
* combinez uses vector MOV (ORR) instead of element MOV (DUP).
The former seems more likely to be handled via renaming.
* combinez disparages the GPR->FPR alternative whereas move_lo_quad
gave it equal cost. The new test gives a token example of when
the combinez behaviour helps.
gcc/
* config/aarch64/aarch64-simd.md (move_lo_quad_internal_<mode>)
(move_lo_quad_internal_be_<mode>): Delete.
(move_lo_quad_<mode>): Use aarch64_combine<Vhalf> instead of the above.
gcc/testsuite/
* gcc.target/aarch64/vec-init-8.c: New test.
---
gcc/config/aarch64/aarch64-simd.md | 37 +------------------
gcc/testsuite/gcc.target/aarch64/vec-init-8.c | 15 ++++++++
2 files changed, 17 insertions(+), 35 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/vec-init-8.c
@@ -1584,46 +1584,13 @@ (define_insn "aarch64_<optab>p<mode>"
;; On little-endian this is { operand, zeroes }
;; On big-endian this is { zeroes, operand }
-(define_insn "move_lo_quad_internal_<mode>"
- [(set (match_operand:VQMOV 0 "register_operand" "=w,w,w")
- (vec_concat:VQMOV
- (match_operand:<VHALF> 1 "register_operand" "w,r,r")
- (match_operand:<VHALF> 2 "aarch64_simd_or_scalar_imm_zero")))]
- "TARGET_SIMD && !BYTES_BIG_ENDIAN"
- "@
- dup\\t%d0, %1.d[0]
- fmov\\t%d0, %1
- dup\\t%d0, %1"
- [(set_attr "type" "neon_dup<q>,f_mcr,neon_dup<q>")
- (set_attr "length" "4")
- (set_attr "arch" "simd,fp,simd")]
-)
-
-(define_insn "move_lo_quad_internal_be_<mode>"
- [(set (match_operand:VQMOV 0 "register_operand" "=w,w,w")
- (vec_concat:VQMOV
- (match_operand:<VHALF> 2 "aarch64_simd_or_scalar_imm_zero")
- (match_operand:<VHALF> 1 "register_operand" "w,r,r")))]
- "TARGET_SIMD && BYTES_BIG_ENDIAN"
- "@
- dup\\t%d0, %1.d[0]
- fmov\\t%d0, %1
- dup\\t%d0, %1"
- [(set_attr "type" "neon_dup<q>,f_mcr,neon_dup<q>")
- (set_attr "length" "4")
- (set_attr "arch" "simd,fp,simd")]
-)
-
(define_expand "move_lo_quad_<mode>"
[(match_operand:VQMOV 0 "register_operand")
(match_operand:<VHALF> 1 "register_operand")]
"TARGET_SIMD"
{
- rtx zs = CONST0_RTX (<VHALF>mode);
- if (BYTES_BIG_ENDIAN)
- emit_insn (gen_move_lo_quad_internal_be_<mode> (operands[0], operands[1], zs));
- else
- emit_insn (gen_move_lo_quad_internal_<mode> (operands[0], operands[1], zs));
+ emit_insn (gen_aarch64_combine<Vhalf> (operands[0], operands[1],
+ CONST0_RTX (<VHALF>mode)));
DONE;
}
)
new file mode 100644
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O" } */
+
+#include <arm_neon.h>
+
+int64x2_t f1(int64_t *ptr) {
+ int64_t x = *ptr;
+ asm volatile ("" ::: "memory");
+ if (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
+ return (int64x2_t) { 0, x };
+ else
+ return (int64x2_t) { x, 0 };
+}
+
+/* { dg-final { scan-assembler {\tldr\td0, \[x0\]\n} } } */