;; On big-endian this is { zeroes, operand }
(define_insn "move_lo_quad_internal_<mode>"
- [(set (match_operand:VQ 0 "register_operand" "=w,w,w")
- (vec_concat:VQ
+ [(set (match_operand:VQ_NO2E 0 "register_operand" "=w,w,w")
+ (vec_concat:VQ_NO2E
(match_operand:<VHALF> 1 "register_operand" "w,r,r")
(vec_duplicate:<VHALF> (const_int 0))))]
"TARGET_SIMD && !BYTES_BIG_ENDIAN"
(set_attr "length" "4")]
)
+(define_insn "move_lo_quad_internal_<mode>"
+ [(set (match_operand:VQ_2E 0 "register_operand" "=w,w,w")
+ (vec_concat:VQ_2E
+ (match_operand:<VHALF> 1 "register_operand" "w,r,r")
+ (const_int 0)))]
+ "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 "simd" "yes,*,yes")
+ (set_attr "fp" "*,yes,*")
+ (set_attr "length" "4")]
+)
+
(define_insn "move_lo_quad_internal_be_<mode>"
- [(set (match_operand:VQ 0 "register_operand" "=w,w,w")
- (vec_concat:VQ
+ [(set (match_operand:VQ_NO2E 0 "register_operand" "=w,w,w")
+ (vec_concat:VQ_NO2E
(vec_duplicate:<VHALF> (const_int 0))
(match_operand:<VHALF> 1 "register_operand" "w,r,r")))]
"TARGET_SIMD && BYTES_BIG_ENDIAN"
(set_attr "length" "4")]
)
+(define_insn "move_lo_quad_internal_be_<mode>"
+ [(set (match_operand:VQ_2E 0 "register_operand" "=w,w,w")
+ (vec_concat:VQ_2E
+ (const_int 0)
+ (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 "simd" "yes,*,yes")
+ (set_attr "fp" "*,yes,*")
+ (set_attr "length" "4")]
+)
+
(define_expand "move_lo_quad_<mode>"
[(match_operand:VQ 0 "register_operand")
(match_operand:VQ 1 "register_operand")]
--- /dev/null
+/* { dg-do compile } */
+/* { dg-options "-g -Os" } */
+
+#include "arm_neon.h"
+
+extern void bar (int32x4_t);
+
+void
+foo ()
+{
+ int32x4x4_t rows;
+ uint64x2x2_t row01;
+
+ row01.val[0] = vreinterpretq_u64_s32 (rows.val[0]);
+ row01.val[1] = vreinterpretq_u64_s32 (rows.val[1]);
+ uint64x1_t row3l = vget_low_u64 (row01.val[0]);
+ row01.val[0] = vcombine_u64 (vget_low_u64 (row01.val[1]), row3l);
+ int32x4_t xxx = vreinterpretq_s32_u64 (row01.val[0]);
+ int32x4_t out = vtrn1q_s32 (xxx, xxx);
+ bar (out);
+}