Fix memory constraint on MVE v[ld/st][2/4] instructions [PR107714]

In the M-Class Arm-ARM:

https://developer.arm.com/documentation/ddi0553/bu/?lang=en

these MVE instructions only have '!' writeback variant and at:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107714

we found that the Um constraint would also allow through a
register offset writeback, resulting in an assembler error.

Here I have added a new constraint and predicate for these
instructions, which (uniquely, AFAICT), only support a `!` writeback
increment by the data size (inside the compiler this is a POST_INC).

No regressions in arm-none-eabi with MVE and MVE.FP.

gcc/ChangeLog:
	PR target/107714
	* config/arm/arm-protos.h (mve_struct_mem_operand): New protoype.
	* config/arm/arm.cc (mve_struct_mem_operand): New function.
	* config/arm/constraints.md (Ug): New constraint.
	* config/arm/mve.md (mve_vst4q<mode>): Change constraint.
	(mve_vst2q<mode>): Likewise.
	(mve_vld4q<mode>): Likewise.
	(mve_vld2q<mode>): Likewise.
	* config/arm/predicates.md (mve_struct_operand): New predicate.

gcc/testsuite/ChangeLog:
	PR target/107714
	* gcc.target/arm/mve/intrinsics/vldst24q_reg_offset.c: New test.

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 550272f..8ea3811 100644 (file)
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -122,6 +122,7 @@ extern int arm_coproc_mem_operand_wb (rtx, int);
 extern int neon_vector_mem_operand (rtx, int, bool);
 extern int mve_vector_mem_operand (machine_mode, rtx, bool);
 extern int neon_struct_mem_operand (rtx);
+extern int mve_struct_mem_operand (rtx);
 
 extern rtx *neon_vcmla_lane_prepare_operands (rtx *);
 

diff --git a/gcc/config/arm/arm.cc b/gcc/config/arm/arm.cc
index b587561..31f2a7b 100644 (file)
--- a/gcc/config/arm/arm.cc
+++ b/gcc/config/arm/arm.cc
@@ -13737,6 +13737,24 @@ neon_vector_mem_operand (rtx op, int type, bool strict)
   return FALSE;
 }
 
+/* Return TRUE if OP is a mem suitable for loading/storing an MVE struct
+   type.  */
+int
+mve_struct_mem_operand (rtx op)
+{
+  rtx ind = XEXP (op, 0);
+
+  /* Match: (mem (reg)).  */
+  if (REG_P (ind))
+    return arm_address_register_rtx_p (ind, 0);
+
+  /* Allow only post-increment by the mode size.  */
+  if (GET_CODE (ind) == POST_INC)
+    return arm_address_register_rtx_p (XEXP (ind, 0), 0);
+
+  return FALSE;
+}
+
 /* Return TRUE if OP is a mem suitable for loading/storing a Neon struct
    type.  */
 int

diff --git a/gcc/config/arm/constraints.md b/gcc/config/arm/constraints.md
index e5a36d2..121ec05 100644 (file)
--- a/gcc/config/arm/constraints.md
+++ b/gcc/config/arm/constraints.md
@@ -474,6 +474,11 @@
  (and (match_code "mem")
       (match_test "TARGET_32BIT && arm_coproc_mem_operand (op, FALSE)")))
 
+(define_memory_constraint "Ug"
+ "@internal
+  In Thumb-2 state a valid MVE struct load/store address."
+ (match_operand 0 "mve_struct_operand"))
+
 (define_memory_constraint "Uj"
  "@internal
   In ARM/Thumb-2 state a VFP load/store address that supports writeback

diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 3fe9db8..0c21db1 100644 (file)
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -99,7 +99,7 @@
 ;; [vst4q])
 ;;
 (define_insn "mve_vst4q<mode>"
-  [(set (match_operand:XI 0 "neon_struct_operand" "=Um")
+  [(set (match_operand:XI 0 "mve_struct_operand" "=Ug")
        (unspec:XI [(match_operand:XI 1 "s_register_operand" "w")
                    (unspec:MVE_VLD_ST [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
         VST4Q))
@@ -9961,7 +9961,7 @@
 ;; [vst2q])
 ;;
 (define_insn "mve_vst2q<mode>"
-  [(set (match_operand:OI 0 "neon_struct_operand" "=Um")
+  [(set (match_operand:OI 0 "mve_struct_operand" "=Ug")
        (unspec:OI [(match_operand:OI 1 "s_register_operand" "w")
                    (unspec:MVE_VLD_ST [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
         VST2Q))
@@ -9990,7 +9990,7 @@
 ;;
 (define_insn "mve_vld2q<mode>"
   [(set (match_operand:OI 0 "s_register_operand" "=w")
-       (unspec:OI [(match_operand:OI 1 "neon_struct_operand" "Um")
+       (unspec:OI [(match_operand:OI 1 "mve_struct_operand" "Ug")
                    (unspec:MVE_VLD_ST [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
         VLD2Q))
   ]
@@ -10018,7 +10018,7 @@
 ;;
 (define_insn "mve_vld4q<mode>"
   [(set (match_operand:XI 0 "s_register_operand" "=w")
-       (unspec:XI [(match_operand:XI 1 "neon_struct_operand" "Um")
+       (unspec:XI [(match_operand:XI 1 "mve_struct_operand" "Ug")
                    (unspec:MVE_VLD_ST [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
         VLD4Q))
   ]

diff --git a/gcc/config/arm/predicates.md b/gcc/config/arm/predicates.md
index aab5a91..67f2fdb 100644 (file)
--- a/gcc/config/arm/predicates.md
+++ b/gcc/config/arm/predicates.md
@@ -876,6 +876,10 @@
   (and (match_code "mem")
        (match_test "TARGET_32BIT && neon_vector_mem_operand (op, 2, true)")))
 
+(define_predicate "mve_struct_operand"
+  (and (match_code "mem")
+       (match_test "TARGET_HAVE_MVE && mve_struct_mem_operand (op)")))
+
 (define_predicate "neon_permissive_struct_operand"
   (and (match_code "mem")
        (match_test "TARGET_32BIT && neon_vector_mem_operand (op, 2, false)")))

diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldst24q_reg_offset.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldst24q_reg_offset.c
new file mode 100644 (file)
index 0000000..d028b91
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldst24q_reg_offset.c
@@ -0,0 +1,300 @@
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-add-options arm_v8_1m_mve } */
+/* { dg-additional-options "-O1" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "arm_mve.h"
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/*
+**test:
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test(const uint8_t * in, uint8_t * out, int width)
+{
+  uint8x16x2_t rg = vld2q(in);
+  uint8x16x2_t gb = vld2q(in + width);
+  vst2q (out, rg);
+  vst2q (out + width, gb);
+}
+
+/*
+**test2:
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]!
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]!
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test2(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x2_t rg = vld2q(in);
+  uint8x16x2_t gb = vld2q(in + 32);
+  vst2q (out, rg);
+  vst2q (out + 32, gb);
+}
+
+/*
+**test3:
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test3(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x2_t rg = vld2q(in);
+  uint8x16x2_t gb = vld2q(in - 32);
+  vst2q (out, rg);
+  vst2q (out - 32, gb);
+}
+
+/*
+**test4:
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test4(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x2_t rg = vld2q(in);
+  uint8x16x2_t gb = vld2q(in + 64);
+  vst2q (out, rg);
+  vst2q (out + 64, gb);
+}
+
+/*
+**test5:
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst20.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst21.8 {q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test5(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x2_t rg = vld2q(in);
+  uint8x16x2_t gb = vld2q(in + 42);
+  vst2q (out, rg);
+  vst2q (out + 42, gb);
+}
+
+/*
+**test6:
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test6(const uint8_t * in, uint8_t * out, int width)
+{
+  uint8x16x4_t rg = vld4q(in);
+  uint8x16x4_t gb = vld4q(in + width);
+  vst4q (out, rg);
+  vst4q (out + width, gb);
+}
+
+/*
+**test7:
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test7(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x4_t rg = vld4q(in);
+  uint8x16x4_t gb = vld4q(in + 32);
+  vst4q (out, rg);
+  vst4q (out + 32, gb);
+}
+
+/*
+**test8:
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]!
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]!
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test8(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x4_t rg = vld4q(in);
+  uint8x16x4_t gb = vld4q(in + 64);
+  vst4q (out, rg);
+  vst4q (out + 64, gb);
+}
+
+/*
+**test9:
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test9(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x4_t rg = vld4q(in);
+  uint8x16x4_t gb = vld4q(in - 64);
+  vst4q (out, rg);
+  vst4q (out - 64, gb);
+}
+
+/*
+**test10:
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vld40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vld43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+**     vst40.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst41.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst42.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     vst43.8 {q[0-9]+, q[0-9]+, q[0-9]+, q[0-9]+}, \[(?:ip|fp|r[0-9]+)\]
+**     ...
+*/
+void
+test10(const uint8_t * in, uint8_t * out)
+{
+  uint8x16x4_t rg = vld4q(in);
+  uint8x16x4_t gb = vld4q(in + 42);
+  vst4q (out, rg);
+  vst4q (out + 42, gb);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+/* { dg-final { scan-assembler-not "__ARM_undef" } } */
\ No newline at end of file