[v2,2/2] arm: Add support for MVE Tail-Predicated Low Overhead Loops

Message ID 20240105175224.3012-3-andre.simoesdiasvieira@arm.com
State Unresolved
Headers
Series arm: Add support for MVE Tail-Predicated Low Overhead Loops |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

Andre Vieira (lists) Jan. 5, 2024, 5:52 p.m. UTC
  Respin after comments on first version.
  

Comments

Kyrylo Tkachov Jan. 17, 2024, 5:20 p.m. UTC | #1
Hi Andre,

> -----Original Message-----
> From: Andre Vieira <andre.simoesdiasvieira@arm.com>
> Sent: Friday, January 5, 2024 5:52 PM
> To: gcc-patches@gcc.gnu.org
> Cc: Richard Earnshaw <Richard.Earnshaw@arm.com>; Stam Markianos-Wright
> <Stam.Markianos-Wright@arm.com>
> Subject: [PATCH v2 2/2] arm: Add support for MVE Tail-Predicated Low Overhead
> Loops
> 
> Respin after comments on first version.

I think I'm nitpicking some code style and implementation points rather than diving deep into the algorithms, I think those were okay last time I looked at this some time ago.

+/* Return true if INSN is a MVE instruction that is VPT-predicable, but in
+   its unpredicated form, or if it is predicated, but on a predicate other
+   than VPR_REG.  */
+
+static bool
+arm_mve_vec_insn_is_unpredicated_or_uses_other_predicate (rtx_insn *insn,
+							  rtx vpr_reg)
+{
+  rtx insn_vpr_reg_operand;
+  if (MVE_VPT_UNPREDICATED_INSN_P (insn)
+      || (MVE_VPT_PREDICATED_INSN_P (insn)
+	  && (insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+	  && !rtx_equal_p (vpr_reg, insn_vpr_reg_operand)))
+    return true;
+  else
+    return false;
+}
+
+/* Return true if INSN is a MVE instruction that is VPT-predicable and is
+   predicated on VPR_REG.  */
+
+static bool
+arm_mve_vec_insn_is_predicated_with_this_predicate (rtx_insn *insn,
+						    rtx vpr_reg)
+{
+  rtx insn_vpr_reg_operand;
+  if (MVE_VPT_PREDICATED_INSN_P (insn)
+      && (insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+      && rtx_equal_p (vpr_reg, insn_vpr_reg_operand))
+    return true;
+  else
+    return false;
+}

These two functions seem to have an "if (condition) return true; else return false;" structure that we try to avoid. How about:
rtx_insn vpr_reg_operand = MVE_VPT_PREDICATED_INSN_P (insn)  ? arm_get_required_vpr_reg_param (insn) : NULL_RTX;
return vpr_reg_operand && rtx_equal_p (vpr_reg, insn_vpr_reg_operand);


+static bool
+arm_is_mve_across_vector_insn (rtx_insn* insn)
+{
+  df_ref insn_defs = NULL;
+  if (!MVE_VPT_PREDICABLE_INSN_P (insn))
+    return false;
+
+  bool is_across_vector = false;
+  FOR_EACH_INSN_DEF (insn_defs, insn)
+    if (!VALID_MVE_MODE (GET_MODE (DF_REF_REG (insn_defs)))
+	&& !arm_get_required_vpr_reg_ret_val (insn))
+      is_across_vector = true;
+

You can just return true here immediately, no need to set is_across_vector....

+  return is_across_vector;

... and you can return false here, avoiding the need for is_across_vector entirely
+}

+static bool
+arm_mve_check_reg_origin_is_num_elems (basic_block body, rtx reg, rtx vctp_step)
+{
+  /* Ok, we now know the loop starts from zero and increments by one.
+     Now just show that the max value of the counter came from an
+     appropriate ASHIFRT expr of the correct amount.  */
+  basic_block pre_loop_bb = body->prev_bb;
+  while (pre_loop_bb && BB_END (pre_loop_bb)
+	 && !df_bb_regno_only_def_find (pre_loop_bb, REGNO (reg)))
+    pre_loop_bb = pre_loop_bb->prev_bb;
+
+  df_ref counter_max_last_def = df_bb_regno_only_def_find (pre_loop_bb, REGNO (reg));
+  if (!counter_max_last_def)
+    return false;
+  rtx counter_max_last_set = single_set (DF_REF_INSN (counter_max_last_def));
+  if (!counter_max_last_set)
+    return false;
+
+  /* If we encounter a simple SET from a REG, follow it through.  */
+  if (REG_P (SET_SRC (counter_max_last_set)))
+    return arm_mve_check_reg_origin_is_num_elems
+	     (pre_loop_bb->next_bb, SET_SRC (counter_max_last_set), vctp_step);
+
+  /* If we encounter a SET from an IF_THEN_ELSE where one of the operands is a
+     constant and the other is a REG, follow through to that REG.  */
+  if (GET_CODE (SET_SRC (counter_max_last_set)) == IF_THEN_ELSE
+      && REG_P (XEXP (SET_SRC (counter_max_last_set), 1))
+      && CONST_INT_P (XEXP (SET_SRC (counter_max_last_set), 2)))
+    return arm_mve_check_reg_origin_is_num_elems
+	     (pre_loop_bb->next_bb, XEXP (SET_SRC (counter_max_last_set), 1), vctp_step);
+
+  if (GET_CODE (SET_SRC (counter_max_last_set)) == ASHIFTRT
+      && CONST_INT_P (XEXP (SET_SRC (counter_max_last_set), 1))
+      && ((1 << INTVAL (XEXP (SET_SRC (counter_max_last_set), 1)))
+	   == abs (INTVAL (vctp_step))))

I'm a bit concerned here with using abs() for HOST_WIDE_INT values that are compared to other HOST_WIDE_INT values.
abs () will implicitly cast the argument and return an int. We should use the abs_hwi function defined in hwint.h. It may not cause problems in practice given the ranges involved, but better safe than sorry at this stage.

Looks decent to me otherwise, and an impressive piece of work, thanks.
I'd give Richard an opportunity to comment next week when he's back before committing though.
Thanks,
Kyrill
  

Patch

diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index 2f5ca79ed8d..4f164c54740 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -65,8 +65,8 @@  extern void arm_emit_speculation_barrier_function (void);
 extern void arm_decompose_di_binop (rtx, rtx, rtx *, rtx *, rtx *, rtx *);
 extern bool arm_q_bit_access (void);
 extern bool arm_ge_bits_access (void);
-extern bool arm_target_insn_ok_for_lob (rtx);
-
+extern bool arm_target_bb_ok_for_lob (basic_block);
+extern rtx arm_attempt_dlstp_transform (rtx);
 #ifdef RTX_CODE
 enum reg_class
 arm_mode_base_reg_class (machine_mode);
diff --git a/gcc/config/arm/arm.cc b/gcc/config/arm/arm.cc
index 0c0cb14a8a4..1ee72bcb7ec 100644
--- a/gcc/config/arm/arm.cc
+++ b/gcc/config/arm/arm.cc
@@ -668,6 +668,12 @@  static const scoped_attribute_specs *const arm_attribute_table[] =
 #undef TARGET_HAVE_CONDITIONAL_EXECUTION
 #define TARGET_HAVE_CONDITIONAL_EXECUTION arm_have_conditional_execution
 
+#undef TARGET_LOOP_UNROLL_ADJUST
+#define TARGET_LOOP_UNROLL_ADJUST arm_loop_unroll_adjust
+
+#undef TARGET_PREDICT_DOLOOP_P
+#define TARGET_PREDICT_DOLOOP_P arm_predict_doloop_p
+
 #undef TARGET_LEGITIMATE_CONSTANT_P
 #define TARGET_LEGITIMATE_CONSTANT_P arm_legitimate_constant_p
 
@@ -34483,19 +34489,1147 @@  arm_invalid_within_doloop (const rtx_insn *insn)
 }
 
 bool
-arm_target_insn_ok_for_lob (rtx insn)
+arm_target_bb_ok_for_lob (basic_block bb)
 {
-  basic_block bb = BLOCK_FOR_INSN (insn);
   /* Make sure the basic block of the target insn is a simple latch
      having as single predecessor and successor the body of the loop
      itself.  Only simple loops with a single basic block as body are
      supported for 'low over head loop' making sure that LE target is
      above LE itself in the generated code.  */
-
   return single_succ_p (bb)
-    && single_pred_p (bb)
-    && single_succ_edge (bb)->dest == single_pred_edge (bb)->src
-    && contains_no_active_insn_p (bb);
+	 && single_pred_p (bb)
+	 && single_succ_edge (bb)->dest == single_pred_edge (bb)->src;
+}
+
+/* Utility fuction: Given a VCTP or a VCTP_M insn, return the number of MVE
+   lanes based on the machine mode being used.  */
+
+static int
+arm_mve_get_vctp_lanes (rtx_insn *insn)
+{
+  rtx insn_set = single_set (insn);
+  if (insn_set
+      && GET_CODE (SET_SRC (insn_set)) == UNSPEC
+      && (XINT (SET_SRC (insn_set), 1) == VCTP
+	  || XINT (SET_SRC (insn_set), 1) == VCTP_M))
+    {
+      machine_mode mode = GET_MODE (SET_SRC (insn_set));
+      return (VECTOR_MODE_P (mode) && VALID_MVE_PRED_MODE (mode))
+	     ? GET_MODE_NUNITS (mode) : 0;
+    }
+  return 0;
+}
+
+/* Check if INSN requires the use of the VPR reg, if it does, return the
+   sub-rtx of the VPR reg.  The TYPE argument controls whether
+   this function should:
+   * For TYPE == 0, check all operands, including the OUT operands,
+     and return the first occurrence of the VPR reg.
+   * For TYPE == 1, only check the input operands.
+   * For TYPE == 2, only check the output operands.
+   (INOUT operands are considered both as input and output operands)
+*/
+static rtx
+arm_get_required_vpr_reg (rtx_insn *insn, unsigned int type = 0)
+{
+  gcc_assert (type < 3);
+  if (!NONJUMP_INSN_P (insn))
+    return NULL_RTX;
+
+  bool requires_vpr;
+  extract_constrain_insn (insn);
+  int n_operands = recog_data.n_operands;
+  if (recog_data.n_alternatives == 0)
+    return NULL_RTX;
+
+  /* Fill in recog_op_alt with information about the constraints of
+     this insn.  */
+  preprocess_constraints (insn);
+
+  for (int op = 0; op < n_operands; op++)
+    {
+      requires_vpr = true;
+      if (type == 1 && recog_data.operand_type[op] == OP_OUT)
+	continue;
+      else if (type == 2 && recog_data.operand_type[op] == OP_IN)
+	continue;
+
+      /* Iterate through alternatives of operand "op" in recog_op_alt and
+	 identify if the operand is required to be the VPR.  */
+      for (int alt = 0; alt < recog_data.n_alternatives; alt++)
+	{
+	  const operand_alternative *op_alt
+	      = &recog_op_alt[alt * n_operands];
+	  /* Fetch the reg_class for each entry and check it against the
+	     VPR_REG reg_class.  */
+	  if (alternative_class (op_alt, op) != VPR_REG)
+	    requires_vpr = false;
+	}
+      /* If all alternatives of the insn require the VPR reg for this operand,
+	 it means that either this is VPR-generating instruction, like a vctp,
+	 vcmp, etc., or it is a VPT-predicated insruction.  Return the subrtx
+	 of the VPR reg operand.  */
+      if (requires_vpr)
+	return recog_data.operand[op];
+    }
+  return NULL_RTX;
+}
+
+/* Wrapper function of arm_get_required_vpr_reg with TYPE == 1, so return
+   something only if the VPR reg is an input operand to the insn.  */
+
+static rtx
+arm_get_required_vpr_reg_param (rtx_insn *insn)
+{
+  return arm_get_required_vpr_reg (insn, 1);
+}
+
+/* Wrapper function of arm_get_required_vpr_reg with TYPE == 2, so return
+   something only if the VPR reg is the return value, an output of, or is
+   clobbered by the insn.  */
+
+static rtx
+arm_get_required_vpr_reg_ret_val (rtx_insn *insn)
+{
+  return arm_get_required_vpr_reg (insn, 2);
+}
+
+/* Scan the basic block of a loop body for a vctp instruction.  If there is
+   at least vctp instruction, return the first rtx_insn *.  */
+
+static rtx_insn *
+arm_mve_get_loop_vctp (basic_block bb)
+{
+  rtx_insn *insn = BB_HEAD (bb);
+
+  /* Now scan through all the instruction patterns and pick out the VCTP
+     instruction.  We require arm_get_required_vpr_reg_param to be false
+     to make sure we pick up a VCTP, rather than a VCTP_M.  */
+  FOR_BB_INSNS (bb, insn)
+    if (NONDEBUG_INSN_P (insn))
+      if (arm_get_required_vpr_reg_ret_val (insn)
+	  && (arm_mve_get_vctp_lanes (insn) != 0)
+	  && !arm_get_required_vpr_reg_param (insn))
+	return insn;
+  return NULL;
+}
+
+/* Return true if INSN is a MVE instruction that is VPT-predicable, but in
+   its unpredicated form, or if it is predicated, but on a predicate other
+   than VPR_REG.  */
+
+static bool
+arm_mve_vec_insn_is_unpredicated_or_uses_other_predicate (rtx_insn *insn,
+							  rtx vpr_reg)
+{
+  rtx insn_vpr_reg_operand;
+  if (MVE_VPT_UNPREDICATED_INSN_P (insn)
+      || (MVE_VPT_PREDICATED_INSN_P (insn)
+	  && (insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+	  && !rtx_equal_p (vpr_reg, insn_vpr_reg_operand)))
+    return true;
+  else
+    return false;
+}
+
+/* Return true if INSN is a MVE instruction that is VPT-predicable and is
+   predicated on VPR_REG.  */
+
+static bool
+arm_mve_vec_insn_is_predicated_with_this_predicate (rtx_insn *insn,
+						    rtx vpr_reg)
+{
+  rtx insn_vpr_reg_operand;
+  if (MVE_VPT_PREDICATED_INSN_P (insn)
+      && (insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+      && rtx_equal_p (vpr_reg, insn_vpr_reg_operand))
+    return true;
+  else
+    return false;
+}
+
+/* Utility function to identify if INSN is an MVE instruction that performs
+   some across-vector operation (and as a result does not align with normal
+   lane predication rules).  All such instructions give one only scalar
+   output, except for vshlcq which gives a PARALLEL of a vector and a scalar
+   (one vector result and one carry output).  */
+
+static bool
+arm_is_mve_across_vector_insn (rtx_insn* insn)
+{
+  df_ref insn_defs = NULL;
+  if (!MVE_VPT_PREDICABLE_INSN_P (insn))
+    return false;
+
+  bool is_across_vector = false;
+  FOR_EACH_INSN_DEF (insn_defs, insn)
+    if (!VALID_MVE_MODE (GET_MODE (DF_REF_REG (insn_defs)))
+	&& !arm_get_required_vpr_reg_ret_val (insn))
+      is_across_vector = true;
+
+  return is_across_vector;
+}
+
+/* Utility function to identify if INSN is an MVE load or store instruction.
+   * For TYPE == 0, check all operands.  If the function returns true,
+     INSN is a load or a store insn.
+   * For TYPE == 1, only check the input operands.  If the function returns
+     true, INSN is a load insn.
+   * For TYPE == 2, only check the output operands.  If the function returns
+     true, INSN is a store insn.  */
+
+static bool
+arm_is_mve_load_store_insn (rtx_insn* insn, int type = 0)
+{
+  int n_operands = recog_data.n_operands;
+  extract_insn (insn);
+
+  for (int op = 0; op < n_operands; op++)
+    {
+      if (type == 1 && recog_data.operand_type[op] == OP_OUT)
+	continue;
+      else if (type == 2 && recog_data.operand_type[op] == OP_IN)
+	continue;
+      if (mve_memory_operand (recog_data.operand[op],
+			      GET_MODE (recog_data.operand[op])))
+      return true;
+    }
+  return false;
+}
+
+/* When transforming an MVE intrinsic loop into an MVE Tail Predicated Low
+   Overhead Loop, there are a number of instructions that, if in their
+   unpredicated form, act across vector lanes, but are still safe to include
+   within the loop, despite the implicit predication added to the vector lanes.
+   This list has been compiled by carefully analyzing the instruction
+   pseudocode in the Arm-ARM.
+   All other across-vector instructions aren't allowed, because the addition
+   of implicit predication could influnce the result of the operation.
+   Any new across-vector instructions to the MVE ISA will have to assessed for
+   inclusion to this list.  */
+
+static bool
+arm_mve_is_allowed_unpredic_across_vector_insn (rtx_insn* insn)
+{
+  gcc_assert (MVE_VPT_UNPREDICATED_INSN_P (insn)
+	      && arm_is_mve_across_vector_insn (insn));
+  rtx insn_set = single_set (insn);
+  if (!insn_set)
+    return false;
+  rtx unspec = SET_SRC (insn_set);
+  if (GET_CODE (unspec) != UNSPEC)
+    return false;
+  switch (XINT (unspec, 1))
+    {
+    case VADDVQ_U:
+    case VADDVQ_S:
+    case VADDVAQ_U:
+    case VADDVAQ_S:
+    case VMLADAVQ_U:
+    case VMLADAVQ_S:
+    case VMLADAVXQ_S:
+    case VMLADAVAQ_U:
+    case VMLADAVAQ_S:
+    case VMLADAVAXQ_S:
+    case VABAVQ_S:
+    case VABAVQ_U:
+    case VADDLVQ_S:
+    case VADDLVQ_U:
+    case VADDLVAQ_S:
+    case VADDLVAQ_U:
+    case VMAXVQ_U:
+    case VMAXAVQ_S:
+    case VMLALDAVQ_U:
+    case VMLALDAVXQ_U:
+    case VMLALDAVXQ_S:
+    case VMLALDAVQ_S:
+    case VMLALDAVAQ_S:
+    case VMLALDAVAQ_U:
+    case VMLALDAVAXQ_S:
+    case VMLALDAVAXQ_U:
+    case VMLSDAVQ_S:
+    case VMLSDAVXQ_S:
+    case VMLSDAVAXQ_S:
+    case VMLSDAVAQ_S:
+    case VMLSLDAVQ_S:
+    case VMLSLDAVXQ_S:
+    case VMLSLDAVAQ_S:
+    case VMLSLDAVAXQ_S:
+    case VRMLALDAVHXQ_S:
+    case VRMLALDAVHQ_U:
+    case VRMLALDAVHQ_S:
+    case VRMLALDAVHAQ_S:
+    case VRMLALDAVHAQ_U:
+    case VRMLALDAVHAXQ_S:
+    case VRMLSLDAVHQ_S:
+    case VRMLSLDAVHXQ_S:
+    case VRMLSLDAVHAQ_S:
+    case VRMLSLDAVHAXQ_S:
+      return true;
+    default:
+      break;
+    }
+  return false;
+}
+
+/* Scan through the DF chain backwards within the basic block and
+   determine if any of the USEs of the original insn (or the USEs of the insns
+   where thy were DEF-ed, etc.) were affected by implicit VPT
+   predication of an MVE_VPT_UNPREDICATED_INSN_P in a dlstp/letp loop.
+   This function returns true if the insn is affected implicit predication
+   and false otherwise.
+   Having such implicit predication on an unpredicated insn wouldn't in itself
+   block tail predication, because the output of that insn might then be used
+   in a correctly predicated store insn, where the disabled lanes will be
+   ignored.  To verify this we later call:
+   `arm_mve_check_df_chain_fwd_for_implic_predic_impact`, which will check the
+   DF chains forward to see if any implicitly-predicated operand gets used in
+   an improper way.  */
+
+static bool
+arm_mve_check_df_chain_back_for_implic_predic
+  (hash_map <rtx_insn *, bool> *safe_insn_map, rtx_insn *insn_in,
+   rtx vctp_vpr_generated)
+{
+
+  auto_vec<rtx_insn *> worklist;
+  worklist.safe_push (insn_in);
+
+  bool *temp = NULL;
+
+  while (worklist.length () > 0)
+    {
+      rtx_insn *insn = worklist.pop ();
+
+      if ((temp = safe_insn_map->get (insn)))
+	return *temp;
+
+      basic_block body = BLOCK_FOR_INSN (insn);
+
+      /* The circumstances under which an instruction is affected by "implicit
+	 predication" are as follows:
+	  * It is an UNPREDICATED_INSN_P:
+	    * That loads/stores from/to memory.
+	    * Where any one of its operands is an MVE vector from outside the
+	      loop body bb.
+	 Or:
+	  * Any of it's operands were affected earlier in the insn chain.  */
+      if (MVE_VPT_UNPREDICATED_INSN_P (insn)
+	  && (arm_is_mve_load_store_insn (insn)
+	      || (arm_is_mve_across_vector_insn (insn)
+		  && !arm_mve_is_allowed_unpredic_across_vector_insn (insn))))
+	{
+	  safe_insn_map->put (insn, true);
+	  return true;
+	}
+
+      df_ref insn_uses = NULL;
+      FOR_EACH_INSN_USE (insn_uses, insn)
+      {
+	/* If the operand is in the input reg set to the the basic block,
+	   (i.e. it has come from outside the loop!), consider it unsafe if:
+	     * It's being used in an unpredicated insn.
+	     * It is a predicable MVE vector.  */
+	if (MVE_VPT_UNPREDICATED_INSN_P (insn)
+	    && VALID_MVE_MODE (GET_MODE (DF_REF_REG (insn_uses)))
+	    && REGNO_REG_SET_P (DF_LR_IN (body), DF_REF_REGNO (insn_uses)))
+	  {
+	    safe_insn_map->put (insn, true);
+	    return true;
+	  }
+
+	/* Scan backwards from the current INSN through the instruction chain
+	   until the start of the basic block.  */
+	for (rtx_insn *prev_insn = PREV_INSN (insn);
+	     prev_insn && prev_insn != PREV_INSN (BB_HEAD (body));
+	     prev_insn = PREV_INSN (prev_insn))
+	  {
+	    /* If a previous insn defines a register that INSN uses, then
+	       add to the worklist to check that insn's USEs.  If any of these
+	       insns return true as MVE_VPT_UNPREDICATED_INSN_Ps, then the
+	       whole chain is affected by the change in behaviour from being
+	       placed in dlstp/letp loop.  */
+	    df_ref prev_insn_defs = NULL;
+	    FOR_EACH_INSN_DEF (prev_insn_defs, prev_insn)
+	    {
+	      if (DF_REF_REGNO (insn_uses) == DF_REF_REGNO (prev_insn_defs)
+		  && !arm_mve_vec_insn_is_predicated_with_this_predicate
+		       (insn, vctp_vpr_generated))
+		worklist.safe_push (prev_insn);
+	    }
+	  }
+      }
+    }
+  safe_insn_map->put (insn_in, false);
+  return false;
+}
+
+/* If we have identified that the current DEF will be modified
+   by such implicit predication, scan through all the
+   insns that USE it and bail out if any one is outside the
+   current basic block (i.e. the reg is live after the loop)
+   or if any are store insns that are unpredicated or using a
+   predicate other than the loop VPR.
+   This function returns true if the insn is not suitable for
+   implicit predication and false otherwise.*/
+
+static bool
+arm_mve_check_df_chain_fwd_for_implic_predic_impact (rtx_insn *insn,
+						     rtx vctp_vpr_generated)
+{
+
+  /* If this insn is indeed an unpredicated store to memory, bail out.  */
+  if (arm_mve_vec_insn_is_unpredicated_or_uses_other_predicate
+	(insn, vctp_vpr_generated)
+      && (arm_is_mve_load_store_insn (insn, 2)
+	  || arm_is_mve_across_vector_insn (insn)))
+    return true;
+
+  /* Next, scan forward to the various USEs of the DEFs in this insn.  */
+  df_ref insn_def = NULL;
+  FOR_EACH_INSN_DEF (insn_def, insn)
+    {
+      for (df_ref use = DF_REG_USE_CHAIN (DF_REF_REGNO (insn_def)); use;
+	   use = DF_REF_NEXT_REG (use))
+	{
+	  rtx_insn *next_use_insn = DF_REF_INSN (use);
+	  if (next_use_insn != insn
+	      && NONDEBUG_INSN_P (next_use_insn))
+	    {
+	      /* If the USE is outside the loop body bb, or it is inside, but
+		 is an differently-predicated store to memory or it is any
+		 across-vector instruction.  */
+	      if (BLOCK_FOR_INSN (insn) != BLOCK_FOR_INSN (next_use_insn)
+		  || (arm_mve_vec_insn_is_unpredicated_or_uses_other_predicate
+		       (next_use_insn, vctp_vpr_generated)
+		     && (arm_is_mve_load_store_insn (next_use_insn, 2)
+			 || arm_is_mve_across_vector_insn (next_use_insn))))
+		return true;
+	    }
+	}
+    }
+  return false;
+}
+
+/* Helper function to `arm_mve_dlstp_check_inc_counter` and to
+   `arm_mve_dlstp_check_dec_counter`.  In the situations where the loop counter
+   is incrementing by 1 or decrementing by 1 in each iteration, ensure that the
+   target value or the initialisation value, respectively, was a calculation
+   of the number of iterations of the loop, which is expected to be an ASHIFTRT
+   by VCTP_STEP.  */
+
+static bool
+arm_mve_check_reg_origin_is_num_elems (basic_block body, rtx reg, rtx vctp_step)
+{
+  /* Ok, we now know the loop starts from zero and increments by one.
+     Now just show that the max value of the counter came from an
+     appropriate ASHIFRT expr of the correct amount.  */
+  basic_block pre_loop_bb = body->prev_bb;
+  while (pre_loop_bb && BB_END (pre_loop_bb)
+	 && !df_bb_regno_only_def_find (pre_loop_bb, REGNO (reg)))
+    pre_loop_bb = pre_loop_bb->prev_bb;
+
+  df_ref counter_max_last_def = df_bb_regno_only_def_find (pre_loop_bb, REGNO (reg));
+  if (!counter_max_last_def)
+    return false;
+  rtx counter_max_last_set = single_set (DF_REF_INSN (counter_max_last_def));
+  if (!counter_max_last_set)
+    return false;
+
+  /* If we encounter a simple SET from a REG, follow it through.  */
+  if (REG_P (SET_SRC (counter_max_last_set)))
+    return arm_mve_check_reg_origin_is_num_elems
+	     (pre_loop_bb->next_bb, SET_SRC (counter_max_last_set), vctp_step);
+
+  /* If we encounter a SET from an IF_THEN_ELSE where one of the operands is a
+     constant and the other is a REG, follow through to that REG.  */
+  if (GET_CODE (SET_SRC (counter_max_last_set)) == IF_THEN_ELSE
+      && REG_P (XEXP (SET_SRC (counter_max_last_set), 1))
+      && CONST_INT_P (XEXP (SET_SRC (counter_max_last_set), 2)))
+    return arm_mve_check_reg_origin_is_num_elems
+	     (pre_loop_bb->next_bb, XEXP (SET_SRC (counter_max_last_set), 1), vctp_step);
+
+  if (GET_CODE (SET_SRC (counter_max_last_set)) == ASHIFTRT
+      && CONST_INT_P (XEXP (SET_SRC (counter_max_last_set), 1))
+      && ((1 << INTVAL (XEXP (SET_SRC (counter_max_last_set), 1)))
+	   == abs (INTVAL (vctp_step))))
+    return true;
+
+  return false;
+}
+
+/* If we have identified the loop to have an incrementing counter, we need to
+   make sure that it increments by 1 and that the loop is structured correctly:
+    * The counter starts from 0
+    * The counter terminates at (num_of_elem + num_of_lanes - 1) / num_of_lanes
+    * The vctp insn uses a reg that decrements appropriately in each iteration.
+*/
+
+static rtx_insn*
+arm_mve_dlstp_check_inc_counter (basic_block body, rtx_insn* vctp_insn,
+				 rtx condconst, rtx condcount)
+{
+  rtx vctp_reg = XVECEXP (XEXP (PATTERN (vctp_insn), 1), 0, 0);
+  /* The loop latch has to be empty.  When compiling all the known MVE LoLs in
+     user applications, none of those with incrementing counters had any real
+     insns in the loop latch.  As such, this function has only been tested with
+     an empty latch and may misbehave or ICE if we somehow get here with an
+     increment in the latch, so, for correctness, error out early.  */
+  if (!empty_block_p (body->loop_father->latch))
+    return NULL;
+
+  class rtx_iv vctp_reg_iv;
+  /* For loops of type B) the loop counter is independent of the decrement
+     of the reg used in the vctp_insn. So run iv analysis on that reg.  This
+     has to succeed for such loops to be supported.  */
+  if (!iv_analyze (vctp_insn, as_a<scalar_int_mode> (GET_MODE (vctp_reg)),
+      vctp_reg, &vctp_reg_iv))
+    return NULL;
+
+  /* Extract the decrementnum of the vctp reg from the iv.  This decrementnum
+     is the number of lanes/elements it decrements from the remaining number of
+     lanes/elements to process in the loop, for this reason this is always a
+     negative number, but to simplify later checks we use it's absolute value.  */
+  int decrementnum = INTVAL (vctp_reg_iv.step);
+  if (decrementnum >= 0)
+    return NULL;
+  decrementnum = abs (decrementnum);
+
+  /* Find where both of those are modified in the loop body bb.  */
+  df_ref condcount_reg_set_df = df_bb_regno_only_def_find (body, REGNO (condcount));
+  df_ref vctp_reg_set_df = df_bb_regno_only_def_find (body, REGNO (vctp_reg));
+  if (!condcount_reg_set_df || !vctp_reg_set_df)
+    return NULL;
+  rtx condcount_reg_set = single_set (DF_REF_INSN (condcount_reg_set_df));
+  rtx vctp_reg_set = single_set (DF_REF_INSN (vctp_reg_set_df));
+  if (!condcount_reg_set || !vctp_reg_set)
+    return NULL;
+
+  /* Ensure the modification of the vctp reg from df is consistent with
+     the iv and the number of lanes on the vctp insn.  */
+  if (GET_CODE (SET_SRC (vctp_reg_set)) != PLUS
+      || !REG_P (SET_DEST (vctp_reg_set))
+      || !REG_P (XEXP (SET_SRC (vctp_reg_set), 0))
+      || REGNO (SET_DEST (vctp_reg_set))
+	  != REGNO (XEXP (SET_SRC (vctp_reg_set), 0))
+      || !CONST_INT_P (XEXP (SET_SRC (vctp_reg_set), 1))
+      || INTVAL (XEXP (SET_SRC (vctp_reg_set), 1)) >= 0
+      || decrementnum != abs (INTVAL (XEXP (SET_SRC (vctp_reg_set), 1)))
+      || decrementnum != arm_mve_get_vctp_lanes (vctp_insn))
+    return NULL;
+
+  if (REG_P (condcount) && REG_P (condconst))
+    {
+      /* First we need to prove that the loop is going 0..condconst with an
+	 inc of 1 in each iteration.  */
+      if (GET_CODE (SET_SRC (condcount_reg_set)) == PLUS
+	  && CONST_INT_P (XEXP (SET_SRC (condcount_reg_set), 1))
+	  && INTVAL (XEXP (SET_SRC (condcount_reg_set), 1)) == 1)
+	{
+	    rtx counter_reg = SET_DEST (condcount_reg_set);
+	    /* Check that the counter did indeed start from zero.  */
+	    df_ref this_set = DF_REG_DEF_CHAIN (REGNO (counter_reg));
+	    if (!this_set)
+	      return NULL;
+	    df_ref last_set_def = DF_REF_NEXT_REG (this_set);
+	    if (!last_set_def)
+	      return NULL;
+	    rtx_insn* last_set_insn = DF_REF_INSN (last_set_def);
+	    rtx last_set = single_set (last_set_insn);
+	    if (!last_set)
+	      return NULL;
+	    rtx counter_orig_set;
+	    counter_orig_set = SET_SRC (last_set);
+	    if (!CONST_INT_P (counter_orig_set)
+		|| (INTVAL (counter_orig_set) != 0))
+	      return NULL;
+	    /* And finally check that the target value of the counter,
+	       condconst, is of the correct shape.  */
+	    if (!arm_mve_check_reg_origin_is_num_elems (body, condconst,
+							vctp_reg_iv.step))
+	      return NULL;
+	}
+      else
+	return NULL;
+    }
+  else
+    return NULL;
+
+  /* Everything looks valid.  */
+  return vctp_insn;
+}
+
+/* Helper function to `arm_mve_loop_valid_for_dlstp`.  In the case of a
+   counter that is decrementing, ensure that it is decrementing by the
+   right amount in each iteration and that the target condition is what
+   we expect.  */
+
+static rtx_insn*
+arm_mve_dlstp_check_dec_counter (basic_block body, rtx_insn* vctp_insn,
+				 rtx condconst, rtx condcount)
+{
+  rtx vctp_reg = XVECEXP (XEXP (PATTERN (vctp_insn), 1), 0, 0);
+  class rtx_iv vctp_reg_iv;
+  int decrementnum;
+  /* For decrementing loops of type A), the counter is usually present in the
+     loop latch.  Here we simply need to verify that this counter is the same
+     reg that is also used in the vctp_insn and that it is not otherwise
+     modified.  */
+  rtx_insn *dec_insn = BB_END (body->loop_father->latch);
+  /* If not in the loop latch, try to find the decrement in the loop body.  */
+  if (!NONDEBUG_INSN_P (dec_insn))
+  {
+    df_ref temp = df_bb_regno_only_def_find (body, REGNO (condcount));
+    /* If we haven't been able to find the decrement, bail out.  */
+    if (!temp)
+      return NULL;
+    dec_insn = DF_REF_INSN (temp);
+  }
+
+  rtx dec_set = single_set (dec_insn);
+
+  /* Next, ensure that it is a PLUS of the form:
+     (set (reg a) (plus (reg a) (const_int)))
+     where (reg a) is the same as condcount.  */
+  if (!dec_set
+      || !REG_P (SET_DEST (dec_set))
+      || !REG_P (XEXP (SET_SRC (dec_set), 0))
+      || !CONST_INT_P (XEXP (SET_SRC (dec_set), 1))
+      || REGNO (SET_DEST (dec_set))
+	  != REGNO (XEXP (SET_SRC (dec_set), 0))
+      || REGNO (SET_DEST (dec_set)) != REGNO (condcount))
+    return NULL;
+
+  decrementnum = INTVAL (XEXP (SET_SRC (dec_set), 1));
+
+  /* This decrementnum is the number of lanes/elements it decrements from the
+     remaining number of lanes/elements to process in the loop, for this reason
+     this is always a negative number, but to simplify later checks we use it's
+     absolute value.  */
+  if (decrementnum >= 0)
+    return NULL;
+  decrementnum = abs (decrementnum);
+
+  /* Ok, so we now know the loop decrement.  If it is a 1, then we need to
+     look at the loop vctp_reg and verify that it also decrements correctly.
+     Then, we need to establish that the starting value of the loop decrement
+     originates from the starting value of the vctp decrement.  */
+  if (decrementnum == 1)
+    {
+      class rtx_iv vctp_reg_iv;
+      /* The loop counter is found to be independent of the decrement
+	 of the reg used in the vctp_insn, again.  Ensure that IV analysis
+	 succeeds and check the step.  */
+      if (!iv_analyze (vctp_insn, as_a<scalar_int_mode> (GET_MODE (vctp_reg)),
+		       vctp_reg, &vctp_reg_iv))
+	return NULL;
+      /* Ensure it matches the number of lanes of the vctp instruction.  */
+      if (abs (INTVAL (vctp_reg_iv.step))
+	  != arm_mve_get_vctp_lanes (vctp_insn))
+	return NULL;
+      if (!arm_mve_check_reg_origin_is_num_elems (body, condcount, vctp_reg_iv.step))
+	return NULL;
+    }
+  /* If the decrements are the same, then the situation is simple: either they
+     are also the same reg, which is safe, or they are different registers, in
+     which case makse sure that there is a only simple SET from one to the
+     other inside the loop.*/
+  else if (decrementnum == arm_mve_get_vctp_lanes (vctp_insn))
+    {
+      if (REGNO (condcount) != REGNO (vctp_reg))
+	{
+	  /* It wasn't the same reg, but it could be behild a
+	     (set (vctp_reg) (condcount)), so instead find where
+	     the VCTP insn is DEF'd inside the loop.  */
+	  rtx_insn *vctp_reg_insn
+	    = DF_REF_INSN (df_bb_regno_only_def_find (body, REGNO (vctp_reg)));
+	  rtx vctp_reg_set = single_set (vctp_reg_insn);
+	  /* This must just be a simple SET from the condcount.  */
+	  if (!vctp_reg_set
+	      || !REG_P (SET_DEST (vctp_reg_set))
+	      || !REG_P (SET_SRC (vctp_reg_set))
+	      || REGNO (SET_SRC (vctp_reg_set)) != REGNO (condcount))
+	    return NULL;
+	}
+    }
+  else
+    return NULL;
+
+  /* We now only need to find out that the loop terminates with a LE
+     zero condition.  If condconst is a const_int, then this is easy.
+     If its a REG, look at the last condition+jump in a bb before
+     the loop, because that usually will have a branch jumping over
+     the loop body.  */
+  if (CONST_INT_P (condconst)
+      && !(INTVAL (condconst) == 0 && JUMP_P (BB_END (body))
+	   && GET_CODE (XEXP (PATTERN (BB_END (body)), 1)) == IF_THEN_ELSE
+	   && (GET_CODE (XEXP (XEXP (PATTERN (BB_END (body)), 1), 0)) == NE
+	       ||GET_CODE (XEXP (XEXP (PATTERN (BB_END (body)), 1), 0)) == GT)))
+    return NULL;
+  else if (REG_P (condconst))
+    {
+      basic_block pre_loop_bb = body;
+      while (pre_loop_bb->prev_bb && BB_END (pre_loop_bb->prev_bb)
+	     && !JUMP_P (BB_END (pre_loop_bb->prev_bb)))
+	pre_loop_bb = pre_loop_bb->prev_bb;
+      if (pre_loop_bb && BB_END (pre_loop_bb))
+	pre_loop_bb = pre_loop_bb->prev_bb;
+      else
+	return NULL;
+      rtx initial_compare = NULL_RTX;
+      if (!(prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb))
+	    && INSN_P (prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb)))))
+	return NULL;
+      else
+	initial_compare
+	    = single_set (prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb)));
+      if (!(initial_compare
+	    && cc_register (SET_DEST (initial_compare), VOIDmode)
+	    && GET_CODE (SET_SRC (initial_compare)) == COMPARE
+	    && CONST_INT_P (XEXP (SET_SRC (initial_compare), 1))
+	    && INTVAL (XEXP (SET_SRC (initial_compare), 1)) == 0))
+	return NULL;
+
+      /* Usually this is a LE condition, but it can also just be a GT or an EQ
+	 condition (if the value is unsigned or the compiler knows its not negative)  */
+      rtx_insn *loop_jumpover = BB_END (pre_loop_bb);
+      if (!(JUMP_P (loop_jumpover)
+	    && GET_CODE (XEXP (PATTERN (loop_jumpover), 1)) == IF_THEN_ELSE
+	    && (GET_CODE (XEXP (XEXP (PATTERN (loop_jumpover), 1), 0)) == LE
+		|| GET_CODE (XEXP (XEXP (PATTERN (loop_jumpover), 1), 0)) == GT
+		|| GET_CODE (XEXP (XEXP (PATTERN (loop_jumpover), 1), 0)) == EQ)))
+	return NULL;
+    }
+
+  /* Everything looks valid.  */
+  return vctp_insn;
+}
+
+/* Function to check a loop's structure to see if it is a valid candidate for
+   an MVE Tail Predicated Low-Overhead Loop.  Returns the loop's VCTP_INSN if
+   it is valid, or NULL if it isn't.  */
+
+static rtx_insn*
+arm_mve_loop_valid_for_dlstp (basic_block body)
+{
+  /* Doloop can only be done "elementwise" with predicated dlstp/letp if it
+     contains a VCTP on the number of elements processed by the loop.
+     Find the VCTP predicate generation inside the loop body BB.  */
+  rtx_insn *vctp_insn = arm_mve_get_loop_vctp (body);
+  if (!vctp_insn)
+    return NULL;
+
+  /* There are only two types of loops that can be turned into dlstp/letp
+     loops:
+      A) Loops of the form:
+	  while (num_of_elem > 0)
+	    {
+	      p = vctp<size> (num_of_elem)
+	      n -= num_of_lanes;
+	    }
+      B) Loops of the form:
+	  int num_of_iters = (num_of_elem + num_of_lanes - 1) / num_of_lanes
+	  for (i = 0; i < num_of_iters; i++)
+	    {
+	      p = vctp<size> (num_of_elem)
+	      n -= num_of_lanes;
+	    }
+
+    Then, depending on the type of loop above we need will need to do
+    different sets of checks.  */
+  iv_analysis_loop_init (body->loop_father);
+
+  /* In order to find out if the loop is of type A or B above look for the
+     loop counter: it will either be incrementing by one per iteration or
+     it will be decrementing by num_of_lanes.  We can find the loop counter
+     in the condition at the end of the loop.  */
+  rtx_insn *loop_cond = prev_nonnote_nondebug_insn_bb (BB_END (body));
+  if (!(cc_register (XEXP (PATTERN (loop_cond), 0), VOIDmode)
+	&& GET_CODE (XEXP (PATTERN (loop_cond), 1)) == COMPARE))
+    return NULL;
+
+  /* The operands in the condition:  Try to identify which one is the
+     constant and which is the counter and run IV analysis on the latter.  */
+  rtx cond_arg_1 = XEXP (XEXP (PATTERN (loop_cond), 1), 0);
+  rtx cond_arg_2 = XEXP (XEXP (PATTERN (loop_cond), 1), 1);
+
+  rtx loop_cond_constant;
+  rtx loop_counter;
+  class rtx_iv cond_counter_iv, cond_temp_iv;
+
+  if (CONST_INT_P (cond_arg_1))
+    {
+      /* cond_arg_1 is the constant and cond_arg_2 is the counter.  */
+      loop_cond_constant = cond_arg_1;
+      loop_counter = cond_arg_2;
+      iv_analyze (loop_cond, as_a<scalar_int_mode> (GET_MODE (cond_arg_2)),
+		  cond_arg_2, &cond_counter_iv);
+    }
+  else if (CONST_INT_P (cond_arg_2))
+    {
+      /* cond_arg_2 is the constant and cond_arg_1 is the counter.  */
+      loop_cond_constant = cond_arg_2;
+      loop_counter = cond_arg_1;
+      iv_analyze (loop_cond, as_a<scalar_int_mode> (GET_MODE (cond_arg_1)),
+		  cond_arg_1, &cond_counter_iv);
+    }
+  else if (REG_P (cond_arg_1) && REG_P (cond_arg_2))
+    {
+      /* If both operands to the compare are REGs, we can safely
+	 run IV analysis on both and then determine which is the
+	 constant by looking at the step.
+	 First assume cond_arg_1 is the counter.  */
+      loop_counter = cond_arg_1;
+      loop_cond_constant = cond_arg_2;
+      iv_analyze (loop_cond, as_a<scalar_int_mode> (GET_MODE (cond_arg_1)),
+		  cond_arg_1, &cond_counter_iv);
+      iv_analyze (loop_cond, as_a<scalar_int_mode> (GET_MODE (cond_arg_2)),
+		  cond_arg_2, &cond_temp_iv);
+
+      /* Look at the steps and swap around the rtx's if needed.  Error out if
+	 one of them cannot be identified as constant.  */
+      if (!CONST_INT_P (cond_counter_iv.step) || !CONST_INT_P (cond_temp_iv.step))
+	return NULL;
+      if (INTVAL (cond_counter_iv.step) != 0 && INTVAL (cond_temp_iv.step) != 0)
+	return NULL;
+      if (INTVAL (cond_counter_iv.step) == 0 && INTVAL (cond_temp_iv.step) != 0)
+	{
+	  loop_counter = cond_arg_2;
+	  loop_cond_constant = cond_arg_1;
+	  cond_counter_iv = cond_temp_iv;
+	}
+    }
+  else
+    return NULL;
+
+  if (!REG_P (loop_counter))
+    return NULL;
+  if (!(REG_P (loop_cond_constant) || CONST_INT_P (loop_cond_constant)))
+    return NULL;
+
+  /* Now we have extracted the IV step of the loop counter, call the
+     appropriate checking function.  */
+  if (INTVAL (cond_counter_iv.step) > 0)
+    return arm_mve_dlstp_check_inc_counter (body, vctp_insn,
+					    loop_cond_constant, loop_counter);
+  else if (INTVAL (cond_counter_iv.step) < 0)
+    return arm_mve_dlstp_check_dec_counter (body, vctp_insn,
+					    loop_cond_constant, loop_counter);
+  else
+    return NULL;
+}
+
+/* Predict whether the given loop in gimple will be transformed in the RTL
+   doloop_optimize pass.  It could be argued that turning large enough loops
+   into low-overhead loops would not show a signficant performance boost.
+   Howeer, in the case of tail predication we would still avoid using VPT/VPST
+   instructions inside the loop, and in either case using low-overhead loops
+   would not be detrimental, so we decided to not consider size, avoiding the
+   need of a heuristic to determine what an appropriate size boundary is.  */
+
+static bool
+arm_predict_doloop_p (struct loop *loop)
+{
+  gcc_assert (loop);
+  /* On arm, targetm.can_use_doloop_p is actually
+     can_use_doloop_if_innermost.  Ensure the loop is innermost,
+     it is valid and as per arm_target_bb_ok_for_lob and the
+     correct architecture flags are enabled.  */
+  if (!(TARGET_HAVE_LOB && optimize > 0))
+    {
+      if (dump_file && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file, "Predict doloop failure due to"
+			    " target architecture or optimisation flags.\n");
+      return false;
+    }
+  else if (loop->inner != NULL)
+    {
+      if (dump_file && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file, "Predict doloop failure due to"
+			    " loop nesting.\n");
+      return false;
+    }
+  else if (!arm_target_bb_ok_for_lob (loop->header->next_bb))
+    {
+      if (dump_file && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file, "Predict doloop failure due to"
+			    " loop bb complexity.\n");
+      return false;
+    }
+
+  return true;
+}
+
+/* Implement targetm.loop_unroll_adjust.  Use this to block unrolling of loops
+   that may later be turned into MVE Tail Predicated Low Overhead Loops.  The
+   performance benefit of an MVE LoL is likely to be much higher than that of
+   the unrolling.  */
+
+unsigned
+arm_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
+{
+  if (TARGET_HAVE_MVE
+      && arm_target_bb_ok_for_lob (loop->latch)
+      && arm_mve_loop_valid_for_dlstp (loop->header))
+    return 0;
+  else
+    return nunroll;
+}
+
+/* Function to hadle emitting a VPT-unpredicated version of a VPT-predicated
+   insn to a sequence.  */
+
+static bool
+arm_emit_mve_unpredicated_insn_to_seq (rtx_insn* insn)
+{
+  rtx insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn);
+  int new_icode = get_attr_mve_unpredicated_insn (insn);
+  if (!in_sequence_p ()
+      || !MVE_VPT_PREDICATED_INSN_P (insn)
+      || (!insn_vpr_reg_operand)
+      || (!new_icode))
+    return false;
+
+  extract_insn (insn);
+  rtx arr[8];
+  int j = 0;
+
+  /* When transforming a VPT-predicated instruction
+     into its unpredicated equivalent we need to drop
+     the VPR operand and we may need to also drop a
+     merge "vuninit" input operand, depending on the
+     instruction pattern.  Here ensure that we have at
+     most a two-operand difference between the two
+     instrunctions.  */
+  int n_operands_diff
+      = recog_data.n_operands - insn_data[new_icode].n_operands;
+  if (!(n_operands_diff > 0 && n_operands_diff <= 2))
+    return false;
+
+  /* Then, loop through the operands of the predicated
+     instruction, and retain the ones that map to the
+     unpredicated instruction.  */
+  for (int i = 0; i < recog_data.n_operands; i++)
+    {
+      /* Ignore the VPR and, if needed, the vuninit
+	 operand.  */
+      if (insn_vpr_reg_operand == recog_data.operand[i]
+	  || (n_operands_diff == 2
+	      && !strcmp (recog_data.constraints[i], "0")))
+	continue;
+      else
+	{
+	  arr[j] = recog_data.operand[i];
+	  j++;
+	}
+    }
+
+  /* Finally, emit the upredicated instruction.  */
+  rtx_insn *new_insn;
+  switch (j)
+    {
+      case 1:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0]));
+	break;
+      case 2:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1]));
+	break;
+      case 3:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2]));
+	break;
+      case 4:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2],
+						   arr[3]));
+	break;
+      case 5:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2],
+						   arr[3], arr[4]));
+	break;
+      case 6:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2],
+						   arr[3], arr[4], arr[5]));
+	break;
+      case 7:
+	new_insn = emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2],
+						   arr[3], arr[4], arr[5],
+						   arr[6]));
+	break;
+      default:
+	gcc_unreachable ();
+    }
+  INSN_LOCATION (new_insn) = INSN_LOCATION (insn);
+  return true;
+}
+
+/* When a vctp insn is used, its out is often followed by
+   a zero-extend insn to SImode, which is then SUBREG'd into a
+   vector form of mode VALID_MVE_PRED_MODE: this vector form is
+   what is then used as an input to the instructions within the
+   loop.  Hence, store that vector form of the VPR reg into
+   vctp_vpr_generated, so that we can match it with instructions
+   in the loop to determine if they are predicated on this same
+   VPR.  If there is no zero-extend and subreg or it is otherwise
+   invalid, then return NULL to cancel the dlstp transform.  */
+
+static rtx
+arm_mve_get_vctp_vec_form (rtx_insn *insn)
+{
+  rtx vctp_vpr_generated = NULL_RTX;
+  rtx_insn *next_use1 = NULL;
+  df_ref use;
+  for (use
+	= DF_REG_USE_CHAIN
+	   (DF_REF_REGNO (DF_INSN_INFO_DEFS (DF_INSN_INFO_GET (insn))));
+       use; use = DF_REF_NEXT_REG (use))
+    if (!next_use1 && NONDEBUG_INSN_P (DF_REF_INSN (use)))
+      next_use1 = DF_REF_INSN (use);
+
+  rtx next_use1_set = single_set (next_use1);
+  if (next_use1_set
+      && GET_CODE (SET_SRC (next_use1_set)) == ZERO_EXTEND)
+    {
+      rtx_insn *next_use2 = NULL;
+      for (use
+	    = DF_REG_USE_CHAIN
+	       (DF_REF_REGNO
+		 (DF_INSN_INFO_DEFS (DF_INSN_INFO_GET (next_use1))));
+	   use; use = DF_REF_NEXT_REG (use))
+	if (!next_use2 && NONDEBUG_INSN_P (DF_REF_INSN (use)))
+	  next_use2 = DF_REF_INSN (use);
+
+      rtx next_use2_set = single_set (next_use2);
+      if (next_use2_set
+	  && GET_CODE (SET_SRC (next_use2_set)) == SUBREG)
+	vctp_vpr_generated = SET_DEST (next_use2_set);
+    }
+
+  if (!vctp_vpr_generated || !REG_P (vctp_vpr_generated)
+      || !VALID_MVE_PRED_MODE (GET_MODE (vctp_vpr_generated)))
+    return NULL_RTX;
+
+  return vctp_vpr_generated;
+}
+
+/* Attempt to transform the loop contents of loop basic block from VPT
+   predicated insns into unpredicated insns for a dlstp/letp loop.  Returns
+   rtx constant value to decrement from the total number of elements.  Return
+   (const_int 1) if we can't use tail predication and fallback to scalar
+   low-overhead loops.  */
+
+rtx
+arm_attempt_dlstp_transform (rtx label)
+{
+  basic_block body = BLOCK_FOR_INSN (label)->prev_bb;
+
+  /* Ensure that the bb is within a loop that has all required metadata.  */
+  if (!body->loop_father || !body->loop_father->header
+      || !body->loop_father->simple_loop_desc)
+    return const1_rtx;
+
+  rtx_insn *vctp_insn = arm_mve_loop_valid_for_dlstp (body);
+  if (!vctp_insn)
+    return const1_rtx;
+
+  gcc_assert (single_set (vctp_insn));
+
+  rtx vctp_vpr_generated = arm_mve_get_vctp_vec_form (vctp_insn);
+  if (!vctp_vpr_generated)
+    return const1_rtx;
+
+  /* decrementunum is already known to be valid at this point.  */
+  int decrementnum = arm_mve_get_vctp_lanes (vctp_insn);
+
+  rtx_insn *insn = 0;
+  rtx_insn *cur_insn = 0;
+  rtx_insn *seq;
+  hash_map <rtx_insn *, bool> *safe_insn_map
+      = new hash_map <rtx_insn *, bool>;
+
+  /* Scan through the insns in the loop bb and emit the transformed bb
+     insns to a sequence.  */
+  start_sequence ();
+  FOR_BB_INSNS (body, insn)
+    {
+      if (GET_CODE (insn) == CODE_LABEL || NOTE_INSN_BASIC_BLOCK_P (insn))
+	continue;
+      else if (NOTE_P (insn))
+	emit_note ((enum insn_note)NOTE_KIND (insn));
+      else if (DEBUG_INSN_P (insn))
+	emit_debug_insn (PATTERN (insn));
+      else if (!INSN_P (insn))
+	{
+	  end_sequence ();
+	  return const1_rtx;
+	}
+      /* When we find the vctp instruction: continue.  */
+      else if (insn == vctp_insn)
+	continue;
+       /* If the insn pattern requires the use of the VPR value from the
+	  vctp as an input parameter for predication.  */
+      else if (arm_mve_vec_insn_is_predicated_with_this_predicate
+		(insn, vctp_vpr_generated))
+	{
+	  bool success = arm_emit_mve_unpredicated_insn_to_seq (insn);
+	  if (!success)
+	    {
+	      end_sequence ();
+	      return const1_rtx;
+	    }
+	}
+      /* If the insn isn't VPT predicated on vctp_vpr_generated, we need to
+	 make sure that it is still valid within the dlstp/letp loop.  */
+      else
+	{
+	  /* If this instruction USE-s the vctp_vpr_generated other than for
+	     predication, this blocks the transformation as we are not allowed
+	     to optimise the VPR value away.  */
+	  df_ref insn_uses = NULL;
+	  FOR_EACH_INSN_USE (insn_uses, insn)
+	  {
+	    if (rtx_equal_p (vctp_vpr_generated, DF_REF_REG (insn_uses)))
+	      {
+		end_sequence ();
+		return const1_rtx;
+	      }
+	  }
+	  /* If within the loop we have an MVE vector instruction that is
+	     unpredicated, the dlstp/letp looping will add implicit
+	     predication to it.  This will result in a change in behaviour
+	     of the instruction, so we need to find out if any instructions
+	     that feed into the current instruction were implicitly
+	     predicated.  */
+	  if (arm_mve_check_df_chain_back_for_implic_predic
+	       (safe_insn_map, insn, vctp_vpr_generated))
+	    {
+	      if (arm_mve_check_df_chain_fwd_for_implic_predic_impact
+		    (insn, vctp_vpr_generated))
+		{
+		  end_sequence ();
+		  return const1_rtx;
+		}
+	    }
+	  emit_insn (PATTERN (insn));
+	}
+    }
+  seq = get_insns ();
+  end_sequence ();
+
+  /* Re-write the entire BB contents with the transformed
+     sequence.  */
+  FOR_BB_INSNS_SAFE (body, insn, cur_insn)
+    if (!(GET_CODE (insn) == CODE_LABEL || NOTE_INSN_BASIC_BLOCK_P (insn)))
+      delete_insn (insn);
+
+  emit_insn_after (seq, BB_END (body));
+
+  /* The transformation has succeeded, so now modify the "count"
+     (a.k.a. niter_expr) for the middle-end.  Also set noloop_assumptions
+     to NULL to stop the middle-end from making assumptions about the
+     number of iterations.  */
+  simple_loop_desc (body->loop_father)->niter_expr
+    = XVECEXP (SET_SRC (PATTERN (vctp_insn)), 0, 0);
+  simple_loop_desc (body->loop_father)->noloop_assumptions = NULL_RTX;
+  return GEN_INT (decrementnum);
 }
 
 #if CHECKING_P
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 5ea2d9e8668..9398702cddd 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -2673,6 +2673,17 @@  (define_int_iterator MRRCI [VUNSPEC_MRRC VUNSPEC_MRRC2])
 (define_int_attr mrrc [(VUNSPEC_MRRC "mrrc") (VUNSPEC_MRRC2 "mrrc2")])
 (define_int_attr MRRC [(VUNSPEC_MRRC "MRRC") (VUNSPEC_MRRC2 "MRRC2")])
 
+(define_int_attr dlstp_elemsize [(DLSTP8 "8") (DLSTP16 "16") (DLSTP32 "32")
+				 (DLSTP64 "64")])
+
+(define_int_attr letp_num_lanes [(LETP8 "16") (LETP16 "8") (LETP32 "4")
+				 (LETP64 "2")])
+(define_int_attr letp_num_lanes_neg [(LETP8 "-16") (LETP16 "-8") (LETP32 "-4")
+				     (LETP64 "-2")])
+
+(define_int_attr letp_num_lanes_minus_1 [(LETP8 "15") (LETP16 "7") (LETP32 "3")
+					 (LETP64 "1")])
+
 (define_int_attr opsuffix [(UNSPEC_DOT_S "s8")
 			   (UNSPEC_DOT_U "u8")
 			   (UNSPEC_DOT_US "s8")
@@ -2916,6 +2927,10 @@  (define_int_iterator SQRSHRLQ [SQRSHRL_64 SQRSHRL_48])
 (define_int_iterator VSHLCQ_M [VSHLCQ_M_S VSHLCQ_M_U])
 (define_int_iterator VQSHLUQ_M_N [VQSHLUQ_M_N_S])
 (define_int_iterator VQSHLUQ_N [VQSHLUQ_N_S])
+(define_int_iterator DLSTP [DLSTP8 DLSTP16 DLSTP32
+				   DLSTP64])
+(define_int_iterator LETP [LETP8 LETP16 LETP32
+			   LETP64])
 
 ;; Define iterators for VCMLA operations
 (define_int_iterator VCMLA_OP [UNSPEC_VCMLA
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index b1862d7977e..5748e2333eb 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -6918,3 +6918,41 @@  (define_expand "@arm_mve_reinterpret<mode>"
       }
   }
 )
+
+;; Originally expanded by 'predicated_doloop_end'.
+;; In the rare situation where the branch is too far, we do also need to
+;; revert FPSCR.LTPSIZE back to 0x100 after the last iteration.
+(define_insn "predicated_doloop_end_internal<letp_num_lanes>"
+  [(set (pc)
+	(if_then_else
+	   (gtu (unspec:SI [(plus:SI (match_operand:SI 0 "s_register_operand" "=r")
+				     (const_int <letp_num_lanes_neg>))]
+		LETP)
+		(const_int <letp_num_lanes_minus_1>))
+	 (match_operand 1 "" "")
+	 (pc)))
+   (set (match_dup 0)
+	(plus:SI (match_dup 0) (const_int <letp_num_lanes_neg>)))
+   (clobber (reg:CC CC_REGNUM))]
+  "TARGET_HAVE_MVE"
+  {
+    if (get_attr_length (insn) == 4)
+      return "letp\t%|lr, %l1";
+    else
+      return "subs\t%|lr, #<letp_num_lanes>\n\tbhi\t%l1\n\tlctp";
+  }
+  [(set (attr "length")
+	(if_then_else
+	   (ltu (minus (pc) (match_dup 1)) (const_int 1024))
+	    (const_int 4)
+	    (const_int 6)))
+   (set_attr "type" "branch")])
+
+(define_insn "dlstp<dlstp_elemsize>_insn"
+  [
+    (set (reg:SI LR_REGNUM)
+	 (unspec:SI [(match_operand:SI 0 "s_register_operand" "r")]
+	  DLSTP))
+  ]
+  "TARGET_HAVE_MVE"
+  "dlstp.<dlstp_elemsize>\t%|lr, %0")
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index e1e013befa7..f2801cea36a 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1613,7 +1613,7 @@  (define_expand "doloop_end"
    (use (match_operand 1 "" ""))]     ; label
   "TARGET_32BIT"
   "
- {
+{
    /* Currently SMS relies on the do-loop pattern to recognize loops
       where (1) the control part consists of all insns defining and/or
       using a certain 'count' register and (2) the loop count can be
@@ -1623,41 +1623,77 @@  (define_expand "doloop_end"
 
       Also used to implement the low over head loops feature, which is part of
       the Armv8.1-M Mainline Low Overhead Branch (LOB) extension.  */
-   if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
-   {
-     rtx s0;
-     rtx bcomp;
-     rtx loc_ref;
-     rtx cc_reg;
-     rtx insn;
-     rtx cmp;
-
-     if (GET_MODE (operands[0]) != SImode)
-       FAIL;
-
-     s0 = operands [0];
-
-     /* Low over head loop instructions require the first operand to be LR.  */
-     if (TARGET_HAVE_LOB && arm_target_insn_ok_for_lob (operands [1]))
-       s0 = gen_rtx_REG (SImode, LR_REGNUM);
-
-     if (TARGET_THUMB2)
-       insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0, GEN_INT (-1)));
-     else
-       insn = emit_insn (gen_addsi3_compare0 (s0, s0, GEN_INT (-1)));
-
-     cmp = XVECEXP (PATTERN (insn), 0, 0);
-     cc_reg = SET_DEST (cmp);
-     bcomp = gen_rtx_NE (VOIDmode, cc_reg, const0_rtx);
-     loc_ref = gen_rtx_LABEL_REF (VOIDmode, operands [1]);
-     emit_jump_insn (gen_rtx_SET (pc_rtx,
-                                  gen_rtx_IF_THEN_ELSE (VOIDmode, bcomp,
-                                                        loc_ref, pc_rtx)));
-     DONE;
-   }
- else
-   FAIL;
- }")
+  if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
+    {
+      rtx s0;
+      rtx bcomp;
+      rtx loc_ref;
+      rtx cc_reg;
+      rtx insn;
+      rtx cmp;
+      rtx decrement_num;
+
+      if (GET_MODE (operands[0]) != SImode)
+	FAIL;
+
+      s0 = operands[0];
+
+       if (TARGET_HAVE_LOB && arm_target_bb_ok_for_lob (BLOCK_FOR_INSN (operands[1])))
+	{
+	  s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
+	  /* If we have a compatible MVE target, try and analyse the loop
+	     contents to determine if we can use predicated dlstp/letp
+	     looping.  */
+	  if (TARGET_HAVE_MVE
+	      && (decrement_num = arm_attempt_dlstp_transform (operands[1]))
+	      && (INTVAL (decrement_num) != 1))
+	    {
+	      loc_ref = gen_rtx_LABEL_REF (VOIDmode, operands[1]);
+	      switch (INTVAL (decrement_num))
+		{
+		  case 2:
+		    insn = emit_jump_insn (gen_predicated_doloop_end_internal2
+					    (s0, loc_ref));
+		    break;
+		  case 4:
+		    insn = emit_jump_insn (gen_predicated_doloop_end_internal4
+					    (s0, loc_ref));
+		    break;
+		  case 8:
+		    insn = emit_jump_insn (gen_predicated_doloop_end_internal8
+					    (s0, loc_ref));
+		    break;
+		  case 16:
+		    insn = emit_jump_insn (gen_predicated_doloop_end_internal16
+					    (s0, loc_ref));
+		    break;
+		  default:
+		    gcc_unreachable ();
+		}
+	      DONE;
+	    }
+	}
+
+	/* Otherwise, try standard decrement-by-one dls/le looping.  */
+	if (TARGET_THUMB2)
+	  insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0,
+							GEN_INT (-1)));
+	else
+	  insn = emit_insn (gen_addsi3_compare0 (s0, s0, GEN_INT (-1)));
+
+	cmp = XVECEXP (PATTERN (insn), 0, 0);
+	cc_reg = SET_DEST (cmp);
+	bcomp = gen_rtx_NE (VOIDmode, cc_reg, const0_rtx);
+	loc_ref = gen_rtx_LABEL_REF (VOIDmode, operands[1]);
+	emit_jump_insn (gen_rtx_SET (pc_rtx,
+				     gen_rtx_IF_THEN_ELSE (VOIDmode, bcomp,
+							   loc_ref, pc_rtx)));
+	DONE;
+    }
+  else
+    FAIL;
+}")
 
 (define_insn "*clear_apsr"
   [(unspec_volatile:SI [(const_int 0)] VUNSPEC_CLRM_APSR)
@@ -1755,7 +1791,37 @@  (define_expand "doloop_begin"
   {
     if (REGNO (operands[0]) == LR_REGNUM)
       {
-	emit_insn (gen_dls_insn (operands[0]));
+	/* Pick out the number by which we are decrementing the loop counter
+	   in every iteration.  If it's > 1, then use dlstp.  */
+	int const_int_dec_num
+	     = abs (INTVAL (XEXP (XEXP (XVECEXP (PATTERN (operands[1]), 0, 1),
+				  1),
+			    1)));
+	switch (const_int_dec_num)
+	  {
+	    case 16:
+	      emit_insn (gen_dlstp8_insn (operands[0]));
+	      break;
+
+	    case 8:
+	      emit_insn (gen_dlstp16_insn (operands[0]));
+	      break;
+
+	    case 4:
+	      emit_insn (gen_dlstp32_insn (operands[0]));
+	      break;
+
+	    case 2:
+	      emit_insn (gen_dlstp64_insn (operands[0]));
+	      break;
+
+	    case 1:
+	      emit_insn (gen_dls_insn (operands[0]));
+	      break;
+
+	    default:
+	      gcc_unreachable ();
+	  }
 	DONE;
       }
     else
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 4713ec840ab..2d6f27c14f4 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -583,6 +583,14 @@  (define_c_enum "unspec" [
   VADDLVQ_U
   VCTP
   VCTP_M
+  DLSTP8
+  DLSTP16
+  DLSTP32
+  DLSTP64
+  LETP8
+  LETP16
+  LETP32
+  LETP64
   VPNOT
   VCREATEQ_F
   VCVTQ_N_TO_F_S
diff --git a/gcc/df-core.cc b/gcc/df-core.cc
index d4812b04a7c..4fcc14bf790 100644
--- a/gcc/df-core.cc
+++ b/gcc/df-core.cc
@@ -1964,6 +1964,21 @@  df_bb_regno_last_def_find (basic_block bb, unsigned int regno)
   return NULL;
 }
 
+/* Return the one and only def of REGNO within BB.  If there is no def or
+   there are multiple defs, return NULL.  */
+
+df_ref
+df_bb_regno_only_def_find (basic_block bb, unsigned int regno)
+{
+  df_ref temp = df_bb_regno_first_def_find (bb, regno);
+  if (!temp)
+    return NULL;
+  else if (temp == df_bb_regno_last_def_find (bb, regno))
+    return temp;
+  else
+    return NULL;
+}
+
 /* Finds the reference corresponding to the definition of REG in INSN.
    DF is the dataflow object.  */
 
diff --git a/gcc/df.h b/gcc/df.h
index 402657a7076..98623637f9c 100644
--- a/gcc/df.h
+++ b/gcc/df.h
@@ -987,6 +987,7 @@  extern void df_check_cfg_clean (void);
 #endif
 extern df_ref df_bb_regno_first_def_find (basic_block, unsigned int);
 extern df_ref df_bb_regno_last_def_find (basic_block, unsigned int);
+extern df_ref df_bb_regno_only_def_find (basic_block, unsigned int);
 extern df_ref df_find_def (rtx_insn *, rtx);
 extern bool df_reg_defined (rtx_insn *, rtx);
 extern df_ref df_find_use (rtx_insn *, rtx);
diff --git a/gcc/loop-doloop.cc b/gcc/loop-doloop.cc
index 4feb0a25ab9..d919207505c 100644
--- a/gcc/loop-doloop.cc
+++ b/gcc/loop-doloop.cc
@@ -85,10 +85,10 @@  doloop_condition_get (rtx_insn *doloop_pat)
      forms:
 
      1)  (parallel [(set (pc) (if_then_else (condition)
-	  			            (label_ref (label))
-				            (pc)))
-	             (set (reg) (plus (reg) (const_int -1)))
-	             (additional clobbers and uses)])
+					    (label_ref (label))
+					    (pc)))
+		     (set (reg) (plus (reg) (const_int -1)))
+		     (additional clobbers and uses)])
 
      The branch must be the first entry of the parallel (also required
      by jump.cc), and the second entry of the parallel must be a set of
@@ -96,19 +96,34 @@  doloop_condition_get (rtx_insn *doloop_pat)
      the loop counter in an if_then_else too.
 
      2)  (set (reg) (plus (reg) (const_int -1))
-         (set (pc) (if_then_else (reg != 0)
-	                         (label_ref (label))
-			         (pc))).  
+	 (set (pc) (if_then_else (reg != 0)
+				 (label_ref (label))
+				 (pc))).
 
      Some targets (ARM) do the comparison before the branch, as in the
      following form:
 
-     3) (parallel [(set (cc) (compare ((plus (reg) (const_int -1), 0)))
-                   (set (reg) (plus (reg) (const_int -1)))])
-        (set (pc) (if_then_else (cc == NE)
-                                (label_ref (label))
-                                (pc))) */
-
+     3) (parallel [(set (cc) (compare (plus (reg) (const_int -1)) 0))
+		   (set (reg) (plus (reg) (const_int -1)))])
+	(set (pc) (if_then_else (cc == NE)
+				(label_ref (label))
+				(pc)))
+
+      The ARM target also supports a special case of a counter that decrements
+      by `n` and terminating in a GTU condition.  In that case, the compare and
+      branch are all part of one insn, containing an UNSPEC:
+
+      4) (parallel [
+	    (set (pc)
+		(if_then_else (gtu (unspec:SI [(plus:SI (reg:SI 14 lr)
+							(const_int -n))])
+				   (const_int n-1]))
+		    (label_ref)
+		    (pc)))
+	    (set (reg:SI 14 lr)
+		 (plus:SI (reg:SI 14 lr)
+			  (const_int -n)))
+     */
   pattern = PATTERN (doloop_pat);
 
   if (GET_CODE (pattern) != PARALLEL)
@@ -143,7 +158,7 @@  doloop_condition_get (rtx_insn *doloop_pat)
 	      || GET_CODE (cmp_arg1) != PLUS)
 	    return 0;
 	  reg_orig = XEXP (cmp_arg1, 0);
-	  if (XEXP (cmp_arg1, 1) != GEN_INT (-1) 
+	  if (XEXP (cmp_arg1, 1) != GEN_INT (-1)
 	      || !REG_P (reg_orig))
 	    return 0;
 	  cc_reg = SET_DEST (cmp_orig);
@@ -173,15 +188,17 @@  doloop_condition_get (rtx_insn *doloop_pat)
   if (! REG_P (reg))
     return 0;
 
-  /* Check if something = (plus (reg) (const_int -1)).
+  /* Check if something = (plus (reg) (const_int -n)).
      On IA-64, this decrement is wrapped in an if_then_else.  */
   inc_src = SET_SRC (inc);
   if (GET_CODE (inc_src) == IF_THEN_ELSE)
     inc_src = XEXP (inc_src, 1);
   if (GET_CODE (inc_src) != PLUS
       || XEXP (inc_src, 0) != reg
-      || XEXP (inc_src, 1) != constm1_rtx)
+      || !CONST_INT_P (XEXP (inc_src, 1))
+      || INTVAL (XEXP (inc_src, 1)) >= 0)
     return 0;
+  int dec_num = abs (INTVAL (XEXP (inc_src, 1)));
 
   /* Check for (set (pc) (if_then_else (condition)
                                        (label_ref (label))
@@ -196,60 +213,71 @@  doloop_condition_get (rtx_insn *doloop_pat)
   /* Extract loop termination condition.  */
   condition = XEXP (SET_SRC (cmp), 0);
 
-  /* We expect a GE or NE comparison with 0 or 1.  */
-  if ((GET_CODE (condition) != GE
-       && GET_CODE (condition) != NE)
-      || (XEXP (condition, 1) != const0_rtx
-          && XEXP (condition, 1) != const1_rtx))
+  /* We expect a GE or NE comparison with 0 or 1, or a GTU comparison with
+     dec_num - 1.  */
+  if (!((GET_CODE (condition) == GE
+	 || GET_CODE (condition) == NE)
+	&& (XEXP (condition, 1) == const0_rtx
+	    || XEXP (condition, 1) == const1_rtx ))
+      &&!(GET_CODE (condition) == GTU
+	  && ((INTVAL (XEXP (condition, 1))) == (dec_num - 1))))
     return 0;
 
-  if ((XEXP (condition, 0) == reg)
+  /* For the ARM special case of having a GTU: re-form the condition without
+     the unspec for the benefit of the middle-end.  */
+  if (GET_CODE (condition) == GTU)
+    {
+      condition = gen_rtx_fmt_ee (GTU, VOIDmode, inc_src,
+				  GEN_INT (dec_num - 1));
+      return condition;
+    }
+  else if ((XEXP (condition, 0) == reg)
       /* For the third case:  */  
       || ((cc_reg != NULL_RTX)
 	  && (XEXP (condition, 0) == cc_reg)
 	  && (reg_orig == reg))
       || (GET_CODE (XEXP (condition, 0)) == PLUS
 	  && XEXP (XEXP (condition, 0), 0) == reg))
-   {
+    {
      if (GET_CODE (pattern) != PARALLEL)
      /*  For the second form we expect:
 
-         (set (reg) (plus (reg) (const_int -1))
-         (set (pc) (if_then_else (reg != 0)
-                                 (label_ref (label))
-                                 (pc))).
+	 (set (reg) (plus (reg) (const_int -1))
+	 (set (pc) (if_then_else (reg != 0)
+				 (label_ref (label))
+				 (pc))).
 
-         is equivalent to the following:
+	 is equivalent to the following:
 
-         (parallel [(set (pc) (if_then_else (reg != 1)
-                                            (label_ref (label))
-                                            (pc)))
-                     (set (reg) (plus (reg) (const_int -1)))
-                     (additional clobbers and uses)])
+	 (parallel [(set (pc) (if_then_else (reg != 1)
+					    (label_ref (label))
+					    (pc)))
+		     (set (reg) (plus (reg) (const_int -1)))
+		     (additional clobbers and uses)])
 
-        For the third form we expect:
+	For the third form we expect:
 
-        (parallel [(set (cc) (compare ((plus (reg) (const_int -1)), 0))
-                   (set (reg) (plus (reg) (const_int -1)))])
-        (set (pc) (if_then_else (cc == NE)
-                                (label_ref (label))
-                                (pc))) 
+	(parallel [(set (cc) (compare ((plus (reg) (const_int -1)), 0))
+		   (set (reg) (plus (reg) (const_int -1)))])
+	(set (pc) (if_then_else (cc == NE)
+				(label_ref (label))
+				(pc))) 
 
-        which is equivalent to the following:
+	which is equivalent to the following:
 
-        (parallel [(set (cc) (compare (reg,  1))
-                   (set (reg) (plus (reg) (const_int -1)))
-                   (set (pc) (if_then_else (NE == cc)
-                                           (label_ref (label))
-                                           (pc))))])
+	(parallel [(set (cc) (compare (reg,  1))
+		   (set (reg) (plus (reg) (const_int -1)))
+		   (set (pc) (if_then_else (NE == cc)
+					   (label_ref (label))
+					   (pc))))])
 
-        So we return the second form instead for the two cases.
+	So we return the second form instead for the two cases.
 
      */
-        condition = gen_rtx_fmt_ee (NE, VOIDmode, inc_src, const1_rtx);
+	condition = gen_rtx_fmt_ee (NE, VOIDmode, inc_src, const1_rtx);
 
     return condition;
-   }
+    }
 
   /* ??? If a machine uses a funny comparison, we could return a
      canonicalized form here.  */
@@ -507,6 +535,11 @@  doloop_modify (class loop *loop, class niter_desc *desc,
 	nonneg = 1;
       break;
 
+    case GTU:
+      /* The iteration count does not need incrementing for a GTU test.  */
+      increment_count = false;
+      break;
+
       /* Abort if an invalid doloop pattern has been generated.  */
     default:
       gcc_unreachable ();
@@ -529,6 +562,10 @@  doloop_modify (class loop *loop, class niter_desc *desc,
 
   if (desc->noloop_assumptions)
     {
+      /* The GTU case has only been implemented for the ARM target, where
+	 noloop_assumptions gets explicitly set to NULL for that case, so
+	 assert here for safety.  */
+      gcc_assert (GET_CODE (condition) != GTU);
       rtx ass = copy_rtx (desc->noloop_assumptions);
       basic_block preheader = loop_preheader_edge (loop)->src;
       basic_block set_zero = split_edge (loop_preheader_edge (loop));
@@ -642,7 +679,7 @@  doloop_optimize (class loop *loop)
 {
   scalar_int_mode mode;
   rtx doloop_reg;
-  rtx count;
+  rtx count = NULL_RTX;
   widest_int iterations, iterations_max;
   rtx_code_label *start_label;
   rtx condition;
@@ -685,17 +722,6 @@  doloop_optimize (class loop *loop)
       return false;
     }
 
-  max_cost
-    = COSTS_N_INSNS (param_max_iterations_computation_cost);
-  if (set_src_cost (desc->niter_expr, mode, optimize_loop_for_speed_p (loop))
-      > max_cost)
-    {
-      if (dump_file)
-	fprintf (dump_file,
-		 "Doloop: number of iterations too costly to compute.\n");
-      return false;
-    }
-
   if (desc->const_iter)
     iterations = widest_int::from (rtx_mode_t (desc->niter_expr, mode),
 				   UNSIGNED);
@@ -716,12 +742,25 @@  doloop_optimize (class loop *loop)
 
   /* Generate looping insn.  If the pattern FAILs then give up trying
      to modify the loop since there is some aspect the back-end does
-     not like.  */
-  count = copy_rtx (desc->niter_expr);
+     not like.  If this succeeds, there is a chance that the loop
+     desc->niter_expr has been altered by the backend, so only extract
+     that data after the gen_doloop_end.  */
   start_label = block_label (desc->in_edge->dest);
   doloop_reg = gen_reg_rtx (mode);
   rtx_insn *doloop_seq = targetm.gen_doloop_end (doloop_reg, start_label);
 
+  max_cost
+    = COSTS_N_INSNS (param_max_iterations_computation_cost);
+  if (set_src_cost (desc->niter_expr, mode, optimize_loop_for_speed_p (loop))
+      > max_cost)
+    {
+      if (dump_file)
+	fprintf (dump_file,
+		 "Doloop: number of iterations too costly to compute.\n");
+      return false;
+    }
+
+  count = copy_rtx (desc->niter_expr);
   word_mode_size = GET_MODE_PRECISION (word_mode);
   word_mode_max = (HOST_WIDE_INT_1U << (word_mode_size - 1) << 1) - 1;
   if (! doloop_seq
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
index feaae7cc899..3941fe7a8b6 100644
--- a/gcc/testsuite/gcc.target/arm/lob.h
+++ b/gcc/testsuite/gcc.target/arm/lob.h
@@ -1,15 +1,131 @@ 
 #include <string.h>
-
+#include <stdint.h>
 /* Common code for lob tests.  */
 
 #define NO_LOB asm volatile ("@ clobber lr" : : : "lr" )
 
-#define N 10000
+#define N 100
+
+static void
+reset_data (int *a, int *b, int *c, int x)
+{
+  memset (a, -1, x * sizeof (*a));
+  memset (b, -1, x * sizeof (*b));
+  memset (c, 0, x * sizeof (*c));
+}
+
+static void
+reset_data8 (int8_t *a, int8_t *b, int8_t *c, int x)
+{
+  memset (a, -1, x * sizeof (*a));
+  memset (b, -1, x * sizeof (*b));
+  memset (c, 0, x * sizeof (*c));
+}
+
+static void
+reset_data16 (int16_t *a, int16_t *b, int16_t *c, int x)
+{
+  memset (a, -1, x * sizeof (*a));
+  memset (b, -1, x * sizeof (*b));
+  memset (c, 0, x * sizeof (*c));
+}
+
+static void
+reset_data32 (int32_t *a, int32_t *b, int32_t *c, int x)
+{
+  memset (a, -1, x * sizeof (*a));
+  memset (b, -1, x * sizeof (*b));
+  memset (c, 0, x * sizeof (*c));
+}
+
+static void
+reset_data64 (int64_t *a, int64_t *c, int x)
+{
+  memset (a, -1, x * sizeof (*a));
+  memset (c, 0, x * sizeof (*c));
+}
+
+static void
+check_plus (int *a, int *b, int *c, int x)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (i < x)
+	{
+	  if (c[i] != (a[i] + b[i])) abort ();
+	}
+      else
+	{
+	  if (c[i] != 0) abort ();
+	}
+    }
+}
+
+static void
+check_plus8 (int8_t *a, int8_t *b, int8_t *c, int x)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (i < x)
+	{
+	  if (c[i] != (a[i] + b[i])) abort ();
+	}
+      else
+	{
+	  if (c[i] != 0) abort ();
+	}
+    }
+}
+
+static void
+check_plus16 (int16_t *a, int16_t *b, int16_t *c, int x)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (i < x)
+	{
+	  if (c[i] != (a[i] + b[i])) abort ();
+	}
+      else
+	{
+	  if (c[i] != 0) abort ();
+	}
+    }
+}
+
+static void
+check_plus32 (int32_t *a, int32_t *b, int32_t *c, int x)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (i < x)
+	{
+	  if (c[i] != (a[i] + b[i])) abort ();
+	}
+      else
+	{
+	  if (c[i] != 0) abort ();
+	}
+    }
+}
 
 static void
-reset_data (int *a, int *b, int *c)
+check_memcpy64 (int64_t *a, int64_t *c, int x)
 {
-  memset (a, -1, N * sizeof (*a));
-  memset (b, -1, N * sizeof (*b));
-  memset (c, -1, N * sizeof (*c));
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (i < x)
+	{
+	  if (c[i] != a[i]) abort ();
+	}
+      else
+	{
+	  if (c[i] != 0) abort ();
+	}
+    }
 }
diff --git a/gcc/testsuite/gcc.target/arm/lob1.c b/gcc/testsuite/gcc.target/arm/lob1.c
index ba5c82cd55c..c8ce653a5c3 100644
--- a/gcc/testsuite/gcc.target/arm/lob1.c
+++ b/gcc/testsuite/gcc.target/arm/lob1.c
@@ -54,29 +54,18 @@  loop3 (int *a, int *b, int *c)
     } while (i < N);
 }
 
-void
-check (int *a, int *b, int *c)
-{
-  for (int i = 0; i < N; i++)
-    {
-      NO_LOB;
-      if (c[i] != a[i] + b[i])
-	abort ();
-    }
-}
-
 int
 main (void)
 {
-  reset_data (a, b, c);
+  reset_data (a, b, c, N);
   loop1 (a, b ,c);
-  check (a, b ,c);
-  reset_data (a, b, c);
+  check_plus (a, b, c, N);
+  reset_data (a, b, c, N);
   loop2 (a, b ,c);
-  check (a, b ,c);
-  reset_data (a, b, c);
+  check_plus (a, b, c, N);
+  reset_data (a, b, c, N);
   loop3 (a, b ,c);
-  check (a, b ,c);
+  check_plus (a, b, c, N);
 
   return 0;
 }
diff --git a/gcc/testsuite/gcc.target/arm/lob6.c b/gcc/testsuite/gcc.target/arm/lob6.c
index 17b6124295e..4fe116e2c2b 100644
--- a/gcc/testsuite/gcc.target/arm/lob6.c
+++ b/gcc/testsuite/gcc.target/arm/lob6.c
@@ -79,14 +79,14 @@  check (void)
 int
 main (void)
 {
-  reset_data (a1, b1, c1);
-  reset_data (a2, b2, c2);
+  reset_data (a1, b1, c1, N);
+  reset_data (a2, b2, c2, N);
   loop1 (a1, b1, c1);
   ref1 (a2, b2, c2);
   check ();
 
-  reset_data (a1, b1, c1);
-  reset_data (a2, b2, c2);
+  reset_data (a1, b1, c1, N);
+  reset_data (a2, b2, c2, N);
   loop2 (a1, b1, c1);
   ref2 (a2, b2, c2);
   check ();
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-compile-asm.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-compile-asm.c
new file mode 100644
index 00000000000..5ddd994e53d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-compile-asm.c
@@ -0,0 +1,561 @@ 
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-options "-O3 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <arm_mve.h>
+
+#define IMM 5
+
+#define TEST_COMPILE_IN_DLSTP_TERNARY(BITS, LANES, LDRSTRYTPE, TYPE, SIGN, NAME, PRED)				\
+void test_##NAME##PRED##_##SIGN##BITS (TYPE##BITS##_t *a, TYPE##BITS##_t *b,  TYPE##BITS##_t *c, int n)	\
+{											\
+  while (n > 0)										\
+    {											\
+      mve_pred16_t p = vctp##BITS##q (n);						\
+      TYPE##BITS##x##LANES##_t va = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (a, p);		\
+      TYPE##BITS##x##LANES##_t vb = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (b, p);		\
+      TYPE##BITS##x##LANES##_t vc = NAME##PRED##_##SIGN##BITS (va, vb, p);		\
+      vstr##LDRSTRYTPE##q_p_##SIGN##BITS (c, vc, p);					\
+      c += LANES;									\
+      a += LANES;									\
+      b += LANES;									\
+      n -= LANES;									\
+    }											\
+}
+
+#define TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY(BITS, LANES, LDRSTRYTPE, NAME, PRED)	\
+TEST_COMPILE_IN_DLSTP_TERNARY (BITS, LANES, LDRSTRYTPE, int, s, NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_TERNARY (BITS, LANES, LDRSTRYTPE, uint, u, NAME, PRED)
+
+#define TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY(NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY (8, 16, b, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY (16, 8, h, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY (32, 4, w, NAME, PRED)
+
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY (vaddq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY (vmulq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY (vsubq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY (vhaddq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY (vorrq, _x)
+
+
+#define TEST_COMPILE_IN_DLSTP_TERNARY_M(BITS, LANES, LDRSTRYTPE, TYPE, SIGN, NAME, PRED)				\
+void test_##NAME##PRED##_##SIGN##BITS (TYPE##BITS##x##LANES##_t __inactive, TYPE##BITS##_t *a, TYPE##BITS##_t *b,  TYPE##BITS##_t *c, int n)	\
+{											\
+  while (n > 0)										\
+    {											\
+      mve_pred16_t p = vctp##BITS##q (n);						\
+      TYPE##BITS##x##LANES##_t va = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (a, p);		\
+      TYPE##BITS##x##LANES##_t vb = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (b, p);		\
+      TYPE##BITS##x##LANES##_t vc = NAME##PRED##_##SIGN##BITS (__inactive, va, vb, p);		\
+      vstr##LDRSTRYTPE##q_p_##SIGN##BITS (c, vc, p);					\
+      c += LANES;									\
+      a += LANES;									\
+      b += LANES;									\
+      n -= LANES;									\
+    }											\
+}
+
+#define TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M(BITS, LANES, LDRSTRYTPE, NAME, PRED)	\
+TEST_COMPILE_IN_DLSTP_TERNARY_M (BITS, LANES, LDRSTRYTPE, int, s, NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_TERNARY_M (BITS, LANES, LDRSTRYTPE, uint, u, NAME, PRED)
+
+#define TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M(NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M (8, 16, b, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M (16, 8, h, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M (32, 4, w, NAME, PRED)
+
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M (vaddq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M (vmulq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M (vsubq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M (vhaddq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M (vorrq, _m)
+
+#define TEST_COMPILE_IN_DLSTP_TERNARY_N(BITS, LANES, LDRSTRYTPE, TYPE, SIGN, NAME, PRED)	\
+void test_##NAME##PRED##_n_##SIGN##BITS (TYPE##BITS##_t *a,  TYPE##BITS##_t *c, int n)	\
+{											\
+  while (n > 0)										\
+    {											\
+      mve_pred16_t p = vctp##BITS##q (n);						\
+      TYPE##BITS##x##LANES##_t va = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (a, p);		\
+      TYPE##BITS##x##LANES##_t vc = NAME##PRED##_n_##SIGN##BITS (va, IMM, p);		\
+      vstr##LDRSTRYTPE##q_p_##SIGN##BITS (c, vc, p);					\
+      c += LANES;									\
+      a += LANES;									\
+      n -= LANES;									\
+    }											\
+}
+
+#define TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_N(BITS, LANES, LDRSTRYTPE, NAME, PRED)	\
+TEST_COMPILE_IN_DLSTP_TERNARY_N (BITS, LANES, LDRSTRYTPE, int, s, NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_TERNARY_N (BITS, LANES, LDRSTRYTPE, uint, u, NAME, PRED)
+
+#define TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N(NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_N (8, 16, b, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_N (16, 8, h, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_N (32, 4, w, NAME, PRED)
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vaddq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vmulq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vsubq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vhaddq, _x)
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vbrsrq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vshlq, _x)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_N (vshrq, _x)
+
+#define TEST_COMPILE_IN_DLSTP_TERNARY_M_N(BITS, LANES, LDRSTRYTPE, TYPE, SIGN, NAME, PRED)	\
+void test_##NAME##PRED##_n_##SIGN##BITS (TYPE##BITS##x##LANES##_t __inactive, TYPE##BITS##_t *a,  TYPE##BITS##_t *c, int n)	\
+{											\
+  while (n > 0)										\
+    {											\
+      mve_pred16_t p = vctp##BITS##q (n);						\
+      TYPE##BITS##x##LANES##_t va = vldr##LDRSTRYTPE##q_z_##SIGN##BITS (a, p);		\
+      TYPE##BITS##x##LANES##_t vc = NAME##PRED##_n_##SIGN##BITS (__inactive, va, IMM, p);		\
+      vstr##LDRSTRYTPE##q_p_##SIGN##BITS (c, vc, p);					\
+      c += LANES;									\
+      a += LANES;									\
+      n -= LANES;									\
+    }											\
+}
+
+#define TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M_N(BITS, LANES, LDRSTRYTPE, NAME, PRED)	\
+TEST_COMPILE_IN_DLSTP_TERNARY_M_N (BITS, LANES, LDRSTRYTPE, int, s, NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_TERNARY_M_N (BITS, LANES, LDRSTRYTPE, uint, u, NAME, PRED)
+
+#define TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N(NAME, PRED)			\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M_N (8, 16, b, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M_N (16, 8, h, NAME, PRED)				\
+TEST_COMPILE_IN_DLSTP_SIGNED_UNSIGNED_TERNARY_M_N (32, 4, w, NAME, PRED)
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vaddq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vmulq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vsubq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vhaddq, _m)
+
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vbrsrq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vshlq, _m)
+TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY_M_N (vshrq, _m)
+
+/* Now test some more configurations.  */
+
+/* Using a >=1 condition.  */
+void test1 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n >= 1)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c+=4;
+      a+=4;
+      b+=4;
+      n-=4;
+    }
+}
+
+/* Test a for loop format of decrementing to zero */
+int32_t a[] = {0, 1, 2, 3, 4, 5, 6, 7};
+void test2 (int32_t *b, int num_elems)
+{
+    for (int i = num_elems; i > 0; i-= 4)
+    {
+        mve_pred16_t p = vctp32q (i);
+        int32x4_t va = vldrwq_z_s32 (&(a[i]), p);
+        vstrwq_p_s32 (b + i, va, p);
+    }
+}
+
+/* Iteration counter counting up to num_iter.  */
+void test3 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int num_iter = (n + 15)/16;
+    for (int i = 0; i < num_iter; i++)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        uint8x16_t vb = vldrbq_z_u8 (b, p);
+        uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+        vstrbq_p_u8 (c, vc, p);
+        n-=16;
+    }
+}
+
+/* Iteration counter counting down from num_iter.  */
+void test4 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int num_iter = (n + 15)/16;
+    for (int i = num_iter; i > 0; i--)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        uint8x16_t vb = vldrbq_z_u8 (b, p);
+        uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+        vstrbq_p_u8 (c, vc, p);
+        n-=16;
+    }
+}
+
+/* Using an unpredicated arithmetic instruction within the loop.  */
+void test5 (uint8_t *a, uint8_t *b, uint8_t *c,  uint8_t *d, int n)
+{
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        uint8x16_t vb = vldrbq_u8 (b);
+	/* Is affected by implicit predication, because vb also
+	came from an unpredicated load, but there is no functional
+	problem, because the result is used in a predicated store.  */ 
+        uint8x16_t vc = vaddq_u8 (va, vb);
+        uint8x16_t vd = vaddq_x_u8 (va, vb, p);
+        vstrbq_p_u8 (c, vc, p);
+        vstrbq_p_u8 (d, vd, p);
+        n-=16;
+    }
+}
+
+/* Using a different VPR value for one instruction in the loop.  */
+void test6 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p1)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using another VPR value in the loop, with a vctp.
+   The doloop logic will always try to do the transform on the first
+   vctp it encounters, so this is still expected to work.  */
+void test7 (int32_t *a, int32_t *b, int32_t *c, int n, int g)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      mve_pred16_t p1 = vctp32q (g);
+      int32x4_t vb = vldrwq_z_s32 (b, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using a different VPR value in the loop, with a vctp,
+   but this time the p1 will also change in every loop (still fine)  */
+void test8 (int32_t *a, int32_t *b, int32_t *c, int n, int g)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      mve_pred16_t p1 = vctp32q (g);
+      int32x4_t vb = vldrwq_z_s32 (b, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+      g++;
+    }
+}
+
+/* Generating and using a different VPR value in the loop, with a vctp_m
+   that is independent of the loop vctp VPR.  */
+void test9 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p1)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      mve_pred16_t p2 = vctp32q_m (n, p1);
+      int32x4_t vb = vldrwq_z_s32 (b, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p2);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using a different VPR value in the loop,
+   with a vctp_m that is tied to the base vctp VPR.  This
+   is still fine, because the vctp_m will be transformed
+   into a vctp and be implicitly predicated.  */
+void test10 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      mve_pred16_t p1 = vctp32q_m (n, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p1);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using a different VPR value in the loop, with a vcmp.  */
+void test11 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      mve_pred16_t p1 = vcmpeqq_s32 (va, vb);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p1);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using a different VPR value in the loop, with a vcmp_m.  */
+void test12 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p1)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      mve_pred16_t p2 = vcmpeqq_m_s32 (va, vb, p1);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p2);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Generating and using a different VPR value in the loop, with a vcmp_m 
+   that is tied to the base vctp VPR (same as above, this will be turned
+   into a vcmp and be implicitly predicated).  */
+void test13 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p1)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      mve_pred16_t p2 = vcmpeqq_m_s32 (va, vb, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p2);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using an unpredicated op with a scalar output, where the result is valid
+   outside the bb.  This is valid, because all the inputs to the unpredicated
+   op are correctly predicated.  */
+uint8_t test14 (uint8_t *a, uint8_t *b, uint8_t *c, int n, uint8x16_t vx)
+{
+    uint8_t sum = 0;
+    while (n > 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_m_u8 (vx, va, vb, p);
+       sum += vaddvq_u8 (vc);
+       a += 16;
+       b += 16;
+       n -= 16;
+    }
+    return sum;
+}
+
+/* Same as above, but with another scalar op between the unpredicated op and
+   the scalar op outside the loop.  */
+uint8_t test15 (uint8_t *a, uint8_t *b, uint8_t *c, int n, uint8x16_t vx, int g)
+{
+    uint8_t sum = 0;
+    while (n > 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_m_u8 (vx, va, vb, p);
+       sum += vaddvq_u8 (vc);
+       sum += g;
+       a += 16;
+       b += 16;
+       n -= 16;
+    }
+    return sum;
+}
+
+/* Using an unpredicated vcmp to generate a new predicate value in the
+   loop and then using it in a predicated store insn.  */
+void test16 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_s32 (b);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      mve_pred16_t p1 = vcmpeqq_s32 (va, vc);
+      vstrwq_p_s32 (c, vc, p1);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using a predicated vcmp to generate a new predicate value in the
+   loop and then using it in a predicated store insn.  */
+void test17 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_s32 (va, vb);
+      mve_pred16_t p1 = vcmpeqq_m_s32 (va, vc, p);
+      vstrwq_p_s32 (c, vc, p1);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using an across-vector unpredicated instruction in a valid way.
+   This tests that "vc" has correctly masked the risky "vb".  */
+uint16_t test18 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16x8_t vb = vldrhq_u16 (b);
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      uint16x8_t vc = vaddq_x_u16 (va, vb, p);
+      res = vaddvq_u16 (vc);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+/* Using an across-vector unpredicated instruction with a scalar from outside the loop.  */
+uint16_t test19 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16x8_t vb = vldrhq_u16 (b);
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      uint16x8_t vc = vaddq_x_u16 (va, vb, p);
+      res = vaddvaq_u16 (res, vc);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+/* Using an across-vector predicated instruction in a valid way.  */
+uint16_t  test20 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t vb = vldrhq_u16 (b);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      res = vaddvaq_p_u16 (res, vb, p);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+/* Using an across-vector predicated instruction in a valid way.  */
+uint16_t  test21 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t vb = vldrhq_u16 (b);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      res++;
+      res = vaddvaq_p_u16 (res, vb, p);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+int test22 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        res = vmaxvq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+int test23 (int8_t *a, int8_t *b, int8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        int8x16_t va = vldrbq_z_s8 (a, p);
+        res = vmaxavq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+/* The final number of DLSTPs currently is calculated by the number of
+  `TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY.*` macros * 6 + 23.  */
+/* { dg-final { scan-assembler-times {\tdlstp} 167 } } */
+/* { dg-final { scan-assembler-times {\tletp} 167 } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8-run.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8-run.c
new file mode 100644
index 00000000000..6966a396604
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8-run.c
@@ -0,0 +1,44 @@ 
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-require-effective-target arm_mve_hw } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+#include "dlstp-int16x8.c"
+
+int main ()
+{
+  int i;
+  int16_t temp1[N];
+  int16_t temp2[N];
+  int16_t temp3[N];
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 0);
+  check_plus16 (temp1, temp2, temp3, 0);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 1);
+  check_plus16 (temp1, temp2, temp3, 1);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 7);
+  check_plus16 (temp1, temp2, temp3, 7);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 8);
+  check_plus16 (temp1, temp2, temp3, 8);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 9);
+  check_plus16 (temp1, temp2, temp3, 9);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 16);
+  check_plus16 (temp1, temp2, temp3, 16);
+
+  reset_data16 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 17);
+  check_plus16 (temp1, temp2, temp3, 17);
+
+  reset_data16 (temp1, temp2, temp3, N);
+}
+
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8.c
new file mode 100644
index 00000000000..33632c5f14d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int16x8.c
@@ -0,0 +1,31 @@ 
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <arm_mve.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "../lob.h"
+
+void  __attribute__ ((noinline)) test (int16_t *a, int16_t *b, int16_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      int16x8_t va = vldrhq_z_s16 (a, p);
+      int16x8_t vb = vldrhq_z_s16 (b, p);
+      int16x8_t vc = vaddq_x_s16 (va, vb, p);
+      vstrhq_p_s16 (c, vc, p);
+      c+=8;
+      a+=8;
+      b+=8;
+      n-=8;
+    }
+}
+
+/* { dg-final { scan-assembler-times {\tdlstp.16} 1 } } */
+/* { dg-final { scan-assembler-times {\tletp} 1 } } */
+/* { dg-final { scan-assembler-not "\tvctp" } } */
+/* { dg-final { scan-assembler-not "\tvpst" } } */
+/* { dg-final { scan-assembler-not "p0" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4-run.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4-run.c
new file mode 100644
index 00000000000..6833dddde92
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4-run.c
@@ -0,0 +1,45 @@ 
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-require-effective-target arm_mve_hw } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include "dlstp-int32x4.c"
+
+int main ()
+{
+  int i;
+  int32_t temp1[N];
+  int32_t temp2[N];
+  int32_t temp3[N];
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 0);
+  check_plus32 (temp1, temp2, temp3, 0);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 1);
+  check_plus32 (temp1, temp2, temp3, 1);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 3);
+  check_plus32 (temp1, temp2, temp3, 3);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 4);
+  check_plus32 (temp1, temp2, temp3, 4);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 5);
+  check_plus32 (temp1, temp2, temp3, 5);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 8);
+  check_plus32 (temp1, temp2, temp3, 8);
+
+  reset_data32 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 9);
+  check_plus32 (temp1, temp2, temp3, 9);
+
+  reset_data32 (temp1, temp2, temp3, N);
+}
+
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4.c
new file mode 100644
index 00000000000..5d09f784b77
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int32x4.c
@@ -0,0 +1,31 @@ 
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <arm_mve.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "../lob.h"
+
+void  __attribute__ ((noinline)) test (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c+=4;
+      a+=4;
+      b+=4;
+      n-=4;
+    }
+}
+
+/* { dg-final { scan-assembler-times {\tdlstp.32} 1 } } */
+/* { dg-final { scan-assembler-times {\tletp} 1 } } */
+/* { dg-final { scan-assembler-not "\tvctp" } } */
+/* { dg-final { scan-assembler-not "\tvpst" } } */
+/* { dg-final { scan-assembler-not "p0" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2-run.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2-run.c
new file mode 100644
index 00000000000..cc0b9ce7ee9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2-run.c
@@ -0,0 +1,48 @@ 
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-require-effective-target arm_mve_hw } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include "dlstp-int64x2.c"
+
+int main ()
+{
+  int i;
+  int64_t temp1[N];
+  int64_t temp3[N];
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 0);
+  check_memcpy64 (temp1, temp3, 0);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 1);
+  check_memcpy64 (temp1, temp3, 1);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 2);
+  check_memcpy64 (temp1, temp3, 2);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 3);
+  check_memcpy64 (temp1, temp3, 3);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 4);
+  check_memcpy64 (temp1, temp3, 4);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 5);
+  check_memcpy64 (temp1, temp3, 5);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 6);
+  check_memcpy64 (temp1, temp3, 6);
+
+  reset_data64  (temp1, temp3, N);
+  test (temp1, temp3, 7);
+  check_memcpy64 (temp1, temp3, 7);
+
+  reset_data64  (temp1, temp3, N);
+}
+
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2.c
new file mode 100644
index 00000000000..21e882424ec
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int64x2.c
@@ -0,0 +1,28 @@ 
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <arm_mve.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "../lob.h"
+
+void  __attribute__ ((noinline)) test (int64_t *a, int64_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp64q (n);
+      int64x2_t va = vldrdq_gather_offset_z_s64 (a, vcreateq_u64 (0, 8), p);
+      vstrdq_scatter_offset_p_s64 (c, vcreateq_u64 (0, 8), va, p);
+      c+=2;
+      a+=2;
+      n-=2;
+    }
+}
+
+/* { dg-final { scan-assembler-times {\tdlstp.64} 1 } } */
+/* { dg-final { scan-assembler-times {\tletp} 1 } } */
+/* { dg-final { scan-assembler-not "\tvctp" } } */
+/* { dg-final { scan-assembler-not "\tvpst" } } */
+/* { dg-final { scan-assembler-not "p0" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-int8x16.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-int8x16.c
new file mode 100644
index 00000000000..8ea181c82d4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-int8x16.c
@@ -0,0 +1,69 @@ 
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-require-effective-target arm_mve_hw } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <arm_mve.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include "../lob.h"
+
+void  __attribute__ ((noinline)) test (int8_t *a, int8_t *b, int8_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp8q (n);
+      int8x16_t va = vldrbq_z_s8 (a, p);
+      int8x16_t vb = vldrbq_z_s8 (b, p);
+      int8x16_t vc = vaddq_x_s8 (va, vb, p);
+      vstrbq_p_s8 (c, vc, p);
+      c+=16;
+      a+=16;
+      b+=16;
+      n-=16;
+    }
+}
+
+int main ()
+{
+  int i;
+  int8_t temp1[N];
+  int8_t temp2[N];
+  int8_t temp3[N];
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 0);
+  check_plus8 (temp1, temp2, temp3, 0);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 1);
+  check_plus8 (temp1, temp2, temp3, 1);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 15);
+  check_plus8 (temp1, temp2, temp3, 15);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 16);
+  check_plus8 (temp1, temp2, temp3, 16);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 17);
+  check_plus8 (temp1, temp2, temp3, 17);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 32);
+  check_plus8 (temp1, temp2, temp3, 32);
+
+  reset_data8 (temp1, temp2, temp3, N);
+  test (temp1, temp2, temp3, 33);
+  check_plus8 (temp1, temp2, temp3, 33);
+
+  reset_data8 (temp1, temp2, temp3, N);
+}
+
+/* { dg-final { scan-assembler-times {\tdlstp.8} 1 } } */
+/* { dg-final { scan-assembler-times {\tletp} 1 } } */
+/* { dg-final { scan-assembler-not "\tvctp" } } */
+/* { dg-final { scan-assembler-not "\tvpst" } } */
+/* { dg-final { scan-assembler-not "p0" } } */
diff --git a/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c b/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c
new file mode 100644
index 00000000000..f7c3e04f883
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/mve/dlstp-invalid-asm.c
@@ -0,0 +1,391 @@ 
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-options "-O3 -save-temps" } */
+/* { dg-add-options arm_v8_1m_mve } */
+
+#include <limits.h>
+#include <arm_mve.h>
+
+/* Terminating on a non-zero number of elements.  */
+void test0 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    while (n > 1)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+       vstrbq_p_u8 (c, vc, p);
+       n -= 16;
+    }
+}
+
+/* Terminating on n >= 0.  */
+void test1 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    while (n >= 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+       vstrbq_p_u8 (c, vc, p);
+       n -= 16;
+    }
+}
+
+/* Similar, terminating on a non-zero number of elements, but in a for loop
+   format.  */
+int32_t a[] = {0, 1, 2, 3, 4, 5, 6, 7};
+void test2 (int32_t *b, int num_elems)
+{
+    for (int i = num_elems; i >= 2; i-= 4)
+    {
+       mve_pred16_t p = vctp32q (i);
+       int32x4_t va = vldrwq_z_s32 (&(a[i]), p);
+       vstrwq_p_s32 (b + i, va, p);
+    }
+}
+
+/* Iteration counter counting up to num_iter, with a non-zero starting num.  */
+void test3 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int num_iter = (n + 15)/16;
+    for (int i = 1; i < num_iter; i++)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+       vstrbq_p_u8 (c, vc, p);
+       n -= 16;
+    }
+}
+
+/* Iteration counter counting up to num_iter, with a larger increment  */
+void test4 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int num_iter = (n + 15)/16;
+    for (int i = 0; i < num_iter; i+=2)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+       vstrbq_p_u8 (c, vc, p);
+       n -= 16;
+    }
+}
+
+/* Using an unpredicated store instruction within the loop.  */
+void test5 (uint8_t *a, uint8_t *b, uint8_t *c,  uint8_t *d, int n)
+{
+    while (n > 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_u8 (va, vb);
+       uint8x16_t vd = vaddq_x_u8 (va, vb, p);
+       vstrbq_u8 (d, vd);
+       n -= 16;
+    }
+}
+
+/* Using an unpredicated store outside the loop.  */
+void test6 (uint8_t *a, uint8_t *b, uint8_t *c, int n, uint8x16_t vx)
+{
+    while (n > 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_z_u8 (b, p);
+       uint8x16_t vc = vaddq_m_u8 (vx, va, vb, p);
+       vx = vaddq_u8 (vx, vc);
+       a += 16;
+       b += 16;
+       n -= 16;
+    }
+    vstrbq_u8 (c, vx);
+}
+
+/* Using a VPR that gets modified within the loop.  */
+void test9 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      p++;
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using a VPR that gets re-generated within the loop.  */
+void test10 (int32_t *a, int32_t *b, int32_t *c, int n)
+{
+  mve_pred16_t p = vctp32q (n);
+  while (n > 0)
+    {
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      p = vctp32q (n);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using vctp32q_m instead of vctp32q.  */
+void test11 (int32_t *a, int32_t *b, int32_t *c, int n, mve_pred16_t p0)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q_m (n, p0);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using an unpredicated op with a scalar output, where the result is valid
+   outside the bb.  This is invalid, because one of the inputs to the
+   unpredicated op is also unpredicated.  */
+uint8_t test12 (uint8_t *a, uint8_t *b, uint8_t *c, int n, uint8x16_t vx)
+{
+    uint8_t sum = 0;
+    while (n > 0)
+    {
+       mve_pred16_t p = vctp8q (n);
+       uint8x16_t va = vldrbq_z_u8 (a, p);
+       uint8x16_t vb = vldrbq_u8 (b);
+       uint8x16_t vc = vaddq_u8 (va, vb);
+       sum += vaddvq_u8 (vc);
+       a += 16;
+       b += 16;
+       n -= 16;
+    }
+    return sum;
+}
+
+/* Using an unpredicated vcmp to generate a new predicate value in the
+   loop and then using that VPR to predicate a store insn.  */
+void test13 (int32_t *a, int32_t *b, int32x4_t vc, int32_t *c, int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_s32 (a);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_s32 (va, vb);
+      mve_pred16_t p1 = vcmpeqq_s32 (va, vc);
+      vstrwq_p_s32 (c, vc, p1);
+      c += 4;
+      a += 4;
+      b += 4;
+      n -= 4;
+    }
+}
+
+/* Using an across-vector unpredicated instruction. "vb" is the risk.  */
+uint16_t test14 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16x8_t vb = vldrhq_u16 (b);
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      vb = vaddq_u16 (va, vb);
+      res = vaddvq_u16 (vb);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+/* Using an across-vector unpredicated instruction. "vc" is the risk. */
+uint16_t test15 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16x8_t vb = vldrhq_u16 (b);
+  uint16_t res = 0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      uint16x8_t vc = vaddq_u16 (va, vb);
+      res = vaddvaq_u16 (res, vc);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+uint16_t test16 (uint16_t *a, uint16_t *b,  uint16_t *c, int n)
+{
+  uint16_t res =0;
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp16q (n);
+      uint16x8_t vb = vldrhq_u16 (b);
+      uint16x8_t va = vldrhq_z_u16 (a, p);
+      res = vaddvaq_u16 (res, vb);
+      res = vaddvaq_p_u16 (res, va, p);
+      c += 8;
+      a += 8;
+      b += 8;
+      n -= 8;
+    }
+  return res;
+}
+
+int test17 (int8_t *a, int8_t *b, int8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        int8x16_t va = vldrbq_z_s8 (a, p);
+        res = vmaxvq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+
+
+int test18 (int8_t *a, int8_t *b, int8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        int8x16_t va = vldrbq_z_s8 (a, p);
+        res = vminvq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+int test19 (int8_t *a, int8_t *b, int8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        int8x16_t va = vldrbq_z_s8 (a, p);
+        res = vminavq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+int test20 (uint8_t *a, uint8_t *b, uint8_t *c, int n)
+{
+    int res = 0;
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        res = vminvq (res, va);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+uint8x16_t test21 (uint8_t *a, uint32_t *b, int n, uint8x16_t res)
+{
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        res = vshlcq_u8 (va, b, 1);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+int8x16_t test22 (int8_t *a, int32_t *b, int n, int8x16_t res)
+{
+    while (n > 0)
+    {
+        mve_pred16_t p = vctp8q (n);
+        int8x16_t va = vldrbq_z_s8 (a, p);
+        res = vshlcq_s8 (va, b, 1);
+        n-=16;
+        a+=16;
+    }
+    return res;
+}
+
+/* Using an unsigned number of elements to count down from, with a >0*/
+void test23 (int32_t *a, int32_t *b, int32_t *c, unsigned int n)
+{
+  while (n > 0)
+    {
+      mve_pred16_t p = vctp32q (n);
+      int32x4_t va = vldrwq_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      int32x4_t vc = vaddq_x_s32 (va, vb, p);
+      vstrwq_p_s32 (c, vc, p);
+      c+=4;
+      a+=4;
+      b+=4;
+      n-=4;
+    }
+}
+
+/* Using an unsigned number of elements to count up to, with a <n*/
+void test24 (uint8_t *a, uint8_t *b, uint8_t *c, unsigned int n)
+{
+    for (int i = 0; i < n; i+=16)
+    {
+        mve_pred16_t p = vctp8q (n-i);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        uint8x16_t vb = vldrbq_z_u8 (b, p);
+        uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+        vstrbq_p_u8 (c, vc, p);
+        n-=16;
+    }
+}
+
+
+/* Using an unsigned number of elements to count up to, with a <=n*/
+void test25 (uint8_t *a, uint8_t *b, uint8_t *c, unsigned int n)
+{
+    for (int i = 1; i <= n; i+=16)
+    {
+        mve_pred16_t p = vctp8q (n-i+1);
+        uint8x16_t va = vldrbq_z_u8 (a, p);
+        uint8x16_t vb = vldrbq_z_u8 (b, p);
+        uint8x16_t vc = vaddq_x_u8 (va, vb, p);
+        vstrbq_p_u8 (c, vc, p);
+        n-=16;
+    }
+}
+
+/* { dg-final { scan-assembler-not "\tdlstp" } } */
+/* { dg-final { scan-assembler-not "\tletp" } } */
\ No newline at end of file