diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index aea472bfbb9deaa8e925756963c7c5cc6fdc0d09..10ffc713f7744252655e9d78510df5cef98c2355 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -65,7 +65,7 @@ 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 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 1d285051fa6d8e6c05813801eb678e58da25714d..d4ac04e095f01f42c1c4611074c3499a01242716 100644
--- a/gcc/config/arm/arm.cc
+++ b/gcc/config/arm/arm.cc
@@ -472,6 +472,9 @@ static const struct attribute_spec arm_attribute_table[] =
 #undef TARGET_SCHED_REORDER
 #define TARGET_SCHED_REORDER arm_sched_reorder
 
+#undef TARGET_ALLOW_ELEMENTWISE_DOLOOP_P
+#define TARGET_ALLOW_ELEMENTWISE_DOLOOP_P arm_allow_elementwise_doloop_p
+
 #undef TARGET_REGISTER_MOVE_COST
 #define TARGET_REGISTER_MOVE_COST arm_register_move_cost
 
@@ -33067,7 +33070,7 @@ arm_block_set_vect (rtx dstbase,
     return arm_block_set_unaligned_vect (dstbase, length, value, align);
 }
 
-/* Expand string store operation.  Firstly we try to do that by using
+/* Expand string store operation.  First we try to do that by using
    vectorization instructions, then try with ARM unaligned access and
    double-word store if profitable.  OPERANDS[0] is the destination,
    OPERANDS[1] is the number of bytes, operands[2] is the value to
@@ -34395,8 +34398,563 @@ arm_target_insn_ok_for_lob (rtx insn)
 
   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_succ_edge (bb)->dest == single_pred_edge (bb)->src;
+}
+
+static int
+arm_mve_get_vctp_lanes (rtx x)
+{
+  if (GET_CODE (x) == SET && GET_CODE (XEXP (x, 1)) == UNSPEC
+      && XINT (XEXP (x, 1), 1) == VCTP)
+    {
+      switch (GET_MODE (XEXP (x, 1)))
+	{
+	  case V16BImode:
+	    return 16;
+	  case V8BImode:
+	    return 8;
+	  case V4BImode:
+	    return 4;
+	  case V2QImode:
+	    return 2;
+	  default:
+	    break;
+	}
+    }
+  return 0;
+}
+
+/* Check if an 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 occurance 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
+			|| recog_data.operand_type[op] == OP_INOUT))
+	continue;
+      else if (type == 2 && (recog_data.operand_type[op] == OP_IN
+			     || recog_data.operand_type[op] == OP_INOUT))
+	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;
+}
+
+static rtx
+ALWAYS_INLINE ATTRIBUTE_UNUSED
+arm_get_required_vpr_reg_ret_val (rtx_insn *insn)
+{
+  return arm_get_required_vpr_reg (insn, 2);
+}
+
+static rtx
+ALWAYS_INLINE
+arm_get_required_vpr_reg_param (rtx_insn *insn)
+{
+  return arm_get_required_vpr_reg (insn, 1);
+}
+
+/* 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 any MVE instructions.  */
+  FOR_BB_INSNS (bb, insn)
+    if (INSN_P (insn))
+      if (arm_mve_get_vctp_lanes (PATTERN (insn)) != 0)
+	return insn;
+  return NULL;
+}
+
+/* Recursively 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., recursively) were affected by implicit VPT
+   predication of an MVE_VPT_UNPREDICATED_INSN_P in a dlstp/letp loop.  */
+
+static bool
+arm_mve_check_df_for_implic_predic (rtx_insn *insn, rtx_insn* loop_vctp,
+				    rtx vctp_vpr_generated)
+{
+  rtx insn_vpr_reg_operand = NULL_RTX;
+
+  /* Exit the recursion with a "true" when we find an unpredicated insn, or with
+     a false if we find the dlstp/letp loop vctp or a correctly dlstp/letp
+     predicated insn.  */
+  if (MVE_VPT_UNPREDICATED_INSN_P (insn) && insn != loop_vctp)
+    return true;
+  else if (insn == loop_vctp
+	   || ((insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+	       && rtx_equal_p (vctp_vpr_generated, insn_vpr_reg_operand)))
+    return false;
+
+  /* For each USE in the instruction we are called for, we will loop backwards
+     up the BB to try and find if it was DEF-ed within the dlstp/letp loop.
+     If we do find such a DEF, then recurse on it's INSN.  The intention here
+     is find if any of the inputs to the current instruction were affected by
+     implicit predication by being MVE_VPT_UNPREDICATED_INSN_Ps in a dlstp/letp
+     loop.  */
+  df_ref insn_uses = NULL;
+  FOR_EACH_INSN_USE (insn_uses, insn)
+  {
+    /* Starting from the current insn, scan backwards through the insn chain
+       until BB_HEAD: "for each insn in the BB prior to the current one".  */
+    rtx_insn *prev_insn = NULL;
+    for (prev_insn = insn;
+	 prev_insn && prev_insn != PREV_INSN (BB_HEAD (BLOCK_FOR_INSN (insn)));
+	 prev_insn = PREV_INSN (prev_insn))
+      {
+	/* Look at all the DEFs of that previous insn: if one of them is on
+	   the same REG as our current insn, then recurse in order 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)
+	      && insn != prev_insn
+	      && BLOCK_FOR_INSN (insn) == BLOCK_FOR_INSN (prev_insn)
+	      && arm_mve_check_df_for_implic_predic (prev_insn,
+						     loop_vctp,
+						     vctp_vpr_generated))
+	    return true;
+	}
+      }
+  }
+  return false;
+}
+
+/* Attempt to transform the loop contents of loop basic block from VPT
+   predicated insns into unpredicated insns for a dlstp/letp loop.  */
+
+rtx
+arm_attempt_dlstp_transform (rtx label)
+{
+  int decrementnum;
+  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 GEN_INT (1);
+  basic_block pre_loop_bb1 = loop_preheader_edge (body->loop_father)->src;
+  basic_block pre_loop_bb2 = pre_loop_bb1->prev_bb;
+  rtx count = simple_loop_desc (body->loop_father)->niter_expr;
+  rtx shift_expr = NULL_RTX;
+  rtx initial_compare = NULL_RTX;
+
+  /* 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 GEN_INT (1);
+
+  /* Additionally, the iteration counter must only get decremented by the
+     number of MVE lanes (as per the data type).
+     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;
+	   }
+
+     These can be verified through the "count" variable in the middle-end
+     (a.k.a. get_simple_loop_desc (loop)->desc->niter_expr).  This is the
+     expression used to calculate the number of iterations that the loop would
+     execute for a standard dls/le loop.
+
+     For dlstp/letp we only support cases where this is a power of 2, so from
+     "count" we want to extract something like:
+	( [l/a] shiftrt: (x) (const_int y))
+     For loops of form A), "count" is already a shiftrt expression.
+     For loops of form B), "count" gets given as:
+	(plus: (not (i)) (num_of_iters))
+     with setup happening in a previous basic block.  Here we need to verify:
+       * That i is _always_ initialized to (const_int 0)
+       * That num_of_iters is a shiftrt expression.
+  */
+  if (GET_CODE (count) == LSHIFTRT
+      || GET_CODE (count) == ASHIFTRT)
+    {
+      shift_expr = count;
+      /* In this situation where we are looping on a decreasing number of
+	 elements, a dlstp/letp loop can only work if the looping ends when the
+	 element counter reaches zero and not some other value (e.g. n > 0
+	 works, not n > 1), or we can incorrectly end up running one additional
+	 iteration.  To by-pass any hoisting that the compiler may have done
+	 with the first arg to `count`, we can instead look at the bb before
+	 the loop preheader: this should end with a cmp+jump pair, where the
+	 cmp needs to be: (const_int 0).  */
+      if (!pre_loop_bb2 || !BB_END (pre_loop_bb2)
+	  || !prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb2))
+	  || !INSN_P (prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb2))))
+	return GEN_INT (1);
+      else
+	initial_compare
+	    = PATTERN (prev_nonnote_nondebug_insn_bb (BB_END (pre_loop_bb2)));
+
+      if (!(initial_compare && GET_CODE (initial_compare) == SET
+	    && cc_register (XEXP (initial_compare, 0), VOIDmode)
+	    && GET_CODE (XEXP (initial_compare, 1)) == COMPARE
+	    && CONST_INT_P (XEXP (XEXP (initial_compare, 1), 1))
+	    && INTVAL (XEXP (XEXP (initial_compare, 1), 1)) == 0))
+	return GEN_INT (1);
+    }
+  else if (GET_CODE (count) == PLUS)
+    {
+      if (!(GET_CODE (XEXP (count, 0)) == NOT
+	    && REG_P (XEXP (XEXP (count, 0), 0)) && REG_P (XEXP (count, 1))))
+	return GEN_INT (1);
+      else
+	{
+	  /* Verify the first argument to the plus.  */
+	  rtx loop_counter = XEXP (XEXP (count, 0), 0);
+	  df_ref loop_counter_init_def = NULL;
+	  loop_counter_init_def
+	      = df_bb_regno_last_def_find (pre_loop_bb1, REGNO (loop_counter));
+	  rtx loop_counter_init
+	      = PATTERN (DF_REF_INSN (loop_counter_init_def));
+	  if (!(loop_counter_init_def && GET_CODE (loop_counter_init) == SET
+		&& CONST_INT_P (XEXP (loop_counter_init, 1))
+		&& INTVAL (XEXP (loop_counter_init, 1)) == 0))
+	    return GEN_INT (1);
+
+	  /* Verify the second argument to the plus.  */
+	  rtx count_max = XEXP (count, 1);
+	  df_ref counter_max_def = NULL;
+	  counter_max_def = DF_REG_DEF_CHAIN (REGNO (count_max));
+	  if (counter_max_def
+	      && (GET_CODE (XEXP (single_set (DF_REF_INSN (counter_max_def)),
+				  1))
+		      == LSHIFTRT
+		  || GET_CODE (
+			 XEXP (single_set (DF_REF_INSN (counter_max_def)), 1))
+			 == ASHIFTRT))
+	    {
+	      shift_expr
+		  = XEXP (single_set (DF_REF_INSN (counter_max_def)), 1);
+	    }
+	  else
+	    return GEN_INT (1);
+	}
+    }
+  else
+    return GEN_INT (1);
+
+  /* Check the validity of the shift: the second operand needs to be a
+     constant.  */
+  if (!CONSTANT_P (XEXP (shift_expr, 1)))
+    return GEN_INT (1);
+  /* Extract the loop decrement from the [A/L]SHIFTR 2nd operand of count.  */
+  decrementnum = (1 << (INTVAL (XEXP (shift_expr, 1))));
+  /* Ensure it matches the number of lanes of the vctp instruction.  */
+  if (decrementnum != arm_mve_get_vctp_lanes (PATTERN (vctp_insn)))
+    return GEN_INT (1);
+
+  rtx_insn *insn = 0;
+  rtx_insn *cur_insn = 0;
+  rtx_insn *seq;
+  rtx vctp_vpr_generated = NULL_RTX;
+
+  /* Scan through the insns in the loop bb and emit the transformed bb
+     insns to a sequence.  */
+  start_sequence ();
+  FOR_BB_INSNS (body, insn)
+    {
+      rtx insn_vpr_reg_operand = NULL_RTX;
+      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 GEN_INT (1);
+	}
+      /* When we find the vctp instruction: This may be followed by
+      a zero-extend insn to SImode.  If it is, then save the
+      zero-extended REG into vctp_vpr_generated.  If there is no
+      zero-extend, then store the raw output of the vctp.
+      For any VPT-predicated instructions we need to ensure that
+      the VPR they use is the same as the one given here and
+      they often consume the output of a subreg of the SImode
+      zero-extended VPR-reg.  As a result, comparing against the
+      output of the zero-extend is more likely to succeed.
+      This code also guarantees to us that the vctp comes before
+      any instructions that use the VPR within the loop, for the
+      dlstp/letp transform to succeed.  */
+      else if (insn == vctp_insn)
+	{
+	  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);
+
+	  if (GET_CODE (SET_SRC (single_set (next_use1))) == 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);
+
+	      if (GET_CODE (SET_SRC (single_set (next_use2))) == SUBREG)
+		vctp_vpr_generated = XEXP (PATTERN (next_use2), 0);
+	    }
+
+	  if (!vctp_vpr_generated)
+	    {
+	      end_sequence ();
+	      return GEN_INT (1);
+	    }
+	    /* Also emit a USE of the source register of the vctp.
+	     This holds the number of elements being processed
+	     by the loop.  This later gets stored into `count`
+	     for the middle-end to initialise the loop counter.  */
+	  emit_use (XVECEXP (XEXP (PATTERN (insn), 1), 0, 0));
+	  continue;
+	}
+       /* If the insn pattern requires the use of the VPR value from the
+	  vctp as an input parameter.  */
+      else if ((insn_vpr_reg_operand = arm_get_required_vpr_reg_param (insn))
+	       && rtx_equal_p (vctp_vpr_generated, insn_vpr_reg_operand))
+	{
+	  gcc_assert (MVE_VPT_PREDICATED_INSN_P (insn));
+	  int new_icode = get_attr_mve_unpredicated_insn (insn);
+	  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;
+	  gcc_assert (n_operands_diff > 0 && n_operands_diff <= 2);
+
+	  /* 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.  */
+	  switch (j)
+	    {
+	      case 1:
+		emit_insn (GEN_FCN (new_icode) (arr[0]));
+		break;
+	      case 2:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1]));
+		break;
+	      case 3:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2]));
+		break;
+	      case 4:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2],
+						arr[3]));
+		break;
+	      case 5:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2], arr[3],
+						arr[4]));
+		break;
+	      case 6:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2], arr[3],
+						arr[4], arr[5]));
+		break;
+	      case 7:
+		emit_insn (GEN_FCN (new_icode) (arr[0], arr[1], arr[2], arr[3],
+						arr[4], arr[5], arr[6]));
+		break;
+	      default:
+		gcc_unreachable ();
+	    }
+	}
+      /* 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
+	{
+	  /* None of registers USE-d by the instruction need can be the VPR
+	     vctp_vpr_generated.  This blocks the optimisation if there any
+	     instructions that use the optimised-out VPR value in any way
+	     other than as a VPT block predicate.  */
+	  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 GEN_INT (1);
+	      }
+	  }
+	  /* 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_for_implic_predic (insn, vctp_insn,
+						  vctp_vpr_generated))
+	    {
+	      if (mve_memory_operand (SET_DEST (single_set (insn)),
+				      GET_MODE (SET_DEST (single_set (insn)))))
+		{
+		  end_sequence ();
+		  return GEN_INT (1);
+		}
+
+	     /* Next, 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.  */
+	      df_ref insn_def = NULL;
+	      insn_def = DF_INSN_INFO_DEFS (DF_INSN_INFO_GET (insn));
+	      if (insn_def)
+		{
+		  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 (NONDEBUG_INSN_P (next_use_insn))
+			{
+			  rtx next_insn_set_dest
+			      = SET_DEST (single_set (next_use_insn));
+			  if (BLOCK_FOR_INSN (insn)
+			      != BLOCK_FOR_INSN (next_use_insn))
+			  {
+			    end_sequence ();
+			    return GEN_INT (1);
+			  }
+			}
+		    }
+		}
+	    }
+	  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);
+  for (insn = seq; NEXT_INSN (insn); insn = NEXT_INSN (insn))
+    if (NOTE_P (insn))
+      emit_note_after ((enum insn_note)NOTE_KIND (insn), BB_END (body));
+    else if (DEBUG_INSN_P (insn))
+      emit_debug_insn_after (PATTERN (insn), BB_END (body));
+    else
+      emit_insn_after (PATTERN (insn), BB_END (body));
+
+  emit_jump_insn_after (PATTERN (insn), BB_END (body));
+  return GEN_INT (decrementnum);
+}
+
+/* Target hook to the number of elements to be processed by a dlstp/letp loop
+   into `count` to intialise the counter register.  The number of elements was
+   previously extracted from the vctp insn and placed into a USE rtx.
+   We only check that the doloop_end pattern successfully decrements by a
+   number other than -1 for a valid dlstp/letp loop.  No other checking is
+   needed as that was done previously.  */
+
+rtx
+arm_allow_elementwise_doloop_p (rtx count, rtx label, rtx doloop)
+{
+  if (doloop
+      && INTVAL (XEXP (SET_SRC (XVECEXP (PATTERN (doloop), 0, 1)), 1)) != -1)
+    {
+      basic_block body = BLOCK_FOR_INSN (label)->prev_bb;
+      rtx_insn* insn;
+      FOR_BB_INSNS (body, insn)
+	{
+	  if (INSN_P (insn) && GET_CODE (PATTERN (insn)) == USE)
+	    {
+	      rtx num_elem_reg = copy_rtx (XEXP (PATTERN (insn), 0));
+	      delete_insn (insn);
+	      return num_elem_reg;
+	    }
+	}
+    }
+  return count;
 }
 
 #if CHECKING_P
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index 39895ad62aa3afd55d3cbc92c55b45bc56710bcb..95024fe01612c0dfcd3a7dc97d3f1eda1fccc063 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -1464,6 +1464,10 @@
 		       (VADCIQ_M_S "s") (SQRSHRL_64 "64") (SQRSHRL_48 "48")
 		       (UQRSHLL_64 "64") (UQRSHLL_48 "48") (VSHLCQ_M_S "s")
 		       (VSHLCQ_M_U "u")])
+
+(define_int_attr mode1 [(DLSTP8 "8") (DLSTP16 "16") (DLSTP32 "32")
+			(DLSTP64 "64")])
+
 ;; Both kinds of return insn.
 (define_code_iterator RETURNS [return simple_return])
 (define_code_attr return_str [(return "") (simple_return "simple_")])
@@ -1769,6 +1773,8 @@
 (define_int_iterator UQRSHLLQ [UQRSHLL_64 UQRSHLL_48])
 (define_int_iterator SQRSHRLQ [SQRSHRL_64 SQRSHRL_48])
 (define_int_iterator VSHLCQ_M [VSHLCQ_M_S VSHLCQ_M_U])
+(define_int_iterator DLSTP [DLSTP8 DLSTP16 DLSTP32
+				   DLSTP64])
 
 ;; 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 854b8ab935f82ad0eb99e6af9852ce8154cf9d9d..8dd3567759e5d794b1039c114ccb13765a131304 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -11100,3 +11100,38 @@
     }
   DONE;
 })
+
+;; Originally expanded by 'predicated_doloop_end'.
+(define_insn "*predicated_doloop_end_internal"
+  [(set (pc)
+	(if_then_else
+	   (ge (plus:SI (reg:SI LR_REGNUM)
+			(match_operand:SI 0 "const_int_operand" ""))
+		(const_int 0))
+	 (label_ref (match_operand 1 "" ""))
+	 (pc)))
+   (set (reg:SI LR_REGNUM)
+	(plus:SI (reg:SI LR_REGNUM) (match_dup 0)))
+   (clobber (reg:CC CC_REGNUM))]
+  "TARGET_32BIT && TARGET_HAVE_LOB && TARGET_HAVE_MVE && TARGET_THUMB2"
+  {
+    if (get_attr_length (insn) == 4)
+      return "letp\t%|lr, %l1";
+    else
+      return "subs\t%|lr, #%0;bgt\t%l1";
+  }
+  [(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<mode1>_insn"
+  [
+    (set (reg:SI LR_REGNUM)
+	 (unspec:SI [(match_operand:SI 0 "s_register_operand" "r")]
+	  DLSTP))
+  ]
+  "TARGET_32BIT && TARGET_HAVE_LOB && TARGET_HAVE_MVE && TARGET_THUMB2"
+  "dlstp.<mode1>\t%|lr, %0")
\ No newline at end of file
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index e1e013befa7a67ddbf517bf22797bdaeeb96b94f..3beb4d4b48cd47c8e946fba53c49975ff8271ac1 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1613,7 +1613,7 @@
    (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 +1623,67 @@
 
       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_insn_ok_for_lob (operands[1]))
+	{
+	  s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
+	  /* If we have a compatibe MVE target, try and analyse the loop
+	     contents to determine if we can use predicated dlstp/letp
+	     looping.  */
+	  if (TARGET_HAVE_MVE && TARGET_THUMB2
+	      && (decrement_num = arm_attempt_dlstp_transform (operands[1]))
+	      && (INTVAL (decrement_num) != 1))
+	    {
+	      insn = emit_insn
+		      (gen_thumb2_addsi3_compare0
+			  (s0, s0, GEN_INT ((-1) * (INTVAL (decrement_num)))));
+	      cmp = XVECEXP (PATTERN (insn), 0, 0);
+	      cc_reg = SET_DEST (cmp);
+	      bcomp = gen_rtx_GE (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;
+	    }
+
+	  /* 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;
+    }
+  else
+    FAIL;
+}")
 
 (define_insn "*clear_apsr"
   [(unspec_volatile:SI [(const_int 0)] VUNSPEC_CLRM_APSR)
@@ -1755,7 +1781,37 @@
   {
     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 84384ee798de363b874c41a16dc5daae34eccb94..e533c60215a49fe0aabfa8b5fb6d988faf3c4f51 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -581,6 +581,10 @@
   VADDLVQ_U
   VCTP
   VCTP_M
+  DLSTP8
+  DLSTP16
+  DLSTP32
+  DLSTP64
   VPNOT
   VCREATEQ_F
   VCVTQ_N_TO_F_S
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index c6c891972d1e58cd163b259ba96a599d62326865..4e3fcb1a845ed176386be41b3ace9f067fef9361 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -11796,6 +11796,14 @@ loops, and will help ivopts to make some decisions.
 The default version of this hook returns false.
 @end deftypefn
 
+@deftypefn {Target Hook} rtx TARGET_ALLOW_ELEMENTWISE_DOLOOP_P (rtx @var{count}, rtx @var{label}, rtx @var{doloop})
+This target hook allows the target to support loop-doloop optimisations
+where the value that gets put into the loop counter register is not a
+pre-calculation of the number of iteration of the loop.  For instance,
+the value used can be the number of elements that the loop will process.
+The default version of this hook returns the same rtx it was given.
+@end deftypefn
+
 @deftypevr {Target Hook} bool TARGET_HAVE_COUNT_REG_DECR_P
 Return true if the target supports hardware count register for decrement
 and branch.
diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
index 613b2534149415f442163d599503efaf423b673b..f3e74dfd553c2b5a5857668f6835e762ce2c2616 100644
--- a/gcc/doc/tm.texi.in
+++ b/gcc/doc/tm.texi.in
@@ -7732,6 +7732,8 @@ to by @var{ce_info}.
 
 @hook TARGET_PREDICT_DOLOOP_P
 
+@hook TARGET_ALLOW_ELEMENTWISE_DOLOOP_P
+
 @hook TARGET_HAVE_COUNT_REG_DECR_P
 
 @hook TARGET_DOLOOP_COST_FOR_GENERIC
diff --git a/gcc/loop-doloop.cc b/gcc/loop-doloop.cc
index 4feb0a25ab9331b7124df900f73c9fc6fb3eb10b..38024e223439cac1ca00c0fe2af87d7628c8a815 100644
--- a/gcc/loop-doloop.cc
+++ b/gcc/loop-doloop.cc
@@ -85,29 +85,29 @@ 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 -n)))
+		     (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
      the loop counter register.  Some targets (IA-64) wrap the set of
      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))).  
+     2)  (set (reg) (plus (reg) (const_int -n))
+	 (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 -n), 0)))
+		   (set (reg) (plus (reg) (const_int -n)))])
+	(set (pc) (if_then_else (cc == NE)
+				(label_ref (label))
+				(pc))) */
 
   pattern = PATTERN (doloop_pat);
 
@@ -143,7 +143,7 @@ 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 (!CONST_INT_P (XEXP (cmp_arg1, 1))
 	      || !REG_P (reg_orig))
 	    return 0;
 	  cc_reg = SET_DEST (cmp_orig);
@@ -156,7 +156,8 @@ doloop_condition_get (rtx_insn *doloop_pat)
 	{
 	  /* We expect the condition to be of the form (reg != 0)  */
 	  cond = XEXP (SET_SRC (cmp), 0);
-	  if (GET_CODE (cond) != NE || XEXP (cond, 1) != const0_rtx)
+	  if ((GET_CODE (cond) != NE && GET_CODE (cond) != GE)
+	      || XEXP (cond, 1) != const0_rtx)
 	    return 0;
 	}
     }
@@ -173,14 +174,14 @@ 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)))
     return 0;
 
   /* Check for (set (pc) (if_then_else (condition)
@@ -211,42 +212,49 @@ doloop_condition_get (rtx_insn *doloop_pat)
       || (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 -n))
+	 (set (pc) (if_then_else (reg != 0)
+				 (label_ref (label))
+				 (pc))).
 
-         is equivalent to the following:
+	 If n == 1, that 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 -n)), 0))
+		   (set (reg) (plus (reg) (const_int -n)))])
+	(set (pc) (if_then_else (cc == NE)
+				(label_ref (label))
+				(pc)))
 
-        which is equivalent to the following:
+	Which also for n == 1 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.
 
+	For the "elementwise" form where the decrement number isn't -1,
+	the final value may be exceeded, so use GE instead of NE.
      */
-        condition = gen_rtx_fmt_ee (NE, VOIDmode, inc_src, const1_rtx);
+     if (GET_CODE (pattern) != PARALLEL)
+       {
+	if (INTVAL (XEXP (inc_src, 1)) != -1)
+	  condition = gen_rtx_fmt_ee (GE, VOIDmode, inc_src, const0_rtx);
+	else
+	  condition = gen_rtx_fmt_ee (NE, VOIDmode, inc_src, const1_rtx);;
+       }
 
     return condition;
    }
@@ -685,17 +693,6 @@ 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);
@@ -722,6 +719,23 @@ doloop_optimize (class loop *loop)
   doloop_reg = gen_reg_rtx (mode);
   rtx_insn *doloop_seq = targetm.gen_doloop_end (doloop_reg, start_label);
 
+  /* Not all targets need to pre-calculate the number of the iterations of
+     the loop, they instead work by storing the number of elements in the
+     counter_reg and decrementing that.  Call the appropriate target hook to
+     change the value of count.  */
+  count = targetm.allow_elementwise_doloop_p (count, start_label, doloop_seq);
+
+  max_cost
+    = COSTS_N_INSNS (param_max_iterations_computation_cost);
+  if (set_src_cost (count, 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;
+    }
+
   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/target.def b/gcc/target.def
index db8af0cbe81624513f114fc9bbd8be61d855f409..e799cd97de50b814b0428c0f2960912a6091d330 100644
--- a/gcc/target.def
+++ b/gcc/target.def
@@ -4411,6 +4411,16 @@ The default version of this hook returns false.",
  bool, (class loop *loop),
  default_predict_doloop_p)
 
+DEFHOOK
+(allow_elementwise_doloop_p,
+ "This target hook allows the target to support loop-doloop optimisations\n\
+where the value that gets put into the loop counter register is not a\n\
+pre-calculation of the number of iteration of the loop.  For instance,\n\
+the value used can be the number of elements that the loop will process.\n\
+The default version of this hook returns the same rtx it was given.",
+ rtx, (rtx count, rtx label, rtx doloop),
+ default_allow_elementwise_doloop_p)
+
 DEFHOOKPOD
 (have_count_reg_decr_p,
  "Return true if the target supports hardware count register for decrement\n\
diff --git a/gcc/targhooks.h b/gcc/targhooks.h
index a1df260f5483dc84f18d8f12c5202484a32d5bb7..e94ac1fe09dd48bd24210a8c8982f7a59e4cbc63 100644
--- a/gcc/targhooks.h
+++ b/gcc/targhooks.h
@@ -88,6 +88,7 @@ extern bool default_fixed_point_supported_p (void);
 extern bool default_has_ifunc_p (void);
 
 extern bool default_predict_doloop_p (class loop *);
+extern rtx default_allow_elementwise_doloop_p (rtx, rtx, rtx);
 extern machine_mode default_preferred_doloop_mode (machine_mode);
 extern const char * default_invalid_within_doloop (const rtx_insn *);
 
diff --git a/gcc/targhooks.cc b/gcc/targhooks.cc
index fe0116521feaf32187e7bc113bf93b1805852c79..de4eea9ec0302a6bc4e5274893925aecf2444676 100644
--- a/gcc/targhooks.cc
+++ b/gcc/targhooks.cc
@@ -661,6 +661,12 @@ default_predict_doloop_p (class loop *loop ATTRIBUTE_UNUSED)
   return false;
 }
 
+rtx
+default_allow_elementwise_doloop_p (rtx count, rtx, rtx)
+{
+  return count;
+}
+
 /* By default, just use the input MODE itself.  */
 
 machine_mode
diff --git a/gcc/testsuite/gcc.target/arm/dlstp-compile-asm.c b/gcc/testsuite/gcc.target/arm/dlstp-compile-asm.c
index acf0836050c19b983feeaf97c3e52e1318bb194d..e036b0386260a547a3a2e42d8f34f0913793e593 100644
--- a/gcc/testsuite/gcc.target/arm/dlstp-compile-asm.c
+++ b/gcc/testsuite/gcc.target/arm/dlstp-compile-asm.c
@@ -140,10 +140,196 @@ 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.  */
+
+/* Test a for loop format of decrementing to zero */
+int32_t a[] = {0, 1, 2, 3, 4, 5, 6, 7};
+void test1 (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 test2 (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;
+    }
+}
+
+/* Using an unpredicated arithmetic instruction within the loop.  */
+void test3 (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);
+        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 test4 (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 a constant VPR value in the loop, with a vctp.  */
+void test5 (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.  */
+void test6 (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.  */
+void test7 (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.  */
+void test8 (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 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);
+      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 test10 (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.  */
+void test11 (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;
+    }
+}
+
 /* The final number of DLSTPs currently is calculated by the number of
-  `TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY.*` macros * 6.  */
-/* { dg-final { scan-assembler-times {\tdlstp} 144 } } */
-/* { dg-final { scan-assembler-times {\tletp} 144 } } */
-/* { dg-final { scan-assembler-not "\tvctp\t" } } */
-/* { dg-final { scan-assembler-not "\tvpst\t" } } */
-/* { dg-final { scan-assembler-not "p0" } } */
+  `TEST_COMPILE_IN_DLSTP_INTBITS_SIGNED_UNSIGNED_TERNARY.*` macros * 6 + 11.  */
+/* { dg-final { scan-assembler-times {\tdlstp} 155 } } */
+/* { dg-final { scan-assembler-times {\tletp} 155 } } */
diff --git a/gcc/testsuite/gcc.target/arm/dlstp-int16x8.c b/gcc/testsuite/gcc.target/arm/dlstp-int16x8.c
new file mode 100644
index 0000000000000000000000000000000000000000..b1c03b618e0dcc7d4268f2f004663b6e332a402a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/dlstp-int16x8.c
@@ -0,0 +1,68 @@
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main+fp.dp+mve.fp -mfloat-abi=hard -mfpu=auto -O3 --save-temps" } */
+
+#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;
+    }
+}
+
+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);
+}
+
+/* { 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/dlstp-int32x4.c b/gcc/testsuite/gcc.target/arm/dlstp-int32x4.c
new file mode 100644
index 0000000000000000000000000000000000000000..4a3eb0577be0631ab4e07f6f75c2c802b535c88c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/dlstp-int32x4.c
@@ -0,0 +1,68 @@
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main+fp.dp+mve.fp -mfloat-abi=hard -mfpu=auto -O3 --save-temps" } */
+
+#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;
+    }
+}
+
+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);
+}
+
+/* { 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/dlstp-int64x2.c b/gcc/testsuite/gcc.target/arm/dlstp-int64x2.c
new file mode 100644
index 0000000000000000000000000000000000000000..f05ff834363e2a47a9faddb6b8b09b60eb94a3c2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/dlstp-int64x2.c
@@ -0,0 +1,68 @@
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main+fp.dp+mve.fp -mfloat-abi=hard -mfpu=auto -O3 --save-temps" } */
+
+#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 (8, 0), p);
+      vstrdq_scatter_offset_p_s64 (c, vcreateq_u64 (8, 0), va, p);
+      c+=2;
+      a+=2;
+      n-=2;
+    }
+}
+
+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);
+}
+
+/* { 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/dlstp-int8x16.c b/gcc/testsuite/gcc.target/arm/dlstp-int8x16.c
new file mode 100644
index 0000000000000000000000000000000000000000..f281ba7848d1ba3321124e996eb5bea44977c2ab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/dlstp-int8x16.c
@@ -0,0 +1,68 @@
+/* { dg-do run { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main+fp.dp+mve.fp -mfloat-abi=hard -mfpu=auto -O3 --save-temps" } */
+
+#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/dlstp-invalid-asm.c b/gcc/testsuite/gcc.target/arm/dlstp-invalid-asm.c
new file mode 100644
index 0000000000000000000000000000000000000000..b250625ce426400ad6be1edcb77e854cc6b79dc9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/dlstp-invalid-asm.c
@@ -0,0 +1,210 @@
+
+/* { dg-do compile { target { arm*-*-* } } } */
+/* { dg-require-effective-target arm_v8_1m_mve_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main+fp.dp+mve.fp -mfloat-abi=hard -mfpu=auto -O3 --save-temps" } */
+
+#include <arm_mve.h>
+
+/* Terminating on a non-zero number of elements.  */
+void test1 (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;
+    }
+}
+
+/* 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 vcmp to generate a new predicate value in the
+   loop and then using it in a store insn.  */
+void test14 (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_z_s32 (a, p);
+      int32x4_t vb = vldrwq_z_s32 (b, p);
+      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 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 an unpredicated op with a scalar output, where the result is valid
+   outside the bb.  */
+uint8_t test7 (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;
+}
+
+/* Using an unpredicated op with a scalar output, then a scalar op,
+   where the result is valid outside the bb.  */
+uint8_t test8 (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 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;
+    }
+}
+
+/* { dg-final { scan-assembler-not "\tdlstp" } } */
+/* { dg-final { scan-assembler-not "\tletp" } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
index feaae7cc89959b3147368980120700bbc3e85ecb..3941fe7a8b620e62a5f742722be1ba2d031f5a8d 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 ba5c82cd55c582c96a18ad417a3041e43d843613..c8ce653a5c39fb1ffcf82a6e584d9a0467a130c0 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 17b6124295e8ae9e1cb57e41fa43a954b3390eec..4fe116e2c2be3748d1bb6da7bb9092db8f962abc 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 ();