[v2,08/14] arm: Implement auto-vectorized MVE comparisons with vectors of boolean predicates

Message ID 20211013101554.2732342-9-christophe.lyon@foss.st.com
State New
Headers show
Series
  • ARM/MVE use vectors of boolean for predicates
Related show

Commit Message

Jason Merrill via Gcc-patches Oct. 13, 2021, 10:15 a.m.
We make use of qualifier_predicate to describe MVE builtins
prototypes, restricting to auto-vectorizable vcmp* and vpsel builtins,
as they are exercised by the tests added earlier in the series.

Special handling is needed for mve_vpselq because it has a v2di
variant, which has no natural VPR.P0 representation: we keep HImode
for it.

The vector_compare expansion code is updated to use the right VxBI
mode instead of HI for the result.

New mov patterns are introduced to handle the new modes.

2021-10-13  Christophe Lyon <christophe.lyon@foss.st.com>

	gcc/
	PR target/100757
	PR target/101325
	* config/arm/arm-builtins.c (BINOP_PRED_UNONE_UNONE_QUALIFIERS)
	(BINOP_PRED_NONE_NONE_QUALIFIERS)
	(TERNOP_NONE_NONE_NONE_PRED_QUALIFIERS)
	(TERNOP_UNONE_UNONE_UNONE_PRED_QUALIFIERS): New.
	* config/arm/arm.c (arm_hard_regno_mode_ok): Handle new VxBI
	modes.
	(arm_mode_to_pred_mode): New.
	(arm_expand_vector_compare): Use the right VxBI mode instead of
	HI.
	(arm_expand_vcond): Likewise.
	* config/arm/arm_mve_builtins.def (vcmpneq_, vcmphiq_, vcmpcsq_)
	(vcmpltq_, vcmpleq_, vcmpgtq_, vcmpgeq_, vcmpeqq_, vcmpneq_f)
	(vcmpltq_f, vcmpleq_f, vcmpgtq_f, vcmpgeq_f, vcmpeqq_f, vpselq_u)
	(vpselq_s, vpselq_f): Use new predicated qualifiers.
	* config/arm/iterators.md (MVE_7): New mode iterator.
	(MVE_VPRED, MVE_vpred): New attribute iterators.
	* config/arm/mve.md (@mve_vcmp<mve_cmp_op>q_<mode>)
	(@mve_vcmp<mve_cmp_op>q_f<mode>, @mve_vpselq_<supf><mode>)
	(@mve_vpselq_f<mode>): Use MVE_VPRED instead of HI.
	(@mve_vpselq_<supf>v2di): Define separately.
	(mov<mode>): New expander for VxBI modes.
	(mve_mov<mode>): New insn for VxBI modes.

-- 
2.25.1

Patch

diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c
index 771759f0cdd..6e3638869f1 100644
--- a/gcc/config/arm/arm-builtins.c
+++ b/gcc/config/arm/arm-builtins.c
@@ -469,6 +469,12 @@  arm_binop_unone_unone_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
 #define BINOP_UNONE_UNONE_UNONE_QUALIFIERS \
   (arm_binop_unone_unone_unone_qualifiers)
 
+static enum arm_type_qualifiers
+arm_binop_pred_unone_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+  = { qualifier_predicate, qualifier_unsigned, qualifier_unsigned };
+#define BINOP_PRED_UNONE_UNONE_QUALIFIERS \
+  (arm_binop_pred_unone_unone_qualifiers)
+
 static enum arm_type_qualifiers
 arm_binop_unone_none_imm_qualifiers[SIMD_MAX_BUILTIN_ARGS]
   = { qualifier_unsigned, qualifier_none, qualifier_immediate };
@@ -487,6 +493,12 @@  arm_binop_unone_none_none_qualifiers[SIMD_MAX_BUILTIN_ARGS]
 #define BINOP_UNONE_NONE_NONE_QUALIFIERS \
   (arm_binop_unone_none_none_qualifiers)
 
+static enum arm_type_qualifiers
+arm_binop_pred_none_none_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+  = { qualifier_predicate, qualifier_none, qualifier_none };
+#define BINOP_PRED_NONE_NONE_QUALIFIERS \
+  (arm_binop_pred_none_none_qualifiers)
+
 static enum arm_type_qualifiers
 arm_binop_unone_unone_none_qualifiers[SIMD_MAX_BUILTIN_ARGS]
   = { qualifier_unsigned, qualifier_unsigned, qualifier_none };
@@ -558,6 +570,12 @@  arm_ternop_none_none_none_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
 #define TERNOP_NONE_NONE_NONE_UNONE_QUALIFIERS \
   (arm_ternop_none_none_none_unone_qualifiers)
 
+static enum arm_type_qualifiers
+arm_ternop_none_none_none_pred_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+  = { qualifier_none, qualifier_none, qualifier_none, qualifier_predicate };
+#define TERNOP_NONE_NONE_NONE_PRED_QUALIFIERS \
+  (arm_ternop_none_none_none_pred_qualifiers)
+
 static enum arm_type_qualifiers
 arm_ternop_none_none_imm_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
   = { qualifier_none, qualifier_none, qualifier_immediate, qualifier_unsigned };
@@ -577,6 +595,13 @@  arm_ternop_unone_unone_unone_unone_qualifiers[SIMD_MAX_BUILTIN_ARGS]
 #define TERNOP_UNONE_UNONE_UNONE_UNONE_QUALIFIERS \
   (arm_ternop_unone_unone_unone_unone_qualifiers)
 
+static enum arm_type_qualifiers
+arm_ternop_unone_unone_unone_pred_qualifiers[SIMD_MAX_BUILTIN_ARGS]
+  = { qualifier_unsigned, qualifier_unsigned, qualifier_unsigned,
+    qualifier_predicate };
+#define TERNOP_UNONE_UNONE_UNONE_PRED_QUALIFIERS \
+  (arm_ternop_unone_unone_unone_pred_qualifiers)
+
 static enum arm_type_qualifiers
 arm_ternop_none_none_none_none_qualifiers[SIMD_MAX_BUILTIN_ARGS]
   = { qualifier_none, qualifier_none, qualifier_none, qualifier_none };
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 9f52a152444..94696d528f8 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -25304,7 +25304,10 @@  arm_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
     return false;
 
   if (IS_VPR_REGNUM (regno))
-    return mode == HImode;
+    return mode == HImode
+      || mode == V16BImode
+      || mode == V8BImode
+      || mode == V4BImode;
 
   if (TARGET_THUMB1)
     /* For the Thumb we only allow values bigger than SImode in
@@ -30991,6 +30994,19 @@  arm_split_atomic_op (enum rtx_code code, rtx old_out, rtx new_out, rtx mem,
     arm_post_atomic_barrier (model);
 }
 
+/* Return the mode for the MVE vector of predicates corresponding to MODE.  */
+machine_mode
+arm_mode_to_pred_mode (machine_mode mode)
+{
+  switch (GET_MODE_NUNITS (mode))
+    {
+    case 16: return V16BImode;
+    case 8: return V8BImode;
+    case 4: return V4BImode;
+    }
+  gcc_unreachable ();
+}
+
 /* Expand code to compare vectors OP0 and OP1 using condition CODE.
    If CAN_INVERT, store either the result or its inverse in TARGET
    and return true if TARGET contains the inverse.  If !CAN_INVERT,
@@ -31074,7 +31090,7 @@  arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1,
 	  if (vcond_mve)
 	    vpr_p0 = target;
 	  else
-	    vpr_p0 = gen_reg_rtx (HImode);
+	    vpr_p0 = gen_reg_rtx (arm_mode_to_pred_mode (cmp_mode));
 
 	  switch (GET_MODE_CLASS (cmp_mode))
 	    {
@@ -31116,7 +31132,7 @@  arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1,
 	  if (vcond_mve)
 	    vpr_p0 = target;
 	  else
-	    vpr_p0 = gen_reg_rtx (HImode);
+	    vpr_p0 = gen_reg_rtx (arm_mode_to_pred_mode (cmp_mode));
 
 	  emit_insn (gen_mve_vcmpq (code, cmp_mode, vpr_p0, op0, force_reg (cmp_mode, op1)));
 	  if (!vcond_mve)
@@ -31143,7 +31159,7 @@  arm_expand_vector_compare (rtx target, rtx_code code, rtx op0, rtx op1,
 	  if (vcond_mve)
 	    vpr_p0 = target;
 	  else
-	    vpr_p0 = gen_reg_rtx (HImode);
+	    vpr_p0 = gen_reg_rtx (arm_mode_to_pred_mode (cmp_mode));
 
 	  emit_insn (gen_mve_vcmpq (swap_condition (code), cmp_mode, vpr_p0, force_reg (cmp_mode, op1), op0));
 	  if (!vcond_mve)
@@ -31196,7 +31212,7 @@  arm_expand_vcond (rtx *operands, machine_mode cmp_result_mode)
   if (TARGET_HAVE_MVE)
     {
       vcond_mve=true;
-      mask = gen_reg_rtx (HImode);
+      mask = gen_reg_rtx (arm_mode_to_pred_mode (cmp_result_mode));
     }
   else
     mask = gen_reg_rtx (cmp_result_mode);
diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def
index e9b5b28f506..58a05e61bd9 100644
--- a/gcc/config/arm/arm_mve_builtins.def
+++ b/gcc/config/arm/arm_mve_builtins.def
@@ -89,7 +89,7 @@  VAR3 (BINOP_UNONE_UNONE_IMM, vshrq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_NONE_NONE_IMM, vshrq_n_s, v16qi, v8hi, v4si)
 VAR1 (BINOP_NONE_NONE_UNONE, vaddlvq_p_s, v4si)
 VAR1 (BINOP_UNONE_UNONE_UNONE, vaddlvq_p_u, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpneq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_NONE_NONE_NONE, vshlq_s, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_NONE, vshlq_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vsubq_u, v16qi, v8hi, v4si)
@@ -117,9 +117,9 @@  VAR3 (BINOP_UNONE_UNONE_UNONE, vhsubq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vhaddq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, veorq_u, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_UNONE_UNONE, vcmphiq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vcmphiq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_UNONE_UNONE, vcmpcsq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vcmpcsq_n_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vbicq_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_UNONE, vandq_u, v16qi, v8hi, v4si)
@@ -143,15 +143,15 @@  VAR3 (BINOP_UNONE_UNONE_IMM, vshlq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_IMM, vrshrq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_UNONE_IMM, vqshlq_n_u, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpneq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpltq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpltq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpleq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpleq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpgtq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpgtq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpgeq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpgeq_n_, v16qi, v8hi, v4si)
-VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_, v16qi, v8hi, v4si)
+VAR3 (BINOP_PRED_NONE_NONE, vcmpeqq_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_NONE, vcmpeqq_n_, v16qi, v8hi, v4si)
 VAR3 (BINOP_UNONE_NONE_IMM, vqshluq_n_s, v16qi, v8hi, v4si)
 VAR3 (BINOP_NONE_NONE_UNONE, vaddvq_p_s, v16qi, v8hi, v4si)
@@ -219,17 +219,17 @@  VAR2 (BINOP_UNONE_UNONE_IMM, vshllbq_n_u, v16qi, v8hi)
 VAR2 (BINOP_UNONE_UNONE_IMM, vorrq_n_u, v8hi, v4si)
 VAR2 (BINOP_UNONE_UNONE_IMM, vbicq_n_u, v8hi, v4si)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpneq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpneq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpneq_f, v8hf, v4sf)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpltq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpltq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpltq_f, v8hf, v4sf)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpleq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpleq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpleq_f, v8hf, v4sf)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpgtq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpgtq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpgtq_f, v8hf, v4sf)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpgeq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpgeq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpgeq_f, v8hf, v4sf)
 VAR2 (BINOP_UNONE_NONE_NONE, vcmpeqq_n_f, v8hf, v4sf)
-VAR2 (BINOP_UNONE_NONE_NONE, vcmpeqq_f, v8hf, v4sf)
+VAR2 (BINOP_PRED_NONE_NONE, vcmpeqq_f, v8hf, v4sf)
 VAR2 (BINOP_NONE_NONE_NONE, vsubq_f, v8hf, v4sf)
 VAR2 (BINOP_NONE_NONE_NONE, vqmovntq_s, v8hi, v4si)
 VAR2 (BINOP_NONE_NONE_NONE, vqmovnbq_s, v8hi, v4si)
@@ -295,8 +295,8 @@  VAR2 (TERNOP_UNONE_UNONE_NONE_UNONE, vcvtaq_m_u, v8hi, v4si)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vcvtaq_m_s, v8hi, v4si)
 VAR3 (TERNOP_UNONE_UNONE_UNONE_IMM, vshlcq_vec_u, v16qi, v8hi, v4si)
 VAR3 (TERNOP_NONE_NONE_UNONE_IMM, vshlcq_vec_s, v16qi, v8hi, v4si)
-VAR4 (TERNOP_UNONE_UNONE_UNONE_UNONE, vpselq_u, v16qi, v8hi, v4si, v2di)
-VAR4 (TERNOP_NONE_NONE_NONE_UNONE, vpselq_s, v16qi, v8hi, v4si, v2di)
+VAR4 (TERNOP_UNONE_UNONE_UNONE_PRED, vpselq_u, v16qi, v8hi, v4si, v2di)
+VAR4 (TERNOP_NONE_NONE_NONE_PRED, vpselq_s, v16qi, v8hi, v4si, v2di)
 VAR3 (TERNOP_UNONE_UNONE_UNONE_UNONE, vrev64q_m_u, v16qi, v8hi, v4si)
 VAR3 (TERNOP_UNONE_UNONE_UNONE_UNONE, vmvnq_m_u, v16qi, v8hi, v4si)
 VAR3 (TERNOP_UNONE_UNONE_UNONE_UNONE, vmlasq_n_u, v16qi, v8hi, v4si)
@@ -426,7 +426,7 @@  VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vrev64q_m_f, v8hf, v4sf)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vrev32q_m_s, v16qi, v8hi)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vqmovntq_m_s, v8hi, v4si)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vqmovnbq_m_s, v8hi, v4si)
-VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vpselq_f, v8hf, v4sf)
+VAR2 (TERNOP_NONE_NONE_NONE_PRED, vpselq_f, v8hf, v4sf)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vnegq_m_f, v8hf, v4sf)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vmovntq_m_s, v8hi, v4si)
 VAR2 (TERNOP_NONE_NONE_NONE_UNONE, vmovnbq_m_s, v8hi, v4si)
diff --git a/gcc/config/arm/iterators.md b/gcc/config/arm/iterators.md
index fafbd2f94b8..b7249f2b189 100644
--- a/gcc/config/arm/iterators.md
+++ b/gcc/config/arm/iterators.md
@@ -272,6 +272,7 @@  (define_mode_iterator MVE_3 [V16QI V8HI])
 (define_mode_iterator MVE_2 [V16QI V8HI V4SI])
 (define_mode_iterator MVE_5 [V8HI V4SI])
 (define_mode_iterator MVE_6 [V8HI V4SI])
+(define_mode_iterator MVE_7 [V16BI V8BI V4BI])
 
 ;;----------------------------------------------------------------------------
 ;; Code iterators
@@ -946,6 +947,10 @@  (define_mode_attr V_extr_elem [(V16QI "u8") (V8HI "u16") (V4SI "32")
 			       (V8HF "u16") (V4SF "32")])
 (define_mode_attr earlyclobber_32 [(V16QI "=w") (V8HI "=w") (V4SI "=&w")
 						(V8HF "=w") (V4SF "=&w")])
+(define_mode_attr MVE_VPRED [(V16QI "V16BI") (V8HI "V8BI") (V4SI "V4BI")
+                             (V2DI "HI") (V8HF "V8BI")   (V4SF "V4BI")])
+(define_mode_attr MVE_vpred [(V16QI "v16bi") (V8HI "v8bi") (V4SI "v4bi")
+                             (V2DI "hi") (V8HF "v8bi")   (V4SF "v4bi")])
 
 ;;----------------------------------------------------------------------------
 ;; Code attributes
diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md
index 14d17060290..9da78657798 100644
--- a/gcc/config/arm/mve.md
+++ b/gcc/config/arm/mve.md
@@ -839,8 +839,8 @@  (define_insn "mve_vaddlvq_p_<supf>v4si"
 ;;
 (define_insn "@mve_vcmp<mve_cmp_op>q_<mode>"
   [
-   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
-	(MVE_COMPARISONS:HI (match_operand:MVE_2 1 "s_register_operand" "w")
+   (set (match_operand:<MVE_VPRED> 0 "vpr_register_operand" "=Up")
+	(MVE_COMPARISONS:<MVE_VPRED> (match_operand:MVE_2 1 "s_register_operand" "w")
 		    (match_operand:MVE_2 2 "s_register_operand" "w")))
   ]
   "TARGET_HAVE_MVE"
@@ -1929,8 +1929,8 @@  (define_insn "mve_vcaddq<mve_rot><mode>"
 ;;
 (define_insn "@mve_vcmp<mve_cmp_op>q_f<mode>"
   [
-   (set (match_operand:HI 0 "vpr_register_operand" "=Up")
-	(MVE_FP_COMPARISONS:HI (match_operand:MVE_0 1 "s_register_operand" "w")
+   (set (match_operand:<MVE_VPRED> 0 "vpr_register_operand" "=Up")
+	(MVE_FP_COMPARISONS:<MVE_VPRED> (match_operand:MVE_0 1 "s_register_operand" "w")
 			       (match_operand:MVE_0 2 "s_register_operand" "w")))
   ]
   "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
@@ -3324,7 +3324,7 @@  (define_insn "@mve_vpselq_<supf><mode>"
    (set (match_operand:MVE_1 0 "s_register_operand" "=w")
 	(unspec:MVE_1 [(match_operand:MVE_1 1 "s_register_operand" "w")
 		       (match_operand:MVE_1 2 "s_register_operand" "w")
-		       (match_operand:HI 3 "vpr_register_operand" "Up")]
+		       (match_operand:<MVE_VPRED> 3 "vpr_register_operand" "Up")]
 	 VPSELQ))
   ]
   "TARGET_HAVE_MVE"
@@ -4419,7 +4419,7 @@  (define_insn "@mve_vpselq_f<mode>"
    (set (match_operand:MVE_0 0 "s_register_operand" "=w")
 	(unspec:MVE_0 [(match_operand:MVE_0 1 "s_register_operand" "w")
 		       (match_operand:MVE_0 2 "s_register_operand" "w")
-		       (match_operand:HI 3 "vpr_register_operand" "Up")]
+		       (match_operand:<MVE_VPRED> 3 "vpr_register_operand" "Up")]
 	 VPSELQ_F))
   ]
   "TARGET_HAVE_MVE && TARGET_HAVE_MVE_FLOAT"
@@ -10516,3 +10516,27 @@  (define_insn "*movmisalign<mode>_mve_load"
   "vldr<V_sz_elem1>.<V_sz_elem>\t%q0, %E1"
   [(set_attr "type" "mve_load")]
 )
+
+(define_expand "mov<mode>"
+  [(set (match_operand:MVE_7 0 "nonimmediate_operand")
+        (match_operand:MVE_7 1 "nonimmediate_operand"))]
+  "TARGET_HAVE_MVE"
+  {
+    if (!register_operand (operands[0], <MODE>mode))
+      operands[1] = force_reg (<MODE>mode, operands[1]);
+  }
+)
+
+(define_insn "*mve_mov<mode>"
+  [(set (match_operand:MVE_7 0 "nonimmediate_operand" "=rk, m, r, Up, r")
+        (match_operand:MVE_7 1 "nonimmediate_operand"  "rk, r, m, r, Up"))]
+  "TARGET_HAVE_MVE
+  && (register_operand (operands[0], <MODE>mode)
+      || register_operand (operands[1], <MODE>mode))"
+  "@
+  mov%?\t%0, %1
+  strh%?\t%1, %0
+  ldrh%?\t%0, %1
+  vmsr%?\t P0, %1
+  vmrs%?\t %0, P0"
+)