diff mbox series

[08/nn,AArch64] Pass number of units to aarch64_simd_vect_par_cnst_half

Message ID 871slobtye.fsf@linaro.org
State New
Headers show
Series [08/nn,AArch64] Pass number of units to aarch64_simd_vect_par_cnst_half | expand

Commit Message

Richard Sandiford Oct. 27, 2017, 1:28 p.m. UTC
This patch passes the number of units to aarch64_simd_vect_par_cnst_half,
which avoids a to_constant () once GET_MODE_NUNITS is variable.


2017-10-27  Richard Sandiford  <richard.sandiford@linaro.org>
	    Alan Hayward  <alan.hayward@arm.com>
	    David Sherwood  <david.sherwood@arm.com>

gcc/
	* config/aarch64/aarch64-protos.h (aarch64_simd_vect_par_cnst_half):
	Take the number of units too.
	* config/aarch64/aarch64.c (aarch64_simd_vect_par_cnst_half): Likewise.
	(aarch64_simd_check_vect_par_cnst_half): Update call accordingly,
	but check for a vector mode before rather than after the call.
	* config/aarch64/aarch64-simd.md (aarch64_split_simd_mov<mode>)
	(move_hi_quad_<mode>, vec_unpack<su>_hi_<mode>)
	(vec_unpack<su>_lo_<mode, vec_widen_<su>mult_lo_<mode>)
	(vec_widen_<su>mult_hi_<mode>, vec_unpacks_lo_<mode>)
	(vec_unpacks_hi_<mode>, aarch64_saddl2<mode>, aarch64_uaddl2<mode>)
	(aarch64_ssubl2<mode>, aarch64_usubl2<mode>, widen_ssum<mode>3)
	(widen_usum<mode>3, aarch64_saddw2<mode>, aarch64_uaddw2<mode>)
	(aarch64_ssubw2<mode>, aarch64_usubw2<mode>, aarch64_sqdmlal2<mode>)
	(aarch64_sqdmlsl2<mode>, aarch64_sqdmlal2_lane<mode>)
	(aarch64_sqdmlal2_laneq<mode>, aarch64_sqdmlsl2_lane<mode>)
	(aarch64_sqdmlsl2_laneq<mode>, aarch64_sqdmlal2_n<mode>)
	(aarch64_sqdmlsl2_n<mode>, aarch64_sqdmull2<mode>)
	(aarch64_sqdmull2_lane<mode>, aarch64_sqdmull2_laneq<mode>)
	(aarch64_sqdmull2_n<mode>): Update accordingly.

Comments

James Greenhalgh Nov. 2, 2017, 9:59 a.m. UTC | #1
On Fri, Oct 27, 2017 at 02:28:57PM +0100, Richard Sandiford wrote:
> This patch passes the number of units to aarch64_simd_vect_par_cnst_half,

> which avoids a to_constant () once GET_MODE_NUNITS is variable.


OK.


Reviewed-by: James GReenhalgh <james.greenhalgh@arm.com>


Thanks,
James

> 2017-10-27  Richard Sandiford  <richard.sandiford@linaro.org>

> 	    Alan Hayward  <alan.hayward@arm.com>

> 	    David Sherwood  <david.sherwood@arm.com>

> 

> gcc/

> 	* config/aarch64/aarch64-protos.h (aarch64_simd_vect_par_cnst_half):

> 	Take the number of units too.

> 	* config/aarch64/aarch64.c (aarch64_simd_vect_par_cnst_half): Likewise.

> 	(aarch64_simd_check_vect_par_cnst_half): Update call accordingly,

> 	but check for a vector mode before rather than after the call.

> 	* config/aarch64/aarch64-simd.md (aarch64_split_simd_mov<mode>)

> 	(move_hi_quad_<mode>, vec_unpack<su>_hi_<mode>)

> 	(vec_unpack<su>_lo_<mode, vec_widen_<su>mult_lo_<mode>)

> 	(vec_widen_<su>mult_hi_<mode>, vec_unpacks_lo_<mode>)

> 	(vec_unpacks_hi_<mode>, aarch64_saddl2<mode>, aarch64_uaddl2<mode>)

> 	(aarch64_ssubl2<mode>, aarch64_usubl2<mode>, widen_ssum<mode>3)

> 	(widen_usum<mode>3, aarch64_saddw2<mode>, aarch64_uaddw2<mode>)

> 	(aarch64_ssubw2<mode>, aarch64_usubw2<mode>, aarch64_sqdmlal2<mode>)

> 	(aarch64_sqdmlsl2<mode>, aarch64_sqdmlal2_lane<mode>)

> 	(aarch64_sqdmlal2_laneq<mode>, aarch64_sqdmlsl2_lane<mode>)

> 	(aarch64_sqdmlsl2_laneq<mode>, aarch64_sqdmlal2_n<mode>)

> 	(aarch64_sqdmlsl2_n<mode>, aarch64_sqdmull2<mode>)

> 	(aarch64_sqdmull2_lane<mode>, aarch64_sqdmull2_laneq<mode>)

> 	(aarch64_sqdmull2_n<mode>): Update accordingly.

>
diff mbox series

Patch

Index: gcc/config/aarch64/aarch64-protos.h
===================================================================
--- gcc/config/aarch64/aarch64-protos.h	2017-10-27 14:12:04.192082112 +0100
+++ gcc/config/aarch64/aarch64-protos.h	2017-10-27 14:12:07.203885483 +0100
@@ -403,7 +403,7 @@  const char *aarch64_output_move_struct (
 rtx aarch64_return_addr (int, rtx);
 rtx aarch64_simd_gen_const_vector_dup (machine_mode, HOST_WIDE_INT);
 bool aarch64_simd_mem_operand_p (rtx);
-rtx aarch64_simd_vect_par_cnst_half (machine_mode, bool);
+rtx aarch64_simd_vect_par_cnst_half (machine_mode, int, bool);
 rtx aarch64_tls_get_addr (void);
 tree aarch64_fold_builtin (tree, int, tree *, bool);
 unsigned aarch64_dbx_register_number (unsigned);
Index: gcc/config/aarch64/aarch64.c
===================================================================
--- gcc/config/aarch64/aarch64.c	2017-10-27 14:12:04.193939530 +0100
+++ gcc/config/aarch64/aarch64.c	2017-10-27 14:12:07.205742901 +0100
@@ -12007,12 +12007,12 @@  aarch64_simd_scalar_immediate_valid_for_
 
 Low Mask:         { 2, 3 }                { 0, 1 }
 High Mask:        { 0, 1 }                { 2, 3 }
-*/
+
+   MODE Is the mode of the vector and NUNITS is the number of units in it.  */
 
 rtx
-aarch64_simd_vect_par_cnst_half (machine_mode mode, bool high)
+aarch64_simd_vect_par_cnst_half (machine_mode mode, int nunits, bool high)
 {
-  int nunits = GET_MODE_NUNITS (mode);
   rtvec v = rtvec_alloc (nunits / 2);
   int high_base = nunits / 2;
   int low_base = 0;
@@ -12041,14 +12041,15 @@  aarch64_simd_vect_par_cnst_half (machine
 aarch64_simd_check_vect_par_cnst_half (rtx op, machine_mode mode,
 				       bool high)
 {
-  rtx ideal = aarch64_simd_vect_par_cnst_half (mode, high);
+  if (!VECTOR_MODE_P (mode))
+    return false;
+
+  rtx ideal = aarch64_simd_vect_par_cnst_half (mode, GET_MODE_NUNITS (mode),
+					       high);
   HOST_WIDE_INT count_op = XVECLEN (op, 0);
   HOST_WIDE_INT count_ideal = XVECLEN (ideal, 0);
   int i = 0;
 
-  if (!VECTOR_MODE_P (mode))
-    return false;
-
   if (count_op != count_ideal)
     return false;
 
Index: gcc/config/aarch64/aarch64-simd.md
===================================================================
--- gcc/config/aarch64/aarch64-simd.md	2017-10-27 14:12:04.193010821 +0100
+++ gcc/config/aarch64/aarch64-simd.md	2017-10-27 14:12:07.203885483 +0100
@@ -252,8 +252,8 @@  (define_expand "aarch64_split_simd_mov<m
       {
         rtx dst_low_part = gen_lowpart (<VHALF>mode, dst);
         rtx dst_high_part = gen_highpart (<VHALF>mode, dst);
-        rtx lo = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
-        rtx hi = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+	rtx lo = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
+	rtx hi = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
 
         emit_insn
           (gen_aarch64_simd_mov_from_<mode>low (dst_low_part, src, lo));
@@ -1436,7 +1436,7 @@  (define_expand "move_hi_quad_<mode>"
   (match_operand:<VHALF> 1 "register_operand" "")]
  "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
   if (BYTES_BIG_ENDIAN)
     emit_insn (gen_aarch64_simd_move_hi_quad_be_<mode> (operands[0],
 		    operands[1], p));
@@ -1520,7 +1520,7 @@  (define_expand "vec_unpack<su>_hi_<mode>
    (ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand"))]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
     emit_insn (gen_aarch64_simd_vec_unpack<su>_hi_<mode> (operands[0],
 							  operands[1], p));
     DONE;
@@ -1532,7 +1532,7 @@  (define_expand "vec_unpack<su>_lo_<mode>
    (ANY_EXTEND:<VWIDE> (match_operand:VQW 1 "register_operand" ""))]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
     emit_insn (gen_aarch64_simd_vec_unpack<su>_lo_<mode> (operands[0],
 							  operands[1], p));
     DONE;
@@ -1652,7 +1652,7 @@  (define_expand "vec_widen_<su>mult_lo_<m
    (ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand" ""))]
  "TARGET_SIMD"
  {
-   rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+   rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
    emit_insn (gen_aarch64_simd_vec_<su>mult_lo_<mode> (operands[0],
 						       operands[1],
 						       operands[2], p));
@@ -1679,7 +1679,7 @@  (define_expand "vec_widen_<su>mult_hi_<m
    (ANY_EXTEND:<VWIDE> (match_operand:VQW 2 "register_operand" ""))]
  "TARGET_SIMD"
  {
-   rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+   rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
    emit_insn (gen_aarch64_simd_vec_<su>mult_hi_<mode> (operands[0],
 						       operands[1],
 						       operands[2], p));
@@ -2083,7 +2083,7 @@  (define_expand "vec_unpacks_lo_<mode>"
    (match_operand:VQ_HSF 1 "register_operand" "")]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
     emit_insn (gen_aarch64_simd_vec_unpacks_lo_<mode> (operands[0],
 						       operands[1], p));
     DONE;
@@ -2106,7 +2106,7 @@  (define_expand "vec_unpacks_hi_<mode>"
    (match_operand:VQ_HSF 1 "register_operand" "")]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
     emit_insn (gen_aarch64_simd_vec_unpacks_lo_<mode> (operands[0],
 						       operands[1], p));
     DONE;
@@ -3027,7 +3027,7 @@  (define_expand "aarch64_saddl2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_saddl<mode>_hi_internal (operands[0], operands[1],
                                                   operands[2], p));
   DONE;
@@ -3039,7 +3039,7 @@  (define_expand "aarch64_uaddl2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_uaddl<mode>_hi_internal (operands[0], operands[1],
                                                   operands[2], p));
   DONE;
@@ -3051,7 +3051,7 @@  (define_expand "aarch64_ssubl2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_ssubl<mode>_hi_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3063,7 +3063,7 @@  (define_expand "aarch64_usubl2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_usubl<mode>_hi_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3089,7 +3089,7 @@  (define_expand "widen_ssum<mode>3"
 		      (match_operand:<VDBLW> 2 "register_operand" "")))]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
     rtx temp = gen_reg_rtx (GET_MODE (operands[0]));
 
     emit_insn (gen_aarch64_saddw<mode>_internal (temp, operands[2],
@@ -3117,7 +3117,7 @@  (define_expand "widen_usum<mode>3"
 		      (match_operand:<VDBLW> 2 "register_operand" "")))]
   "TARGET_SIMD"
   {
-    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, false);
+    rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, false);
     rtx temp = gen_reg_rtx (GET_MODE (operands[0]));
 
     emit_insn (gen_aarch64_uaddw<mode>_internal (temp, operands[2],
@@ -3178,7 +3178,7 @@  (define_expand "aarch64_saddw2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_saddw2<mode>_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3190,7 +3190,7 @@  (define_expand "aarch64_uaddw2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_uaddw2<mode>_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3203,7 +3203,7 @@  (define_expand "aarch64_ssubw2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_ssubw2<mode>_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3215,7 +3215,7 @@  (define_expand "aarch64_usubw2<mode>"
    (match_operand:VQW 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_usubw2<mode>_internal (operands[0], operands[1],
 						operands[2], p));
   DONE;
@@ -3735,7 +3735,7 @@  (define_expand "aarch64_sqdmlal2<mode>"
    (match_operand:VQ_HSI 3 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlal2<mode>_internal (operands[0], operands[1],
 						  operands[2], operands[3], p));
   DONE;
@@ -3748,7 +3748,7 @@  (define_expand "aarch64_sqdmlsl2<mode>"
    (match_operand:VQ_HSI 3 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlsl2<mode>_internal (operands[0], operands[1],
 						  operands[2], operands[3], p));
   DONE;
@@ -3816,7 +3816,7 @@  (define_expand "aarch64_sqdmlal2_lane<mo
    (match_operand:SI 4 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlal2_lane<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       operands[4], p));
@@ -3831,7 +3831,7 @@  (define_expand "aarch64_sqdmlal2_laneq<m
    (match_operand:SI 4 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlal2_laneq<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       operands[4], p));
@@ -3846,7 +3846,7 @@  (define_expand "aarch64_sqdmlsl2_lane<mo
    (match_operand:SI 4 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlsl2_lane<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       operands[4], p));
@@ -3861,7 +3861,7 @@  (define_expand "aarch64_sqdmlsl2_laneq<m
    (match_operand:SI 4 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlsl2_laneq<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       operands[4], p));
@@ -3894,7 +3894,7 @@  (define_expand "aarch64_sqdmlal2_n<mode>
    (match_operand:<VEL> 3 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlal2_n<mode>_internal (operands[0], operands[1],
 						    operands[2], operands[3],
 						    p));
@@ -3908,7 +3908,7 @@  (define_expand "aarch64_sqdmlsl2_n<mode>
    (match_operand:<VEL> 3 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmlsl2_n<mode>_internal (operands[0], operands[1],
 						    operands[2], operands[3],
 						    p));
@@ -4062,7 +4062,7 @@  (define_expand "aarch64_sqdmull2<mode>"
    (match_operand:VQ_HSI 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmull2<mode>_internal (operands[0], operands[1],
 						  operands[2], p));
   DONE;
@@ -4123,7 +4123,7 @@  (define_expand "aarch64_sqdmull2_lane<mo
    (match_operand:SI 3 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmull2_lane<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       p));
@@ -4137,7 +4137,7 @@  (define_expand "aarch64_sqdmull2_laneq<m
    (match_operand:SI 3 "immediate_operand" "i")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmull2_laneq<mode>_internal (operands[0], operands[1],
 						       operands[2], operands[3],
 						       p));
@@ -4170,7 +4170,7 @@  (define_expand "aarch64_sqdmull2_n<mode>
    (match_operand:<VEL> 2 "register_operand" "w")]
   "TARGET_SIMD"
 {
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, true);
+  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
   emit_insn (gen_aarch64_sqdmull2_n<mode>_internal (operands[0], operands[1],
 						    operands[2], p));
   DONE;