diff mbox series

[1/7,V3] ifn/optabs: Support vector load/store with length

Message ID 99427c42-113d-7fbc-5617-f64c2317250d@linux.ibm.com
State New
Headers show
Series [1/7,V3] ifn/optabs: Support vector load/store with length | expand

Commit Message

Kewen.Lin June 10, 2020, 12:36 p.m. UTC
on 2020/6/10 下午5:22, Richard Sandiford wrote:
> "Kewen.Lin" <linkw@linux.ibm.com> writes:
>> @@ -2497,6 +2499,9 @@ expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
>>  
>>    if (optab == vec_mask_load_lanes_optab)
>>      icode = get_multi_vector_move (type, optab);
>> +  else if (optab == lenload_optab)
>> +    icode = convert_optab_handler (optab, TYPE_MODE (type),
>> +				   targetm.vectorize.length_mode);
>>    else
>>      icode = convert_optab_handler (optab, TYPE_MODE (type),
>>  				   TYPE_MODE (TREE_TYPE (maskt)));
> 
> I think lenload_optab should just be a direct optab, based only on
> the vector mode.  It seems unlikely that targets would provide the
> “same” load with different length modes.

Good point!  Yes, targets unlikely have this need.

> 
>> @@ -2507,15 +2512,20 @@ expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
>>    target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
>>    create_output_operand (&ops[0], target, TYPE_MODE (type));
>>    create_fixed_operand (&ops[1], mem);
>> -  create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
>> +  if (optab == lenload_optab)
>> +    create_convert_operand_from (&ops[2], mask, targetm.vectorize.length_mode,
>> +				 TYPE_UNSIGNED (TREE_TYPE (maskt)));
> 
> The mode argument should be TYPE_MODE (TREE_TYPE (maskt)) -- i.e. the
> arguments should specify the precision and signedness of the existing rtx.
> 

Thanks for correcting this.  I found I misunderstood its usage.

> Hopefully this means that we don't need the target hook at all.
> 

New version v3 attached to get rid of length mode hook.

BR,
Kewen

---
gcc/ChangeLog:

2020-MM-DD  Kewen Lin  <linkw@gcc.gnu.org>

	* doc/md.texi (lenload@var{m}): Document.
	(lenstore@var{m}): Likewise.
	* internal-fn.c (len_load_direct): New macro.
	(len_store_direct): Likewise.
	(expand_len_load_optab_fn): Likewise.
	(expand_len_store_optab_fn): Likewise.
	(direct_len_load_optab_supported_p): Likewise.
	(direct_len_store_optab_supported_p): Likewise.
	(expand_mask_load_optab_fn): Add handlings for lenload_optab.
	(expand_mask_store_optab_fn): Add handlings for lenstore_optab.
	(internal_load_fn_p): Handle IFN_LEN_LOAD.
	(internal_store_fn_p): Handle IFN_LEN_STORE.
	(internal_fn_stored_value_index): Handle IFN_LEN_STORE.
	* internal-fn.def (LEN_LOAD): New internal function.
	(LEN_STORE): Likewise.
	* optabs.def (lenload_optab, lenstore_optab): New optab.
---
 gcc/doc/md.texi     | 18 ++++++++++++++++++
 gcc/internal-fn.c   | 29 +++++++++++++++++++++++++----
 gcc/internal-fn.def |  6 ++++++
 gcc/optabs.def      |  2 ++
 4 files changed, 51 insertions(+), 4 deletions(-)

--
diff mbox series

Patch

diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index 2c67c818da5..dd0d3ec203b 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -5167,6 +5167,24 @@  mode @var{n}.
 
 This pattern is not allowed to @code{FAIL}.
 
+@cindex @code{lenload@var{m}} instruction pattern
+@item @samp{lenload@var{m}}
+Perform a vector load with length from memory operand 1 of mode @var{m}
+into register operand 0.  Length is provided in register operand 2 with
+appropriate mode which should afford the maximal required precision of
+any available lengths.
+
+This pattern is not allowed to @code{FAIL}.
+
+@cindex @code{lenstore@var{m}} instruction pattern
+@item @samp{lenstore@var{m}}
+Perform a vector store with length from register operand 1 of mode @var{m}
+into memory operand 0.  Length is provided in register operand 2 with
+appropriate mode which should afford the maximal required precision of
+any available lengths.
+
+This pattern is not allowed to @code{FAIL}.
+
 @cindex @code{vec_perm@var{m}} instruction pattern
 @item @samp{vec_perm@var{m}}
 Output a (variable) vector permutation.  Operand 0 is the destination
diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c
index 5e9aa60721e..e85df5cbd92 100644
--- a/gcc/internal-fn.c
+++ b/gcc/internal-fn.c
@@ -104,10 +104,12 @@  init_internal_fns ()
 #define load_lanes_direct { -1, -1, false }
 #define mask_load_lanes_direct { -1, -1, false }
 #define gather_load_direct { 3, 1, false }
+#define len_load_direct { -1, 2, false }
 #define mask_store_direct { 3, 2, false }
 #define store_lanes_direct { 0, 0, false }
 #define mask_store_lanes_direct { 0, 0, false }
 #define scatter_store_direct { 3, 1, false }
+#define len_store_direct { 3, 2, false }
 #define unary_direct { 0, 0, true }
 #define binary_direct { 0, 0, true }
 #define ternary_direct { 0, 0, true }
@@ -2478,7 +2480,7 @@  expand_call_mem_ref (tree type, gcall *stmt, int index)
   return fold_build2 (MEM_REF, type, addr, build_int_cst (alias_ptr_type, 0));
 }
 
-/* Expand MASK_LOAD{,_LANES} call STMT using optab OPTAB.  */
+/* Expand MASK_LOAD{,_LANES} and LEN_LOAD call STMT using optab OPTAB.  */
 
 static void
 expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
@@ -2497,6 +2499,8 @@  expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
 
   if (optab == vec_mask_load_lanes_optab)
     icode = get_multi_vector_move (type, optab);
+  else if (optab == lenload_optab)
+    icode = direct_optab_handler (optab, TYPE_MODE (type));
   else
     icode = convert_optab_handler (optab, TYPE_MODE (type),
 				   TYPE_MODE (TREE_TYPE (maskt)));
@@ -2507,15 +2511,20 @@  expand_mask_load_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
   target = expand_expr (lhs, NULL_RTX, VOIDmode, EXPAND_WRITE);
   create_output_operand (&ops[0], target, TYPE_MODE (type));
   create_fixed_operand (&ops[1], mem);
-  create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
+  if (optab == lenload_optab)
+    create_convert_operand_from (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)),
+				 TYPE_UNSIGNED (TREE_TYPE (maskt)));
+  else
+    create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
   expand_insn (icode, 3, ops);
   if (!rtx_equal_p (target, ops[0].value))
     emit_move_insn (target, ops[0].value);
 }
 
 #define expand_mask_load_lanes_optab_fn expand_mask_load_optab_fn
+#define expand_len_load_optab_fn expand_mask_load_optab_fn
 
-/* Expand MASK_STORE{,_LANES} call STMT using optab OPTAB.  */
+/* Expand MASK_STORE{,_LANES} and LEN_STORE call STMT using optab OPTAB.  */
 
 static void
 expand_mask_store_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
@@ -2532,6 +2541,8 @@  expand_mask_store_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
 
   if (optab == vec_mask_store_lanes_optab)
     icode = get_multi_vector_move (type, optab);
+  else if (optab == lenstore_optab)
+    icode = direct_optab_handler (optab, TYPE_MODE (type));
   else
     icode = convert_optab_handler (optab, TYPE_MODE (type),
 				   TYPE_MODE (TREE_TYPE (maskt)));
@@ -2542,11 +2553,16 @@  expand_mask_store_optab_fn (internal_fn, gcall *stmt, convert_optab optab)
   reg = expand_normal (rhs);
   create_fixed_operand (&ops[0], mem);
   create_input_operand (&ops[1], reg, TYPE_MODE (type));
-  create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
+  if (optab == lenstore_optab)
+    create_convert_operand_from (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)),
+				 TYPE_UNSIGNED (TREE_TYPE (maskt)));
+  else
+    create_input_operand (&ops[2], mask, TYPE_MODE (TREE_TYPE (maskt)));
   expand_insn (icode, 3, ops);
 }
 
 #define expand_mask_store_lanes_optab_fn expand_mask_store_optab_fn
+#define expand_len_store_optab_fn expand_mask_store_optab_fn
 
 static void
 expand_ABNORMAL_DISPATCHER (internal_fn, gcall *)
@@ -3128,10 +3144,12 @@  multi_vector_optab_supported_p (convert_optab optab, tree_pair types,
 #define direct_load_lanes_optab_supported_p multi_vector_optab_supported_p
 #define direct_mask_load_lanes_optab_supported_p multi_vector_optab_supported_p
 #define direct_gather_load_optab_supported_p convert_optab_supported_p
+#define direct_len_load_optab_supported_p direct_optab_supported_p
 #define direct_mask_store_optab_supported_p direct_optab_supported_p
 #define direct_store_lanes_optab_supported_p multi_vector_optab_supported_p
 #define direct_mask_store_lanes_optab_supported_p multi_vector_optab_supported_p
 #define direct_scatter_store_optab_supported_p convert_optab_supported_p
+#define direct_len_store_optab_supported_p direct_optab_supported_p
 #define direct_while_optab_supported_p convert_optab_supported_p
 #define direct_fold_extract_optab_supported_p direct_optab_supported_p
 #define direct_fold_left_optab_supported_p direct_optab_supported_p
@@ -3498,6 +3516,7 @@  internal_load_fn_p (internal_fn fn)
     case IFN_MASK_LOAD_LANES:
     case IFN_GATHER_LOAD:
     case IFN_MASK_GATHER_LOAD:
+    case IFN_LEN_LOAD:
       return true;
 
     default:
@@ -3517,6 +3536,7 @@  internal_store_fn_p (internal_fn fn)
     case IFN_MASK_STORE_LANES:
     case IFN_SCATTER_STORE:
     case IFN_MASK_SCATTER_STORE:
+    case IFN_LEN_STORE:
       return true;
 
     default:
@@ -3577,6 +3597,7 @@  internal_fn_stored_value_index (internal_fn fn)
     case IFN_MASK_STORE:
     case IFN_SCATTER_STORE:
     case IFN_MASK_SCATTER_STORE:
+    case IFN_LEN_STORE:
       return 3;
 
     default:
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index 1d190d492ff..ed6561f296a 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -49,11 +49,13 @@  along with GCC; see the file COPYING3.  If not see
    - load_lanes: currently just vec_load_lanes
    - mask_load_lanes: currently just vec_mask_load_lanes
    - gather_load: used for {mask_,}gather_load
+   - len_load: currently just lenload
 
    - mask_store: currently just maskstore
    - store_lanes: currently just vec_store_lanes
    - mask_store_lanes: currently just vec_mask_store_lanes
    - scatter_store: used for {mask_,}scatter_store
+   - len_store: currently just lenstore
 
    - unary: a normal unary optab, such as vec_reverse_<mode>
    - binary: a normal binary optab, such as vec_interleave_lo_<mode>
@@ -127,6 +129,8 @@  DEF_INTERNAL_OPTAB_FN (GATHER_LOAD, ECF_PURE, gather_load, gather_load)
 DEF_INTERNAL_OPTAB_FN (MASK_GATHER_LOAD, ECF_PURE,
 		       mask_gather_load, gather_load)
 
+DEF_INTERNAL_OPTAB_FN (LEN_LOAD, ECF_PURE, lenload, len_load)
+
 DEF_INTERNAL_OPTAB_FN (SCATTER_STORE, 0, scatter_store, scatter_store)
 DEF_INTERNAL_OPTAB_FN (MASK_SCATTER_STORE, 0,
 		       mask_scatter_store, scatter_store)
@@ -136,6 +140,8 @@  DEF_INTERNAL_OPTAB_FN (STORE_LANES, ECF_CONST, vec_store_lanes, store_lanes)
 DEF_INTERNAL_OPTAB_FN (MASK_STORE_LANES, 0,
 		       vec_mask_store_lanes, mask_store_lanes)
 
+DEF_INTERNAL_OPTAB_FN (LEN_STORE, 0, lenstore, len_store)
+
 DEF_INTERNAL_OPTAB_FN (WHILE_ULT, ECF_CONST | ECF_NOTHROW, while_ult, while)
 DEF_INTERNAL_OPTAB_FN (CHECK_RAW_PTRS, ECF_CONST | ECF_NOTHROW,
 		       check_raw_ptrs, check_ptrs)
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 0c64eb52a8d..9fe4ac1840d 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -435,3 +435,5 @@  OPTAB_D (check_war_ptrs_optab, "check_war_ptrs$a")
 OPTAB_DC (vec_duplicate_optab, "vec_duplicate$a", VEC_DUPLICATE)
 OPTAB_DC (vec_series_optab, "vec_series$a", VEC_SERIES)
 OPTAB_D (vec_shl_insert_optab, "vec_shl_insert_$a")
+OPTAB_D (lenload_optab, "lenload$a")
+OPTAB_D (lenstore_optab, "lenstore$a")