[PATCH] Machine Description: Add LEN_MASK_{GATHER_LOAD,SCATTER_STORE} pattern

[juzhe.zhong@rivai.ai]

From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>

Hi, Richi and Richard.

This patch is adding LEN_MASK_{GATHER_LOAD,SCATTER_STORE} to allow targets
handle flow control by mask and loop control by length on gather/scatter memory
operations. Consider this following case:

#include <stdint.h>
void
f (uint8_t *restrict a, 
   uint8_t *restrict b, int n,
   int base, int step,
   int *restrict cond)
{
  for (int i = 0; i < n; ++i)
    {
      if (cond[i])
        a[i * step + base] = b[i * step + base];
    }
}

We hope RVV can vectorize such case into following IR:

loop_len = SELECT_VL
control_mask = comparison
v = LEN_MASK_GATHER_LOAD (.., loop_len, control_mask)
LEN_SCATTER_STORE (... v, ..., loop_len, control_mask)

This patch doesn't apply such patterns into vectorizer, just add patterns
and update the documents.

Will send patch which apply such patterns into vectorizer soon after this
patch is approved.

Thanks.

gcc/ChangeLog:

        * doc/md.texi: Add LEN_MASK_{GATHER_LOAD,SCATTER_STORE}.
        * internal-fn.cc (expand_scatter_store_optab_fn): Ditto.
        (expand_gather_load_optab_fn): Ditto.
        (internal_load_fn_p): Ditto.
        (internal_store_fn_p): Ditto.
        (internal_gather_scatter_fn_p): Ditto.
        (internal_fn_mask_index): Ditto.
        (internal_fn_stored_value_index): Ditto.
        * internal-fn.def (LEN_MASK_GATHER_LOAD): Ditto.
        (LEN_MASK_SCATTER_STORE): Ditto.
        * optabs.def (OPTAB_CD): Ditto.

---
 gcc/doc/md.texi     | 14 ++++++++++++++
 gcc/internal-fn.cc  | 32 ++++++++++++++++++++++++++++++--
 gcc/internal-fn.def |  8 ++++++--
 gcc/optabs.def      |  2 ++
 4 files changed, 52 insertions(+), 4 deletions(-)

diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index 9648fdc846a..a7512506358 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -5040,6 +5040,14 @@ operand 5.  Bit @var{i} of the mask is set if element @var{i}
 of the result should be loaded from memory and clear if element @var{i}
 of the result should be set to zero.
 
+@cindex @code{len_mask_gather_load@var{m}@var{n}} instruction pattern
+@item @samp{len_mask_gather_load@var{m}@var{n}}
+Like @samp{gather_load@var{m}@var{n}}, but takes an extra len operand
+as operand 5 and an extra mask operand as operand 6.  Bit @var{i} of
+the mask is set and i < len if element @var{i} of the result should be
+loaded from memory.  Element @var{i} of the result should be undefined
+value when either Bit @var{i} of the mask is clear or i >= len.
+
 @cindex @code{scatter_store@var{m}@var{n}} instruction pattern
 @item @samp{scatter_store@var{m}@var{n}}
 Store a vector of mode @var{m} into several distinct memory locations.
@@ -5069,6 +5077,12 @@ Like @samp{scatter_store@var{m}@var{n}}, but takes an extra mask operand as
 operand 5.  Bit @var{i} of the mask is set if element @var{i}
 of the result should be stored to memory.
 
+@cindex @code{len_mask_scatter_store@var{m}@var{n}} instruction pattern
+@item @samp{len_mask_scatter_store@var{m}@var{n}}
+Like @samp{scatter_store@var{m}@var{n}}, but takes an extra len operand as
+operand 5 and an extra mask operand as operand 6.  Bit @var{i} of the mask
+is set and i < len if element @var{i} of the result should be stored to memory.
+
 @cindex @code{vec_set@var{m}} instruction pattern
 @item @samp{vec_set@var{m}}
 Set given field in the vector value.  Operand 0 is the vector to modify,
diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc
index 9017176dc7a..335ff9971bc 100644
--- a/gcc/internal-fn.cc
+++ b/gcc/internal-fn.cc
@@ -3537,7 +3537,7 @@ expand_scatter_store_optab_fn (internal_fn, gcall *stmt, direct_optab optab)
   HOST_WIDE_INT scale_int = tree_to_shwi (scale);
   rtx rhs_rtx = expand_normal (rhs);
 
-  class expand_operand ops[6];
+  class expand_operand ops[7];
   int i = 0;
   create_address_operand (&ops[i++], base_rtx);
   create_input_operand (&ops[i++], offset_rtx, TYPE_MODE (TREE_TYPE (offset)));
@@ -3546,6 +3546,14 @@ expand_scatter_store_optab_fn (internal_fn, gcall *stmt, direct_optab optab)
   create_input_operand (&ops[i++], rhs_rtx, TYPE_MODE (TREE_TYPE (rhs)));
   if (mask_index >= 0)
     {
+      if (optab == len_mask_scatter_store_optab)
+	{
+	  tree len = gimple_call_arg (stmt, mask_index - 1);
+	  rtx len_rtx = expand_normal (len);
+	  create_convert_operand_from (&ops[i++], len_rtx,
+				       TYPE_MODE (TREE_TYPE (len)),
+				       TYPE_UNSIGNED (TREE_TYPE (len)));
+	}
       tree mask = gimple_call_arg (stmt, mask_index);
       rtx mask_rtx = expand_normal (mask);
       create_input_operand (&ops[i++], mask_rtx, TYPE_MODE (TREE_TYPE (mask)));
@@ -3572,7 +3580,7 @@ expand_gather_load_optab_fn (internal_fn, gcall *stmt, direct_optab optab)
   HOST_WIDE_INT scale_int = tree_to_shwi (scale);
 
   int i = 0;
-  class expand_operand ops[6];
+  class expand_operand ops[7];
   create_output_operand (&ops[i++], lhs_rtx, TYPE_MODE (TREE_TYPE (lhs)));
   create_address_operand (&ops[i++], base_rtx);
   create_input_operand (&ops[i++], offset_rtx, TYPE_MODE (TREE_TYPE (offset)));
@@ -3584,6 +3592,17 @@ expand_gather_load_optab_fn (internal_fn, gcall *stmt, direct_optab optab)
       rtx mask_rtx = expand_normal (mask);
       create_input_operand (&ops[i++], mask_rtx, TYPE_MODE (TREE_TYPE (mask)));
     }
+  else if (optab == len_mask_gather_load_optab)
+    {
+      tree len = gimple_call_arg (stmt, 4);
+      rtx len_rtx = expand_normal (len);
+      create_convert_operand_from (&ops[i++], len_rtx,
+				   TYPE_MODE (TREE_TYPE (len)),
+				   TYPE_UNSIGNED (TREE_TYPE (len)));
+      tree mask = gimple_call_arg (stmt, 5);
+      rtx mask_rtx = expand_normal (mask);
+      create_input_operand (&ops[i++], mask_rtx, TYPE_MODE (TREE_TYPE (mask)));
+    }
   insn_code icode = convert_optab_handler (optab, TYPE_MODE (TREE_TYPE (lhs)),
 					   TYPE_MODE (TREE_TYPE (offset)));
   expand_insn (icode, i, ops);
@@ -4434,6 +4453,7 @@ internal_load_fn_p (internal_fn fn)
     case IFN_MASK_LOAD_LANES:
     case IFN_GATHER_LOAD:
     case IFN_MASK_GATHER_LOAD:
+    case IFN_LEN_MASK_GATHER_LOAD:
     case IFN_LEN_LOAD:
     case IFN_LEN_MASK_LOAD:
       return true;
@@ -4455,6 +4475,7 @@ internal_store_fn_p (internal_fn fn)
     case IFN_MASK_STORE_LANES:
     case IFN_SCATTER_STORE:
     case IFN_MASK_SCATTER_STORE:
+    case IFN_LEN_MASK_SCATTER_STORE:
     case IFN_LEN_STORE:
     case IFN_LEN_MASK_STORE:
       return true;
@@ -4473,8 +4494,10 @@ internal_gather_scatter_fn_p (internal_fn fn)
     {
     case IFN_GATHER_LOAD:
     case IFN_MASK_GATHER_LOAD:
+    case IFN_LEN_MASK_GATHER_LOAD:
     case IFN_SCATTER_STORE:
     case IFN_MASK_SCATTER_STORE:
+    case IFN_LEN_MASK_SCATTER_STORE:
       return true;
 
     default:
@@ -4500,6 +4523,10 @@ internal_fn_mask_index (internal_fn fn)
     case IFN_MASK_SCATTER_STORE:
       return 4;
 
+    case IFN_LEN_MASK_GATHER_LOAD:
+    case IFN_LEN_MASK_SCATTER_STORE:
+      return 5;
+
     case IFN_LEN_MASK_LOAD:
     case IFN_LEN_MASK_STORE:
       return 3;
@@ -4522,6 +4549,7 @@ internal_fn_stored_value_index (internal_fn fn)
     case IFN_MASK_STORE_LANES:
     case IFN_SCATTER_STORE:
     case IFN_MASK_SCATTER_STORE:
+    case IFN_LEN_MASK_SCATTER_STORE:
     case IFN_LEN_STORE:
       return 3;
 
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index bc947c0fde7..5be24decf88 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -48,14 +48,14 @@ along with GCC; see the file COPYING3.  If not see
    - mask_load: currently just maskload
    - load_lanes: currently just vec_load_lanes
    - mask_load_lanes: currently just vec_mask_load_lanes
-   - gather_load: used for {mask_,}gather_load
+   - gather_load: used for {mask_,len_mask_,}gather_load
    - len_load: currently just len_load
    - len_maskload: currently just len_maskload
 
    - 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
+   - scatter_store: used for {mask_,len_mask_,}scatter_store
    - len_store: currently just len_store
    - len_maskstore: currently just len_maskstore
 
@@ -157,6 +157,8 @@ DEF_INTERNAL_OPTAB_FN (MASK_LOAD_LANES, ECF_PURE,
 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_MASK_GATHER_LOAD, ECF_PURE,
+		       len_mask_gather_load, gather_load)
 
 DEF_INTERNAL_OPTAB_FN (LEN_LOAD, ECF_PURE, len_load, len_load)
 DEF_INTERNAL_OPTAB_FN (LEN_MASK_LOAD, ECF_PURE, len_maskload, len_maskload)
@@ -164,6 +166,8 @@ DEF_INTERNAL_OPTAB_FN (LEN_MASK_LOAD, ECF_PURE, len_maskload, len_maskload)
 DEF_INTERNAL_OPTAB_FN (SCATTER_STORE, 0, scatter_store, scatter_store)
 DEF_INTERNAL_OPTAB_FN (MASK_SCATTER_STORE, 0,
 		       mask_scatter_store, scatter_store)
+DEF_INTERNAL_OPTAB_FN (LEN_MASK_SCATTER_STORE, 0,
+		       len_mask_scatter_store, scatter_store)
 
 DEF_INTERNAL_OPTAB_FN (MASK_STORE, 0, maskstore, mask_store)
 DEF_INTERNAL_OPTAB_FN (STORE_LANES, ECF_CONST, vec_store_lanes, store_lanes)
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 9533eb11565..58933e61817 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -95,8 +95,10 @@ OPTAB_CD(len_maskload_optab, "len_maskload$a$b")
 OPTAB_CD(len_maskstore_optab, "len_maskstore$a$b")
 OPTAB_CD(gather_load_optab, "gather_load$a$b")
 OPTAB_CD(mask_gather_load_optab, "mask_gather_load$a$b")
+OPTAB_CD(len_mask_gather_load_optab, "len_mask_gather_load$a$b")
 OPTAB_CD(scatter_store_optab, "scatter_store$a$b")
 OPTAB_CD(mask_scatter_store_optab, "mask_scatter_store$a$b")
+OPTAB_CD(len_mask_scatter_store_optab, "len_mask_scatter_store$a$b")
 OPTAB_CD(vec_extract_optab, "vec_extract$a$b")
 OPTAB_CD(vec_init_optab, "vec_init$a$b")
 
-- 
2.36.3