Hi, Richard and Richi.
This is the last autovec pattern I want to add for RVV (length loop control).
This patch is supposed to handled this following case:
int __attribute__ ((noinline, noclone))
condition_reduction (int *a, int min_v, int n)
{
int last = 66; /* High start value. */
for (int i = 0; i < n; i++)
if (a[i] < min_v)
last = i;
return last;
}
ARM SVE IR:
...
mask__7.11_39 = vect__4.10_37 < vect_cst__38;
_40 = loop_mask_36 & mask__7.11_39;
last_5 = .FOLD_EXTRACT_LAST (last_15, _40, vect_vec_iv_.7_32);
...
RVV IR, we want to see:
...
loop_len = SELECT_VL
mask__7.11_39 = vect__4.10_37 < vect_cst__38;
last_5 = .LEN_FOLD_EXTRACT_LAST (last_15, _40, vect_vec_iv_.7_32, loop_len,
bias);
...
gcc/ChangeLog:
* doc/md.texi: Add LEN_FOLD_EXTRACT_LAST pattern.
* internal-fn.cc (fold_len_extract_direct): Ditto.
(expand_fold_len_extract_optab_fn): Ditto.
(direct_fold_len_extract_optab_supported_p): Ditto.
* internal-fn.def (LEN_FOLD_EXTRACT_LAST): Ditto.
---
gcc/doc/md.texi | 6 ++++++
gcc/internal-fn.cc | 5 +++++
gcc/internal-fn.def | 3 +++
3 files changed, 14 insertions(+)
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index 89562fdb43c..24453693d89 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -5636,6 +5636,12 @@ has mode @var{m} and operands 0 and 1 have the mode
appropriate for
one element of @var{m}. Operand 2 has the usual mask mode for vectors
of mode @var{m}; see @code{TARGET_VECTORIZE_GET_MASK_MODE}.
+@cindex @code{len_fold_extract_last_@var{m}} instruction pattern
+@item @code{len_fold_extract_last_@var{m}}
+Like @samp{fold_extract_last_@var{m}}, but takes an extra length operand as
+operand 4 and an extra bias operand as operand 5. The last associated element
+is extracted should have the index i < len (operand 4) + bias (operand 5).
+
@cindex @code{fold_left_plus_@var{m}} instruction pattern
@item @code{fold_left_plus_@var{m}}
Take scalar operand 1 and successively add each element from vector
diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc
index 314f63b614b..4138cc31d7e 100644
--- a/gcc/internal-fn.cc
+++ b/gcc/internal-fn.cc
@@ -188,6 +188,7 @@ init_internal_fns ()
#define cond_len_ternary_direct { 1, 1, true }
#define while_direct { 0, 2, false }
#define fold_extract_direct { 2, 2, false }
+#define fold_len_extract_direct { 2, 2, false }
#define fold_left_direct { 1, 1, false }
#define mask_fold_left_direct { 1, 1, false }
#define mask_len_fold_left_direct { 1, 1, false }
@@ -3863,6 +3864,9 @@ expand_convert_optab_fn (internal_fn fn, gcall *stmt,
convert_optab optab,
#define expand_fold_extract_optab_fn(FN, STMT, OPTAB) \
expand_direct_optab_fn (FN, STMT, OPTAB, 3)
+#define expand_fold_len_extract_optab_fn(FN, STMT, OPTAB) \
+ expand_direct_optab_fn (FN, STMT, OPTAB, 5)
+
#define expand_fold_left_optab_fn(FN, STMT, OPTAB) \
expand_direct_optab_fn (FN, STMT, OPTAB, 2)
@@ -3980,6 +3984,7 @@ multi_vector_optab_supported_p (convert_optab optab,
tree_pair types,
#define direct_mask_len_store_optab_supported_p convert_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_len_extract_optab_supported_p direct_optab_supported_p
#define direct_fold_left_optab_supported_p direct_optab_supported_p
#define direct_mask_fold_left_optab_supported_p direct_optab_supported_p
#define direct_mask_len_fold_left_optab_supported_p direct_optab_supported_p
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index 594f7881511..d09403c0a91 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -312,6 +312,9 @@ DEF_INTERNAL_OPTAB_FN (EXTRACT_LAST, ECF_CONST |
ECF_NOTHROW,
DEF_INTERNAL_OPTAB_FN (FOLD_EXTRACT_LAST, ECF_CONST | ECF_NOTHROW,
fold_extract_last, fold_extract)
+DEF_INTERNAL_OPTAB_FN (LEN_FOLD_EXTRACT_LAST, ECF_CONST | ECF_NOTHROW,
+ len_fold_extract_last, fold_len_extract)
+
DEF_INTERNAL_OPTAB_FN (FOLD_LEFT_PLUS, ECF_CONST | ECF_NOTHROW,
fold_left_plus, fold_left)
--
2.36.3
