diff options
author | Juzhe-Zhong <juzhe.zhong@rivai.ai> | 2023-08-22 18:51:37 +0800 |
---|---|---|
committer | Pan Li <pan2.li@intel.com> | 2023-08-22 22:10:25 +0800 |
commit | f4658e025424ac281dd8b7e61f798f435dbf1cab (patch) | |
tree | 6df89fa7bf24c43ed51abd0478c0657f0082a76e | |
parent | 2c27600fa79431576f47d55b9ed7b2f4790def67 (diff) | |
download | gcc-f4658e025424ac281dd8b7e61f798f435dbf1cab.zip gcc-f4658e025424ac281dd8b7e61f798f435dbf1cab.tar.gz gcc-f4658e025424ac281dd8b7e61f798f435dbf1cab.tar.bz2 |
VECT: Add LEN_FOLD_EXTRACT_LAST pattern
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.
* optabs.def (OPTAB_D): Ditto.
-rw-r--r-- | gcc/doc/md.texi | 6 | ||||
-rw-r--r-- | gcc/internal-fn.cc | 5 | ||||
-rw-r--r-- | gcc/internal-fn.def | 3 | ||||
-rw-r--r-- | gcc/optabs.def | 1 |
4 files changed, 15 insertions, 0 deletions
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 89562fd..2445369 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 df673fd..8baf4d4 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 594f788..d09403c 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) diff --git a/gcc/optabs.def b/gcc/optabs.def index e216572..2ccbe41 100644 --- a/gcc/optabs.def +++ b/gcc/optabs.def @@ -393,6 +393,7 @@ OPTAB_D (mask_len_fold_left_plus_optab, "mask_len_fold_left_plus_$a") OPTAB_D (extract_last_optab, "extract_last_$a") OPTAB_D (fold_extract_last_optab, "fold_extract_last_$a") +OPTAB_D (len_fold_extract_last_optab, "len_fold_extract_last_$a") OPTAB_D (uabd_optab, "uabd$a3") OPTAB_D (sabd_optab, "sabd$a3") |