From: Andrei Nichita Tirziu <[email protected]>
The MATCH Pattern is a new addition to the vectorizer.
After the pattern is identified, a replacement node
is created for the initial expression.
This requires several new Internal Functions:
- `IFN_MATCH_EQ`, `IFN_MATCH_NE`: the basic IFNs for
unpredicated `match / nmatch` instructions.
These are used when building the new node, but are expected to
get transformed into the conditional versions.
- `IFN_COND_MATCH_EQ`, `IFN_COND_MATCH_NE`: conditional versions.
- `IFN_COND_LEN_MATCH_EQ`, `IFN_COND_LEN_MATCH_NE`: conditional
with length versions.
The arguments of these functions are:
- `IFN_MATCH_EQ (variants, invariants)`
- `IFN_MATCH_NE (variants, invariants)`
- `IFN_COND_MATCH_EQ (variants, invariants, mask, else)`
- `IFN_COND_MATCH_NE (variants, invariants, mask, else)`
- `IFN_COND_LEN_MATCH_EQ (variants, invariants, mask, else, len, bias)`
- `IFN_COND_LEN_MATCH_NE (variants, invariants, mask, else, len, bias)`
These IFNs have corresponding optabs. It is up to the backends to support
them further. All the optabs are declared as "conversion direct" optabs,
since two modes are being used. It is expected that the first mode
corresponds to the result, while the second mode represents the input.
The modes are required because the output of the `match / nmatch`
instructions is a vector of booleans (or a mask), while the inputs
are the arrays of variants and invariants (which are INT types
of different sizes).
gcc/ChangeLog:
* internal-fn.def: New IFN for MATCH and NMATCH (including
conditional versions).
* internal-fn.cc: Define paramater positions for new IFNs.
* optabs.def: New optabs for MATCH and NMATCH (including
conditional versions).
Change-Id: I173c5989b844137a600622ebfa5c474f8829321b
---
gcc/internal-fn.cc | 33 ++++++++++++++++++++++++++++++++-
gcc/internal-fn.def | 11 +++++++++++
gcc/optabs.def | 6 ++++++
3 files changed, 49 insertions(+), 1 deletion(-)
diff --git a/gcc/internal-fn.cc b/gcc/internal-fn.cc
index d879568c6e3e..bae1cb38d433 100644
--- a/gcc/internal-fn.cc
+++ b/gcc/internal-fn.cc
@@ -179,6 +179,7 @@ init_internal_fns ()
#define unary_direct { 0, 0, true }
#define unary_convert_direct { -1, 0, true }
#define binary_direct { 0, 0, true }
+#define binary_convert_direct { -1, 1, true }
#define ternary_direct { 0, 0, true }
#define cond_unary_direct { 1, 1, true }
#define cond_binary_direct { 1, 1, true }
@@ -186,6 +187,8 @@ init_internal_fns ()
#define cond_len_unary_direct { 1, 1, true }
#define cond_len_binary_direct { 1, 1, true }
#define cond_len_ternary_direct { 1, 1, true }
+#define cond_binary_convert_direct { -1, 1, true }
+#define cond_len_binary_convert_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 }
@@ -4253,6 +4256,15 @@ expand_reduc_sbool_optab_fn (internal_fn fn, gcall
*stmt, direct_optab optab)
#define expand_unary_convert_optab_fn(FN, STMT, OPTAB) \
expand_convert_optab_fn (FN, STMT, OPTAB, 1)
+#define expand_binary_convert_optab_fn(FN, STMT, OPTAB) \
+ expand_convert_optab_fn (FN, STMT, OPTAB, 2)
+
+#define expand_cond_binary_convert_optab_fn(FN, STMT, OPTAB) \
+ expand_convert_optab_fn (FN, STMT, OPTAB, 4)
+
+#define expand_cond_len_binary_convert_optab_fn(FN, STMT, OPTAB) \
+ expand_convert_optab_fn (FN, STMT, OPTAB, 6)
+
#define expand_vec_extract_optab_fn(FN, STMT, OPTAB) \
expand_convert_optab_fn (FN, STMT, OPTAB, 2)
@@ -4330,6 +4342,7 @@ multi_vector_optab_supported_p (convert_optab optab,
tree_pair types,
#define direct_unary_optab_supported_p direct_optab_supported_p
#define direct_unary_convert_optab_supported_p convert_optab_supported_p
#define direct_binary_optab_supported_p direct_optab_supported_p
+#define direct_binary_convert_optab_supported_p convert_optab_supported_p
#define direct_ternary_optab_supported_p direct_optab_supported_p
#define direct_cond_unary_optab_supported_p direct_optab_supported_p
#define direct_cond_binary_optab_supported_p direct_optab_supported_p
@@ -4337,6 +4350,8 @@ multi_vector_optab_supported_p (convert_optab optab,
tree_pair types,
#define direct_cond_len_unary_optab_supported_p direct_optab_supported_p
#define direct_cond_len_binary_optab_supported_p direct_optab_supported_p
#define direct_cond_len_ternary_optab_supported_p direct_optab_supported_p
+#define direct_cond_binary_convert_optab_supported_p convert_optab_supported_p
+#define direct_cond_len_binary_convert_optab_supported_p
convert_optab_supported_p
#define direct_crc_optab_supported_p convert_optab_supported_p
#define direct_mask_load_optab_supported_p convert_optab_supported_p
#define direct_load_lanes_optab_supported_p multi_vector_optab_supported_p
@@ -4834,7 +4849,9 @@ get_conditional_len_internal_fn (tree_code code)
T (ROUND) \
T (FLOOR) \
T (RINT) \
- T (CEIL)
+ T (CEIL) \
+ T (MATCH_EQ) \
+ T (MATCH_NE)
/* Return a function that only performs internal function FN when a
certain condition is met and that uses a given fallback value otherwise.
@@ -4890,6 +4907,10 @@ get_len_internal_fn (internal_fn fn)
return IFN_MASK_LEN_LOAD_LANES;
case IFN_MASK_GATHER_LOAD:
return IFN_MASK_LEN_GATHER_LOAD;
+ case IFN_MATCH_EQ:
+ return IFN_COND_LEN_MATCH_EQ;
+ case IFN_MATCH_NE:
+ return IFN_COND_LEN_MATCH_NE;
default:
return IFN_LAST;
}
@@ -5106,6 +5127,8 @@ internal_fn_len_index (internal_fn fn)
case IFN_COND_LEN_XOR:
case IFN_COND_LEN_SHL:
case IFN_COND_LEN_SHR:
+ case IFN_COND_LEN_MATCH_EQ:
+ case IFN_COND_LEN_MATCH_NE:
case IFN_MASK_LEN_STRIDED_STORE:
return 4;
@@ -5179,6 +5202,10 @@ internal_fn_else_index (internal_fn fn)
case IFN_COND_LEN_XOR:
case IFN_COND_LEN_SHL:
case IFN_COND_LEN_SHR:
+ case IFN_COND_MATCH_EQ:
+ case IFN_COND_MATCH_NE:
+ case IFN_COND_LEN_MATCH_EQ:
+ case IFN_COND_LEN_MATCH_NE:
return 3;
case IFN_MASK_LOAD:
@@ -5225,6 +5252,10 @@ internal_fn_mask_index (internal_fn fn)
case IFN_MASK_LEN_STORE_LANES:
case IFN_MASK_LEN_LOAD:
case IFN_MASK_LEN_STORE:
+ case IFN_COND_MATCH_EQ:
+ case IFN_COND_MATCH_NE:
+ case IFN_COND_LEN_MATCH_EQ:
+ case IFN_COND_LEN_MATCH_NE:
return 2;
case IFN_MASK_LEN_STRIDED_LOAD:
diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
index 084a92716312..de3d71ea981d 100644
--- a/gcc/internal-fn.def
+++ b/gcc/internal-fn.def
@@ -246,6 +246,17 @@ DEF_INTERNAL_OPTAB_FN (VEC_SET, ECF_CONST | ECF_NOTHROW,
vec_set, vec_set)
DEF_INTERNAL_OPTAB_FN (VEC_EXTRACT, ECF_CONST | ECF_NOTHROW,
vec_extract, vec_extract)
+// Internal functions for Match EQ and Match NE patterns
+// (conjuction of inequalities or disjunction of equalities)
+DEF_INTERNAL_OPTAB_FN (MATCH_EQ, ECF_PURE | ECF_NOTHROW,
+ vec_match_eq, binary_convert)
+DEF_INTERNAL_OPTAB_FN (MATCH_NE, ECF_PURE | ECF_NOTHROW,
+ vec_match_ne, binary_convert)
+DEF_INTERNAL_COND_FN (MATCH_EQ, ECF_PURE | ECF_NOTHROW,
+ vec_match_eq, binary_convert)
+DEF_INTERNAL_COND_FN (MATCH_NE, ECF_PURE | ECF_NOTHROW,
+ vec_match_ne, binary_convert)
+
DEF_INTERNAL_OPTAB_FN (LEN_STORE, 0, len_store, len_store)
DEF_INTERNAL_OPTAB_FN (MASK_LEN_STORE, 0, mask_len_store, mask_len_store)
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 193f42a728a2..6d9007730e8b 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -99,6 +99,12 @@ OPTAB_CD(vcond_mask_optab, "vcond_mask_$a$b")
OPTAB_CD(vec_cmp_optab, "vec_cmp$a$b")
OPTAB_CD(vec_cmpu_optab, "vec_cmpu$a$b")
OPTAB_CD(vec_cmpeq_optab, "vec_cmpeq$a$b")
+OPTAB_CD(vec_match_eq_optab, "vec_match_$a$b")
+OPTAB_CD(vec_match_ne_optab, "vec_nmatch_$a$b")
+OPTAB_CD(cond_vec_match_eq_optab, "vec_match_cond_$a$b")
+OPTAB_CD(cond_vec_match_ne_optab, "vec_nmatch_cond_$a$b")
+OPTAB_CD(cond_len_vec_match_eq_optab, "vec_match_cond_len_$a$b")
+OPTAB_CD(cond_len_vec_match_ne_optab, "vec_nmatch_cond_len_$a$b")
OPTAB_CD(maskload_optab, "maskload$a$b")
OPTAB_CD(maskstore_optab, "maskstore$a$b")
OPTAB_CD(mask_len_load_optab, "mask_len_load$a$b")
--
2.52.0
