diff options
| author | Andrew Pinski <quic_apinski@quicinc.com> | 2024-08-16 00:39:32 -0700 |
|---|---|---|
| committer | Andrew Pinski <quic_apinski@quicinc.com> | 2024-08-20 17:16:07 -0700 |
| commit | 50b5000a5e430aaf99a5e00465cc9e25563d908b (patch) | |
| tree | f8c3d68e25978ea743f8c57db0fc70f2d68099f8 /gcc | |
| parent | efe3da62758ed031486005e0b912de23a0a6b4c6 (diff) | |
| download | gcc-50b5000a5e430aaf99a5e00465cc9e25563d908b.zip gcc-50b5000a5e430aaf99a5e00465cc9e25563d908b.tar.gz gcc-50b5000a5e430aaf99a5e00465cc9e25563d908b.tar.bz2 | |
builtins: Don't expand bit query builtins for __int128_t if the target supports an optab for it
On aarch64 (without !CSSC instructions), since popcount is implemented using the SIMD instruction cnt,
instead of using two SIMD cnt (V8QI mode), it is better to use one 128bit cnt (V16QI mode). And only one
reduction addition instead of 2. Currently fold_builtin_bit_query will expand always without checking
if there was an optab for the type, so this changes that to check the optab to see if we should expand
or have the backend handle it.
Bootstrapped and tested on x86_64-linux-gnu and built and tested for aarch64-linux-gnu.
gcc/ChangeLog:
* builtins.cc (fold_builtin_bit_query): Don't expand double
`unsigned long long` typess if there is an optab entry for that
type.
Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com>
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/builtins.cc | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/gcc/builtins.cc b/gcc/builtins.cc index 0b90289..b4d51ea 100644 --- a/gcc/builtins.cc +++ b/gcc/builtins.cc @@ -10185,7 +10185,9 @@ fold_builtin_bit_query (location_t loc, enum built_in_function fcode, tree call = NULL_TREE, tem; if (TYPE_PRECISION (arg0_type) == MAX_FIXED_MODE_SIZE && (TYPE_PRECISION (arg0_type) - == 2 * TYPE_PRECISION (long_long_unsigned_type_node))) + == 2 * TYPE_PRECISION (long_long_unsigned_type_node)) + /* If the target supports the optab, then don't do the expansion. */ + && !direct_internal_fn_supported_p (ifn, arg0_type, OPTIMIZE_FOR_BOTH)) { /* __int128 expansions using up to 2 long long builtins. */ arg0 = save_expr (arg0); |