diff options
author | Richard Sandiford <richard.sandiford@arm.com> | 2024-10-24 14:22:33 +0100 |
---|---|---|
committer | Richard Sandiford <richard.sandiford@arm.com> | 2024-10-24 14:22:33 +0100 |
commit | d6c4badffafa295f6082b7d74de314e131f30a96 (patch) | |
tree | 0fd7eb32174e5c36bc140b60b04b9fc3d46e26cc | |
parent | ec8e8d359690e7347e6e718cc9254d59f694e138 (diff) | |
download | gcc-d6c4badffafa295f6082b7d74de314e131f30a96.zip gcc-d6c4badffafa295f6082b7d74de314e131f30a96.tar.gz gcc-d6c4badffafa295f6082b7d74de314e131f30a96.tar.bz2 |
Handle POLY_INT_CSTs in get_nonzero_bits
This patch extends get_nonzero_bits to handle POLY_INT_CSTs,
The easiest (but also most useful) case is that the number
of trailing zeros in the runtime value is at least the number
of trailing zeros in each individual component.
In principle, we could do this for coeffs 1 and above only,
and then OR in ceoff 0. This would give ~0x11 for [14, 32], say.
But that's future work.
gcc/
* tree-ssanames.cc (get_nonzero_bits): Handle POLY_INT_CSTs.
* match.pd (with_possible_nonzero_bits): Likewise.
gcc/testsuite/
* gcc.target/aarch64/sve/cnt_fold_4.c: New test.
-rw-r--r-- | gcc/match.pd | 2 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_4.c | 61 | ||||
-rw-r--r-- | gcc/tree-ssanames.cc | 3 |
3 files changed, 66 insertions, 0 deletions
diff --git a/gcc/match.pd b/gcc/match.pd index 17613ec..391c60b 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -2873,6 +2873,8 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (match with_possible_nonzero_bits INTEGER_CST@0) (match with_possible_nonzero_bits + POLY_INT_CST@0) +(match with_possible_nonzero_bits SSA_NAME@0 (if (INTEGRAL_TYPE_P (TREE_TYPE (@0)) || POINTER_TYPE_P (TREE_TYPE (@0))))) /* Slightly extended version, do not make it recursive to keep it cheap. */ diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_4.c b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_4.c new file mode 100644 index 0000000..b7a5370 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/cnt_fold_4.c @@ -0,0 +1,61 @@ +/* { dg-do compile } */ +/* { dg-options "-O2" } */ +/* { dg-final { check-function-bodies "**" "" } } */ + +#include <arm_sve.h> + +/* +** f1: +** cnth x0 +** ret +*/ +uint64_t +f1 () +{ + uint64_t x = svcntw (); + x >>= 2; + return x << 3; +} + +/* +** f2: +** [^\n]+ +** [^\n]+ +** ... +** ret +*/ +uint64_t +f2 () +{ + uint64_t x = svcntd (); + x >>= 2; + return x << 3; +} + +/* +** f3: +** cntb x0, all, mul #4 +** ret +*/ +uint64_t +f3 () +{ + uint64_t x = svcntd (); + x >>= 1; + return x << 6; +} + +/* +** f4: +** [^\n]+ +** [^\n]+ +** ... +** ret +*/ +uint64_t +f4 () +{ + uint64_t x = svcntd (); + x >>= 2; + return x << 2; +} diff --git a/gcc/tree-ssanames.cc b/gcc/tree-ssanames.cc index 4f83fcb..ae6a0cd 100644 --- a/gcc/tree-ssanames.cc +++ b/gcc/tree-ssanames.cc @@ -502,6 +502,9 @@ get_nonzero_bits (const_tree name) if (TREE_CODE (name) == INTEGER_CST) return wi::to_wide (name); + if (POLY_INT_CST_P (name)) + return -known_alignment (wi::to_poly_wide (name)); + /* Use element_precision instead of TYPE_PRECISION so complex and vector types get a non-zero precision. */ unsigned int precision = element_precision (TREE_TYPE (name)); |