diff options
author | liuhongt <hongtao.liu@intel.com> | 2021-09-02 13:05:54 +0800 |
---|---|---|
committer | liuhongt <hongtao.liu@intel.com> | 2021-09-16 16:35:29 +0800 |
commit | a26ff83ed07e33c4aa46f3314553c0d15ca21100 (patch) | |
tree | 5f6c5fa4a159fb95184b17896df2a1ada6e72059 | |
parent | a73d59089a9daca7316eeccece13166ad60dbf13 (diff) | |
download | gcc-a26ff83ed07e33c4aa46f3314553c0d15ca21100.zip gcc-a26ff83ed07e33c4aa46f3314553c0d15ca21100.tar.gz gcc-a26ff83ed07e33c4aa46f3314553c0d15ca21100.tar.bz2 |
Check mask type when doing cond_op related gimple simplification.
gcc/ChangeLog:
PR middle-end/102080
* match.pd: Check mask type when doing cond_op related gimple
simplification.
* tree.c (is_truth_type_for): New function.
* tree.h (is_truth_type_for): New declaration.
gcc/testsuite/ChangeLog:
PR middle-end/102080
* gcc.target/i386/pr102080.c: New test.
-rw-r--r-- | gcc/match.pd | 8 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/i386/pr102080.c | 19 | ||||
-rw-r--r-- | gcc/tree.c | 29 | ||||
-rw-r--r-- | gcc/tree.h | 1 |
4 files changed, 53 insertions, 4 deletions
diff --git a/gcc/match.pd b/gcc/match.pd index 008f775..41f9e6d 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -7020,13 +7020,13 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (vec_cond @0 (view_convert? (uncond_op@4 @1 @2)) @3) (with { tree op_type = TREE_TYPE (@4); } (if (vectorized_internal_fn_supported_p (as_internal_fn (cond_op), op_type) - && element_precision (type) == element_precision (op_type)) + && is_truth_type_for (op_type, TREE_TYPE (@0))) (view_convert (cond_op @0 @1 @2 (view_convert:op_type @3)))))) (simplify (vec_cond @0 @1 (view_convert? (uncond_op@4 @2 @3))) (with { tree op_type = TREE_TYPE (@4); } (if (vectorized_internal_fn_supported_p (as_internal_fn (cond_op), op_type) - && element_precision (type) == element_precision (op_type)) + && is_truth_type_for (op_type, TREE_TYPE (@0))) (view_convert (cond_op (bit_not @0) @2 @3 (view_convert:op_type @1))))))) /* Same for ternary operations. */ @@ -7036,13 +7036,13 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (vec_cond @0 (view_convert? (uncond_op@5 @1 @2 @3)) @4) (with { tree op_type = TREE_TYPE (@5); } (if (vectorized_internal_fn_supported_p (as_internal_fn (cond_op), op_type) - && element_precision (type) == element_precision (op_type)) + && is_truth_type_for (op_type, TREE_TYPE (@0))) (view_convert (cond_op @0 @1 @2 @3 (view_convert:op_type @4)))))) (simplify (vec_cond @0 @1 (view_convert? (uncond_op@5 @2 @3 @4))) (with { tree op_type = TREE_TYPE (@5); } (if (vectorized_internal_fn_supported_p (as_internal_fn (cond_op), op_type) - && element_precision (type) == element_precision (op_type)) + && is_truth_type_for (op_type, TREE_TYPE (@0))) (view_convert (cond_op (bit_not @0) @2 @3 @4 (view_convert:op_type @1))))))) #endif diff --git a/gcc/testsuite/gcc.target/i386/pr102080.c b/gcc/testsuite/gcc.target/i386/pr102080.c new file mode 100644 index 0000000..4c5ee32 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr102080.c @@ -0,0 +1,19 @@ +/* { dg-do compile } */ +/* { dg-options "-O2" } */ + +#include<immintrin.h> +typedef float __m256 __attribute__((__vector_size__(32))); +__m256 _mm256_blendv_ps___Y, _mm256_blendv_ps___M, _mm256_mul_ps___A, + _mm256_mul_ps___B, IfThenElse___trans_tmp_9; + +void +__attribute__ ((target("avx"))) +IfThenElse (__m256 no) { + IfThenElse___trans_tmp_9 = _mm256_blendv_ps (no, _mm256_blendv_ps___Y, _mm256_blendv_ps___M); +} +void +__attribute__ ((target("avx512vl"))) +EncodedFromDisplay() { + __m256 __trans_tmp_11 = _mm256_mul_ps___A * _mm256_mul_ps___B; + IfThenElse(__trans_tmp_11); +} @@ -10737,6 +10737,35 @@ signed_type_for (tree type) return signed_or_unsigned_type_for (0, type); } +/* - For VECTOR_TYPEs: + - The truth type must be a VECTOR_BOOLEAN_TYPE. + - The number of elements must match (known_eq). + - targetm.vectorize.get_mask_mode exists, and exactly + the same mode as the truth type. + - Otherwise, the truth type must be a BOOLEAN_TYPE + or useless_type_conversion_p to BOOLEAN_TYPE. */ +bool +is_truth_type_for (tree type, tree truth_type) +{ + machine_mode mask_mode = TYPE_MODE (truth_type); + machine_mode vmode = TYPE_MODE (type); + machine_mode tmask_mode; + + if (TREE_CODE (type) == VECTOR_TYPE) + { + if (VECTOR_BOOLEAN_TYPE_P (truth_type) + && known_eq (TYPE_VECTOR_SUBPARTS (type), + TYPE_VECTOR_SUBPARTS (truth_type)) + && targetm.vectorize.get_mask_mode (vmode).exists (&tmask_mode) + && tmask_mode == mask_mode) + return true; + + return false; + } + + return useless_type_conversion_p (boolean_type_node, truth_type); +} + /* If TYPE is a vector type, return a signed integer vector type with the same width and number of subparts. Otherwise return boolean_type_node. */ @@ -4591,6 +4591,7 @@ extern tree build_string_literal (unsigned, const char * = NULL, extern tree signed_or_unsigned_type_for (int, tree); extern tree signed_type_for (tree); extern tree unsigned_type_for (tree); +extern bool is_truth_type_for (tree, tree); extern tree truth_type_for (tree); extern tree build_pointer_type_for_mode (tree, machine_mode, bool); extern tree build_pointer_type (tree); |