diff options
| author | Kewen Lin <linkw@gcc.gnu.org> | 2020-06-04 10:09:01 +0800 |
|---|---|---|
| committer | Kewen Lin <linkw@linux.ibm.com> | 2020-06-11 03:26:54 -0500 |
| commit | b3372425ecf3e225d7a2b3c73e061e11498b6f74 (patch) | |
| tree | af7caddd007715254f4c61fb526c3c918f29a352 /gcc/tree-vectorizer.h | |
| parent | 042f4082979aa22e08c008ed4c5b4bab3915a9c2 (diff) | |
| download | gcc-b3372425ecf3e225d7a2b3c73e061e11498b6f74.zip gcc-b3372425ecf3e225d7a2b3c73e061e11498b6f74.tar.gz gcc-b3372425ecf3e225d7a2b3c73e061e11498b6f74.tar.bz2 | |
vect: Rename fully_masked_p to using_partial_vectors_p
Power supports vector memory access with length (in bytes) instructions.
Like existing fully masking for SVE, it is another approach to vectorize
the loop using partially-populated vectors.
As Richard Sandiford suggested, this patch is to update the existing
fully_masked_p field to using_partial_vectors_p. Introduce one macro
LOOP_VINFO_USING_PARTIAL_VECTORS_P for partial vectorization checking
usage, update the LOOP_VINFO_FULLY_MASKED_P with
LOOP_VINFO_USING_PARTIAL_VECTORS_P && !masks.is_empty() and still use
it for mask-based partial vectors approach specific checks.
Bootstrapped/regtested on aarch64-linux-gnu.
gcc/ChangeLog:
* tree-vect-loop-manip.c (vect_set_loop_condition): Rename
LOOP_VINFO_FULLY_MASKED_P to LOOP_VINFO_USING_PARTIAL_VECTORS_P.
(vect_gen_vector_loop_niters): Likewise.
(vect_do_peeling): Likewise.
* tree-vect-loop.c (_loop_vec_info::_loop_vec_info): Rename
fully_masked_p to using_partial_vectors_p.
(vect_analyze_loop_costing): Rename LOOP_VINFO_FULLY_MASKED_P to
LOOP_VINFO_USING_PARTIAL_VECTORS_P.
(determine_peel_for_niter): Likewise.
(vect_estimate_min_profitable_iters): Likewise.
(vect_transform_loop): Likewise.
* tree-vectorizer.h (LOOP_VINFO_FULLY_MASKED_P): Updated.
(LOOP_VINFO_USING_PARTIAL_VECTORS_P): New macro.
Diffstat (limited to 'gcc/tree-vectorizer.h')
| -rw-r--r-- | gcc/tree-vectorizer.h | 11 |
1 files changed, 8 insertions, 3 deletions
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index c459280..9be4d15 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -637,8 +637,9 @@ public: fewer than VF scalars. */ bool can_use_partial_vectors_p; - /* True if have decided to use a fully-masked loop. */ - bool fully_masked_p; + /* True if we've decided to use partially-populated vectors, so that + the vector loop can handle fewer than VF scalars. */ + bool using_partial_vectors_p; /* When we have grouped data accesses with gaps, we may introduce invalid memory accesses. We peel the last iteration of the loop to prevent @@ -702,7 +703,7 @@ public: #define LOOP_VINFO_VERSIONING_THRESHOLD(L) (L)->versioning_threshold #define LOOP_VINFO_VECTORIZABLE_P(L) (L)->vectorizable #define LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P(L) (L)->can_use_partial_vectors_p -#define LOOP_VINFO_FULLY_MASKED_P(L) (L)->fully_masked_p +#define LOOP_VINFO_USING_PARTIAL_VECTORS_P(L) (L)->using_partial_vectors_p #define LOOP_VINFO_VECT_FACTOR(L) (L)->vectorization_factor #define LOOP_VINFO_MAX_VECT_FACTOR(L) (L)->max_vectorization_factor #define LOOP_VINFO_MASKS(L) (L)->masks @@ -739,6 +740,10 @@ public: #define LOOP_VINFO_ORIG_LOOP_INFO(L) (L)->orig_loop_info #define LOOP_VINFO_SIMD_IF_COND(L) (L)->simd_if_cond +#define LOOP_VINFO_FULLY_MASKED_P(L) \ + (LOOP_VINFO_USING_PARTIAL_VECTORS_P (L) \ + && !LOOP_VINFO_MASKS (L).is_empty ()) + #define LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT(L) \ ((L)->may_misalign_stmts.length () > 0) #define LOOP_REQUIRES_VERSIONING_FOR_ALIAS(L) \ |