diff options
| author | Richard Biener <rguenther@suse.de> | 2023-11-10 12:39:11 +0100 |
|---|---|---|
| committer | Richard Biener <rguenther@suse.de> | 2023-11-10 14:17:12 +0100 |
| commit | e5f1956498251a4973d52c8aad3faf34d0443169 (patch) | |
| tree | d0b490c010b5e888c3682eb884122e54f2ab60a2 /gcc | |
| parent | a5922427c29fad177251d89cc946d1c5bfc135eb (diff) | |
| download | gcc-e5f1956498251a4973d52c8aad3faf34d0443169.zip gcc-e5f1956498251a4973d52c8aad3faf34d0443169.tar.gz gcc-e5f1956498251a4973d52c8aad3faf34d0443169.tar.bz2 | |
tree-optimization/110221 - SLP and loop mask/len
The following fixes the issue that when SLP stmts are internal defs
but appear invariant because they end up only using invariant defs
then they get scheduled outside of the loop. This nice optimization
breaks down when loop masks or lens are applied since those are not
explicitly tracked as dependences. The following makes sure to never
schedule internal defs outside of the vectorized loop when the
loop uses masks/lens.
PR tree-optimization/110221
* tree-vect-slp.cc (vect_schedule_slp_node): When loop
masking / len is applied make sure to not schedule
intenal defs outside of the loop.
* gfortran.dg/pr110221.f: New testcase.
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/testsuite/gfortran.dg/pr110221.f | 17 | ||||
| -rw-r--r-- | gcc/tree-vect-slp.cc | 10 |
2 files changed, 27 insertions, 0 deletions
diff --git a/gcc/testsuite/gfortran.dg/pr110221.f b/gcc/testsuite/gfortran.dg/pr110221.f new file mode 100644 index 0000000..8b57384 --- /dev/null +++ b/gcc/testsuite/gfortran.dg/pr110221.f @@ -0,0 +1,17 @@ +C PR middle-end/68146 +C { dg-do compile } +C { dg-options "-O2 -w" } +C { dg-additional-options "-mavx512f --param vect-partial-vector-usage=2" { target avx512f } } + SUBROUTINE CJYVB(V,Z,V0,CBJ,CDJ,CBY,CYY) + IMPLICIT DOUBLE PRECISION (A,B,G,O-Y) + IMPLICIT COMPLEX*16 (C,Z) + DIMENSION CBJ(0:*),CDJ(0:*),CBY(0:*) + N=INT(V) + CALL GAMMA2(VG,GA) + DO 65 K=1,N + CBY(K)=CYY +65 CONTINUE + CDJ(0)=V0/Z*CBJ(0)-CBJ(1) + DO 70 K=1,N +70 CDJ(K)=-(K+V0)/Z*CBJ(K)+CBJ(K-1) + END diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc index 3e5814c..80e279d 100644 --- a/gcc/tree-vect-slp.cc +++ b/gcc/tree-vect-slp.cc @@ -9081,6 +9081,16 @@ vect_schedule_slp_node (vec_info *vinfo, /* Emit other stmts after the children vectorized defs which is earliest possible. */ gimple *last_stmt = NULL; + if (auto loop_vinfo = dyn_cast <loop_vec_info> (vinfo)) + if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo) + || LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)) + { + /* But avoid scheduling internal defs outside of the loop when + we might have only implicitly tracked loop mask/len defs. */ + gimple_stmt_iterator si + = gsi_after_labels (LOOP_VINFO_LOOP (loop_vinfo)->header); + last_stmt = *si; + } bool seen_vector_def = false; FOR_EACH_VEC_ELT (SLP_TREE_CHILDREN (node), i, child) if (SLP_TREE_DEF_TYPE (child) == vect_internal_def) |