tree-optimization/105053 - fix reduction chain epilogue generation
Commit Message
When we optimize permutations in a reduction chain we have to
be careful to select the correct live-out stmt, otherwise the
reduction result will be unused and the retained scalar code will
execute only the number of vector iterations.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed to trunk.
2022-03-25 Richard Biener <rguenther@suse.de>
PR tree-optimization/105053
* tree-vect-loop.cc (vect_create_epilog_for_reduction): Pick
the correct live-out stmt for a reduction chain.
* g++.dg/vect/pr105053.cc: New testcase.
---
gcc/testsuite/g++.dg/vect/pr105053.cc | 25 +++++++++++++++++++++++++
gcc/tree-vect-loop.cc | 14 +++++++++++---
2 files changed, 36 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/g++.dg/vect/pr105053.cc
new file mode 100644
@@ -0,0 +1,25 @@
+// { dg-require-effective-target c++11 }
+// { dg-require-effective-target int32plus }
+
+#include <vector>
+#include <tuple>
+#include <algorithm>
+
+int main()
+{
+ const int n = 4;
+ std::vector<std::tuple<int,int,double>> vec
+ = { { 1597201307, 1817606674, 0. },
+ { 1380347796, 1721941769, 0.},
+ {837975613, 1032707773, 0.},
+ {1173654292, 2020064272, 0.} } ;
+ int sup1 = 0;
+ for(int i=0;i<n;++i)
+ sup1=std::max(sup1,std::max(std::get<0>(vec[i]),std::get<1>(vec[i])));
+ int sup2 = 0;
+ for(int i=0;i<n;++i)
+ sup2=std::max(std::max(sup2,std::get<0>(vec[i])),std::get<1>(vec[i]));
+ if (sup1 != sup2)
+ std::abort ();
+ return 0;
+}
@@ -5271,9 +5271,17 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo,
/* All statements produce live-out values. */
live_out_stmts = SLP_TREE_SCALAR_STMTS (slp_node);
else if (slp_node)
- /* The last statement in the reduction chain produces the live-out
- value. */
- single_live_out_stmt[0] = SLP_TREE_SCALAR_STMTS (slp_node)[group_size - 1];
+ {
+ /* The last statement in the reduction chain produces the live-out
+ value. Note SLP optimization can shuffle scalar stmts to
+ optimize permutations so we have to search for the last stmt. */
+ for (k = 0; k < group_size; ++k)
+ if (!REDUC_GROUP_NEXT_ELEMENT (SLP_TREE_SCALAR_STMTS (slp_node)[k]))
+ {
+ single_live_out_stmt[0] = SLP_TREE_SCALAR_STMTS (slp_node)[k];
+ break;
+ }
+ }
unsigned vec_num;
int ncopies;