diff --git a/gcc/testsuite/gcc.dg/vect/vect-fncall-mask.c b/gcc/testsuite/gcc.dg/vect/vect-fncall-mask.c new file mode 100644 index 0000000000000000000000000000000000000000..554488e06308717eacca79003d96555d99c7c0f5 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-fncall-mask.c @@ -0,0 +1,31 @@ +/* { dg-do compile { target { aarch64*-*-* } } } */ +/* { dg-additional-options "-march=armv8.2-a+sve -fdump-tree-ifcvt-raw -Ofast" { target { aarch64*-*-* } } } */ + +extern int __attribute__ ((simd, const)) fn (int); + +const int N = 20; +const float lim = 101.0; +const float cst = -1.0; +float tot = 0.0; + +float b[20]; +float a[20] = { [0 ... 9] = 1.7014118e39, /* If branch. */ + [10 ... 19] = 100.0 }; /* Else branch. */ + +int main (void) +{ + #pragma omp simd + for (int i = 0; i < N; i += 1) + { + if (a[i] > lim) + b[i] = cst; + else + b[i] = fn (a[i]); + tot += b[i]; + } + return (0); +} + +/* { dg-final { scan-tree-dump {gimple_assign <gt_expr, _12, _1, 1.01e\+2, NULL>} ifcvt } } */ +/* { dg-final { scan-tree-dump {gimple_assign <bit_not_expr, _34, _12, NULL, NULL>} ifcvt } } */ +/* { dg-final { scan-tree-dump {gimple_call <.MASK_CALL, _3, fn, _2, _34>} ifcvt } } */ diff --git a/gcc/tree-if-conv.cc b/gcc/tree-if-conv.cc index 0346a1376c5f87f538e3573c05b1aa3d02be6eaf..3b04d1e8d34fa43639bdac8c00826eed2d9998bb 100644 --- a/gcc/tree-if-conv.cc +++ b/gcc/tree-if-conv.cc @@ -2907,6 +2907,7 @@ predicate_statements (loop_p loop) This will cause the vectorizer to match the "in branch" clone variants, and serves to build the mask vector in a natural way. */ + tree mask = cond; gcall *call = dyn_cast <gcall *> (gsi_stmt (gsi)); tree orig_fn = gimple_call_fn (call); int orig_nargs = gimple_call_num_args (call); @@ -2914,7 +2915,18 @@ predicate_statements (loop_p loop) args.safe_push (orig_fn); for (int i = 0; i < orig_nargs; i++) args.safe_push (gimple_call_arg (call, i)); - args.safe_push (cond); + /* If `swap', we invert the mask used for the if branch for use + when masking the function call. */ + if (swap) + { + gimple_seq stmts = NULL; + tree true_val + = constant_boolean_node (true, TREE_TYPE (mask)); + mask = gimple_build (&stmts, BIT_XOR_EXPR, + TREE_TYPE (mask), mask, true_val); + gsi_insert_seq_before (&gsi, stmts, GSI_SAME_STMT); + } + args.safe_push (mask); /* Replace the call with a IFN_MASK_CALL that has the extra condition parameter. */