From 83d26d0e1b3625ab6c2d83610a13976b52f63e0a Mon Sep 17 00:00:00 2001 From: Jakub Jelinek Date: Tue, 27 Apr 2021 15:42:47 +0200 Subject: [PATCH] veclower: Fix up vec_shl matching of VEC_PERM_EXPR [PR100239] The following testcase ICEs at -O0, because lower_vec_perm sees the _1 = { 0, 0, 0, 0, 0, 0, 0, 0 }; _2 = VEC_COND_EXPR <_1, { -1, -1, -1, -1, -1, -1, -1, -1 }, { 0, 0, 0, 0, 0, 0, 0, 0 }>; _3 = { 6, 0, 0, 0, 0, 0, 0, 0 }; _4 = VEC_PERM_EXPR <{ 0, 0, 0, 0, 0, 0, 0, 0 }, _2, _3>; and as the ISA is SSE2, there is no support for the particular permutation nor for variable mask permutation. But, the code to match vec_shl matches it, because the permutation has the first operand a zero vector and the mask picks all elements randomly from that vector. So, in the end that isn't a vec_shl, but the permutation could be in theory optimized into the first argument. As we keep it as is, it will fail during expansion though, because that for vec_shl correctly requires that it actually is a shift: unsigned firstidx = 0; for (unsigned int i = 0; i < nelt; i++) { if (known_eq (sel[i], nelt)) { if (i == 0 || firstidx) return NULL_RTX; firstidx = i; } else if (firstidx ? maybe_ne (sel[i], nelt + i - firstidx) : maybe_ge (sel[i], nelt)) return NULL_RTX; } if (firstidx == 0) return NULL_RTX; first = firstidx; The if (firstidx == 0) return NULL; is what is missing a counterpart on the lower_vec_perm side. As with optimize != 0 we fold it in other spots, I think it is not needed to optimize this cornercase in lower_vec_perm (which would mean we'd need to recurse on the newly created _4 = { 0, 0, 0, 0, 0, 0, 0, 0 }; whether it is supported or not). 2021-04-27 Jakub Jelinek PR tree-optimization/100239 * tree-vect-generic.c (lower_vec_perm): Don't accept constant permutations with all indices from the first zero element as vec_shl. * gcc.dg/pr100239.c: New test. --- gcc/testsuite/gcc.dg/pr100239.c | 12 ++++++++++++ gcc/tree-vect-generic.c | 2 +- 2 files changed, 13 insertions(+), 1 deletion(-) create mode 100644 gcc/testsuite/gcc.dg/pr100239.c diff --git a/gcc/testsuite/gcc.dg/pr100239.c b/gcc/testsuite/gcc.dg/pr100239.c new file mode 100644 index 0000000..1ade810 --- /dev/null +++ b/gcc/testsuite/gcc.dg/pr100239.c @@ -0,0 +1,12 @@ +/* PR tree-optimization/100239 */ +/* { dg-do compile } */ +/* { dg-options "-O0" } */ + +typedef short __attribute__((__vector_size__ (8 * sizeof (short)))) V; +V v, w; + +void +foo (void) +{ + w = __builtin_shuffle (v != v, 0 < (V) {}, (V) {192} >> 5); +} diff --git a/gcc/tree-vect-generic.c b/gcc/tree-vect-generic.c index 751f181..5cc32c4 100644 --- a/gcc/tree-vect-generic.c +++ b/gcc/tree-vect-generic.c @@ -1563,7 +1563,7 @@ lower_vec_perm (gimple_stmt_iterator *gsi) elements + i - first) : maybe_ge (poly_uint64 (indices[i]), elements)) break; - if (i == elements) + if (first && i == elements) { gimple_assign_set_rhs3 (stmt, mask); update_stmt (stmt); -- 2.7.4