The following zeros paddings of vector bools when expanding compares and the mode used for the compare is an integer mode. In that case targets cannot distinguish between a 4 element and 8 element vector compare (both get to the QImode compare optab) so we have to do the job in the middle-end.
Bootstrapped and tested on x86_64-unknown-linux-gnu. OK? Thanks, Richard. PR middle-end/113576 * expr.cc (do_store_flag): For vector bool compares of vectors with padding zero that. * dojump.cc (do_compare_and_jump): Likewise. --- gcc/dojump.cc | 16 ++++++++++++++++ gcc/expr.cc | 17 +++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/gcc/dojump.cc b/gcc/dojump.cc index e2d2b3cb111..ec2a365e488 100644 --- a/gcc/dojump.cc +++ b/gcc/dojump.cc @@ -1266,6 +1266,7 @@ do_compare_and_jump (tree treeop0, tree treeop1, enum rtx_code signed_code, machine_mode mode; int unsignedp; enum rtx_code code; + unsigned HOST_WIDE_INT nunits; /* Don't crash if the comparison was erroneous. */ op0 = expand_normal (treeop0); @@ -1308,6 +1309,21 @@ do_compare_and_jump (tree treeop0, tree treeop1, enum rtx_code signed_code, emit_insn (targetm.gen_canonicalize_funcptr_for_compare (new_op1, op1)); op1 = new_op1; } + /* For boolean vectors with less than mode precision precision + make sure to fill padding with consistent values. */ + else if (VECTOR_BOOLEAN_TYPE_P (type) + && SCALAR_INT_MODE_P (mode) + && TYPE_VECTOR_SUBPARTS (type).is_constant (&nunits) + && maybe_ne (GET_MODE_PRECISION (mode), nunits)) + { + gcc_assert (code == EQ || code == NE); + op0 = expand_binop (mode, and_optab, op0, + GEN_INT ((1 << nunits) - 1), NULL_RTX, + true, OPTAB_WIDEN); + op1 = expand_binop (mode, and_optab, op1, + GEN_INT ((1 << nunits) - 1), NULL_RTX, + true, OPTAB_WIDEN); + } do_compare_rtx_and_jump (op0, op1, code, unsignedp, treeop0, mode, ((mode == BLKmode) diff --git a/gcc/expr.cc b/gcc/expr.cc index fc5e998e329..096081fdc53 100644 --- a/gcc/expr.cc +++ b/gcc/expr.cc @@ -13502,6 +13502,7 @@ do_store_flag (sepops ops, rtx target, machine_mode mode) rtx op0, op1; rtx subtarget = target; location_t loc = ops->location; + unsigned HOST_WIDE_INT nunits; arg0 = ops->op0; arg1 = ops->op1; @@ -13694,6 +13695,22 @@ do_store_flag (sepops ops, rtx target, machine_mode mode) expand_operands (arg0, arg1, subtarget, &op0, &op1, EXPAND_NORMAL); + /* For boolean vectors with less than mode precision precision + make sure to fill padding with consistent values. */ + if (VECTOR_BOOLEAN_TYPE_P (type) + && SCALAR_INT_MODE_P (operand_mode) + && TYPE_VECTOR_SUBPARTS (type).is_constant (&nunits) + && maybe_ne (GET_MODE_PRECISION (operand_mode), nunits)) + { + gcc_assert (code == EQ || code == NE); + op0 = expand_binop (mode, and_optab, op0, + GEN_INT ((1 << nunits) - 1), NULL_RTX, + true, OPTAB_WIDEN); + op1 = expand_binop (mode, and_optab, op1, + GEN_INT ((1 << nunits) - 1), NULL_RTX, + true, OPTAB_WIDEN); + } + if (target == 0) target = gen_reg_rtx (mode); -- 2.35.3