Split out the tail of fold_neg to fold_neg_no_const so that we can avoid attempting to constant fold vector negate.
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2150 Signed-off-by: Richard Henderson <richard.hender...@linaro.org> --- tcg/optimize.c | 17 ++++++++--------- tests/tcg/aarch64/test-2150.c | 12 ++++++++++++ tests/tcg/aarch64/Makefile.target | 2 +- 3 files changed, 21 insertions(+), 10 deletions(-) create mode 100644 tests/tcg/aarch64/test-2150.c diff --git a/tcg/optimize.c b/tcg/optimize.c index 275db77b42..2e9e5725a9 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -1990,16 +1990,10 @@ static bool fold_nand(OptContext *ctx, TCGOp *op) return false; } -static bool fold_neg(OptContext *ctx, TCGOp *op) +static bool fold_neg_no_const(OptContext *ctx, TCGOp *op) { - uint64_t z_mask; - - if (fold_const1(ctx, op)) { - return true; - } - /* Set to 1 all bits to the left of the rightmost. */ - z_mask = arg_info(op->args[1])->z_mask; + uint64_t z_mask = arg_info(op->args[1])->z_mask; ctx->z_mask = -(z_mask & -z_mask); /* @@ -2010,6 +2004,11 @@ static bool fold_neg(OptContext *ctx, TCGOp *op) return true; } +static bool fold_neg(OptContext *ctx, TCGOp *op) +{ + return fold_const1(ctx, op) || fold_neg_no_const(ctx, op); +} + static bool fold_nor(OptContext *ctx, TCGOp *op) { if (fold_const2_commutative(ctx, op) || @@ -2418,7 +2417,7 @@ static bool fold_sub_to_neg(OptContext *ctx, TCGOp *op) if (have_neg) { op->opc = neg_op; op->args[1] = op->args[2]; - return fold_neg(ctx, op); + return fold_neg_no_const(ctx, op); } return false; } diff --git a/tests/tcg/aarch64/test-2150.c b/tests/tcg/aarch64/test-2150.c new file mode 100644 index 0000000000..fb86c11958 --- /dev/null +++ b/tests/tcg/aarch64/test-2150.c @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* See https://gitlab.com/qemu-project/qemu/-/issues/2150 */ + +int main() +{ + asm volatile( + "movi v6.4s, #1\n" + "movi v7.4s, #0\n" + "sub v6.2d, v7.2d, v6.2d\n" + : : : "v6", "v7"); + return 0; +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index 0efd565f05..70d728ae9a 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -10,7 +10,7 @@ VPATH += $(AARCH64_SRC) # Base architecture tests AARCH64_TESTS=fcvt pcalign-a64 lse2-fault -AARCH64_TESTS += test-2248 +AARCH64_TESTS += test-2248 test-2150 fcvt: LDFLAGS+=-lm -- 2.34.1
