@@ -8568,7 +8568,7 @@ static bool trans_FCVT_s_sh(DisasContext *s, arg_rr *a)
if (fp_access_check(s)) {
TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn);
TCGv_i32 tcg_rd = tcg_temp_new_i32();
- TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR_A64);
+ TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR_F16_A64);
TCGv_i32 tcg_ahp = get_ahp_flag();
gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp);
@@ -8582,7 +8582,7 @@ static bool trans_FCVT_s_dh(DisasContext *s, arg_rr *a)
if (fp_access_check(s)) {
TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn);
TCGv_i64 tcg_rd = tcg_temp_new_i64();
- TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR_A64);
+ TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR_F16_A64);
TCGv_i32 tcg_ahp = get_ahp_flag();
gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp);
@@ -9511,13 +9511,14 @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a)
return true;
}
- fpst = fpstatus_ptr(FPST_FPCR_A64);
if (a->esz == MO_64) {
/* 32 -> 64 bit fp conversion */
TCGv_i64 tcg_res[2];
TCGv_i32 tcg_op = tcg_temp_new_i32();
int srcelt = a->q ? 2 : 0;
+ fpst = fpstatus_ptr(FPST_FPCR_A64);
+
for (pass = 0; pass < 2; pass++) {
tcg_res[pass] = tcg_temp_new_i64();
read_vec_element_i32(s, tcg_op, a->rn, srcelt + pass, MO_32);
@@ -9532,6 +9533,8 @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a)
TCGv_i32 tcg_res[4];
TCGv_i32 ahp = get_ahp_flag();
+ fpst = fpstatus_ptr(FPST_FPCR_F16_A64);
+
for (pass = 0; pass < 4; pass++) {
tcg_res[pass] = tcg_temp_new_i32();
read_vec_element_i32(s, tcg_res[pass], a->rn, srcelt + pass, MO_16);
@@ -3887,7 +3887,7 @@ TRANS_FEAT(FCMLA_zzxz, aa64_sve, gen_gvec_fpst_zzzz, fcmla_idx_fns[a->esz],
TRANS_FEAT(FCVT_sh, aa64_sve, gen_gvec_fpst_arg_zpz,
gen_helper_sve_fcvt_sh, a, 0, FPST_FPCR_A64)
TRANS_FEAT(FCVT_hs, aa64_sve, gen_gvec_fpst_arg_zpz,
- gen_helper_sve_fcvt_hs, a, 0, FPST_FPCR_A64)
+ gen_helper_sve_fcvt_hs, a, 0, FPST_FPCR_F16_A64)
TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz,
gen_helper_sve_bfcvt, a, 0, FPST_FPCR_A64)
@@ -3895,7 +3895,7 @@ TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz,
TRANS_FEAT(FCVT_dh, aa64_sve, gen_gvec_fpst_arg_zpz,
gen_helper_sve_fcvt_dh, a, 0, FPST_FPCR_A64)
TRANS_FEAT(FCVT_hd, aa64_sve, gen_gvec_fpst_arg_zpz,
- gen_helper_sve_fcvt_hd, a, 0, FPST_FPCR_A64)
+ gen_helper_sve_fcvt_hd, a, 0, FPST_FPCR_F16_A64)
TRANS_FEAT(FCVT_ds, aa64_sve, gen_gvec_fpst_arg_zpz,
gen_helper_sve_fcvt_ds, a, 0, FPST_FPCR_A64)
TRANS_FEAT(FCVT_sd, aa64_sve, gen_gvec_fpst_arg_zpz,
We should be using the F16-specific float_status for conversions from half-precision, because halfprec inputs never set Input Denormal. Without FEAT_AHP, using the wrong fpst here had no effect, because the only difference between the F16_A64 and A64 fpst is its handling of flush-to-zero on input and output, and the helper functions vfp_fcvt_f16_to_* and vfp_fcvt_*_to_f16 all explicitly squash the relevant flushing flags, and flush_inputs_to_zero was the only way that IDC could be set. With FEAT_AHP, the FPCR.AH=1 behaviour sets IDC for input_denormal_used, which we will only ignore in vfp_get_fpsr_from_host() for the F16_A64 fpst; so it matters that we use that one for f16 inputs (and the normal one for single/double to f16 conversions). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 9 ++++++--- target/arm/tcg/translate-sve.c | 4 ++-- 2 files changed, 8 insertions(+), 5 deletions(-)