target/arm: Implement MVE VCLZ

Implement the MVE VCLZ insn (and the necessary machinery
for MVE 1-input vector ops).

Note that for non-load instructions predication is always performed
at a byte level granularity regardless of element size (R_ZLSJ),
and so the masking logic here differs from that used in the VLDR
and VSTR helpers.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-4-peter.maydell@linaro.org
This commit is contained in:
Peter Maydell 2021-06-17 13:15:47 +01:00
parent 2fc6b7510c
commit 0f0f2bd548
4 changed files with 132 additions and 0 deletions

View file

@ -29,6 +29,7 @@
#include "decode-mve.c.inc"
typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
/* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
static inline long mve_qreg_offset(unsigned reg)
@ -160,3 +161,40 @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a)
DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h)
DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w)
DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w)
static bool do_1op(DisasContext *s, arg_1op *a, MVEGenOneOpFn fn)
{
TCGv_ptr qd, qm;
if (!dc_isar_feature(aa32_mve, s) ||
!mve_check_qreg_bank(s, a->qd | a->qm) ||
!fn) {
return false;
}
if (!mve_eci_check(s) || !vfp_access_check(s)) {
return true;
}
qd = mve_qreg_ptr(a->qd);
qm = mve_qreg_ptr(a->qm);
fn(cpu_env, qd, qm);
tcg_temp_free_ptr(qd);
tcg_temp_free_ptr(qm);
mve_update_eci(s);
return true;
}
#define DO_1OP(INSN, FN) \
static bool trans_##INSN(DisasContext *s, arg_1op *a) \
{ \
static MVEGenOneOpFn * const fns[] = { \
gen_helper_mve_##FN##b, \
gen_helper_mve_##FN##h, \
gen_helper_mve_##FN##w, \
NULL, \
}; \
return do_1op(s, a, fns[a->size]); \
}
DO_1OP(VCLZ, vclz)