ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

target/arm: Implement fp16 for Neon VMUL, VMLA, VMLS 

Convert the Neon floating-point VMUL, VMLA and VMLS to use gvec,
and use this to implement fp16 support.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-45-peter.maydell@linaro.org
This commit is contained in:
Peter Maydell 2020-08-28 19:33:53 +01:00
parent c50d8d1440
commit fc8ae79031
1 changed files with 57 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

114
target/arm/translate-neon.c.inc
View File

@ -2432,70 +2432,70 @@ static bool trans_VMLS_2sc(DisasContext *s, arg_2scalar *a)
return do_2scalar(s, a, opfn[a->size], accfn[a->size]); return do_2scalar(s, a, opfn[a->size], accfn[a->size]);
} }
/* static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a,
* Rather than have a float-specific version of do_2scalar just for gen_helper_gvec_3_ptr *fn)
* three insns, we wrap a NeonGenTwoSingleOpFn to turn it into {
* a NeonGenTwoOpFn. /* Two registers and a scalar, using gvec */
*/ int vec_size = a->q ? 16 : 8;
#define WRAP_FP_FN(WRAPNAME, FUNC) \ int rd_ofs = neon_reg_offset(a->vd, 0);
static void WRAPNAME(TCGv_i32 rd, TCGv_i32 rn, TCGv_i32 rm) \ int rn_ofs = neon_reg_offset(a->vn, 0);
{ \ int rm_ofs;
TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD); \ int idx;
FUNC(rd, rn, rm, fpstatus); \ TCGv_ptr fpstatus;
tcg_temp_free_ptr(fpstatus); \
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
return false;
} }
WRAP_FP_FN(gen_VMUL_F_mul, gen_helper_vfp_muls) /* UNDEF accesses to D16-D31 if they don't exist. */
WRAP_FP_FN(gen_VMUL_F_add, gen_helper_vfp_adds) if (!dc_isar_feature(aa32_simd_r32, s) &&
WRAP_FP_FN(gen_VMUL_F_sub, gen_helper_vfp_subs) ((a->vd | a->vn | a->vm) & 0x10)) {
return false;
}
static bool trans_VMUL_F_2sc(DisasContext *s, arg_2scalar *a) if (!fn) {
{ /* Bad size (including size == 3, which is a different insn group) */
static NeonGenTwoOpFn * const opfn[] = { return false;
NULL, }
NULL, /* TODO: fp16 support */
gen_VMUL_F_mul,
NULL,
};
return do_2scalar(s, a, opfn[a->size], NULL); if (a->q && ((a->vd | a->vn) & 1)) {
return false;
}
if (!vfp_access_check(s)) {
return true;
}
/* a->vm is M:Vm, which encodes both register and index */
idx = extract32(a->vm, a->size + 2, 2);
a->vm = extract32(a->vm, 0, a->size + 2);
rm_ofs = neon_reg_offset(a->vm, 0);
fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD);
tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus,
vec_size, vec_size, idx, fn);
tcg_temp_free_ptr(fpstatus);
return true;
} }
static bool trans_VMLA_F_2sc(DisasContext *s, arg_2scalar *a) #define DO_VMUL_F_2sc(NAME, FUNC) \
{ static bool trans_##NAME##_F_2sc(DisasContext *s, arg_2scalar *a) \
static NeonGenTwoOpFn * const opfn[] = { { \
NULL, static gen_helper_gvec_3_ptr * const opfn[] = { \
NULL, /* TODO: fp16 support */ NULL, \
gen_VMUL_F_mul, gen_helper_##FUNC##_h, \
NULL, gen_helper_##FUNC##_s, \
}; NULL, \
static NeonGenTwoOpFn * const accfn[] = { }; \
NULL, if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { \
NULL, /* TODO: fp16 support */ return false; \
gen_VMUL_F_add, } \
NULL, return do_2scalar_fp_vec(s, a, opfn[a->size]); \
}; }
return do_2scalar(s, a, opfn[a->size], accfn[a->size]); DO_VMUL_F_2sc(VMUL, gvec_fmul_idx)
} DO_VMUL_F_2sc(VMLA, gvec_fmla_nf_idx)
DO_VMUL_F_2sc(VMLS, gvec_fmls_nf_idx)
static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a)
{
static NeonGenTwoOpFn * const opfn[] = {
NULL,
NULL, /* TODO: fp16 support */
gen_VMUL_F_mul,
NULL,
};
static NeonGenTwoOpFn * const accfn[] = {
NULL,
NULL, /* TODO: fp16 support */
gen_VMUL_F_sub,
NULL,
};
return do_2scalar(s, a, opfn[a->size], accfn[a->size]);
}
WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16) WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16)
WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32) WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32)