target/arm: Implement SVE Floating Point Arithmetic - Unpredicated Group

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180613015641.5667-19-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Richard Henderson 2018-06-15 14:57:15 +01:00 committed by Peter Maydell
parent 6e6a157d68
commit 29b80469dc
5 changed files with 154 additions and 0 deletions

View File

@ -705,3 +705,17 @@ DEF_HELPER_FLAGS_4(sve_umini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_umini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_umini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_4(sve_umini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
DEF_HELPER_FLAGS_5(gvec_recps_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_recps_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_recps_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)

View File

@ -601,6 +601,25 @@ DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
#ifdef TARGET_AARCH64
#include "helper-a64.h"
#include "helper-sve.h"

View File

@ -648,6 +648,16 @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u
# SVE integer multiply immediate (unpredicated)
MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s
### SVE Floating Point Arithmetic - Unpredicated Group
# SVE floating-point arithmetic (unpredicated)
FADD_zzz 01100101 .. 0 ..... 000 000 ..... ..... @rd_rn_rm
FSUB_zzz 01100101 .. 0 ..... 000 001 ..... ..... @rd_rn_rm
FMUL_zzz 01100101 .. 0 ..... 000 010 ..... ..... @rd_rn_rm
FTSMUL 01100101 .. 0 ..... 000 011 ..... ..... @rd_rn_rm
FRECPS 01100101 .. 0 ..... 000 110 ..... ..... @rd_rn_rm
FRSQRTS 01100101 .. 0 ..... 000 111 ..... ..... @rd_rn_rm
### SVE Memory - 32-bit Gather and Unsized Contiguous Group
# SVE load predicate register

View File

@ -3372,6 +3372,48 @@ DO_ZZI(UMIN, umin)
#undef DO_ZZI
/*
*** SVE Floating Point Arithmetic - Unpredicated Group
*/
static bool do_zzz_fp(DisasContext *s, arg_rrr_esz *a,
gen_helper_gvec_3_ptr *fn)
{
if (fn == NULL) {
return false;
}
if (sve_access_check(s)) {
unsigned vsz = vec_full_reg_size(s);
TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
vec_full_reg_offset(s, a->rn),
vec_full_reg_offset(s, a->rm),
status, vsz, vsz, 0, fn);
tcg_temp_free_ptr(status);
}
return true;
}
#define DO_FP3(NAME, name) \
static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a, uint32_t insn) \
{ \
static gen_helper_gvec_3_ptr * const fns[4] = { \
NULL, gen_helper_gvec_##name##_h, \
gen_helper_gvec_##name##_s, gen_helper_gvec_##name##_d \
}; \
return do_zzz_fp(s, a, fns[a->esz]); \
}
DO_FP3(FADD_zzz, fadd)
DO_FP3(FSUB_zzz, fsub)
DO_FP3(FMUL_zzz, fmul)
DO_FP3(FTSMUL, ftsmul)
DO_FP3(FRECPS, recps)
DO_FP3(FRSQRTS, rsqrts)
#undef DO_FP3
/*
*** SVE Memory - 32-bit Gather and Unsized Contiguous Group
*/

View File

@ -426,3 +426,72 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
/* Floating-point trigonometric starting value.
* See the ARM ARM pseudocode function FPTrigSMul.
*/
static float16 float16_ftsmul(float16 op1, uint16_t op2, float_status *stat)
{
float16 result = float16_mul(op1, op1, stat);
if (!float16_is_any_nan(result)) {
result = float16_set_sign(result, op2 & 1);
}
return result;
}
static float32 float32_ftsmul(float32 op1, uint32_t op2, float_status *stat)
{
float32 result = float32_mul(op1, op1, stat);
if (!float32_is_any_nan(result)) {
result = float32_set_sign(result, op2 & 1);
}
return result;
}
static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat)
{
float64 result = float64_mul(op1, op1, stat);
if (!float64_is_any_nan(result)) {
result = float64_set_sign(result, op2 & 1);
}
return result;
}
#define DO_3OP(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \
{ \
intptr_t i, oprsz = simd_oprsz(desc); \
TYPE *d = vd, *n = vn, *m = vm; \
for (i = 0; i < oprsz / sizeof(TYPE); i++) { \
d[i] = FUNC(n[i], m[i], stat); \
} \
}
DO_3OP(gvec_fadd_h, float16_add, float16)
DO_3OP(gvec_fadd_s, float32_add, float32)
DO_3OP(gvec_fadd_d, float64_add, float64)
DO_3OP(gvec_fsub_h, float16_sub, float16)
DO_3OP(gvec_fsub_s, float32_sub, float32)
DO_3OP(gvec_fsub_d, float64_sub, float64)
DO_3OP(gvec_fmul_h, float16_mul, float16)
DO_3OP(gvec_fmul_s, float32_mul, float32)
DO_3OP(gvec_fmul_d, float64_mul, float64)
DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16)
DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32)
DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64)
#ifdef TARGET_AARCH64
DO_3OP(gvec_recps_h, helper_recpsf_f16, float16)
DO_3OP(gvec_recps_s, helper_recpsf_f32, float32)
DO_3OP(gvec_recps_d, helper_recpsf_f64, float64)
DO_3OP(gvec_rsqrts_h, helper_rsqrtsf_f16, float16)
DO_3OP(gvec_rsqrts_s, helper_rsqrtsf_f32, float32)
DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64)
#endif
#undef DO_3OP