openkylin
/
qemu
mirror of https://gitee.com/openkylin/qemu.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

arm/translate-a64: add FP16 pairwise ops simd_three_reg_same_fp16 

This includes FMAXNMP, FADDP, FMAXP, FMINNMP, FMINP.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180227143852.11175-14-alex.bennee@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Alex Bennée 2018-03-01 11:05:51 +00:00 committed by Peter Maydell
parent 026e2d6ef7
commit 7a2c6e6181
1 changed files with 133 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

208
target/arm/translate-a64.c
View File

@ -10247,6 +10247,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
int datasize, elements; int datasize, elements;
int pass; int pass;
TCGv_ptr fpst; TCGv_ptr fpst;
bool pairwise = false;
if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
unallocated_encoding(s); unallocated_encoding(s);
@ -10272,91 +10273,148 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
datasize = is_q ? 128 : 64; datasize = is_q ? 128 : 64;
elements = datasize / 16; elements = datasize / 16;
switch (fpopcode) {
case 0x10: /* FMAXNMP */
case 0x12: /* FADDP */
case 0x16: /* FMAXP */
case 0x18: /* FMINNMP */
case 0x1e: /* FMINP */
pairwise = true;
break;
}
fpst = get_fpstatus_ptr(true); fpst = get_fpstatus_ptr(true);
for (pass = 0; pass < elements; pass++) { if (pairwise) {
int maxpass = is_q ? 8 : 4;
TCGv_i32 tcg_op1 = tcg_temp_new_i32(); TCGv_i32 tcg_op1 = tcg_temp_new_i32();
TCGv_i32 tcg_op2 = tcg_temp_new_i32(); TCGv_i32 tcg_op2 = tcg_temp_new_i32();
TCGv_i32 tcg_res = tcg_temp_new_i32(); TCGv_i32 tcg_res[8];
read_vec_element_i32(s, tcg_op1, rn, pass, MO_16); for (pass = 0; pass < maxpass; pass++) {
read_vec_element_i32(s, tcg_op2, rm, pass, MO_16); int passreg = pass < (maxpass / 2) ? rn : rm;
int passelt = (pass << 1) & (maxpass - 1);
switch (fpopcode) { read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_16);
case 0x0: /* FMAXNM */ read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_16);
gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); tcg_res[pass] = tcg_temp_new_i32();
break;
case 0x1: /* FMLA */ switch (fpopcode) {
read_vec_element_i32(s, tcg_res, rd, pass, MO_16); case 0x10: /* FMAXNMP */
gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res, gen_helper_advsimd_maxnumh(tcg_res[pass], tcg_op1, tcg_op2,
fpst); fpst);
break; break;
case 0x2: /* FADD */ case 0x12: /* FADDP */
gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_advsimd_addh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
break; break;
case 0x3: /* FMULX */ case 0x16: /* FMAXP */
gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_advsimd_maxh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
break; break;
case 0x4: /* FCMEQ */ case 0x18: /* FMINNMP */
gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst); gen_helper_advsimd_minnumh(tcg_res[pass], tcg_op1, tcg_op2,
break; fpst);
case 0x6: /* FMAX */ break;
gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); case 0x1e: /* FMINP */
break; gen_helper_advsimd_minh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
case 0x7: /* FRECPS */ break;
gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst); default:
break; g_assert_not_reached();
case 0x8: /* FMINNM */ }
gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); }
break;
case 0x9: /* FMLS */ for (pass = 0; pass < maxpass; pass++) {
/* As usual for ARM, separate negation for fused multiply-add */ write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_16);
tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); tcg_temp_free_i32(tcg_res[pass]);
read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
fpst);
break;
case 0xa: /* FSUB */
gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0xe: /* FMIN */
gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0xf: /* FRSQRTS */
gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x13: /* FMUL */
gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x14: /* FCMGE */
gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x15: /* FACGE */
gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x17: /* FDIV */
gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x1a: /* FABD */
gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff);
break;
case 0x1c: /* FCMGT */
gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x1d: /* FACGT */
gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
default:
fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
__func__, insn, fpopcode, s->pc);
g_assert_not_reached();
} }
write_vec_element_i32(s, tcg_res, rd, pass, MO_16);
tcg_temp_free_i32(tcg_res);
tcg_temp_free_i32(tcg_op1); tcg_temp_free_i32(tcg_op1);
tcg_temp_free_i32(tcg_op2); tcg_temp_free_i32(tcg_op2);
} else {
for (pass = 0; pass < elements; pass++) {
TCGv_i32 tcg_op1 = tcg_temp_new_i32();
TCGv_i32 tcg_op2 = tcg_temp_new_i32();
TCGv_i32 tcg_res = tcg_temp_new_i32();
read_vec_element_i32(s, tcg_op1, rn, pass, MO_16);
read_vec_element_i32(s, tcg_op2, rm, pass, MO_16);
switch (fpopcode) {
case 0x0: /* FMAXNM */
gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x1: /* FMLA */
read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
fpst);
break;
case 0x2: /* FADD */
gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x3: /* FMULX */
gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x4: /* FCMEQ */
gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x6: /* FMAX */
gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x7: /* FRECPS */
gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x8: /* FMINNM */
gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x9: /* FMLS */
/* As usual for ARM, separate negation for fused multiply-add */
tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000);
read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
fpst);
break;
case 0xa: /* FSUB */
gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0xe: /* FMIN */
gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0xf: /* FRSQRTS */
gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x13: /* FMUL */
gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x14: /* FCMGE */
gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x15: /* FACGE */
gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x17: /* FDIV */
gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x1a: /* FABD */
gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff);
break;
case 0x1c: /* FCMGT */
gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
case 0x1d: /* FACGT */
gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
break;
default:
fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
__func__, insn, fpopcode, s->pc);
g_assert_not_reached();
}
write_vec_element_i32(s, tcg_res, rd, pass, MO_16);
tcg_temp_free_i32(tcg_res);
tcg_temp_free_i32(tcg_op1);
tcg_temp_free_i32(tcg_op2);
}
} }
tcg_temp_free_ptr(fpst); tcg_temp_free_ptr(fpst);