yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2025-01-23 18:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/arm: Implement FP data-processing (3 source) for fp16

Browse source 
We missed all of the scalar fp16 fma operations.

Backports commit 95f9864fde6078e2d2c036a07cc4fe44f199be96 from qemu
This commit is contained in:
Richard Henderson 2018-05-15 22:16:43 -04:00 committed by Lioncash
parent a614dbb3c7
commit eeab666292
No known key found for this signature in database
GPG key ID: 4E3C3CC1031BA9C7
1 changed files with 50 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

50
qemu/target/arm/translate-a64.c
View file

@ -5579,6 +5579,46 @@ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1,
tcg_temp_free_i64(tcg_ctx, tcg_res);
}
/* Floating-point data-processing (3 source) - half precision */
static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1,
int rd, int rn, int rm, int ra)
{
TCGContext *tcg_ctx = s->uc->tcg_ctx;
TCGv_i32 tcg_op1, tcg_op2, tcg_op3;
TCGv_i32 tcg_res = tcg_temp_new_i32(tcg_ctx);
TCGv_ptr fpst = get_fpstatus_ptr(tcg_ctx, true);
tcg_op1 = read_fp_hreg(s, rn);
tcg_op2 = read_fp_hreg(s, rm);
tcg_op3 = read_fp_hreg(s, ra);
/* These are fused multiply-add, and must be done as one
* floating point operation with no rounding between the
* multiplication and addition steps.
* NB that doing the negations here as separate steps is
* correct : an input NaN should come out with its sign bit
* flipped if it is a negated-input.
*/
if (o1 == true) {
tcg_gen_xori_i32(tcg_ctx, tcg_op3, tcg_op3, 0x8000);
}
if (o0 != o1) {
tcg_gen_xori_i32(tcg_ctx, tcg_op1, tcg_op1, 0x8000);
}
gen_helper_advsimd_muladdh(tcg_ctx, tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst);
write_fp_sreg(s, rd, tcg_res);
tcg_temp_free_ptr(tcg_ctx, fpst);
tcg_temp_free_i32(tcg_ctx, tcg_op1);
tcg_temp_free_i32(tcg_ctx, tcg_op2);
tcg_temp_free_i32(tcg_ctx, tcg_op3);
tcg_temp_free_i32(tcg_ctx, tcg_res);
}
/* Floating point data-processing (3 source)
* 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0
* +---+---+---+-----------+------+----+------+----+------+------+------+
@ -5608,6 +5648,16 @@ static void disas_fp_3src(DisasContext *s, uint32_t insn)
}
handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra);
break;
case 3:
if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
unallocated_encoding(s);
return;
}
if (!fp_access_check(s)) {
return;
}
handle_fp_3src_half(s, o0, o1, rd, rn, rm, ra);
break;
default:
unallocated_encoding(s);
}