yuzu/unicorn
1
0
Fork 0
mirror of https://github.com/yuzu-emu/unicorn.git synced 2024-12-23 16:55:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

target/arm: Convert Neon VQSHL, VRSHL, VQRSHL 3-reg-same insns to decodetree

Browse source 
Convert the VQSHL, VRSHL and VQRSHL insns in the 3-reg-same
group to decodetree. We have already implemented the size==0b11
case of these insns; this commit handles the remaining sizes

Backports commit 6812dfdc6b0286730d6f903ebfbdc4f81b80c29b from qemu
This commit is contained in:
Peter Maydell 2020-05-15 22:53:24 -04:00 committed by Lioncash
parent 5308fb324e
commit f35ae14ab4
3 changed files with 69 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
qemu/target/arm/neon-dp.decode
View file

@ -95,12 +95,30 @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev
@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ @3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \
&3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3
VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev {
VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev
VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev }
VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev {
VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev
VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev
}
{
VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev
}
{
VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev
VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev
}
{
VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev
}
{
VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev
VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev
}
VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same

42
qemu/target/arm/translate-neon.inc.c
View file

@ -892,10 +892,52 @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64)
return do_3same(s, a, gen_##INSN##_3s); \ return do_3same(s, a, gen_##INSN##_3s); \
} }
/*
* Some helper functions need to be passed the cpu_env. In order
* to use those with the gvec APIs like tcg_gen_gvec_3() we need
* to create wrapper functions whose prototype is a NeonGenTwoOpFn()
* and which call a NeonGenTwoOpEnvFn().
*/
#define WRAP_ENV_FN(WRAPNAME, FUNC) \
static void WRAPNAME(TCGContext *s, TCGv_i32 d, TCGv_i32 n, TCGv_i32 m) \
{ \
FUNC(s, d, s->cpu_env, n, m); \
}
#define DO_3SAME_32_ENV(INSN, FUNC) \
WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8); \
WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16); \
WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32); \
static void gen_##INSN##_3s(TCGContext *s, unsigned vece, uint32_t rd_ofs, \
uint32_t rn_ofs, uint32_t rm_ofs, \
uint32_t oprsz, uint32_t maxsz) \
{ \
static const GVecGen3 ops[4] = { \
{ .fni4 = gen_##INSN##_tramp8 }, \
{ .fni4 = gen_##INSN##_tramp16 }, \
{ .fni4 = gen_##INSN##_tramp32 }, \
{ 0 }, \
}; \
tcg_gen_gvec_3(s, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \
} \
static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \
{ \
if (a->size > 2) { \
return false; \
} \
return do_3same(s, a, gen_##INSN##_3s); \
}
DO_3SAME_32(VHADD_S, hadd_s) DO_3SAME_32(VHADD_S, hadd_s)
DO_3SAME_32(VHADD_U, hadd_u) DO_3SAME_32(VHADD_U, hadd_u)
DO_3SAME_32(VHSUB_S, hsub_s) DO_3SAME_32(VHSUB_S, hsub_s)
DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VHSUB_U, hsub_u)
DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_S, rhadd_s)
DO_3SAME_32(VRHADD_U, rhadd_u) DO_3SAME_32(VRHADD_U, rhadd_u)
DO_3SAME_32(VRSHL_S, rshl_s)
DO_3SAME_32(VRSHL_U, rshl_u)
DO_3SAME_32_ENV(VQSHL_S, qshl_s)
DO_3SAME_32_ENV(VQSHL_U, qshl_u)
DO_3SAME_32_ENV(VQRSHL_S, qrshl_s)
DO_3SAME_32_ENV(VQRSHL_U, qrshl_u)

23
qemu/target/arm/translate.c
View file

@ -5566,6 +5566,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
case NEON_3R_VHSUB: case NEON_3R_VHSUB:
case NEON_3R_VABD: case NEON_3R_VABD:
case NEON_3R_VABA: case NEON_3R_VABA:
case NEON_3R_VQSHL:
case NEON_3R_VRSHL:
case NEON_3R_VQRSHL:
/* Already handled by decodetree */ /* Already handled by decodetree */
return 1; return 1;
} }
@ -5576,17 +5579,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
} }
pairwise = 0; pairwise = 0;
switch (op) { switch (op) {
case NEON_3R_VQSHL:
case NEON_3R_VRSHL:
case NEON_3R_VQRSHL:
{
int rtmp;
/* Shift instruction operands are reversed. */
rtmp = rn;
rn = rm;
rm = rtmp;
}
break;
case NEON_3R_VPADD_VQRDMLAH: case NEON_3R_VPADD_VQRDMLAH:
case NEON_3R_VPMAX: case NEON_3R_VPMAX:
case NEON_3R_VPMIN: case NEON_3R_VPMIN:
@ -5646,15 +5638,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
tmp2 = neon_load_reg(s, rm, pass); tmp2 = neon_load_reg(s, rm, pass);
} }
switch (op) { switch (op) {
case NEON_3R_VQSHL:
GEN_NEON_INTEGER_OP_ENV(qshl);
break;
case NEON_3R_VRSHL:
GEN_NEON_INTEGER_OP(rshl);
break;
case NEON_3R_VQRSHL:
GEN_NEON_INTEGER_OP_ENV(qrshl);
break;
case NEON_3R_VPMAX: case NEON_3R_VPMAX:
GEN_NEON_INTEGER_OP(pmax); GEN_NEON_INTEGER_OP(pmax);
break; break;