Decode tile number and index offset beforehand and separately.
Signed-off-by: Richard Henderson <richard.hender...@linaro.org>
---
target/arm/tcg/translate-sme.c | 17 +++++--------
target/arm/tcg/sme.decode | 46 +++++++++++++++++++++++-----------
2 files changed, 38 insertions(+), 25 deletions(-)
diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 13314c5cd7..bd6095ffb6 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -41,15 +41,10 @@ static bool sme2_zt0_enabled_check(DisasContext *s)
return true;
}
-/*
- * Resolve tile.size[index] to a host pointer, where tile and index
- * are always decoded together, dependent on the element size.
- */
+/* Resolve tile.size[rs+imm] to a host pointer. */
static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs,
- int tile_index, bool vertical)
+ int tile, int imm, bool vertical)
{
- int tile = tile_index >> (4 - esz);
- int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz);
int pos, len, offset;
TCGv_i32 tmp;
TCGv_ptr addr;
@@ -57,7 +52,7 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int
rs,
/* Compute the final index, which is Rs+imm. */
tmp = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs));
- tcg_gen_addi_i32(tmp, tmp, index);
+ tcg_gen_addi_i32(tmp, tmp, imm);
/* Prepare a power-of-two modulo via extraction of @len bits. */
len = ctz32(streaming_vec_reg_size(s)) - esz;
@@ -185,7 +180,7 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
t_zr = vec_full_reg_ptr(s, a->zr);
t_pg = pred_full_reg_ptr(s, a->pg);
@@ -264,7 +259,7 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a)
return true;
}
- t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v);
+ t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, a->v);
t_pg = pred_full_reg_ptr(s, a->pg);
addr = tcg_temp_new_i64();
@@ -295,7 +290,7 @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a,
GenLdStR *fn)
}
/* ZA[n] equates to ZA0H.B[n]. */
- base = get_tile_rowcol(s, MO_8, a->rv, imm, false);
+ base = get_tile_rowcol(s, MO_8, a->rv, 0, imm, false);
fn(s, base, 0, svl, a->rn, imm * svl);
return true;
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 83ca6a9104..efe369e079 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -27,17 +27,29 @@ ZERO_zt0 11000000 01 001 00000000000 00000001
### SME Move into/from Array
%mova_rs 13:2 !function=plus_12
-&mova esz rs pg zr za_imm v:bool to_vec:bool
+&mova esz rs pg zr za off v:bool to_vec:bool
-MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \
- &mova to_vec=0 rs=%mova_rs
-MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \
- &mova to_vec=0 rs=%mova_rs esz=4
+MOVA 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \
+ &mova to_vec=0 rs=%mova_rs esz=0 za=0
+MOVA 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \
+ &mova to_vec=0 rs=%mova_rs esz=1
+MOVA 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \
+ &mova to_vec=0 rs=%mova_rs esz=2
+MOVA 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \
+ &mova to_vec=0 rs=%mova_rs esz=3
+MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \
+ &mova to_vec=0 rs=%mova_rs esz=4 off=0
-MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs
-MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \
- &mova to_vec=1 rs=%mova_rs esz=4
+MOVA 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=0 za=0
+MOVA 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=1
+MOVA 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=2
+MOVA 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=3
+MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \
+ &mova to_vec=1 rs=%mova_rs esz=4 off=0
### SME Move into/from ZT0
@@ -46,12 +58,18 @@ MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5
### SME Memory
-&ldst esz rs pg rn rm za_imm v:bool st:bool
+&ldst esz rs pg rn rm za off v:bool st:bool
-LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \
- &ldst rs=%mova_rs
-LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \
- &ldst esz=4 rs=%mova_rs
+LDST1 1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4 \
+ &ldst rs=%mova_rs esz=0 za=0
+LDST1 1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3 \
+ &ldst rs=%mova_rs esz=1
+LDST1 1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2 \
+ &ldst rs=%mova_rs esz=2
+LDST1 1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1 \
+ &ldst rs=%mova_rs esz=3
+LDST1 1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4 \
+ &ldst rs=%mova_rs esz=4 off=0
&ldstr rv rn imm
@ldstr ....... ... . ...... .. ... rn:5 . imm:4 \
--
2.43.0
