@@ -7442,10 +7442,10 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
bool part = extract32(insn, 14, 1);
bool is_q = extract32(insn, 30, 1);
int esize = 8 << size;
- int i, ofs;
+ int i;
int datasize = is_q ? 128 : 64;
int elements = datasize / esize;
- TCGv_i64 tcg_res, tcg_resl, tcg_resh;
+ TCGv_i64 tcg_res[2], tcg_ele;
if (opcode == 0 || (size == 3 && !is_q)) {
unallocated_encoding(s);
@@ -7456,37 +7456,39 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
return;
}
- tcg_resl = tcg_const_i64(0);
- tcg_resh = is_q ? tcg_const_i64(0) : NULL;
- tcg_res = tcg_temp_new_i64();
+ tcg_res[0] = tcg_temp_new_i64();
+ tcg_res[1] = is_q ? tcg_temp_new_i64() : NULL;
+ tcg_ele = tcg_temp_new_i64();
for (i = 0; i < elements; i++) {
+ int o, w;
+
switch (opcode) {
case 1: /* UZP1/2 */
{
int midpoint = elements / 2;
if (i < midpoint) {
- read_vec_element(s, tcg_res, rn, 2 * i + part, size);
+ read_vec_element(s, tcg_ele, rn, 2 * i + part, size);
} else {
- read_vec_element(s, tcg_res, rm,
+ read_vec_element(s, tcg_ele, rm,
2 * (i - midpoint) + part, size);
}
break;
}
case 2: /* TRN1/2 */
if (i & 1) {
- read_vec_element(s, tcg_res, rm, (i & ~1) + part, size);
+ read_vec_element(s, tcg_ele, rm, (i & ~1) + part, size);
} else {
- read_vec_element(s, tcg_res, rn, (i & ~1) + part, size);
+ read_vec_element(s, tcg_ele, rn, (i & ~1) + part, size);
}
break;
case 3: /* ZIP1/2 */
{
int base = part * elements / 2;
if (i & 1) {
- read_vec_element(s, tcg_res, rm, base + (i >> 1), size);
+ read_vec_element(s, tcg_ele, rm, base + (i >> 1), size);
} else {
- read_vec_element(s, tcg_res, rn, base + (i >> 1), size);
+ read_vec_element(s, tcg_ele, rn, base + (i >> 1), size);
}
break;
}
@@ -7494,19 +7496,18 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
g_assert_not_reached();
}
- ofs = i * esize;
- if (ofs < 64) {
- tcg_gen_shli_i64(tcg_res, tcg_res, ofs);
- tcg_gen_or_i64(tcg_resl, tcg_resl, tcg_res);
+ w = (i * esize) / 64;
+ o = (i * esize) % 64;
+ if (o == 0) {
+ tcg_gen_mov_i64(tcg_res[w], tcg_ele);
} else {
- tcg_gen_shli_i64(tcg_res, tcg_res, ofs - 64);
- tcg_gen_or_i64(tcg_resh, tcg_resh, tcg_res);
+ tcg_gen_shli_i64(tcg_ele, tcg_ele, o);
+ tcg_gen_or_i64(tcg_res[w], tcg_res[w], tcg_ele);
}
}
- write_vec_element(s, tcg_resl, rd, 0, MO_64);
- if (is_q) {
- write_vec_element(s, tcg_resh, rd, 1, MO_64);
+ for (i = 0; i <= is_q; ++i) {
+ write_vec_element(s, tcg_res[i], rd, i, MO_64);
}
clear_vec_high(s, is_q, rd);
}
It is easy enough to use mov instead of or-with-zero and relying on the optimizer to fold away the or. Use an array for the output, rather than separate tcg_res{l,h} variables. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/translate-a64.c | 41 +++++++++++++++++----------------- 1 file changed, 21 insertions(+), 20 deletions(-)