diff options
author | Michael Matz <matz@suse.de> | 2014-01-31 14:47:31 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2014-01-31 14:47:31 +0000 |
commit | 5fa5469c08f6e51eed26d6d54e0be8682723d3df (patch) | |
tree | 96dd7b74679afa9dd0625e1b216219f60be49b8a /target-arm | |
parent | 7c51048fa918f64806adf0f76166e9940d772eb1 (diff) | |
download | qemu-5fa5469c08f6e51eed26d6d54e0be8682723d3df.zip qemu-5fa5469c08f6e51eed26d6d54e0be8682723d3df.tar.gz qemu-5fa5469c08f6e51eed26d6d54e0be8682723d3df.tar.bz2 |
target-arm: A64: Add SIMD ZIP/UZP/TRN
Add support for the SIMD ZIP/UZIP/TRN instruction group
(C3.6.3).
Signed-off-by: Michael Matz <matz@suse.de>
[PMM: use new do_vec_get/set etc functions and generally update to new
codebase standards; refactor to pull per-element loop outside switch]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Diffstat (limited to 'target-arm')
-rw-r--r-- | target-arm/translate-a64.c | 76 |
1 files changed, 75 insertions, 1 deletions
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c index 7a6b00a..59e2a85 100644 --- a/target-arm/translate-a64.c +++ b/target-arm/translate-a64.c @@ -4806,7 +4806,81 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) */ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn) { - unsupported_encoding(s, insn); + int rd = extract32(insn, 0, 5); + int rn = extract32(insn, 5, 5); + int rm = extract32(insn, 16, 5); + int size = extract32(insn, 22, 2); + /* opc field bits [1:0] indicate ZIP/UZP/TRN; + * bit 2 indicates 1 vs 2 variant of the insn. + */ + int opcode = extract32(insn, 12, 2); + bool part = extract32(insn, 14, 1); + bool is_q = extract32(insn, 30, 1); + int esize = 8 << size; + int i, ofs; + int datasize = is_q ? 128 : 64; + int elements = datasize / esize; + TCGv_i64 tcg_res, tcg_resl, tcg_resh; + + if (opcode == 0 || (size == 3 && !is_q)) { + unallocated_encoding(s); + return; + } + + tcg_resl = tcg_const_i64(0); + tcg_resh = tcg_const_i64(0); + tcg_res = tcg_temp_new_i64(); + + for (i = 0; i < elements; i++) { + switch (opcode) { + case 1: /* UZP1/2 */ + { + int midpoint = elements / 2; + if (i < midpoint) { + read_vec_element(s, tcg_res, rn, 2 * i + part, size); + } else { + read_vec_element(s, tcg_res, 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); + } else { + read_vec_element(s, tcg_res, 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); + } else { + read_vec_element(s, tcg_res, rn, base + (i >> 1), size); + } + break; + } + default: + 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); + } else { + tcg_gen_shli_i64(tcg_res, tcg_res, ofs - 64); + tcg_gen_or_i64(tcg_resh, tcg_resh, tcg_res); + } + } + + tcg_temp_free_i64(tcg_res); + + write_vec_element(s, tcg_resl, rd, 0, MO_64); + tcg_temp_free_i64(tcg_resl); + write_vec_element(s, tcg_resh, rd, 1, MO_64); + tcg_temp_free_i64(tcg_resh); } /* C3.6.4 AdvSIMD across lanes |