@@ -479,6 +479,8 @@ DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_splice, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
@@ -2088,3 +2088,40 @@ int32_t HELPER(sve_last_active_element)(void *vg, uint32_t pred_desc)
return last_active_element(vg, DIV_ROUND_UP(oprsz, 8), esz);
}
+
+void HELPER(sve_splice)(void *vd, void *vn, void *vm, void *vg, uint32_t desc)
+{
+ intptr_t opr_sz = simd_oprsz(desc) / 8;
+ int esz = simd_data(desc);
+ uint64_t pg, first_g, last_g, len, mask = pred_esz_masks[esz];
+ intptr_t i, first_i, last_i;
+ ARMVectorReg tmp;
+
+ first_i = last_i = 0;
+ first_g = last_g = 0;
+
+ /* Find the extent of the active elements within VG. */
+ for (i = QEMU_ALIGN_UP(opr_sz, 8) - 8; i >= 0; i -= 8) {
+ pg = *(uint64_t *)(vg + i) & mask;
+ if (pg) {
+ if (last_g == 0) {
+ last_g = pg;
+ last_i = i;
+ }
+ first_g = pg;
+ first_i = i;
+ }
+ }
+
+ len = 0;
+ if (first_g != 0) {
+ first_i = first_i * 8 + ctz64(first_g);
+ last_i = last_i * 8 + 63 - clz64(last_g);
+ len = last_i - first_i + (1 << esz);
+ if (vd == vm) {
+ vm = memcpy(&tmp, vm, opr_sz * 8);
+ }
+ swap_memmove(vd, vn + first_i, len);
+ }
+ swap_memmove(vd + len, vm, opr_sz * 8 - len);
+}
@@ -2473,6 +2473,16 @@ static void trans_RBIT(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
do_zpz_ool(s, a, fns[a->esz]);
}
+static void trans_SPLICE(DisasContext *s, arg_rprr_esz *a, uint32_t insn)
+{
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_4_ool(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vec_full_reg_offset(s, a->rm),
+ pred_full_reg_offset(s, a->pg),
+ vsz, vsz, a->esz, gen_helper_sve_splice);
+}
+
/*
*** SVE Memory - 32-bit Gather and Unsized Contiguous Group
*/
@@ -464,6 +464,9 @@ REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn
REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn
RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn
+# SVE vector splice (predicated)
+SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm
+
### SVE Predicate Logical Operations Group
# SVE predicate logical operations
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-sve.h | 2 ++ target/arm/sve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 10 ++++++++++ target/arm/sve.decode | 3 +++ 4 files changed, 52 insertions(+) -- 2.14.3