@@ -2516,6 +2516,16 @@ DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_match_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_match_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_nmatch_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_nmatch_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG,
@@ -1305,6 +1305,11 @@ UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr
UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr
UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr
+### SVE2 Character Match
+
+MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm
+NMATCH 01000101 .. 1 ..... 100 ... ..... 1 .... @pd_pg_rn_rm
+
## SVE2 floating-point pairwise operations
FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm
@@ -6890,3 +6890,32 @@ DO_ST1_ZPZ_D(dd_be, zd, MO_64)
#undef DO_ST1_ZPZ_S
#undef DO_ST1_ZPZ_D
+
+#define DO_ZPZZ_CHAR_MATCH(NAME, TYPE, H, EQUALS) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \
+ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \
+ uint16_t *pd = (uint16_t *)(vd + H1_2(i >> 3)); \
+ *pd = (*pd & ~1) | ((0 & EQUALS) | (1 & !EQUALS)); \
+ if (pg & 1) { \
+ TYPE nn = *(TYPE *)(vn + H(i)); \
+ for (intptr_t j = 0; j < 16; j += sizeof(TYPE)) { \
+ TYPE mm = *(TYPE *)(vm + H(i * 16 + j)); \
+ bool eq = nn == mm; \
+ if ((eq && EQUALS) || (!eq && !EQUALS)) { \
+ *pd = (*pd & ~1) | ((1 & EQUALS) | (0 & !EQUALS)); \
+ } \
+ } \
+ } \
+ } \
+}
+
+DO_ZPZZ_CHAR_MATCH(sve2_match_zpzz_b, uint8_t, H1, true)
+DO_ZPZZ_CHAR_MATCH(sve2_match_zpzz_h, uint16_t, H1_2, true)
+
+DO_ZPZZ_CHAR_MATCH(sve2_nmatch_zpzz_b, uint8_t, H1, false)
+DO_ZPZZ_CHAR_MATCH(sve2_nmatch_zpzz_h, uint16_t, H1_2, false)
+
+#undef DO_ZPZZ_CHAR_MATCH
@@ -7246,6 +7246,49 @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a)
return do_sve2_shr_narrow(s, a, ops);
}
+static bool do_sve2_zpzz_char_match(DisasContext *s, arg_rprr_esz *a,
+ gen_helper_gvec_4 *fn)
+{
+ if (!dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ if (fn == NULL) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ unsigned psz = pred_full_reg_size(s);
+ int dofs = pred_full_reg_offset(s, a->rd);
+ int nofs = vec_full_reg_offset(s, a->rn);
+ int mofs = vec_full_reg_offset(s, a->rm);
+ int gofs = pred_full_reg_offset(s, a->pg);
+
+ /* Save a copy if the destination overwrites the guarding predicate */
+ int tofs = gofs;
+ if (a->rd == a->pg) {
+ tofs = offsetof(CPUARMState, vfp.preg_tmp);
+ tcg_gen_gvec_mov(0, tofs, gofs, psz, psz);
+ }
+
+ tcg_gen_gvec_4_ool(dofs, nofs, mofs, gofs, vsz, vsz, 0, fn);
+ do_predtest(s, dofs, tofs, psz / 8);
+ }
+ return true;
+}
+
+#define DO_SVE2_ZPZZ_CHAR_MATCH(NAME, name) \
+static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a) \
+{ \
+ static gen_helper_gvec_4 * const fns[4] = { \
+ gen_helper_sve2_##name##_zpzz_b, gen_helper_sve2_##name##_zpzz_h, \
+ NULL, NULL \
+ }; \
+ return do_sve2_zpzz_char_match(s, a, fns[a->esz]); \
+}
+
+DO_SVE2_ZPZZ_CHAR_MATCH(MATCH, match)
+DO_SVE2_ZPZZ_CHAR_MATCH(NMATCH, nmatch)
+
static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_4_ptr *fn)
{
Signed-off-by: Stephen Long <steplong@quicinc.com> --- Submitting this for early review. I'm working with Richard on SVE2 support for qemu. I'll be attempting to tackle the insns in the 'SVE2 integer add/subtract narrow high part' category next [1]. [1] ISA manual: https://static.docs.arm.com/ddi0602/d/ISA_A64_xml_futureA-2019-12_OPT.pdf (page 2950) target/arm/helper-sve.h | 10 +++++++++ target/arm/sve.decode | 5 +++++ target/arm/sve_helper.c | 29 +++++++++++++++++++++++++ target/arm/translate-sve.c | 43 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 87 insertions(+)