@@ -676,3 +676,5 @@ DEF_HELPER_FLAGS_4(sve_brkbs_m, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32)
@@ -2724,3 +2724,17 @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc)
return do_zero(vd, oprsz);
}
}
+
+uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
+{
+ intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2;
+ intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2);
+ uint64_t *n = vn, *g = vg, sum = 0, mask = pred_esz_masks[esz];
+ intptr_t i;
+
+ for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) {
+ uint64_t t = n[i] & g[i] & mask;
+ sum += ctpop64(t);
+ }
+ return sum;
+}
@@ -34,6 +34,9 @@
#include "translate-a64.h"
+typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t,
+ TCGv_i64, uint32_t, uint32_t);
+
typedef void gen_helper_gvec_flags_3(TCGv_i32, TCGv_ptr, TCGv_ptr,
TCGv_ptr, TCGv_i32);
typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr,
@@ -2959,6 +2962,136 @@ static bool trans_BRKN(DisasContext *s, arg_rpr_s *a, uint32_t insn)
return do_brk2(s, a, gen_helper_sve_brkn, gen_helper_sve_brkns);
}
+/*
+ *** SVE Predicate Count Group
+ */
+
+static void do_cntp(DisasContext *s, TCGv_i64 val, int esz, int pn, int pg)
+{
+ unsigned psz = pred_full_reg_size(s);
+
+ if (psz <= 8) {
+ uint64_t psz_mask;
+
+ tcg_gen_ld_i64(val, cpu_env, pred_full_reg_offset(s, pn));
+ if (pn != pg) {
+ TCGv_i64 g = tcg_temp_new_i64();
+ tcg_gen_ld_i64(g, cpu_env, pred_full_reg_offset(s, pg));
+ tcg_gen_and_i64(val, val, g);
+ tcg_temp_free_i64(g);
+ }
+
+ /* Reduce the pred_esz_masks value simply to reduce the
+ * size of the code generated here.
+ */
+ psz_mask = MAKE_64BIT_MASK(0, psz * 8);
+ tcg_gen_andi_i64(val, val, pred_esz_masks[esz] & psz_mask);
+
+ tcg_gen_ctpop_i64(val, val);
+ } else {
+ TCGv_ptr t_pn = tcg_temp_new_ptr();
+ TCGv_ptr t_pg = tcg_temp_new_ptr();
+ unsigned desc;
+ TCGv_i32 t_desc;
+
+ desc = psz - 2;
+ desc = deposit32(desc, SIMD_DATA_SHIFT, 2, esz);
+
+ tcg_gen_addi_ptr(t_pn, cpu_env, pred_full_reg_offset(s, pn));
+ tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg));
+ t_desc = tcg_const_i32(desc);
+
+ gen_helper_sve_cntp(val, t_pn, t_pg, t_desc);
+ tcg_temp_free_ptr(t_pn);
+ tcg_temp_free_ptr(t_pg);
+ tcg_temp_free_i32(t_desc);
+ }
+}
+
+static bool trans_CNTP(DisasContext *s, arg_CNTP *a, uint32_t insn)
+{
+ if (sve_access_check(s)) {
+ do_cntp(s, cpu_reg(s, a->rd), a->esz, a->rn, a->pg);
+ }
+ return true;
+}
+
+static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a,
+ uint32_t insn)
+{
+ if (sve_access_check(s)) {
+ TCGv_i64 reg = cpu_reg(s, a->rd);
+ TCGv_i64 val = tcg_temp_new_i64();
+
+ do_cntp(s, val, a->esz, a->pg, a->pg);
+ if (a->d) {
+ tcg_gen_sub_i64(reg, reg, val);
+ } else {
+ tcg_gen_add_i64(reg, reg, val);
+ }
+ tcg_temp_free_i64(val);
+ }
+ return true;
+}
+
+static bool trans_INCDECP_z(DisasContext *s, arg_incdec2_pred *a,
+ uint32_t insn)
+{
+ if (a->esz == 0) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ TCGv_i64 val = tcg_temp_new_i64();
+ GVecGen2sFn *gvec_fn = a->d ? tcg_gen_gvec_subs : tcg_gen_gvec_adds;
+
+ do_cntp(s, val, a->esz, a->pg, a->pg);
+ gvec_fn(a->esz, vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn), val, vsz, vsz);
+ }
+ return true;
+}
+
+static bool trans_SINCDECP_r_32(DisasContext *s, arg_incdec_pred *a,
+ uint32_t insn)
+{
+ if (sve_access_check(s)) {
+ TCGv_i64 reg = cpu_reg(s, a->rd);
+ TCGv_i64 val = tcg_temp_new_i64();
+
+ do_cntp(s, val, a->esz, a->pg, a->pg);
+ do_sat_addsub_32(reg, val, a->u, a->d);
+ }
+ return true;
+}
+
+static bool trans_SINCDECP_r_64(DisasContext *s, arg_incdec_pred *a,
+ uint32_t insn)
+{
+ if (sve_access_check(s)) {
+ TCGv_i64 reg = cpu_reg(s, a->rd);
+ TCGv_i64 val = tcg_temp_new_i64();
+
+ do_cntp(s, val, a->esz, a->pg, a->pg);
+ do_sat_addsub_64(reg, val, a->u, a->d);
+ }
+ return true;
+}
+
+static bool trans_SINCDECP_z(DisasContext *s, arg_incdec2_pred *a,
+ uint32_t insn)
+{
+ if (a->esz == 0) {
+ return false;
+ }
+ if (sve_access_check(s)) {
+ TCGv_i64 val = tcg_temp_new_i64();
+ do_cntp(s, val, a->esz, a->pg, a->pg);
+ do_sat_addsub_vec(s, a->esz, a->rd, a->rn, val, a->u, a->d);
+ }
+ return true;
+}
+
/*
*** SVE Memory - 32-bit Gather and Unsized Contiguous Group
*/
@@ -67,6 +67,8 @@
&ptrue rd esz pat s
&incdec_cnt rd pat esz imm d u
&incdec2_cnt rd rn pat esz imm d u
+&incdec_pred rd pg esz d u
+&incdec2_pred rd rn pg esz d u
###########################################################################
# Named instruction formats. These are generally used to
@@ -113,6 +115,7 @@
# One register operand, with governing predicate, vector element size
@rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz
+@rd_pg4_pn ........ esz:2 ... ... .. pg:4 . rn:4 rd:5 &rpr_esz
# Two register operands with a 6-bit signed immediate.
@rd_rn_i6 ........ ... rn:5 ..... imm:s6 rd:5 &rri
@@ -153,6 +156,12 @@
@incdec2_cnt ........ esz:2 .. .... ...... pat:5 rd:5 \
&incdec2_cnt imm=%imm4_16_p1 rn=%reg_movprfx
+# One register, predicate.
+# User must fill in U and D.
+@incdec_pred ........ esz:2 .... .. ..... .. pg:4 rd:5 &incdec_pred
+@incdec2_pred ........ esz:2 .... .. ..... .. pg:4 rd:5 \
+ &incdec2_pred rn=%reg_movprfx
+
###########################################################################
# Instruction patterns. Grouped according to the SVE encodingindex.xhtml.
@@ -579,6 +588,24 @@ BRKB_m 00100101 1. 01000001 .... 0 .... 1 .... @pd_pg_pn_s
# SVE propagate break to next partition
BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s
+### SVE Predicate Count Group
+
+# SVE predicate count
+CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn
+
+# SVE inc/dec register by predicate count
+INCDECP_r 00100101 .. 10110 d:1 10001 00 .... ..... @incdec_pred u=1
+
+# SVE inc/dec vector by predicate count
+INCDECP_z 00100101 .. 10110 d:1 10000 00 .... ..... @incdec2_pred u=1
+
+# SVE saturating inc/dec register by predicate count
+SINCDECP_r_32 00100101 .. 1010 d:1 u:1 10001 00 .... ..... @incdec_pred
+SINCDECP_r_64 00100101 .. 1010 d:1 u:1 10001 10 .... ..... @incdec_pred
+
+# SVE saturating inc/dec vector by predicate count
+SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred
+
### SVE Memory - 32-bit Gather and Unsized Contiguous Group
# SVE load predicate register