@@ -1956,6 +1956,22 @@ DEF_HELPER_FLAGS_3(sve2_sqxtunt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_sqxtunt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_sqxtunt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_shrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_shrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_rshrnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_rshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_rshrnt_d, TCG_CALL_NO_RWG, void, 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,
@@ -1285,6 +1285,14 @@ UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl
SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl
SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl
+## SVE2 bitwise shift right narrow
+
+# Bit 23 == 0 is handled by esz > 0 in the translator.
+SHRNB 01000101 .. 1 ..... 00 0100 ..... ..... @rd_rn_tszimm_shr
+SHRNT 01000101 .. 1 ..... 00 0101 ..... ..... @rd_rn_tszimm_shr
+RSHRNB 01000101 .. 1 ..... 00 0110 ..... ..... @rd_rn_tszimm_shr
+RSHRNT 01000101 .. 1 ..... 00 0111 ..... ..... @rd_rn_tszimm_shr
+
## SVE2 floating-point pairwise operations
FADDP 01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm
@@ -1882,12 +1882,53 @@ DO_ZPZI(sve_asrd_h, int16_t, H1_2, DO_ASRD)
DO_ZPZI(sve_asrd_s, int32_t, H1_4, DO_ASRD)
DO_ZPZI_D(sve_asrd_d, int64_t, DO_ASRD)
-#undef DO_SHR
-#undef DO_SHL
#undef DO_ASRD
#undef DO_ZPZI
#undef DO_ZPZI_D
+#define DO_SHRNB(NAME, TYPEW, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ int shift = simd_data(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEW *)(vn + i); \
+ *(TYPEW *)(vd + i) = (TYPEN)OP(nn, shift); \
+ } \
+}
+
+#define DO_SHRNT(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ int shift = simd_data(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEW *)(vn + HW(i)); \
+ *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, shift); \
+ } \
+}
+
+DO_SHRNB(sve2_shrnb_h, uint16_t, uint8_t, DO_SHR)
+DO_SHRNB(sve2_shrnb_s, uint32_t, uint16_t, DO_SHR)
+DO_SHRNB(sve2_shrnb_d, uint64_t, uint32_t, DO_SHR)
+
+DO_SHRNT(sve2_shrnt_h, uint16_t, uint8_t, H1_2, H1, DO_SHR)
+DO_SHRNT(sve2_shrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_SHR)
+DO_SHRNT(sve2_shrnt_d, uint64_t, uint32_t, , H1_4, DO_SHR)
+
+#define DO_RSHR(x, sh) ((x >> sh) + ((x >> (sh - 1)) & 1))
+
+DO_SHRNB(sve2_rshrnb_h, uint16_t, uint8_t, DO_RSHR)
+DO_SHRNB(sve2_rshrnb_s, uint32_t, uint16_t, DO_RSHR)
+DO_SHRNB(sve2_rshrnb_d, uint64_t, uint32_t, DO_RSHR)
+
+DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, DO_RSHR)
+DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, DO_RSHR)
+DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, , H1_4, DO_RSHR)
+
+#undef DO_SHRNB
+#undef DO_SHRNT
+
/* Fully general four-operand expander, controlled by a predicate.
*/
#define DO_ZPZZZ(NAME, TYPE, H, OP) \
@@ -6264,6 +6264,166 @@ static bool trans_SQXTUNT(DisasContext *s, arg_rri_esz *a)
return do_sve2_narrow_extract(s, a, ops);
}
+static bool do_sve2_shr_narrow(DisasContext *s, arg_rri_esz *a,
+ const GVecGen2i ops[3])
+{
+ if (a->esz < 0 || a->esz > MO_32 || !dc_isar_feature(aa64_sve2, s)) {
+ return false;
+ }
+ assert(a->imm > 0 && a->imm <= (8 << a->esz));
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_2i(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vsz, vsz, a->imm, &ops[a->esz]);
+ }
+ return true;
+}
+
+static void gen_shrnb_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr)
+{
+ int halfbits = 4 << vece;
+ uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits));
+
+ tcg_gen_shri_i64(d, n, shr);
+ tcg_gen_andi_i64(d, d, mask);
+}
+
+static void gen_shrnb16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ gen_shrnb_i64(MO_16, d, n, shr);
+}
+
+static void gen_shrnb32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ gen_shrnb_i64(MO_32, d, n, shr);
+}
+
+static void gen_shrnb64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ gen_shrnb_i64(MO_64, d, n, shr);
+}
+
+static void gen_shrnb_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ int halfbits = 4 << vece;
+ uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
+
+ tcg_gen_shri_vec(vece, n, n, shr);
+ tcg_gen_dupi_vec(vece, t, mask);
+ tcg_gen_and_vec(vece, d, n, t);
+ tcg_temp_free_vec(t);
+}
+
+static bool trans_SHRNB(DisasContext *s, arg_rri_esz *a)
+{
+ static const TCGOpcode vec_list[] = { INDEX_op_shri_vec, 0 };
+ static const GVecGen2i ops[3] = {
+ { .fni8 = gen_shrnb16_i64,
+ .fniv = gen_shrnb_vec,
+ .opt_opc = vec_list,
+ .fno = gen_helper_sve2_shrnb_h,
+ .vece = MO_16 },
+ { .fni8 = gen_shrnb32_i64,
+ .fniv = gen_shrnb_vec,
+ .opt_opc = vec_list,
+ .fno = gen_helper_sve2_shrnb_s,
+ .vece = MO_32 },
+ { .fni8 = gen_shrnb64_i64,
+ .fniv = gen_shrnb_vec,
+ .opt_opc = vec_list,
+ .fno = gen_helper_sve2_shrnb_d,
+ .vece = MO_64 },
+ };
+ return do_sve2_shr_narrow(s, a, ops);
+}
+
+static void gen_shrnt_i64(unsigned vece, TCGv_i64 d, TCGv_i64 n, int shr)
+{
+ int halfbits = 4 << vece;
+ uint64_t mask = dup_const(vece, MAKE_64BIT_MASK(0, halfbits));
+
+ tcg_gen_shli_i64(n, n, halfbits - shr);
+ tcg_gen_andi_i64(n, n, ~mask);
+ tcg_gen_andi_i64(d, d, mask);
+ tcg_gen_or_i64(d, d, n);
+}
+
+static void gen_shrnt16_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ gen_shrnt_i64(MO_16, d, n, shr);
+}
+
+static void gen_shrnt32_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ gen_shrnt_i64(MO_32, d, n, shr);
+}
+
+static void gen_shrnt64_i64(TCGv_i64 d, TCGv_i64 n, int64_t shr)
+{
+ tcg_gen_shri_i64(n, n, shr);
+ tcg_gen_deposit_i64(d, d, n, 32, 32);
+}
+
+static void gen_shrnt_vec(unsigned vece, TCGv_vec d, TCGv_vec n, int64_t shr)
+{
+ TCGv_vec t = tcg_temp_new_vec_matching(d);
+ int halfbits = 4 << vece;
+ uint64_t mask = MAKE_64BIT_MASK(0, halfbits);
+
+ tcg_gen_shli_vec(vece, n, n, halfbits - shr);
+ tcg_gen_dupi_vec(vece, t, mask);
+ tcg_gen_bitsel_vec(vece, d, t, d, n);
+ tcg_temp_free_vec(t);
+}
+
+static bool trans_SHRNT(DisasContext *s, arg_rri_esz *a)
+{
+ static const TCGOpcode vec_list[] = { INDEX_op_shli_vec, 0 };
+ static const GVecGen2i ops[3] = {
+ { .fni8 = gen_shrnt16_i64,
+ .fniv = gen_shrnt_vec,
+ .opt_opc = vec_list,
+ .load_dest = true,
+ .fno = gen_helper_sve2_shrnt_h,
+ .vece = MO_16 },
+ { .fni8 = gen_shrnt32_i64,
+ .fniv = gen_shrnt_vec,
+ .opt_opc = vec_list,
+ .load_dest = true,
+ .fno = gen_helper_sve2_shrnt_s,
+ .vece = MO_32 },
+ { .fni8 = gen_shrnt64_i64,
+ .fniv = gen_shrnt_vec,
+ .opt_opc = vec_list,
+ .load_dest = true,
+ .fno = gen_helper_sve2_shrnt_d,
+ .vece = MO_64 },
+ };
+ return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_RSHRNB(DisasContext *s, arg_rri_esz *a)
+{
+ static const GVecGen2i ops[3] = {
+ { .fno = gen_helper_sve2_rshrnb_h },
+ { .fno = gen_helper_sve2_rshrnb_s },
+ { .fno = gen_helper_sve2_rshrnb_d },
+ };
+ return do_sve2_shr_narrow(s, a, ops);
+}
+
+static bool trans_RSHRNT(DisasContext *s, arg_rri_esz *a)
+{
+ static const GVecGen2i ops[3] = {
+ { .fno = gen_helper_sve2_rshrnt_h },
+ { .fno = gen_helper_sve2_rshrnt_s },
+ { .fno = gen_helper_sve2_rshrnt_d },
+ };
+ return do_sve2_shr_narrow(s, a, ops);
+}
+
static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_4_ptr *fn)
{
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Fix typo in gen_shrnb_vec (laurent desnogues) --- target/arm/helper-sve.h | 16 ++++ target/arm/sve.decode | 8 ++ target/arm/sve_helper.c | 45 ++++++++++- target/arm/translate-sve.c | 160 +++++++++++++++++++++++++++++++++++++ 4 files changed, 227 insertions(+), 2 deletions(-) -- 2.25.1