@@ -2372,3 +2372,11 @@ DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_sshll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_sshll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_3(sve2_ushll_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_3(sve2_ushll_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
@@ -1207,3 +1207,11 @@ SMULLB_zzz 01000101 .. 0 ..... 011 100 ..... ..... @rd_rn_rm
SMULLT_zzz 01000101 .. 0 ..... 011 101 ..... ..... @rd_rn_rm
UMULLB_zzz 01000101 .. 0 ..... 011 110 ..... ..... @rd_rn_rm
UMULLT_zzz 01000101 .. 0 ..... 011 111 ..... ..... @rd_rn_rm
+
+## SVE2 bitwise shift left long
+
+# Note bit23 == 0 is handled by esz > 0 in do_sve2_shll_tb.
+SSHLLB 01000101 .. 0 ..... 1010 00 ..... ..... @rd_rn_tszimm_shl
+SSHLLT 01000101 .. 0 ..... 1010 01 ..... ..... @rd_rn_tszimm_shl
+USHLLB 01000101 .. 0 ..... 1010 10 ..... ..... @rd_rn_tszimm_shl
+USHLLT 01000101 .. 0 ..... 1010 11 ..... ..... @rd_rn_tszimm_shl
@@ -625,6 +625,8 @@ DO_ZPZZ(sve2_sqrshl_zpzz_h, int16_t, H1_2, do_sqrshl_h)
DO_ZPZZ(sve2_sqrshl_zpzz_s, int32_t, H1_4, do_sqrshl_s)
DO_ZPZZ_D(sve2_sqrshl_zpzz_d, int64_t, do_sqrshl_d)
+#undef do_sqrshl_d
+
#define do_uqrshl_b(n, m) \
({ uint32_t discard; do_uqrshl_bhs(n, m, 8, true, &discard); })
#define do_uqrshl_h(n, m) \
@@ -639,6 +641,8 @@ DO_ZPZZ(sve2_uqrshl_zpzz_h, uint16_t, H1_2, do_uqrshl_h)
DO_ZPZZ(sve2_uqrshl_zpzz_s, uint32_t, H1_4, do_uqrshl_s)
DO_ZPZZ_D(sve2_uqrshl_zpzz_d, uint64_t, do_uqrshl_d)
+#undef do_uqrshl_d
+
#define DO_HADD_BHS(n, m) (((int64_t)n + m) >> 1)
#define DO_HADD_D(n, m) ((n >> 1) + (m >> 1) + (n & m & 1))
@@ -1192,6 +1196,36 @@ DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t, DO_SUB)
#undef DO_ZZZ_WTB
+#define DO_ZZI_SHLL(NAME, TYPE, TYPEN, OP) \
+void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ int sel = (simd_data(desc) & 1) * sizeof(TYPE); \
+ int shift = simd_data(desc) >> 1; \
+ for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \
+ TYPE nn = (TYPEN)(*(TYPE *)(vn + i) >> sel); \
+ *(TYPE *)(vd + i) = OP(nn, shift); \
+ } \
+}
+
+#define DO_SSHLL_H(val, sh) do_sqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_SSHLL_S(val, sh) do_sqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_SSHLL_D(val, sh) do_sqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_sshll_h, int16_t, int8_t, DO_SSHLL_H)
+DO_ZZI_SHLL(sve2_sshll_s, int32_t, int16_t, DO_SSHLL_S)
+DO_ZZI_SHLL(sve2_sshll_d, int64_t, int32_t, DO_SSHLL_D)
+
+#define DO_USHLL_H(val, sh) do_uqrshl_bhs(val, sh, 16, false, NULL)
+#define DO_USHLL_S(val, sh) do_uqrshl_bhs(val, sh, 32, false, NULL)
+#define DO_USHLL_D(val, sh) do_uqrshl_d(val, sh, false, NULL)
+
+DO_ZZI_SHLL(sve2_ushll_h, uint16_t, uint8_t, DO_USHLL_H)
+DO_ZZI_SHLL(sve2_ushll_s, uint32_t, uint16_t, DO_USHLL_S)
+DO_ZZI_SHLL(sve2_ushll_d, uint64_t, uint32_t, DO_USHLL_D)
+
+#undef DO_ZZI_SHLL
+
/* Two-operand reduction expander, controlled by a predicate.
* The difference between TYPERED and TYPERET has to do with
* sign-extension. E.g. for SMAX, TYPERED must be signed,
@@ -6105,3 +6105,52 @@ DO_SVE2_ZZZ_WTB(UADDWB, uaddw, false)
DO_SVE2_ZZZ_WTB(UADDWT, uaddw, true)
DO_SVE2_ZZZ_WTB(USUBWB, usubw, false)
DO_SVE2_ZZZ_WTB(USUBWT, usubw, true)
+
+static bool do_sve2_shll_tb(DisasContext *s, arg_rri_esz *a,
+ bool sel, bool uns)
+{
+ static gen_helper_gvec_2 * const fns[2][3] = {
+ { gen_helper_sve2_sshll_h,
+ gen_helper_sve2_sshll_s,
+ gen_helper_sve2_sshll_d },
+ { gen_helper_sve2_ushll_h,
+ gen_helper_sve2_ushll_s,
+ gen_helper_sve2_ushll_d },
+ };
+
+ if (a->esz <= 0 || !dc_isar_feature(aa64_sve2, s)) {
+ /*
+ * For < 0, invalid tsz encoding -- see tszimm_esz.
+ * For = 0, not a widening operation; note this implies bit23 = 0.
+ */
+ return false;
+ }
+ if (sve_access_check(s)) {
+ unsigned vsz = vec_full_reg_size(s);
+ tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd),
+ vec_full_reg_offset(s, a->rn),
+ vsz, vsz, (a->imm << 1) | sel,
+ fns[uns][a->esz - 1]);
+ }
+ return true;
+}
+
+static bool trans_SSHLLB(DisasContext *s, arg_rri_esz *a)
+{
+ return do_sve2_shll_tb(s, a, false, false);
+}
+
+static bool trans_SSHLLT(DisasContext *s, arg_rri_esz *a)
+{
+ return do_sve2_shll_tb(s, a, true, false);
+}
+
+static bool trans_USHLLB(DisasContext *s, arg_rri_esz *a)
+{
+ return do_sve2_shll_tb(s, a, false, true);
+}
+
+static bool trans_USHLLT(DisasContext *s, arg_rri_esz *a)
+{
+ return do_sve2_shll_tb(s, a, true, true);
+}
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-sve.h | 8 +++++++ target/arm/sve.decode | 8 +++++++ target/arm/sve_helper.c | 34 ++++++++++++++++++++++++++ target/arm/translate-sve.c | 49 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 99 insertions(+) -- 2.20.1