[PATCH v4 03/78] target/arm: Implement SVE2 integer pairwise add and accumulate long

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 14 ++++++++++++
 target/arm/sve.decode      |  5 +++++
 target/arm/sve_helper.c    | 44 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 39 +++++++++++++++++++++++++++++++++
 4 files changed, 102 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index e4cadd2a65..b2a274b40b 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -158,6 +158,20 @@ DEF_HELPER_FLAGS_5(sve_umulh_zpzz_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve_umulh_zpzz_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sadalp_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uadalp_zpzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_sdiv_zpzz_d, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 557706cacb..0524c01fcf 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1100,3 +1100,8 @@ MUL_zzz         00000100 .. 1 ..... 0110 00 ..... .....  @rd_rn_rm
 SMULH_zzz       00000100 .. 1 ..... 0110 10 ..... .....  @rd_rn_rm
 UMULH_zzz       00000100 .. 1 ..... 0110 11 ..... .....  @rd_rn_rm
 PMUL_zzz        00000100 00 1 ..... 0110 01 ..... .....  @rd_rn_rm_e0
+
+### SVE2 Integer - Predicated
+
+SADALP_zpzz     01000100 .. 000 100 101 ... ..... .....  @rdm_pg_rn
+UADALP_zpzz     01000100 .. 000 101 101 ... ..... .....  @rdm_pg_rn
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index fd6c58f96a..00bb82da91 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -517,6 +517,50 @@ DO_ZPZZ_D(sve_asr_zpzz_d, int64_t, DO_ASR)
 DO_ZPZZ_D(sve_lsr_zpzz_d, uint64_t, DO_LSR)
 DO_ZPZZ_D(sve_lsl_zpzz_d, uint64_t, DO_LSL)
 
+static inline uint16_t do_sadalp_h(uint16_t n, uint16_t m)
+{
+    int8_t n1 = n, n2 = n >> 8;
+    return m + n1 + n2;
+}
+
+static inline uint32_t do_sadalp_s(uint32_t n, uint32_t m)
+{
+    int16_t n1 = n, n2 = n >> 16;
+    return m + n1 + n2;
+}
+
+static inline uint64_t do_sadalp_d(uint64_t n, uint64_t m)
+{
+    int32_t n1 = n, n2 = n >> 32;
+    return m + n1 + n2;
+}
+
+DO_ZPZZ(sve2_sadalp_zpzz_h, int16_t, H1_2, do_sadalp_h)
+DO_ZPZZ(sve2_sadalp_zpzz_s, int32_t, H1_4, do_sadalp_s)
+DO_ZPZZ_D(sve2_sadalp_zpzz_d, uint64_t, do_sadalp_d)
+
+static inline uint16_t do_uadalp_h(uint16_t n, uint16_t m)
+{
+    uint8_t n1 = n, n2 = n >> 8;
+    return m + n1 + n2;
+}
+
+static inline uint32_t do_uadalp_s(uint32_t n, uint32_t m)
+{
+    uint16_t n1 = n, n2 = n >> 16;
+    return m + n1 + n2;
+}
+
+static inline uint64_t do_uadalp_d(uint64_t n, uint64_t m)
+{
+    uint32_t n1 = n, n2 = n >> 32;
+    return m + n1 + n2;
+}
+
+DO_ZPZZ(sve2_uadalp_zpzz_h, int16_t, H1_2, do_uadalp_h)
+DO_ZPZZ(sve2_uadalp_zpzz_s, int32_t, H1_4, do_uadalp_s)
+DO_ZPZZ_D(sve2_uadalp_zpzz_d, uint64_t, do_uadalp_d)
+
 #undef DO_ZPZZ
 #undef DO_ZPZZ_D
 
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 06b906bce9..603e673696 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -5846,3 +5846,42 @@ static bool trans_PMUL_zzz(DisasContext *s, arg_rrr_esz *a)
 {
     return do_sve2_zzz_ool(s, a, gen_helper_gvec_pmul_b);
 }
+
+/*
+ * SVE2 Integer - Predicated
+ */
+
+static bool do_sve2_zpzz_ool(DisasContext *s, arg_rprr_esz *a,
+                             gen_helper_gvec_4 *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return do_zpzz_ool(s, a, fn);
+}
+
+static bool trans_SADALP_zpzz(DisasContext *s, arg_rprr_esz *a)
+{
+    static gen_helper_gvec_4 * const fns[3] = {
+        gen_helper_sve2_sadalp_zpzz_h,
+        gen_helper_sve2_sadalp_zpzz_s,
+        gen_helper_sve2_sadalp_zpzz_d,
+    };
+    if (a->esz == 0) {
+        return false;
+    }
+    return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]);
+}
+
+static bool trans_UADALP_zpzz(DisasContext *s, arg_rprr_esz *a)
+{
+    static gen_helper_gvec_4 * const fns[3] = {
+        gen_helper_sve2_uadalp_zpzz_h,
+        gen_helper_sve2_uadalp_zpzz_s,
+        gen_helper_sve2_uadalp_zpzz_d,
+    };
+    if (a->esz == 0) {
+        return false;
+    }
+    return do_sve2_zpzz_ool(s, a, fns[a->esz - 1]);
+}
-- 
2.25.1