[PATCH v3 22/81] target/arm: Implement SVE2 integer absolute difference and accumulate long

[Richard Henderson]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Fix select offsetting and argument order (laurent desnogues).
---
 target/arm/helper-sve.h    | 14 ++++++++++
 target/arm/sve.decode      | 12 +++++++++
 target/arm/sve_helper.c    | 23 ++++++++++++++++
 target/arm/translate-sve.c | 55 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 104 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index b399fb2576..d5dfd4edea 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2402,3 +2402,17 @@ DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sabal_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sabal_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sabal_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uabal_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uabal_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uabal_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 655cb5c12f..6cf09847a0 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -70,6 +70,7 @@
 &rpr_s          rd pg rn s
 &rprr_s         rd pg rn rm s
 &rprr_esz       rd pg rn rm esz
+&rrrr_esz       rd ra rn rm esz
 &rprrr_esz      rd pg rn rm ra esz
 &rpri_esz       rd pg rn imm esz
 &ptrue          rd esz pat s
@@ -119,6 +120,10 @@
 @rdn_i8s        ........ esz:2 ...... ... imm:s8 rd:5 \
                 &rri_esz rn=%reg_movprfx
 
+# Four operand, vector element size
+@rda_rn_rm      ........ esz:2 . rm:5 ... ... rn:5 rd:5 \
+                &rrrr_esz ra=%reg_movprfx
+
 # Three operand with "memory" size, aka immediate left shift
 @rd_rn_msz_rm   ........ ... rm:5 .... imm:2 rn:5 rd:5          &rrri
 
@@ -1235,3 +1240,10 @@ CADD_rot90      01000101 .. 00000 0 11011 0 ..... .....  
@rdn_rm
 CADD_rot270     01000101 .. 00000 0 11011 1 ..... .....  @rdn_rm
 SQCADD_rot90    01000101 .. 00000 1 11011 0 ..... .....  @rdn_rm
 SQCADD_rot270   01000101 .. 00000 1 11011 1 ..... .....  @rdn_rm
+
+## SVE2 integer absolute difference and accumulate long
+
+SABALB          01000101 .. 0 ..... 1100 00 ..... .....  @rda_rn_rm
+SABALT          01000101 .. 0 ..... 1100 01 ..... .....  @rda_rn_rm
+UABALB          01000101 .. 0 ..... 1100 10 ..... .....  @rda_rn_rm
+UABALT          01000101 .. 0 ..... 1100 11 ..... .....  @rda_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index b8541168bf..cc8450c44e 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1241,6 +1241,29 @@ DO_ZZZ_NTB(sve2_eoril_d, uint64_t,     , DO_EOR)
 
 #undef DO_ZZZ_NTB
 
+#define DO_ZZZW_ACC(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc);                      \
+    intptr_t sel1 = simd_data(desc) * sizeof(TYPEN);            \
+    for (i = 0; i < opr_sz; i += sizeof(TYPEW)) {               \
+        TYPEW nn = *(TYPEN *)(vn + HN(i + sel1));               \
+        TYPEW mm = *(TYPEN *)(vm + HN(i + sel1));               \
+        TYPEW aa = *(TYPEW *)(va + HW(i));                      \
+        *(TYPEW *)(vd + HW(i)) = OP(nn, mm) + aa;               \
+    }                                                           \
+}
+
+DO_ZZZW_ACC(sve2_sabal_h, int16_t, int8_t, H1_2, H1, DO_ABD)
+DO_ZZZW_ACC(sve2_sabal_s, int32_t, int16_t, H1_4, H1_2, DO_ABD)
+DO_ZZZW_ACC(sve2_sabal_d, int64_t, int32_t,     , H1_4, DO_ABD)
+
+DO_ZZZW_ACC(sve2_uabal_h, uint16_t, uint8_t, H1_2, H1, DO_ABD)
+DO_ZZZW_ACC(sve2_uabal_s, uint32_t, uint16_t, H1_4, H1_2, DO_ABD)
+DO_ZZZW_ACC(sve2_uabal_d, uint64_t, uint32_t,     , H1_4, DO_ABD)
+
+#undef DO_ZZZW_ACC
+
 #define DO_BITPERM(NAME, TYPE, OP) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 95a81eb101..7b3720e8ef 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -163,6 +163,18 @@ static void gen_gvec_ool_zzz(DisasContext *s, 
gen_helper_gvec_3 *fn,
                        vsz, vsz, data, fn);
 }
 
+/* Invoke an out-of-line helper on 4 Zregs. */
+static void gen_gvec_ool_zzzz(DisasContext *s, gen_helper_gvec_4 *fn,
+                              int rd, int rn, int rm, int ra, int data)
+{
+    unsigned vsz = vec_full_reg_size(s);
+    tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
+                       vec_full_reg_offset(s, rn),
+                       vec_full_reg_offset(s, rm),
+                       vec_full_reg_offset(s, ra),
+                       vsz, vsz, data, fn);
+}
+
 /* Invoke an out-of-line helper on 2 Zregs and a predicate. */
 static void gen_gvec_ool_zzp(DisasContext *s, gen_helper_gvec_3 *fn,
                              int rd, int rn, int pg, int data)
@@ -6326,3 +6338,46 @@ static bool trans_SQCADD_rot270(DisasContext *s, 
arg_rrr_esz *a)
 {
     return do_cadd(s, a, true, true);
 }
+
+static bool do_sve2_zzzz_ool(DisasContext *s, arg_rrrr_esz *a,
+                             gen_helper_gvec_4 *fn, int data)
+{
+    if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, data);
+    }
+    return true;
+}
+
+static bool do_abal(DisasContext *s, arg_rrrr_esz *a, bool uns, bool sel)
+{
+    static gen_helper_gvec_4 * const fns[2][4] = {
+        { NULL,                    gen_helper_sve2_sabal_h,
+          gen_helper_sve2_sabal_s, gen_helper_sve2_sabal_d },
+        { NULL,                    gen_helper_sve2_uabal_h,
+          gen_helper_sve2_uabal_s, gen_helper_sve2_uabal_d },
+    };
+    return do_sve2_zzzz_ool(s, a, fns[uns][a->esz], sel);
+}
+
+static bool trans_SABALB(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_abal(s, a, false, false);
+}
+
+static bool trans_SABALT(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_abal(s, a, false, true);
+}
+
+static bool trans_UABALB(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_abal(s, a, true, false);
+}
+
+static bool trans_UABALT(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_abal(s, a, true, true);
+}
-- 
2.25.1