target/arm: Implement SVE2 integer add/subtract wide

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-13-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 78 insertions, 0 deletions

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index a81297b..3286a9c 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1391,6 +1391,22 @@ DEF_HELPER_FLAGS_4(sve2_uabdl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_uabdl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_uabdl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve2_saddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_saddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_saddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_ssubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_ssubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_ssubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_uaddw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uaddw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_uaddw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_usubw_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_usubw_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_usubw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 12be058..f6f2142 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1184,3 +1184,15 @@ UABDLT          01000101 .. 0 ..... 00 1111 ..... .....  @rd_rn_rm
 SADDLBT         01000101 .. 0 ..... 1000 00 ..... .....  @rd_rn_rm
 SSUBLBT         01000101 .. 0 ..... 1000 10 ..... .....  @rd_rn_rm
 SSUBLTB         01000101 .. 0 ..... 1000 11 ..... .....  @rd_rn_rm
+
+## SVE2 integer add/subtract wide
+
+SADDWB          01000101 .. 0 ..... 010 000 ..... .....  @rd_rn_rm
+SADDWT          01000101 .. 0 ..... 010 001 ..... .....  @rd_rn_rm
+UADDWB          01000101 .. 0 ..... 010 010 ..... .....  @rd_rn_rm
+UADDWT          01000101 .. 0 ..... 010 011 ..... .....  @rd_rn_rm
+
+SSUBWB          01000101 .. 0 ..... 010 100 ..... .....  @rd_rn_rm
+SSUBWT          01000101 .. 0 ..... 010 101 ..... .....  @rd_rn_rm
+USUBWB          01000101 .. 0 ..... 010 110 ..... .....  @rd_rn_rm
+USUBWT          01000101 .. 0 ..... 010 111 ..... .....  @rd_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index d88fab9..374e02d 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1165,6 +1165,36 @@ DO_ZZZ_TB(sve2_uabdl_d, uint64_t, uint32_t,     , H1_4, DO_ABD)
 
 #undef DO_ZZZ_TB
 
+#define DO_ZZZ_WTB(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{                                                              \
+    intptr_t i, opr_sz = simd_oprsz(desc);                     \
+    int sel2 = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \
+    for (i = 0; i < opr_sz; i += sizeof(TYPEW)) {              \
+        TYPEW nn = *(TYPEW *)(vn + HW(i));                     \
+        TYPEW mm = *(TYPEN *)(vm + HN(i + sel2));              \
+        *(TYPEW *)(vd + HW(i)) = OP(nn, mm);                   \
+    }                                                          \
+}
+
+DO_ZZZ_WTB(sve2_saddw_h, int16_t, int8_t, H1_2, H1, DO_ADD)
+DO_ZZZ_WTB(sve2_saddw_s, int32_t, int16_t, H1_4, H1_2, DO_ADD)
+DO_ZZZ_WTB(sve2_saddw_d, int64_t, int32_t,     , H1_4, DO_ADD)
+
+DO_ZZZ_WTB(sve2_ssubw_h, int16_t, int8_t, H1_2, H1, DO_SUB)
+DO_ZZZ_WTB(sve2_ssubw_s, int32_t, int16_t, H1_4, H1_2, DO_SUB)
+DO_ZZZ_WTB(sve2_ssubw_d, int64_t, int32_t,     , H1_4, DO_SUB)
+
+DO_ZZZ_WTB(sve2_uaddw_h, uint16_t, uint8_t, H1_2, H1, DO_ADD)
+DO_ZZZ_WTB(sve2_uaddw_s, uint32_t, uint16_t, H1_4, H1_2, DO_ADD)
+DO_ZZZ_WTB(sve2_uaddw_d, uint64_t, uint32_t,     , H1_4, DO_ADD)
+
+DO_ZZZ_WTB(sve2_usubw_h, uint16_t, uint8_t, H1_2, H1, DO_SUB)
+DO_ZZZ_WTB(sve2_usubw_s, uint32_t, uint16_t, H1_4, H1_2, DO_SUB)
+DO_ZZZ_WTB(sve2_usubw_d, uint64_t, uint32_t,     , H1_4, DO_SUB)
+
+#undef DO_ZZZ_WTB
+
 /* 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,
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index ae8323a..70900c1 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6020,3 +6020,23 @@ DO_SVE2_ZZZ_TB(UABDLT, uabdl, true, true)
 DO_SVE2_ZZZ_TB(SADDLBT, saddl, false, true)
 DO_SVE2_ZZZ_TB(SSUBLBT, ssubl, false, true)
 DO_SVE2_ZZZ_TB(SSUBLTB, ssubl, true, false)
+
+#define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \
+static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a)       \
+{                                                               \
+    static gen_helper_gvec_3 * const fns[4] = {                 \
+        NULL,                       gen_helper_sve2_##name##_h, \
+        gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \
+    };                                                          \
+    return do_sve2_zzw_ool(s, a, fns[a->esz], SEL2);            \
+}
+
+DO_SVE2_ZZZ_WTB(SADDWB, saddw, false)
+DO_SVE2_ZZZ_WTB(SADDWT, saddw, true)
+DO_SVE2_ZZZ_WTB(SSUBWB, ssubw, false)
+DO_SVE2_ZZZ_WTB(SSUBWT, ssubw, true)
+
+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)