target/arm: Implement SVE2 complex integer multiply-add

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-38-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

6 files changed, 113 insertions, 8 deletions

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 457a421455..d154218452 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2601,3 +2601,21 @@ DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_umlsl_zzzw_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cmla_zzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_b, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index b28b50e05c..936977eacb 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1362,3 +1362,8 @@ SMLSLB_zzzw     01000100 .. 0 ..... 010 100 ..... .....  @rda_rn_rm
 SMLSLT_zzzw     01000100 .. 0 ..... 010 101 ..... .....  @rda_rn_rm
 UMLSLB_zzzw     01000100 .. 0 ..... 010 110 ..... .....  @rda_rn_rm
 UMLSLT_zzzw     01000100 .. 0 ..... 010 111 ..... .....  @rda_rn_rm
+
+## SVE2 complex integer multiply-add
+
+CMLA_zzzz       01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5  ra=%reg_movprfx
+SQRDCMLAH_zzzz  01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5  ra=%reg_movprfx
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index c1a92a2ba5..263663cfc4 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1453,6 +1453,52 @@ DO_SQDMLAL(sve2_sqdmlsl_zzzw_d, int64_t, int32_t,     , H1_4,
 
 #undef DO_SQDMLAL
 
+#define DO_CMLA_FUNC(NAME, TYPE, H, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(TYPE);       \
+    int rot = simd_data(desc);                                  \
+    int sel_a = rot & 1, sel_b = sel_a ^ 1;                     \
+    bool sub_r = rot == 1 || rot == 2;                          \
+    bool sub_i = rot >= 2;                                      \
+    TYPE *d = vd, *n = vn, *m = vm, *a = va;                    \
+    for (i = 0; i < opr_sz; i += 2) {                           \
+        TYPE elt1_a = n[H(i + sel_a)];                          \
+        TYPE elt2_a = m[H(i + sel_a)];                          \
+        TYPE elt2_b = m[H(i + sel_b)];                          \
+        d[H(i)] = OP(elt1_a, elt2_a, a[H(i)], sub_r);           \
+        d[H(i + 1)] = OP(elt1_a, elt2_b, a[H(i + 1)], sub_i);   \
+    }                                                           \
+}
+
+#define DO_CMLA(N, M, A, S) (A + (N * M) * (S ? -1 : 1))
+
+DO_CMLA_FUNC(sve2_cmla_zzzz_b, uint8_t, H1, DO_CMLA)
+DO_CMLA_FUNC(sve2_cmla_zzzz_h, uint16_t, H2, DO_CMLA)
+DO_CMLA_FUNC(sve2_cmla_zzzz_s, uint32_t, H4, DO_CMLA)
+DO_CMLA_FUNC(sve2_cmla_zzzz_d, uint64_t,   , DO_CMLA)
+
+#define DO_SQRDMLAH_B(N, M, A, S) \
+    do_sqrdmlah_b(N, M, A, S, true)
+#define DO_SQRDMLAH_H(N, M, A, S) \
+    ({ uint32_t discard; do_sqrdmlah_h(N, M, A, S, true, &discard); })
+#define DO_SQRDMLAH_S(N, M, A, S) \
+    ({ uint32_t discard; do_sqrdmlah_s(N, M, A, S, true, &discard); })
+#define DO_SQRDMLAH_D(N, M, A, S) \
+    do_sqrdmlah_d(N, M, A, S, true)
+
+DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_b, int8_t, H1, DO_SQRDMLAH_B)
+DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_h, int16_t, H2, DO_SQRDMLAH_H)
+DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S)
+DO_CMLA_FUNC(sve2_sqrdcmlah_zzzz_d, int64_t,   , DO_SQRDMLAH_D)
+
+#undef DO_CMLA
+#undef DO_CMLA_FUNC
+#undef DO_SQRDMLAH_B
+#undef DO_SQRDMLAH_H
+#undef DO_SQRDMLAH_S
+#undef DO_SQRDMLAH_D
+
 #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 f878b0d033..05d9edead4 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7656,3 +7656,35 @@ static bool trans_UMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a)
 {
     return do_umlsl_zzzw(s, a, true);
 }
+
+static bool trans_CMLA_zzzz(DisasContext *s, arg_CMLA_zzzz *a)
+{
+    static gen_helper_gvec_4 * const fns[] = {
+        gen_helper_sve2_cmla_zzzz_b, gen_helper_sve2_cmla_zzzz_h,
+        gen_helper_sve2_cmla_zzzz_s, gen_helper_sve2_cmla_zzzz_d,
+    };
+
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot);
+    }
+    return true;
+}
+
+static bool trans_SQRDCMLAH_zzzz(DisasContext *s, arg_SQRDCMLAH_zzzz *a)
+{
+    static gen_helper_gvec_4 * const fns[] = {
+        gen_helper_sve2_sqrdcmlah_zzzz_b, gen_helper_sve2_sqrdcmlah_zzzz_h,
+        gen_helper_sve2_sqrdcmlah_zzzz_s, gen_helper_sve2_sqrdcmlah_zzzz_d,
+    };
+
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        gen_gvec_ool_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot);
+    }
+    return true;
+}
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index c56337e724..19006f50f7 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -38,8 +38,8 @@
 #endif
 
 /* Signed saturating rounding doubling multiply-accumulate high half, 8-bit */
-static int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3,
-                            bool neg, bool round)
+int8_t do_sqrdmlah_b(int8_t src1, int8_t src2, int8_t src3,
+                     bool neg, bool round)
 {
     /*
      * Simplify:
@@ -82,8 +82,8 @@ void HELPER(sve2_sqrdmlsh_b)(void *vd, void *vn, void *vm,
 }
 
 /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */
-static int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3,
-                             bool neg, bool round, uint32_t *sat)
+int16_t do_sqrdmlah_h(int16_t src1, int16_t src2, int16_t src3,
+                      bool neg, bool round, uint32_t *sat)
 {
     /* Simplify similarly to do_sqrdmlah_b above.  */
     int32_t ret = (int32_t)src1 * src2;
@@ -199,8 +199,8 @@ void HELPER(sve2_sqrdmlsh_h)(void *vd, void *vn, void *vm,
 }
 
 /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
-static int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
-                             bool neg, bool round, uint32_t *sat)
+int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
+                      bool neg, bool round, uint32_t *sat)
 {
     /* Simplify similarly to do_sqrdmlah_b above.  */
     int64_t ret = (int64_t)src1 * src2;
@@ -321,8 +321,7 @@ static int64_t do_sat128_d(Int128 r)
     return ls;
 }
 
-static int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a,
-                             bool neg, bool round)
+int64_t do_sqrdmlah_d(int64_t n, int64_t m, int64_t a, bool neg, bool round)
 {
     uint64_t l, h;
     Int128 r, t;
diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h
index 5b78e79329..ff694d870a 100644
--- a/target/arm/vec_internal.h
+++ b/target/arm/vec_internal.h
@@ -168,4 +168,9 @@ static inline int64_t do_suqrshl_d(int64_t src, int64_t shift,
     return do_uqrshl_d(src, shift, round, sat);
 }
 
+int8_t do_sqrdmlah_b(int8_t, int8_t, int8_t, bool, bool);
+int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *);
+int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *);
+int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool);
+
 #endif /* TARGET_ARM_VEC_INTERNALS_H */