[PULL 084/114] target/arm: Implement SVE2 complex integer multiply-add (indexed)

[Peter Maydell]

From: Richard Henderson <richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-63-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-sve.h    |  9 +++++++++
 target/arm/sve.decode      | 12 ++++++++++++
 target/arm/sve_helper.c    | 28 ++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 15 +++++++++++++++
 4 files changed, 64 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 3bec807e134..d6399a6d6e2 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2715,3 +2715,12 @@ DEF_HELPER_FLAGS_4(sve2_smull_idx_s, TCG_CALL_NO_RWG, 
void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_smull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_umull_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_umull_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_cmla_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_cmla_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 9c5761347ad..42cf344ad64 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -823,6 +823,18 @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... .....   
@rrxr_2a esz=3
 SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... .....   @rrxr_3a esz=2
 SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... .....   @rrxr_2a esz=3
 
+# SVE2 complex integer multiply-add (indexed)
+CMLA_zzxz_h     01000100 10 1 index:2 rm:3 0110 rot:2 rn:5 rd:5 \
+                ra=%reg_movprfx
+CMLA_zzxz_s     01000100 11 1 index:1 rm:4 0110 rot:2 rn:5 rd:5 \
+                ra=%reg_movprfx
+
+# SVE2 complex saturating integer multiply-add (indexed)
+SQRDCMLAH_zzxz_h  01000100 10 1 index:2 rm:3 0111 rot:2 rn:5 rd:5 \
+                  ra=%reg_movprfx
+SQRDCMLAH_zzxz_s  01000100 11 1 index:1 rm:4 0111 rot:2 rn:5 rd:5 \
+                  ra=%reg_movprfx
+
 # SVE2 multiply-add long (indexed)
 SMLALB_zzxw_s   01000100 10 1 ..... 1000.0 ..... .....   @rrxr_3a esz=2
 SMLALB_zzxw_d   01000100 11 1 ..... 1000.0 ..... .....   @rrxr_2a esz=3
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 20ed2f34bcc..eb083e40612 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1492,8 +1492,36 @@ 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)
 
+#define DO_CMLA_IDX_FUNC(NAME, TYPE, H, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc)    \
+{                                                                           \
+    intptr_t i, j, oprsz = simd_oprsz(desc);                                \
+    int rot = extract32(desc, SIMD_DATA_SHIFT, 2);                          \
+    int idx = extract32(desc, SIMD_DATA_SHIFT + 2, 2) * 2;                  \
+    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 < oprsz / sizeof(TYPE); i += 16 / sizeof(TYPE)) {         \
+        TYPE elt2_a = m[H(i + idx + sel_a)];                                \
+        TYPE elt2_b = m[H(i + idx + sel_b)];                                \
+        for (j = 0; j < 16 / sizeof(TYPE); j += 2) {                        \
+            TYPE elt1_a = n[H(i + j + sel_a)];                              \
+            d[H2(i + j)] = OP(elt1_a, elt2_a, a[H(i + j)], sub_r);          \
+            d[H2(i + j + 1)] = OP(elt1_a, elt2_b, a[H(i + j + 1)], sub_i);  \
+        }                                                                   \
+    }                                                                       \
+}
+
+DO_CMLA_IDX_FUNC(sve2_cmla_idx_h, int16_t, H2, DO_CMLA)
+DO_CMLA_IDX_FUNC(sve2_cmla_idx_s, int32_t, H4, DO_CMLA)
+
+DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H)
+DO_CMLA_IDX_FUNC(sve2_sqrdcmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S)
+
 #undef DO_CMLA
 #undef DO_CMLA_FUNC
+#undef DO_CMLA_IDX_FUNC
 #undef DO_SQRDMLAH_B
 #undef DO_SQRDMLAH_H
 #undef DO_SQRDMLAH_S
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index e8e2a4e948f..91aa2506de1 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3976,6 +3976,21 @@ DO_SVE2_RRXR_TB(trans_UMLSLT_zzxw_d, 
gen_helper_sve2_umlsl_idx_d, true)
 
 #undef DO_SVE2_RRXR_TB
 
+#define DO_SVE2_RRXR_ROT(NAME, FUNC) \
+    static bool trans_##NAME(DisasContext *s, arg_##NAME *a)       \
+    {                                                              \
+        return do_sve2_zzzz_data(s, a->rd, a->rn, a->rm, a->ra,    \
+                                 (a->index << 2) | a->rot, FUNC);  \
+    }
+
+DO_SVE2_RRXR_ROT(CMLA_zzxz_h, gen_helper_sve2_cmla_idx_h)
+DO_SVE2_RRXR_ROT(CMLA_zzxz_s, gen_helper_sve2_cmla_idx_s)
+
+DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_h, gen_helper_sve2_sqrdcmlah_idx_h)
+DO_SVE2_RRXR_ROT(SQRDCMLAH_zzxz_s, gen_helper_sve2_sqrdcmlah_idx_s)
+
+#undef DO_SVE2_RRXR_ROT
+
 /*
  *** SVE Floating Point Multiply-Add Indexed Group
  */
-- 
2.20.1