[PATCH v3 20/44] target/arm: Implement MVE VMLSLDAV

[Peter Maydell]

Implement the MVE insn VMLSLDAV, which multiplies source elements,
alternately adding and subtracting them, and accumulates into a
64-bit result in a pair of general purpose registers.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  5 +++++
 target/arm/mve.decode      |  2 ++
 target/arm/mve_helper.c    |  5 +++++
 target/arm/translate-mve.c | 11 +++++++++++
 4 files changed, 23 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 0138e28278a..7356385d60c 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -152,3 +152,8 @@ DEF_HELPER_FLAGS_4(mve_vmlaldavxsw, TCG_CALL_NO_WG, i64, 
env, ptr, ptr, i64)
 
 DEF_HELPER_FLAGS_4(mve_vmlaldavuh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
+
+DEF_HELPER_FLAGS_4(mve_vmlsldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
+DEF_HELPER_FLAGS_4(mve_vmlsldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
+DEF_HELPER_FLAGS_4(mve_vmlsldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
+DEF_HELPER_FLAGS_4(mve_vmlsldavxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index bde54d05bb9..1be2d6b270f 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -145,3 +145,5 @@ VDUP             1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 
0000 @vdup size=2
                  qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav
 VMLALDAV_S       1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav
 VMLALDAV_U       1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav
+
+VMLSLDAV         1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 0c8bf9232d6..618f0e66d1d 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -537,3 +537,8 @@ DO_LDAV(vmlaldavxsw, 4, int32_t, true, +=, +=)
 
 DO_LDAV(vmlaldavuh, 2, uint16_t, false, +=, +=)
 DO_LDAV(vmlaldavuw, 4, uint32_t, false, +=, +=)
+
+DO_LDAV(vmlsldavsh, 2, int16_t, false, +=, -=)
+DO_LDAV(vmlsldavxsh, 2, int16_t, true, +=, -=)
+DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=)
+DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index f8ceeac5a4f..77b461c2186 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -461,3 +461,14 @@ static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav 
*a)
     };
     return do_long_dual_acc(s, a, fns[a->size][a->x]);
 }
+
+static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a)
+{
+    static MVEGenDualAccOpFn * const fns[4][2] = {
+        { NULL, NULL },
+        { gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh },
+        { gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw },
+        { NULL, NULL },
+    };
+    return do_long_dual_acc(s, a, fns[a->size][a->x]);
+}
-- 
2.20.1