[PATCH v2 17/57] target/arm: Implement MVE VREV16, VREV32, VREV64

[Peter Maydell]

Implement the MVE instructions VREV16, VREV32 and VREV64.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-mve.h    |  7 +++++++
 target/arm/mve.decode      |  4 ++++
 target/arm/mve_helper.c    |  7 +++++++
 target/arm/translate-mve.c | 33 +++++++++++++++++++++++++++++++++
 4 files changed, 51 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index bdd6675ea14..4c89387587d 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -40,3 +40,10 @@ DEF_HELPER_FLAGS_3(mve_vclsw, TCG_CALL_NO_WG, void, env, 
ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vclzb, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vclzh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vclzw, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
+DEF_HELPER_FLAGS_3(mve_vrev16b, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vrev32b, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vrev32h, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vrev64b, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vrev64h, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vrev64w, TCG_CALL_NO_WG, void, env, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index adceef91597..16ee511a5cb 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -70,3 +70,7 @@ VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111110 
.......   @vldr_vstr \
 
 VCLS             1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
 VCLZ             1111 1111 1 . 11 .. 00 ... 0 0100 11 . 0 ... 0 @1op
+
+VREV16           1111 1111 1 . 11 .. 00 ... 0 0001 01 . 0 ... 0 @1op
+VREV32           1111 1111 1 . 11 .. 00 ... 0 0000 11 . 0 ... 0 @1op
+VREV64           1111 1111 1 . 11 .. 00 ... 0 0000 01 . 0 ... 0 @1op
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 1590b3ac83c..50af6aadec6 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -285,3 +285,10 @@ DO_1OP(vclsw, 4, int32_t, clrsb32)
 DO_1OP(vclzb, 1, uint8_t, DO_CLZ_B)
 DO_1OP(vclzh, 2, uint16_t, DO_CLZ_H)
 DO_1OP(vclzw, 4, uint32_t, clz32)
+
+DO_1OP(vrev16b, 2, uint16_t, bswap16)
+DO_1OP(vrev32b, 4, uint32_t, bswap32)
+DO_1OP(vrev32h, 4, uint32_t, hswap32)
+DO_1OP(vrev64b, 8, uint64_t, bswap64)
+DO_1OP(vrev64h, 8, uint64_t, hswap64)
+DO_1OP(vrev64w, 8, uint64_t, wswap64)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 4e5d032242b..32a8324c5e6 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -199,3 +199,36 @@ static bool do_1op(DisasContext *s, arg_1op *a, 
MVEGenOneOpFn fn)
 
 DO_1OP(VCLZ, vclz)
 DO_1OP(VCLS, vcls)
+
+static bool trans_VREV16(DisasContext *s, arg_1op *a)
+{
+    static MVEGenOneOpFn * const fns[] = {
+        gen_helper_mve_vrev16b,
+        NULL,
+        NULL,
+        NULL,
+    };
+    return do_1op(s, a, fns[a->size]);
+}
+
+static bool trans_VREV32(DisasContext *s, arg_1op *a)
+{
+    static MVEGenOneOpFn * const fns[] = {
+        gen_helper_mve_vrev32b,
+        gen_helper_mve_vrev32h,
+        NULL,
+        NULL,
+    };
+    return do_1op(s, a, fns[a->size]);
+}
+
+static bool trans_VREV64(DisasContext *s, arg_1op *a)
+{
+    static MVEGenOneOpFn * const fns[] = {
+        gen_helper_mve_vrev64b,
+        gen_helper_mve_vrev64h,
+        gen_helper_mve_vrev64w,
+        NULL,
+    };
+    return do_1op(s, a, fns[a->size]);
+}
-- 
2.20.1