target/arm: Implement MVE VHCADD

Implement the MVE VHCADD insn, which is similar to VCADD
but performs a halving step. This one overlaps with VADC.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-43-peter.maydell@linaro.org

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index b8ad3df9cc81c1bae3940e0759b4590fbda1ec8f..161308b67e6970bbd816bd9eb61cf1a27595de44 100644 (file)
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -259,6 +259,14 @@ DEF_HELPER_FLAGS_4(mve_vcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vhcadd90b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vhcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vhcadd90w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vhcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vhcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)

diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index afe600786493cffed7c362f8a988288c6e39c6af..695097dcca41b9ea57e1bc2d454fabd3791e19f4 100644 (file)
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -160,8 +160,12 @@ VQDMULLT         111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28
 VRHADD_S         111 0 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op
 VRHADD_U         111 1 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op
 
-VADC             1110 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 0 @2op_nosz
-VADCI            1110 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 0 @2op_nosz
+{
+  VADC           1110 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 0 @2op_nosz
+  VADCI          1110 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 0 @2op_nosz
+  VHCADD90       1110 1110 0 . .. ... 0 ... 0 1111 . 0 . 0 ... 0 @2op
+  VHCADD270      1110 1110 0 . .. ... 0 ... 1 1111 . 0 . 0 ... 0 @2op
+}
 
 {
   VSBC           1111 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 0 @2op_nosz

diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 620b659fecc283e026c9d2cf5bafb668f7063e1d..e3cec487e020fae2d282523148a90dca6bec61b8 100644 (file)
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -617,6 +617,8 @@ void HELPER(mve_vsbci)(CPUARMState *env, void *vd, void *vn, void *vm)
 
 DO_VCADD_ALL(vcadd90, DO_SUB, DO_ADD)
 DO_VCADD_ALL(vcadd270, DO_ADD, DO_SUB)
+DO_VCADD_ALL(vhcadd90, do_vhsub_s, do_vhadd_s)
+DO_VCADD_ALL(vhcadd270, do_vhadd_s, do_vhsub_s)
 
 static inline int32_t do_sat_bhw(int64_t val, int64_t min, int64_t max, bool *s)
 {

diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index b164907426cdfc3b3936116f15ee8b715ef4b558..73c15f413331caada3601efdb00c521150035349 100644 (file)
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -423,10 +423,12 @@ DO_2OP(VRHADD_U, vrhaddu)
 /*
  * VCADD Qd == Qm at size MO_32 is UNPREDICTABLE; we choose not to diagnose
  * so we can reuse the DO_2OP macro. (Our implementation calculates the
- * "expected" results in this case.)
+ * "expected" results in this case.) Similarly for VHCADD.
  */
 DO_2OP(VCADD90, vcadd90)
 DO_2OP(VCADD270, vcadd270)
+DO_2OP(VHCADD90, vhcadd90)
+DO_2OP(VHCADD270, vhcadd270)
 
 static bool trans_VQDMULLB(DisasContext *s, arg_2op *a)
 {