target/arm: Implement MVE VHADD, VHSUB (scalar)

Implement the scalar variants of the MVE VHADD and VHSUB insns.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-25-peter.maydell@linaro.org

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 912505d01527bdc547b07c6bd8b5500844777dc5..52086d769f42dcf73ff157c5e7da72f7cb0ea23a 100644 (file)
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -157,6 +157,22 @@ DEF_HELPER_FLAGS_4(mve_vmul_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vmul_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(mve_vhadds_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhadds_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhadds_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vhaddu_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhaddu_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhaddu_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vhsubs_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhsubs_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhsubs_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vhsubu_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhsubu_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vhsubu_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)

diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index af5fba78ce29e6ac2a4ebb01f32bcadf52fa8b03..5c332b04a7c5072e49c5dc3248f89d6cec2adf8c 100644 (file)
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -163,3 +163,7 @@ VRMLSLDAVH       1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_no
 VADD_scalar      1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar
 VSUB_scalar      1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar
 VMUL_scalar      1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar
+VHADD_S_scalar   1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
+VHADD_U_scalar   1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar
+VHSUB_S_scalar   1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar
+VHSUB_U_scalar   1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar

diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 33755bc3131a6709d04925e025afe55b78ca44a6..d76168a7a4fadee3e114fa0acaa3a0343f953f22 100644 (file)
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -510,10 +510,18 @@ DO_2OP_U(vhsubu, do_vhsub_u)
     DO_2OP_SCALAR(OP##b, 1, uint8_t, FN)        \
     DO_2OP_SCALAR(OP##h, 2, uint16_t, FN)       \
     DO_2OP_SCALAR(OP##w, 4, uint32_t, FN)
+#define DO_2OP_SCALAR_S(OP, FN)                 \
+    DO_2OP_SCALAR(OP##b, 1, int8_t, FN)         \
+    DO_2OP_SCALAR(OP##h, 2, int16_t, FN)        \
+    DO_2OP_SCALAR(OP##w, 4, int32_t, FN)
 
 DO_2OP_SCALAR_U(vadd_scalar, DO_ADD)
 DO_2OP_SCALAR_U(vsub_scalar, DO_SUB)
 DO_2OP_SCALAR_U(vmul_scalar, DO_MUL)
+DO_2OP_SCALAR_S(vhadds_scalar, do_vhadd_s)
+DO_2OP_SCALAR_U(vhaddu_scalar, do_vhadd_u)
+DO_2OP_SCALAR_S(vhsubs_scalar, do_vhsub_s)
+DO_2OP_SCALAR_U(vhsubu_scalar, do_vhsub_u)
 
 /*
  * Multiply add long dual accumulate ops.

diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 3c059ad91cdd6c4001cde3cdf3ecbfd9eaa5fdb1..4b379bfe6e4cd1b1dfb9d19532b3e8cefa1cd0ca 100644 (file)
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -429,6 +429,10 @@ static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
 DO_2OP_SCALAR(VADD_scalar, vadd_scalar)
 DO_2OP_SCALAR(VSUB_scalar, vsub_scalar)
 DO_2OP_SCALAR(VMUL_scalar, vmul_scalar)
+DO_2OP_SCALAR(VHADD_S_scalar, vhadds_scalar)
+DO_2OP_SCALAR(VHADD_U_scalar, vhaddu_scalar)
+DO_2OP_SCALAR(VHSUB_S_scalar, vhsubs_scalar)
+DO_2OP_SCALAR(VHSUB_U_scalar, vhsubu_scalar)
 
 static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a,
                              MVEGenDualAccOpFn *fn)