[PATCH for-6.2 25/34] target/arm: Implement MVE VMLA

[Peter Maydell]

Implement the MVE VMLA insn, which multiplies a vector by a scalar
and accumulates into another vector.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-mve.h    | 8 ++++++++
 target/arm/mve.decode      | 3 +++
 target/arm/mve_helper.c    | 6 ++++++
 target/arm/translate-mve.c | 2 ++
 4 files changed, 19 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 088bdd3ca50..50b34c601e1 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -371,6 +371,14 @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, 
void, env, ptr, ptr, i3
 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, 
i32)
 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, 
i32)
 
+DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(mve_vmlaub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlauh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlauw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(mve_vmlassb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vmlassh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vmlassw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 0c4708ea988..2e2df61c860 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -412,6 +412,9 @@ VHSUB_U_scalar   1111 1110 0 . .. ... 0 ... 1 1111 . 100 
.... @2scalar
 VQDMULH_scalar   1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 VQRDMULH_scalar  1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 
+VMLA_S           1110 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
+VMLA_U           1111 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
+
 VMLAS_S          1110 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
 VMLAS_U          1111 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
 
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 8b70362f012..91c0add8da7 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1019,6 +1019,12 @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, 
DO_QRDMULH_B)
 DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H)
 DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W)
 
+/* Vector by scalar plus vector */
+#define DO_VMLA(D, N, M) ((N) * (M) + (D))
+
+DO_2OP_ACC_SCALAR_S(vmlas, DO_VMLA)
+DO_2OP_ACC_SCALAR_U(vmlau, DO_VMLA)
+
 /* Vector by vector plus scalar */
 #define DO_VMLAS(D, N, M) ((N) * (D) + (M))
 
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 67b9c07447a..650f3b95edf 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -620,6 +620,8 @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar)
 DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar)
 DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar)
 DO_2OP_SCALAR(VBRSR, vbrsr)
+DO_2OP_SCALAR(VMLA_S, vmlas)
+DO_2OP_SCALAR(VMLA_U, vmlau)
 DO_2OP_SCALAR(VMLAS_S, vmlass)
 DO_2OP_SCALAR(VMLAS_U, vmlasu)
 
-- 
2.20.1