[PULL 26/44] 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>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    | 4 ++++
 target/arm/mve.decode      | 1 +
 target/arm/mve_helper.c    | 5 +++++
 target/arm/translate-mve.c | 1 +
 4 files changed, 11 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 34d644a519c..328e31e2665 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -367,6 +367,10 @@ 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_vmlab, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlah, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlaw, 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)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index cec5a51b0ee..cd9c806a11c 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -413,6 +413,7 @@ VQDMULH_scalar   1110 1110 0 . .. ... 1 ... 0 1110 . 110 
.... @2scalar
 VQRDMULH_scalar  1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 
 # The U bit (28) is don't-care because it does not affect the result
+VMLA             111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar
 VMLAS            111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
 
 # Vector add across vector
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index ea206c932bc..8004b9bb728 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1008,6 +1008,11 @@ 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_U(vmla, 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 92ed1be83e7..f8899af352d 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -620,6 +620,7 @@ 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, vmla)
 DO_2OP_SCALAR(VMLAS, vmlas)
 
 static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a)
-- 
2.20.1