[PATCH v3 14/44] target/arm: Implement MVE VRMULH

[Peter Maydell <peter.maydell@linaro.org>]

Implement the MVE VRMULH insn, which performs a rounding multiply
and then returns the high half.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  7 +++++++
 target/arm/mve.decode      |  3 +++
 target/arm/mve_helper.c    | 22 ++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 34 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 5c80b185ccc..0e496971f02 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -88,3 +88,10 @@ DEF_HELPER_FLAGS_4(mve_vmulhsw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulhub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulhuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulhuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vrmulhsb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrmulhsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrmulhsw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrmulhub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrmulhuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrmulhuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index ca4c27209da..4ab6c9dba90 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -85,6 +85,9 @@ VMUL             1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
 VMULH_S          111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
 VMULH_U          111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
 
+VRMULH_S         111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
+VRMULH_U         111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
+
 # Vector miscellaneous
 
 VCLS             1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 48744f38af1..1f606e0ae70 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -397,9 +397,31 @@ static inline uint32_t do_mulh_w(int64_t n, int64_t m)
     return (n * m) >> 32;
 }
 
+static inline uint8_t do_rmulh_b(int32_t n, int32_t m)
+{
+    return (n * m + (1U << 7)) >> 8;
+}
+
+static inline uint16_t do_rmulh_h(int32_t n, int32_t m)
+{
+    return (n * m + (1U << 15)) >> 16;
+}
+
+static inline uint32_t do_rmulh_w(int64_t n, int64_t m)
+{
+    return (n * m + (1U << 31)) >> 32;
+}
+
 DO_2OP(vmulhsb, 1, int8_t, do_mulh_b)
 DO_2OP(vmulhsh, 2, int16_t, do_mulh_h)
 DO_2OP(vmulhsw, 4, int32_t, do_mulh_w)
 DO_2OP(vmulhub, 1, uint8_t, do_mulh_b)
 DO_2OP(vmulhuh, 2, uint16_t, do_mulh_h)
 DO_2OP(vmulhuw, 4, uint32_t, do_mulh_w)
+
+DO_2OP(vrmulhsb, 1, int8_t, do_rmulh_b)
+DO_2OP(vrmulhsh, 2, int16_t, do_rmulh_h)
+DO_2OP(vrmulhsw, 4, int32_t, do_rmulh_w)
+DO_2OP(vrmulhub, 1, uint8_t, do_rmulh_b)
+DO_2OP(vrmulhuh, 2, uint16_t, do_rmulh_h)
+DO_2OP(vrmulhuw, 4, uint32_t, do_rmulh_w)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index de7d8b6c753..bc66058fd38 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -349,3 +349,5 @@ DO_2OP(VSUB, vsub)
 DO_2OP(VMUL, vmul)
 DO_2OP(VMULH_S, vmulhs)
 DO_2OP(VMULH_U, vmulhu)
+DO_2OP(VRMULH_S, vrmulhs)
+DO_2OP(VRMULH_U, vrmulhu)
-- 
2.20.1