[PATCH v3 13/44] target/arm: Implement MVE VMULH

[Peter Maydell]

Implement the MVE VMULH insn, which performs a vector
multiply and returns the high half of the result.

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    | 26 ++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 38 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 707b9cbd546..5c80b185ccc 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -81,3 +81,10 @@ DEF_HELPER_FLAGS_4(mve_vsubw, TCG_CALL_NO_WG, void, env, 
ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vmulhsb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vmulhsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+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)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index f7d1d303f17..ca4c27209da 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -82,6 +82,9 @@ VADD             1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 
... 0 @2op
 VSUB             1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
 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
+
 # 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 6bbd15a3d9e..48744f38af1 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -377,3 +377,29 @@ DO_2OP(veor, 8, uint64_t, DO_EOR)
 DO_2OP_U(vadd, DO_ADD)
 DO_2OP_U(vsub, DO_SUB)
 DO_2OP_U(vmul, DO_MUL)
+
+/*
+ * Because the computation type is at least twice as large as required,
+ * these work for both signed and unsigned source types.
+ */
+static inline uint8_t do_mulh_b(int32_t n, int32_t m)
+{
+    return (n * m) >> 8;
+}
+
+static inline uint16_t do_mulh_h(int32_t n, int32_t m)
+{
+    return (n * m) >> 16;
+}
+
+static inline uint32_t do_mulh_w(int64_t n, int64_t m)
+{
+    return (n * m) >> 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)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 5d3dee46995..de7d8b6c753 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -347,3 +347,5 @@ DO_LOGIC(VEOR, gen_helper_mve_veor)
 DO_2OP(VADD, vadd)
 DO_2OP(VSUB, vsub)
 DO_2OP(VMUL, vmul)
+DO_2OP(VMULH_S, vmulhs)
+DO_2OP(VMULH_U, vmulhu)
-- 
2.20.1