[PATCH for-6.2 37/53] target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM

[Peter Maydell]

Implement more simple 2-operand floating point MVE insns.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper-mve.h    | 15 +++++++++++++++
 target/arm/mve.decode      |  6 ++++++
 target/arm/mve_helper.c    | 24 ++++++++++++++++++++++++
 target/arm/translate-mve.c |  5 +++++
 4 files changed, 50 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 32fd2e1f9be..370876d7934 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -413,6 +413,21 @@ DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, 
env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vfsubh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfsubs, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vfmulh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfmuls, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vfabdh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vfabds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vmaxnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index e211cb016c6..cdbfaa4245b 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -625,3 +625,9 @@ VCMPLE_scalar     1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 
.... @vcmp_scalar
 
 # 2-operand FP
 VADD_fp           1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
+VSUB_fp           1110 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
+VMUL_fp           1111 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 1 ... 0 @2op_fp
+VABD_fp           1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp
+
+VMAXNM            1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp
+VMINNM            1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index ff087e9d3a4..e0e3e30de68 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2835,3 +2835,27 @@ DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN)
 
 DO_2OP_FP(vfaddh, 2, uint16_t, float16_add)
 DO_2OP_FP(vfadds, 4, uint32_t, float32_add)
+
+DO_2OP_FP(vfsubh, 2, uint16_t, float16_sub)
+DO_2OP_FP(vfsubs, 4, uint32_t, float32_sub)
+
+DO_2OP_FP(vfmulh, 2, uint16_t, float16_mul)
+DO_2OP_FP(vfmuls, 4, uint32_t, float32_mul)
+
+static inline float16 float16_abd(float16 a, float16 b, float_status *s)
+{
+    return float16_abs(float16_sub(a, b, s));
+}
+
+static inline float32 float32_abd(float32 a, float32 b, float_status *s)
+{
+    return float32_abs(float32_sub(a, b, s));
+}
+
+DO_2OP_FP(vfabdh, 2, uint16_t, float16_abd)
+DO_2OP_FP(vfabds, 4, uint32_t, float32_abd)
+
+DO_2OP_FP(vmaxnmh, 2, uint16_t, float16_maxnum)
+DO_2OP_FP(vmaxnms, 4, uint32_t, float32_maxnum)
+DO_2OP_FP(vminnmh, 2, uint16_t, float16_minnum)
+DO_2OP_FP(vminnms, 4, uint32_t, float32_minnum)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index d2c40ede564..98282335820 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -847,6 +847,11 @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a)
     }
 
 DO_2OP_FP(VADD_fp, vfadd)
+DO_2OP_FP(VSUB_fp, vfsub)
+DO_2OP_FP(VMUL_fp, vfmul)
+DO_2OP_FP(VABD_fp, vfabd)
+DO_2OP_FP(VMAXNM, vmaxnm)
+DO_2OP_FP(VMINNM, vminnm)
 
 static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
                           MVEGenTwoOpScalarFn fn)
-- 
2.20.1