[PULL 17/44] target/arm: Implement MVE VPSEL

[Peter Maydell]

Implement the MVE VPSEL insn, which sets each byte of the destination
vector Qd to the byte from either Qn or Qm depending on the value of
the corresponding bit in VPR.P0.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  2 ++
 target/arm/mve.decode      |  7 +++++--
 target/arm/mve_helper.c    | 19 +++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 4f9903e66ef..16c4c3b8f61 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -82,6 +82,8 @@ DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, 
ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index ef708ba80ff..4bd20a9a319 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -468,8 +468,11 @@ VSHLC             111 0 1110 1 . 1 imm:5 ... 0 1111 1100 
rdm:4 qd=%qd
 # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero.
 VCMPEQ            1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp
 VCMPNE            1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp
-VCMPCS            1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp
-VCMPHI            1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp
+{
+  VPSEL           1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz
+  VCMPCS          1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp
+  VCMPHI          1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp
+}
 VCMPGE            1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp
 VCMPLT            1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp
 VCMPGT            1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 1a021a9a817..03171766b57 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1842,3 +1842,22 @@ DO_VCMP_S(vcmpge, DO_GE)
 DO_VCMP_S(vcmplt, DO_LT)
 DO_VCMP_S(vcmpgt, DO_GT)
 DO_VCMP_S(vcmple, DO_LE)
+
+void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm)
+{
+    /*
+     * Qd[n] = VPR.P0[n] ? Qn[n] : Qm[n]
+     * but note that whether bytes are written to Qd is still subject
+     * to (all forms of) predication in the usual way.
+     */
+    uint64_t *d = vd, *n = vn, *m = vm;
+    uint16_t mask = mve_element_mask(env);
+    uint16_t p0 = FIELD_EX32(env->v7m.vpr, V7M_VPR, P0);
+    unsigned e;
+    for (e = 0; e < 16 / 8; e++, mask >>= 8, p0 >>= 8) {
+        uint64_t r = m[H8(e)];
+        mergemask(&r, n[H8(e)], p0);
+        mergemask(&d[H8(e)], r, mask);
+    }
+    mve_advance_vpt(env);
+}
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 6c6f159aa3e..aa38218e08f 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -376,6 +376,8 @@ DO_LOGIC(VORR, gen_helper_mve_vorr)
 DO_LOGIC(VORN, gen_helper_mve_vorn)
 DO_LOGIC(VEOR, gen_helper_mve_veor)
 
+DO_LOGIC(VPSEL, gen_helper_mve_vpsel)
+
 #define DO_2OP(INSN, FN) \
     static bool trans_##INSN(DisasContext *s, arg_2op *a)       \
     {                                                           \
-- 
2.20.1