[PULL 28/44] target/arm: Implement MVE VQABS, VQNEG

[Peter Maydell]

Implement the MVE 1-operand saturating operations VQABS and VQNEG.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  8 ++++++++
 target/arm/mve.decode      |  3 +++
 target/arm/mve_helper.c    | 37 +++++++++++++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 50 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 2f54396b2df..f9345bfafc7 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -76,6 +76,14 @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, 
ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr)
 
+DEF_HELPER_FLAGS_3(mve_vqabsb, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vqabsh, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vqabsw, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
+DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr)
+DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
 DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 7a6de3991b6..a05b882f9d9 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -279,6 +279,9 @@ VABS_fp          1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 
... 0 @1op
 VNEG             1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op
 VNEG_fp          1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op
 
+VQABS            1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op
+VQNEG            1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op
+
 &vdup qd rt size
 # Qd is in the fields usually named Qn
 @vdup            .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index a69fcd2243c..6539012ddd8 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2200,3 +2200,40 @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void 
*vn, void *vm)
     }
     mve_advance_vpt(env);
 }
+
+#define DO_1OP_SAT(OP, ESIZE, TYPE, FN)                                 \
+    void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm)         \
+    {                                                                   \
+        TYPE *d = vd, *m = vm;                                          \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        bool qc = false;                                                \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            bool sat = false;                                           \
+            mergemask(&d[H##ESIZE(e)], FN(m[H##ESIZE(e)], &sat), mask); \
+            qc |= sat & mask & 1;                                       \
+        }                                                               \
+        if (qc) {                                                       \
+            env->vfp.qc[0] = qc;                                        \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
+#define DO_VQABS_B(N, SATP) \
+    do_sat_bhs(DO_ABS((int64_t)N), INT8_MIN, INT8_MAX, SATP)
+#define DO_VQABS_H(N, SATP) \
+    do_sat_bhs(DO_ABS((int64_t)N), INT16_MIN, INT16_MAX, SATP)
+#define DO_VQABS_W(N, SATP) \
+    do_sat_bhs(DO_ABS((int64_t)N), INT32_MIN, INT32_MAX, SATP)
+
+#define DO_VQNEG_B(N, SATP) do_sat_bhs(-(int64_t)N, INT8_MIN, INT8_MAX, SATP)
+#define DO_VQNEG_H(N, SATP) do_sat_bhs(-(int64_t)N, INT16_MIN, INT16_MAX, SATP)
+#define DO_VQNEG_W(N, SATP) do_sat_bhs(-(int64_t)N, INT32_MIN, INT32_MAX, SATP)
+
+DO_1OP_SAT(vqabsb, 1, int8_t, DO_VQABS_B)
+DO_1OP_SAT(vqabsh, 2, int16_t, DO_VQABS_H)
+DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W)
+
+DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B)
+DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H)
+DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index e3e115c1aa9..f2213ec8cde 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -275,6 +275,8 @@ DO_1OP(VCLZ, vclz)
 DO_1OP(VCLS, vcls)
 DO_1OP(VABS, vabs)
 DO_1OP(VNEG, vneg)
+DO_1OP(VQABS, vqabs)
+DO_1OP(VQNEG, vqneg)
 
 /* Narrowing moves: only size 0 and 1 are valid */
 #define DO_VMOVN(INSN, FN) \
-- 
2.20.1