target/arm: Implement MVE VCVT with specified rounding mode

Implement the MVE VCVT which converts from floating-point to integer
using a rounding mode specified by the instruction.  We implement
this similarly to the Neon equivalents, by passing the required
rounding mode as an extra integer parameter to the helper functions.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

4 files changed, 105 insertions, 0 deletions

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index f3c2b43bf4..6d4052a526 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -177,6 +177,11 @@ DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vcvt_rm_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vcvt_rm_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vcvt_rm_ss, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vcvt_rm_us, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 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 89b8c6fc8e..55e8ce304e 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -805,3 +805,13 @@ VCVT_SF           1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op
 VCVT_UF           1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op
 VCVT_FS           1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op
 VCVT_FU           1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op
+
+# VCVT from floating point to integer with specified rounding mode
+VCVTAS            1111 1111 1 . 11 .. 11 ... 000 00 0 1 . 0 ... 0 @1op
+VCVTAU            1111 1111 1 . 11 .. 11 ... 000 00 1 1 . 0 ... 0 @1op
+VCVTNS            1111 1111 1 . 11 .. 11 ... 000 01 0 1 . 0 ... 0 @1op
+VCVTNU            1111 1111 1 . 11 .. 11 ... 000 01 1 1 . 0 ... 0 @1op
+VCVTPS            1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op
+VCVTPU            1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op
+VCVTMS            1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op
+VCVTMU            1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index d829ffe12d..a793199fbe 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -3294,3 +3294,41 @@ DO_VCVT_FIXED(vcvt_sf, 4, int32_t, helper_vfp_sltos)
 DO_VCVT_FIXED(vcvt_uf, 4, uint32_t, helper_vfp_ultos)
 DO_VCVT_FIXED(vcvt_fs, 4, int32_t, helper_vfp_tosls_round_to_zero)
 DO_VCVT_FIXED(vcvt_fu, 4, uint32_t, helper_vfp_touls_round_to_zero)
+
+/* VCVT with specified rmode */
+#define DO_VCVT_RMODE(OP, ESIZE, TYPE, FN)                              \
+    void HELPER(glue(mve_, OP))(CPUARMState *env,                       \
+                                void *vd, void *vm, uint32_t rmode)     \
+    {                                                                   \
+        TYPE *d = vd, *m = vm;                                          \
+        TYPE r;                                                         \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        float_status *fpst;                                             \
+        float_status scratch_fpst;                                      \
+        float_status *base_fpst = (ESIZE == 2) ?                        \
+            &env->vfp.standard_fp_status_f16 :                          \
+            &env->vfp.standard_fp_status;                               \
+        uint32_t prev_rmode = get_float_rounding_mode(base_fpst);       \
+        set_float_rounding_mode(rmode, base_fpst);                      \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) {              \
+                continue;                                               \
+            }                                                           \
+            fpst = base_fpst;                                           \
+            if (!(mask & 1)) {                                          \
+                /* We need the result but without updating flags */     \
+                scratch_fpst = *fpst;                                   \
+                fpst = &scratch_fpst;                                   \
+            }                                                           \
+            r = FN(m[H##ESIZE(e)], 0, fpst);                            \
+            mergemask(&d[H##ESIZE(e)], r, mask);                        \
+        }                                                               \
+        set_float_rounding_mode(prev_rmode, base_fpst);                 \
+        mve_advance_vpt(env);                                           \
+    }
+
+DO_VCVT_RMODE(vcvt_rm_sh, 2, uint16_t, helper_vfp_toshh)
+DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh)
+DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls)
+DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 351033af1e..e80a55eb62 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -49,6 +49,7 @@ typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
 typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
+typedef void MVEGenVCVTRmodeFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
 
 /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
 static inline long mve_qreg_offset(unsigned reg)
@@ -575,6 +576,57 @@ DO_VCVT(VCVT_UF, vcvt_uh, vcvt_uf)
 DO_VCVT(VCVT_FS, vcvt_hs, vcvt_fs)
 DO_VCVT(VCVT_FU, vcvt_hu, vcvt_fu)
 
+static bool do_vcvt_rmode(DisasContext *s, arg_1op *a,
+                          enum arm_fprounding rmode, bool u)
+{
+    /*
+     * Handle VCVT fp to int with specified rounding mode.
+     * This is a 1op fn but we must pass the rounding mode as
+     * an immediate to the helper.
+     */
+    TCGv_ptr qd, qm;
+    static MVEGenVCVTRmodeFn * const fns[4][2] = {
+        { NULL, NULL },
+        { gen_helper_mve_vcvt_rm_sh, gen_helper_mve_vcvt_rm_uh },
+        { gen_helper_mve_vcvt_rm_ss, gen_helper_mve_vcvt_rm_us },
+        { NULL, NULL },
+    };
+    MVEGenVCVTRmodeFn *fn = fns[a->size][u];
+
+    if (!dc_isar_feature(aa32_mve_fp, s) ||
+        !mve_check_qreg_bank(s, a->qd | a->qm) ||
+        !fn) {
+        return false;
+    }
+
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    qd = mve_qreg_ptr(a->qd);
+    qm = mve_qreg_ptr(a->qm);
+    fn(cpu_env, qd, qm, tcg_constant_i32(arm_rmode_to_sf(rmode)));
+    tcg_temp_free_ptr(qd);
+    tcg_temp_free_ptr(qm);
+    mve_update_eci(s);
+    return true;
+}
+
+#define DO_VCVT_RMODE(INSN, RMODE, U)                           \
+    static bool trans_##INSN(DisasContext *s, arg_1op *a)       \
+    {                                                           \
+        return do_vcvt_rmode(s, a, RMODE, U);                   \
+    }                                                           \
+
+DO_VCVT_RMODE(VCVTAS, FPROUNDING_TIEAWAY, false)
+DO_VCVT_RMODE(VCVTAU, FPROUNDING_TIEAWAY, true)
+DO_VCVT_RMODE(VCVTNS, FPROUNDING_TIEEVEN, false)
+DO_VCVT_RMODE(VCVTNU, FPROUNDING_TIEEVEN, true)
+DO_VCVT_RMODE(VCVTPS, FPROUNDING_POSINF, false)
+DO_VCVT_RMODE(VCVTPU, FPROUNDING_POSINF, true)
+DO_VCVT_RMODE(VCVTMS, FPROUNDING_NEGINF, false)
+DO_VCVT_RMODE(VCVTMU, FPROUNDING_NEGINF, true)
+
 /* Narrowing moves: only size 0 and 1 are valid */
 #define DO_VMOVN(INSN, FN) \
     static bool trans_##INSN(DisasContext *s, arg_1op *a)       \