[PULL 40/47] target/arm: Implement fp16 for Neon VRINTX

[Peter Maydell]

Convert the Neon VRINTX insn to use gvec, and use this to implement
fp16 support for it.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-42-peter.maydell@linaro.org
---
 target/arm/helper.h             |  3 +++
 target/arm/vec_helper.c         |  3 +++
 target/arm/translate-neon.c.inc | 45 +++------------------------------
 3 files changed, 9 insertions(+), 42 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 83f7804dfe9..cbdbf824d8d 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -640,6 +640,9 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, 
ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 7ddf1e791c9..20f153b47a1 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -750,6 +750,9 @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16)
 DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32)
 DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64)
 
+DO_2OP(gvec_vrintx_h, float16_round_to_int, float16)
+DO_2OP(gvec_vrintx_s, float32_round_to_int, float32)
+
 DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t)
 DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t)
 DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32)
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index 77a85d468fb..5726afe4d72 100644
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -3679,47 +3679,6 @@ static bool trans_VQNEG(DisasContext *s, arg_2misc *a)
     return do_2misc(s, a, fn[a->size]);
 }
 
-static bool do_2misc_fp(DisasContext *s, arg_2misc *a,
-                        NeonGenOneSingleOpFn *fn)
-{
-    int pass;
-    TCGv_ptr fpst;
-
-    /* Handle a 2-reg-misc operation by iterating 32 bits at a time */
-    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
-        return false;
-    }
-
-    /* UNDEF accesses to D16-D31 if they don't exist. */
-    if (!dc_isar_feature(aa32_simd_r32, s) &&
-        ((a->vd | a->vm) & 0x10)) {
-        return false;
-    }
-
-    if (a->size != 2) {
-        /* TODO: FP16 will be the size == 1 case */
-        return false;
-    }
-
-    if ((a->vd | a->vm) & a->q) {
-        return false;
-    }
-
-    if (!vfp_access_check(s)) {
-        return true;
-    }
-
-    fpst = fpstatus_ptr(FPST_STD);
-    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
-        TCGv_i32 tmp = neon_load_reg(a->vm, pass);
-        fn(tmp, tmp, fpst);
-        neon_store_reg(a->vd, pass, tmp);
-    }
-    tcg_temp_free_ptr(fpst);
-
-    return true;
-}
-
 #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC)                             \
     static void gen_##INSN(unsigned vece, uint32_t rd_ofs,              \
                            uint32_t rm_ofs,                             \
@@ -3758,12 +3717,14 @@ DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, 
gen_helper_gvec_uitos)
 DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs)
 DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs)
 
+DO_2MISC_FP_VEC(VRINTX_impl, gen_helper_gvec_vrintx_h, 
gen_helper_gvec_vrintx_s)
+
 static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
 {
     if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
         return false;
     }
-    return do_2misc_fp(s, a, gen_helper_rints_exact);
+    return trans_VRINTX_impl(s, a);
 }
 
 #define DO_VEC_RMODE(INSN, RMODE, OP)                                   \
-- 
2.20.1