target/arm: Implement fp16 for Neon float-integer VCVT

Convert the Neon float-integer VCVT insns to gvec, and use this
to implement fp16 support for them.

Note that unlike the VFP int<->fp16 VCVT insns we converted
earlier and which convert to/from a 32-bit integer, these
Neon insns convert to/from 16-bit integers. So we can use
the existing vfp conversion helpers for the f32<->u32/i32
case but need to provide our own for f16<->u16/i16.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-37-peter.maydell@linaro.org

diff --git a/target/arm/helper.h b/target/arm/helper.h
index f1f33c696d97c8d77b74b8bc3aa69054545b0020..1d8badf4a217d6ef1052f14a0fb9f61d237e08b3 100644 (file)
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -614,6 +614,15 @@ DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(gvec_touizs, 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/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index d13075986e56b47dd5744fa4b2cc426b9c183b81..5aaea867d8cfc9e6da18a4b4c47520dc5b075dfa 100644 (file)
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -3714,17 +3714,6 @@ static bool do_2misc_fp(DisasContext *s, arg_2misc *a,
     return true;
 }
 
-#define DO_2MISC_FP(INSN, FUNC)                                 \
-    static bool trans_##INSN(DisasContext *s, arg_2misc *a)     \
-    {                                                           \
-        return do_2misc_fp(s, a, FUNC);                         \
-    }
-
-DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos)
-DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos)
-DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs)
-DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs)
-
 #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC)                             \
     static void gen_##INSN(unsigned vece, uint32_t rd_ofs,              \
                            uint32_t rm_ofs,                             \
@@ -3758,6 +3747,10 @@ DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s)
 DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s)
 DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s)
 DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s)
+DO_2MISC_FP_VEC(VCVT_FS, gen_helper_gvec_sstoh, gen_helper_gvec_sitos)
+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)
 
 static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
 {

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 46623d401e79a407b0d6ca85d8f2f73deee4112d..6ea9807b7902927e4af1bc2ab7f96e3a9b6ccce9 100644 (file)
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -711,6 +711,26 @@ static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat)
     return -float32_lt(float32_abs(op2), float32_abs(op1), stat);
 }
 
+static int16_t vfp_tosszh(float16 x, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float16_is_any_nan(x)) {
+        float_raise(float_flag_invalid, fpst);
+        return 0;
+    }
+    return float16_to_int16_round_to_zero(x, fpst);
+}
+
+static uint16_t vfp_touszh(float16 x, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float16_is_any_nan(x)) {
+        float_raise(float_flag_invalid, fpst);
+        return 0;
+    }
+    return float16_to_uint16_round_to_zero(x, fpst);
+}
+
 #define DO_2OP(NAME, FUNC, TYPE) \
 void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc)  \
 {                                                                 \
@@ -730,6 +750,15 @@ 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_sitos, helper_vfp_sitos, int32_t)
+DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t)
+DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32)
+DO_2OP(gvec_touizs, helper_vfp_touizs, float32)
+DO_2OP(gvec_sstoh, int16_to_float16, int16_t)
+DO_2OP(gvec_ustoh, uint16_to_float16, uint16_t)
+DO_2OP(gvec_tosszh, vfp_tosszh, float16)
+DO_2OP(gvec_touszh, vfp_touszh, float16)
+
 #define WRAP_CMP0_FWD(FN, CMPOP, TYPE)                          \
     static TYPE TYPE##_##FN##0(TYPE op, float_status *stat)     \
     {                                                           \