[PATCH v2 08/45] target/arm: Implement VFP fp16 for VABS, VNEG, VSQRT

[Peter Maydell]

Implement VFP fp16 for VABS, VNEG and VSQRT. This is all
the fp16 insns that use the DO_VFP_2OP macro, because there
is no fp16 version of VMOV_reg.

Notes:
 * the gen_helper_vfp_negh already exists as we needed to create
   it for the fp16 multiply-add insns
 * as usual we need to use the f16 version of the fp_status;
   this is only relevant for VSQRT

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper.h            |  2 ++
 target/arm/vfp.decode          |  3 +++
 target/arm/vfp_helper.c        | 10 +++++++++
 target/arm/translate-vfp.c.inc | 40 ++++++++++++++++++++++++++++++++++
 4 files changed, 55 insertions(+)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 538b1a20ce5..37739b0e788 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -128,8 +128,10 @@ DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr)
 DEF_HELPER_1(vfp_negh, f16, f16)
 DEF_HELPER_1(vfp_negs, f32, f32)
 DEF_HELPER_1(vfp_negd, f64, f64)
+DEF_HELPER_1(vfp_absh, f16, f16)
 DEF_HELPER_1(vfp_abss, f32, f32)
 DEF_HELPER_1(vfp_absd, f64, f64)
+DEF_HELPER_2(vfp_sqrth, f16, f16, env)
 DEF_HELPER_2(vfp_sqrts, f32, f32, env)
 DEF_HELPER_2(vfp_sqrtd, f64, f64, env)
 DEF_HELPER_3(vfp_cmps, void, f32, f32, env)
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index af4829e201b..5c64701dde0 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -162,12 +162,15 @@ VMOV_imm_dp  ---- 1110 1.11 .... .... 1011 0000 .... \
 VMOV_reg_sp  ---- 1110 1.11 0000 .... 1010 01.0 ....        @vfp_dm_ss
 VMOV_reg_dp  ---- 1110 1.11 0000 .... 1011 01.0 ....        @vfp_dm_dd
 
+VABS_hp      ---- 1110 1.11 0000 .... 1001 11.0 ....        @vfp_dm_ss
 VABS_sp      ---- 1110 1.11 0000 .... 1010 11.0 ....        @vfp_dm_ss
 VABS_dp      ---- 1110 1.11 0000 .... 1011 11.0 ....        @vfp_dm_dd
 
+VNEG_hp      ---- 1110 1.11 0001 .... 1001 01.0 ....        @vfp_dm_ss
 VNEG_sp      ---- 1110 1.11 0001 .... 1010 01.0 ....        @vfp_dm_ss
 VNEG_dp      ---- 1110 1.11 0001 .... 1011 01.0 ....        @vfp_dm_dd
 
+VSQRT_hp     ---- 1110 1.11 0001 .... 1001 11.0 ....        @vfp_dm_ss
 VSQRT_sp     ---- 1110 1.11 0001 .... 1010 11.0 ....        @vfp_dm_ss
 VSQRT_dp     ---- 1110 1.11 0001 .... 1011 11.0 ....        @vfp_dm_dd
 
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 579ca3832d1..cc7fb6ddb6a 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -276,6 +276,11 @@ float64 VFP_HELPER(neg, d)(float64 a)
     return float64_chs(a);
 }
 
+dh_ctype_f16 VFP_HELPER(abs, h)(dh_ctype_f16 a)
+{
+    return float16_abs(a);
+}
+
 float32 VFP_HELPER(abs, s)(float32 a)
 {
     return float32_abs(a);
@@ -286,6 +291,11 @@ float64 VFP_HELPER(abs, d)(float64 a)
     return float64_abs(a);
 }
 
+dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env)
+{
+    return float16_sqrt(a, &env->vfp.fp_status_f16);
+}
+
 float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env)
 {
     return float32_sqrt(a, &env->vfp.fp_status);
diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index f891d860bb9..99b722b75bd 100644
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -1469,6 +1469,38 @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn 
*fn, int vd, int vm)
     return true;
 }
 
+static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm)
+{
+    /*
+     * Do a half-precision operation. Functionally this is
+     * the same as do_vfp_2op_sp(), except:
+     *  - it doesn't need the VFP vector handling (fp16 is a
+     *    v8 feature, and in v8 VFP vectors don't exist)
+     *  - it does the aa32_fp16_arith feature test
+     */
+    TCGv_i32 f0;
+
+    if (!dc_isar_feature(aa32_fp16_arith, s)) {
+        return false;
+    }
+
+    if (s->vec_len != 0 || s->vec_stride != 0) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    f0 = tcg_temp_new_i32();
+    neon_load_reg32(f0, vm);
+    fn(f0, f0);
+    neon_store_reg32(f0, vd);
+    tcg_temp_free_i32(f0);
+
+    return true;
+}
+
 static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm)
 {
     uint32_t delta_m = 0;
@@ -2244,12 +2276,19 @@ static bool trans_VMOV_imm_dp(DisasContext *s, 
arg_VMOV_imm_dp *a)
 DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32)
 DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64)
 
+DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh)
 DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss)
 DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd)
 
+DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh)
 DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs)
 DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd)
 
+static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm)
+{
+    gen_helper_vfp_sqrth(vd, vm, cpu_env);
+}
+
 static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm)
 {
     gen_helper_vfp_sqrts(vd, vm, cpu_env);
@@ -2260,6 +2299,7 @@ static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm)
     gen_helper_vfp_sqrtd(vd, vm, cpu_env);
 }
 
+DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp)
 DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp)
 DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp)
 
-- 
2.20.1