target/arm: Implement VFP fp16 for VFP_BINOP operations

Implmeent VFP fp16 support for simple binary-operator VFP insns VADD,
VSUB, VMUL, VDIV, VMINNM and VMAXNM:

 * make the VFP_BINOP() macro generate float16 helpers as well as
   float32 and float64
 * implement a do_vfp_3op_hp() function similar to the existing
   do_vfp_3op_sp()
 * add decode for the half-precision insn patterns

Note that the VFP_BINOP macro use creates a couple of unused helper
functions vfp_maxh and vfp_minh, but they're small so it's not worth
splitting the BINOP operations into "needs halfprec" and "no
halfprec" groups.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-4-peter.maydell@linaro.org

5 files changed, 106 insertions, 0 deletions

diff --git a/target/arm/helper.h b/target/arm/helper.h
index 3ca73a1764..61e4e93886 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -101,20 +101,28 @@ DEF_HELPER_FLAGS_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32)
 DEF_HELPER_1(vfp_get_fpscr, i32, env)
 DEF_HELPER_2(vfp_set_fpscr, void, env, i32)
 
+DEF_HELPER_3(vfp_addh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_adds, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_addd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_subh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_subs, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_subd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_mulh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_muls, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_muld, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_divh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_divs, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_divd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_maxh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_maxs, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_maxd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_minh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_mins, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_mind, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_maxnums, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr)
 DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr)
 DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr)
 DEF_HELPER_1(vfp_negs, f32, f32)
diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index 4eeafb494a..01a5fd6511 100644
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -1266,6 +1266,54 @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn,
     return true;
 }
 
+static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn,
+                          int vd, int vn, int vm, bool reads_vd)
+{
+    /*
+     * Do a half-precision operation. Functionally this is
+     * the same as do_vfp_3op_sp(), except:
+     *  - it uses the FPST_FPCR_F16
+     *  - 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, f1, fd;
+    TCGv_ptr fpst;
+
+    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();
+    f1 = tcg_temp_new_i32();
+    fd = tcg_temp_new_i32();
+    fpst = fpstatus_ptr(FPST_FPCR_F16);
+
+    neon_load_reg32(f0, vn);
+    neon_load_reg32(f1, vm);
+
+    if (reads_vd) {
+        neon_load_reg32(fd, vd);
+    }
+    fn(fd, f0, f1, fpst);
+    neon_store_reg32(fd, vd);
+
+    tcg_temp_free_i32(f0);
+    tcg_temp_free_i32(f1);
+    tcg_temp_free_i32(fd);
+    tcg_temp_free_ptr(fpst);
+
+    return true;
+}
+
 static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn,
                           int vd, int vn, int vm, bool reads_vd)
 {
@@ -1643,6 +1691,11 @@ static bool trans_VNMLA_dp(DisasContext *s, arg_VNMLA_dp *a)
     return do_vfp_3op_dp(s, gen_VNMLA_dp, a->vd, a->vn, a->vm, true);
 }
 
+static bool trans_VMUL_hp(DisasContext *s, arg_VMUL_sp *a)
+{
+    return do_vfp_3op_hp(s, gen_helper_vfp_mulh, a->vd, a->vn, a->vm, false);
+}
+
 static bool trans_VMUL_sp(DisasContext *s, arg_VMUL_sp *a)
 {
     return do_vfp_3op_sp(s, gen_helper_vfp_muls, a->vd, a->vn, a->vm, false);
@@ -1677,6 +1730,11 @@ static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_dp *a)
     return do_vfp_3op_dp(s, gen_VNMUL_dp, a->vd, a->vn, a->vm, false);
 }
 
+static bool trans_VADD_hp(DisasContext *s, arg_VADD_sp *a)
+{
+    return do_vfp_3op_hp(s, gen_helper_vfp_addh, a->vd, a->vn, a->vm, false);
+}
+
 static bool trans_VADD_sp(DisasContext *s, arg_VADD_sp *a)
 {
     return do_vfp_3op_sp(s, gen_helper_vfp_adds, a->vd, a->vn, a->vm, false);
@@ -1687,6 +1745,11 @@ static bool trans_VADD_dp(DisasContext *s, arg_VADD_dp *a)
     return do_vfp_3op_dp(s, gen_helper_vfp_addd, a->vd, a->vn, a->vm, false);
 }
 
+static bool trans_VSUB_hp(DisasContext *s, arg_VSUB_sp *a)
+{
+    return do_vfp_3op_hp(s, gen_helper_vfp_subh, a->vd, a->vn, a->vm, false);
+}
+
 static bool trans_VSUB_sp(DisasContext *s, arg_VSUB_sp *a)
 {
     return do_vfp_3op_sp(s, gen_helper_vfp_subs, a->vd, a->vn, a->vm, false);
@@ -1697,6 +1760,11 @@ static bool trans_VSUB_dp(DisasContext *s, arg_VSUB_dp *a)
     return do_vfp_3op_dp(s, gen_helper_vfp_subd, a->vd, a->vn, a->vm, false);
 }
 
+static bool trans_VDIV_hp(DisasContext *s, arg_VDIV_sp *a)
+{
+    return do_vfp_3op_hp(s, gen_helper_vfp_divh, a->vd, a->vn, a->vm, false);
+}
+
 static bool trans_VDIV_sp(DisasContext *s, arg_VDIV_sp *a)
 {
     return do_vfp_3op_sp(s, gen_helper_vfp_divs, a->vd, a->vn, a->vm, false);
@@ -1707,6 +1775,24 @@ static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_dp *a)
     return do_vfp_3op_dp(s, gen_helper_vfp_divd, a->vd, a->vn, a->vm, false);
 }
 
+static bool trans_VMINNM_hp(DisasContext *s, arg_VMINNM_sp *a)
+{
+    if (!dc_isar_feature(aa32_vminmaxnm, s)) {
+        return false;
+    }
+    return do_vfp_3op_hp(s, gen_helper_vfp_minnumh,
+                         a->vd, a->vn, a->vm, false);
+}
+
+static bool trans_VMAXNM_hp(DisasContext *s, arg_VMAXNM_sp *a)
+{
+    if (!dc_isar_feature(aa32_vminmaxnm, s)) {
+        return false;
+    }
+    return do_vfp_3op_hp(s, gen_helper_vfp_maxnumh,
+                         a->vd, a->vn, a->vm, false);
+}
+
 static bool trans_VMINNM_sp(DisasContext *s, arg_VMINNM_sp *a)
 {
     if (!dc_isar_feature(aa32_vminmaxnm, s)) {
diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode
index 34ca164266..ee700e5197 100644
--- a/target/arm/vfp-uncond.decode
+++ b/target/arm/vfp-uncond.decode
@@ -49,6 +49,9 @@ VSEL        1111 1110 0. cc:2 .... .... 1010 .0.0 .... \
 VSEL        1111 1110 0. cc:2 .... .... 1011 .0.0 .... \
             vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1
 
+VMAXNM_hp   1111 1110 1.00 .... .... 1001 .0.0 ....         @vfp_dnm_s
+VMINNM_hp   1111 1110 1.00 .... .... 1001 .1.0 ....         @vfp_dnm_s
+
 VMAXNM_sp   1111 1110 1.00 .... .... 1010 .0.0 ....         @vfp_dnm_s
 VMINNM_sp   1111 1110 1.00 .... .... 1010 .1.0 ....         @vfp_dnm_s
 
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index 2c793e3e87..1ecd5e28ca 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -115,18 +115,22 @@ VNMLS_dp     ---- 1110 0.01 .... .... 1011 .0.0 ....        @vfp_dnm_d
 VNMLA_sp     ---- 1110 0.01 .... .... 1010 .1.0 ....        @vfp_dnm_s
 VNMLA_dp     ---- 1110 0.01 .... .... 1011 .1.0 ....        @vfp_dnm_d
 
+VMUL_hp      ---- 1110 0.10 .... .... 1001 .0.0 ....        @vfp_dnm_s
 VMUL_sp      ---- 1110 0.10 .... .... 1010 .0.0 ....        @vfp_dnm_s
 VMUL_dp      ---- 1110 0.10 .... .... 1011 .0.0 ....        @vfp_dnm_d
 
 VNMUL_sp     ---- 1110 0.10 .... .... 1010 .1.0 ....        @vfp_dnm_s
 VNMUL_dp     ---- 1110 0.10 .... .... 1011 .1.0 ....        @vfp_dnm_d
 
+VADD_hp      ---- 1110 0.11 .... .... 1001 .0.0 ....        @vfp_dnm_s
 VADD_sp      ---- 1110 0.11 .... .... 1010 .0.0 ....        @vfp_dnm_s
 VADD_dp      ---- 1110 0.11 .... .... 1011 .0.0 ....        @vfp_dnm_d
 
+VSUB_hp      ---- 1110 0.11 .... .... 1001 .1.0 ....        @vfp_dnm_s
 VSUB_sp      ---- 1110 0.11 .... .... 1010 .1.0 ....        @vfp_dnm_s
 VSUB_dp      ---- 1110 0.11 .... .... 1011 .1.0 ....        @vfp_dnm_d
 
+VDIV_hp      ---- 1110 1.00 .... .... 1001 .0.0 ....        @vfp_dnm_s
 VDIV_sp      ---- 1110 1.00 .... .... 1010 .0.0 ....        @vfp_dnm_s
 VDIV_dp      ---- 1110 1.00 .... .... 1011 .0.0 ....        @vfp_dnm_d
 
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 02ab8d7f2d..b8ca744bcc 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -236,6 +236,11 @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val)
 #define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p))
 
 #define VFP_BINOP(name) \
+dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, void *fpstp) \
+{ \
+    float_status *fpst = fpstp; \
+    return float16_ ## name(a, b, fpst); \
+} \
 float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \
 { \
     float_status *fpst = fpstp; \