[PATCH 10/22] target/arm: Implement VFP fp16 VCMP

[Peter Maydell]

Implement fp16 version of VCMP.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/helper.h            |  2 ++
 target/arm/vfp.decode          |  2 ++
 target/arm/vfp_helper.c        | 15 +++++++------
 target/arm/translate-vfp.c.inc | 39 ++++++++++++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 7 deletions(-)

diff --git a/target/arm/helper.h b/target/arm/helper.h
index ab3a9bd5d7e..278b4e47fd2 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -134,8 +134,10 @@ DEF_HELPER_1(vfp_absd, f64, f64)
 DEF_HELPER_2(vfp_sqrth, f32, f32, env)
 DEF_HELPER_2(vfp_sqrts, f32, f32, env)
 DEF_HELPER_2(vfp_sqrtd, f64, f64, env)
+DEF_HELPER_3(vfp_cmph, void, f32, f32, env)
 DEF_HELPER_3(vfp_cmps, void, f32, f32, env)
 DEF_HELPER_3(vfp_cmpd, void, f64, f64, env)
+DEF_HELPER_3(vfp_cmpeh, void, f32, f32, env)
 DEF_HELPER_3(vfp_cmpes, void, f32, f32, env)
 DEF_HELPER_3(vfp_cmped, void, f64, f64, env)
 
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index c898183771b..b213da4b55d 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -176,6 +176,8 @@ 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
 
+VCMP_hp      ---- 1110 1.11 010 z:1 .... 1001 e:1 1.0 .... \
+             vd=%vd_sp vm=%vm_sp
 VCMP_sp      ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \
              vd=%vd_sp vm=%vm_sp
 VCMP_dp      ---- 1110 1.11 010 z:1 .... 1011 e:1 1.0 .... \
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 2f04dcf0582..0297b102c24 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -330,19 +330,20 @@ static void softfloat_to_vfp_compare(CPUARMState *env, 
FloatRelation cmp)
 }
 
 /* XXX: check quiet/signaling case */
-#define DO_VFP_cmp(p, type) \
-void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env)  \
+#define DO_VFP_cmp(P, FLOATTYPE, ARGTYPE, FPST) \
+void VFP_HELPER(cmp, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env)  \
 { \
     softfloat_to_vfp_compare(env, \
-        type ## _compare_quiet(a, b, &env->vfp.fp_status)); \
+        FLOATTYPE ## _compare_quiet(a, b, &env->vfp.FPST)); \
 } \
-void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \
+void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \
 { \
     softfloat_to_vfp_compare(env, \
-        type ## _compare(a, b, &env->vfp.fp_status)); \
+        FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \
 }
-DO_VFP_cmp(s, float32)
-DO_VFP_cmp(d, float64)
+DO_VFP_cmp(h, float16, float32, fp_status_f16)
+DO_VFP_cmp(s, float32, float32, fp_status)
+DO_VFP_cmp(d, float64, float64, fp_status)
 #undef DO_VFP_cmp
 
 /* Integer to float and float to integer conversions */
diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index c864178ad4e..00a6363e1e1 100644
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -2325,6 +2325,45 @@ DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp)
 DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp)
 DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp)
 
+static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a)
+{
+    TCGv_i32 vd, vm;
+
+    if (!dc_isar_feature(aa32_fp16_arith, s)) {
+        return false;
+    }
+
+    /* Vm/M bits must be zero for the Z variant */
+    if (a->z && a->vm != 0) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    vd = tcg_temp_new_i32();
+    vm = tcg_temp_new_i32();
+
+    neon_load_reg32(vd, a->vd);
+    if (a->z) {
+        tcg_gen_movi_i32(vm, 0);
+    } else {
+        neon_load_reg32(vm, a->vm);
+    }
+
+    if (a->e) {
+        gen_helper_vfp_cmpeh(vd, vm, cpu_env);
+    } else {
+        gen_helper_vfp_cmph(vd, vm, cpu_env);
+    }
+
+    tcg_temp_free_i32(vd);
+    tcg_temp_free_i32(vm);
+
+    return true;
+}
+
 static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a)
 {
     TCGv_i32 vd, vm;
-- 
2.20.1