[Qemu-devel] [PATCH v6 3/4] target-arm: Implement ARMv8 FP VMAXNM and VMINNM instructions.

[Will Newton <will.newton@linaro.org>]

This adds support for the ARMv8 floating point VMAXNM and VMINNM
instructions.

Signed-off-by: Will Newton <will.newton@linaro.org>
---
 target-arm/helper.c    | 41 +++++++++++++++++++++++++++++++++++++++++
 target-arm/helper.h    |  5 +++++
 target-arm/translate.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 89 insertions(+)

Changes in v6:
 - New patch

diff --git a/target-arm/helper.c b/target-arm/helper.c
index 3445813..e5428d1 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -4079,3 +4079,44 @@ float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp)
     float_status *fpst = fpstp;
     return float64_muladd(a, b, c, 0, fpst);
 }
+
+/* ARMv8 VMAXNM/VMINNM */
+float32 VFP_HELPER(maxnm, s)(float32 a, float32 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float32_is_quiet_nan(a) && !float32_is_quiet_nan(b))
+        return b;
+    else if (float32_is_quiet_nan(b) && !float32_is_quiet_nan(a))
+        return a;
+    return float32_max(a, b, fpst);
+}
+
+float64 VFP_HELPER(maxnm, d)(float64 a, float64 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float64_is_quiet_nan(a) && !float64_is_quiet_nan(b))
+        return b;
+    else if (float64_is_quiet_nan(b) && !float64_is_quiet_nan(a))
+        return a;
+    return float64_max(a, b, fpst);
+}
+
+float32 VFP_HELPER(minnm, s)(float32 a, float32 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float32_is_quiet_nan(a) && !float32_is_quiet_nan(b))
+        return b;
+    else if (float32_is_quiet_nan(b) && !float32_is_quiet_nan(a))
+        return a;
+    return float32_min(a, b, fpst);
+}
+
+float64 VFP_HELPER(minnm, d)(float64 a, float64 b, void *fpstp)
+{
+    float_status *fpst = fpstp;
+    if (float64_is_quiet_nan(a) && !float64_is_quiet_nan(b))
+        return b;
+    else if (float64_is_quiet_nan(b) && !float64_is_quiet_nan(a))
+        return a;
+    return float64_min(a, b, fpst);
+}
diff --git a/target-arm/helper.h b/target-arm/helper.h
index cac9564..d459a39 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -132,6 +132,11 @@ DEF_HELPER_2(neon_fcvt_f32_to_f16, i32, f32, env)
 DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr)
 DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr)

+DEF_HELPER_3(vfp_maxnmd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_maxnms, f32, f32, f32, ptr)
+DEF_HELPER_3(vfp_minnmd, f64, f64, f64, ptr)
+DEF_HELPER_3(vfp_minnms, f32, f32, f32, ptr)
+
 DEF_HELPER_3(recps_f32, f32, f32, f32, env)
 DEF_HELPER_3(rsqrts_f32, f32, f32, f32, env)
 DEF_HELPER_2(recpe_f32, f32, f32, env)
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 4e7077e..cac7668 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -2738,6 +2738,49 @@ static int disas_vfp_v8_insn(CPUARMState *env, DisasContext *s, uint32_t insn)
         }

         return 0;
+    } else if ((insn & 0x0fb00e10) == 0x0e800a00) {
+        /* vmaxnm/vminnm */
+        uint32_t vmin = (insn >> 6) & 1;
+        TCGv_ptr fpst;
+        fpst = get_fpstatus_ptr(0);
+        if (dp) {
+            TCGv_i64 ftmp1, ftmp2, ftmp3;
+
+            ftmp1 = tcg_temp_new_i64();
+            ftmp2 = tcg_temp_new_i64();
+            ftmp3 = tcg_temp_new_i64();
+
+            tcg_gen_ld_f64(ftmp1, cpu_env, vfp_reg_offset(dp, rn));
+            tcg_gen_ld_f64(ftmp2, cpu_env, vfp_reg_offset(dp, rm));
+            if (vmin)
+                gen_helper_vfp_minnmd(ftmp3, ftmp1, ftmp2, fpst);
+            else
+                gen_helper_vfp_maxnmd(ftmp3, ftmp1, ftmp2, fpst);
+            tcg_gen_st_f64(ftmp3, cpu_env, vfp_reg_offset(dp, rd));
+            tcg_temp_free_i64(ftmp1);
+            tcg_temp_free_i64(ftmp2);
+            tcg_temp_free_i64(ftmp3);
+        } else {
+            TCGv_i32 ftmp1, ftmp2, ftmp3;
+
+            ftmp1 = tcg_temp_new_i32();
+            ftmp2 = tcg_temp_new_i32();
+            ftmp3 = tcg_temp_new_i32();
+
+            tcg_gen_ld_f32(ftmp1, cpu_env, vfp_reg_offset(dp, rn));
+            tcg_gen_ld_f32(ftmp2, cpu_env, vfp_reg_offset(dp, rm));
+            if (vmin)
+                gen_helper_vfp_minnms(ftmp3, ftmp1, ftmp2, fpst);
+            else
+                gen_helper_vfp_maxnms(ftmp3, ftmp1, ftmp2, fpst);
+            tcg_gen_st_f32(ftmp3, cpu_env, vfp_reg_offset(dp, rd));
+            tcg_temp_free_i32(ftmp1);
+            tcg_temp_free_i32(ftmp2);
+            tcg_temp_free_i32(ftmp3);
+        }
+
+      tcg_temp_free_ptr(fpst);
+      return 0;
     }
     return 1;
 }
-- 
1.8.1.4