target/mips: msa: Split helpers for MADDV.<B|H|W|D>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@syrmia.com>
Signed-off-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com>
Message-Id: <20200613152133.8964-2-aleksandar.qemu.devel@gmail.com>

3 files changed, 92 insertions, 12 deletions

diff --git a/target/mips/helper.h b/target/mips/helper.h
index 84fdd9fd27..e479a22559 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -950,6 +950,11 @@ DEF_HELPER_4(msa_mod_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_s_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_s_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_maddv_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_maddv_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_maddv_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_maddv_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_asub_s_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_asub_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_asub_s_w, void, env, i32, i32, i32)
@@ -1069,7 +1074,6 @@ DEF_HELPER_5(msa_subs_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subsus_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subsuu_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_mulv_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_maddv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_msubv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dotp_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dotp_u_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index c3b271934a..3b75bdc6a4 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -2883,7 +2883,77 @@ void helper_msa_mod_u_d(CPUMIPSState *env,
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Int Multiply group helpers here */
+static inline int64_t msa_maddv_df(uint32_t df, int64_t dest, int64_t arg1,
+                                   int64_t arg2)
+{
+    return dest + arg1 * arg2;
+}
+
+void helper_msa_maddv_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_maddv_df(DF_BYTE, pwt->b[0],  pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_maddv_df(DF_BYTE, pwt->b[1],  pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_maddv_df(DF_BYTE, pwt->b[2],  pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_maddv_df(DF_BYTE, pwt->b[3],  pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_maddv_df(DF_BYTE, pwt->b[4],  pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_maddv_df(DF_BYTE, pwt->b[5],  pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_maddv_df(DF_BYTE, pwt->b[6],  pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_maddv_df(DF_BYTE, pwt->b[7],  pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_maddv_df(DF_BYTE, pwt->b[8],  pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_maddv_df(DF_BYTE, pwt->b[9],  pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_maddv_df(DF_BYTE, pwt->b[10], pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_maddv_df(DF_BYTE, pwt->b[11], pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_maddv_df(DF_BYTE, pwt->b[12], pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_maddv_df(DF_BYTE, pwt->b[13], pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_maddv_df(DF_BYTE, pwt->b[14], pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_maddv_df(DF_BYTE, pwt->b[15], pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_maddv_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_maddv_df(DF_HALF, pwd->h[0],  pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_maddv_df(DF_HALF, pwd->h[1],  pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_maddv_df(DF_HALF, pwd->h[2],  pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_maddv_df(DF_HALF, pwd->h[3],  pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_maddv_df(DF_HALF, pwd->h[4],  pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_maddv_df(DF_HALF, pwd->h[5],  pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_maddv_df(DF_HALF, pwd->h[6],  pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_maddv_df(DF_HALF, pwd->h[7],  pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_maddv_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_maddv_df(DF_WORD, pwd->w[0],  pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_maddv_df(DF_WORD, pwd->w[1],  pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_maddv_df(DF_WORD, pwd->w[2],  pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_maddv_df(DF_WORD, pwd->w[3],  pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_maddv_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_maddv_df(DF_DOUBLE, pwd->d[0],  pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_maddv_df(DF_DOUBLE, pwd->d[1],  pws->d[1],  pwt->d[1]);
+}
 
 
 /*
@@ -4816,12 +4886,6 @@ void helper_msa_sld_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
     msa_sld_df(df, pwd, pws, env->active_tc.gpr[rt]);
 }
 
-static inline int64_t msa_maddv_df(uint32_t df, int64_t dest, int64_t arg1,
-                                   int64_t arg2)
-{
-    return dest + arg1 * arg2;
-}
-
 static inline int64_t msa_msubv_df(uint32_t df, int64_t dest, int64_t arg1,
                                    int64_t arg2)
 {
@@ -5002,7 +5066,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd,  \
     }                                                                         \
 }
 
-MSA_TEROP_DF(maddv)
 MSA_TEROP_DF(msubv)
 MSA_TEROP_DF(dpadd_s)
 MSA_TEROP_DF(dpadd_u)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index e49f32f6ae..4975e57e35 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -29058,6 +29058,22 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_MADDV_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_maddv_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_maddv_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_maddv_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_maddv_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_ASUB_S_df:
         switch (df) {
         case DF_BYTE:
@@ -29284,9 +29300,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SUBS_U_df:
         gen_helper_msa_subs_u_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MADDV_df:
-        gen_helper_msa_maddv_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SPLAT_df:
         gen_helper_msa_splat_df(cpu_env, tdf, twd, tws, twt);
         break;