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

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-11-git-send-email-aleksandar.markovic@rt-rk.com>

3 files changed, 249 insertions, 186 deletions

diff --git a/target/mips/helper.h b/target/mips/helper.h
index f779404826..7bb13d5c3f 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -967,6 +967,15 @@ DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_xor_v, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_pckev_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_sll_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_sll_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_sll_w, void, env, i32, i32, i32)
@@ -1049,8 +1058,6 @@ DEF_HELPER_5(msa_dpsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dpsub_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_sld_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_splat_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_pckev_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_vshf_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_u_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 38ff1da0dd..24006323c7 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -3430,7 +3430,214 @@ void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws)
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Pack group helpers here */
+
+void helper_msa_pckev_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[8]  = pws->b[9];
+    pwd->b[10] = pws->b[13];
+    pwd->b[12] = pws->b[1];
+    pwd->b[14] = pws->b[5];
+    pwd->b[0]  = pwt->b[9];
+    pwd->b[2]  = pwt->b[13];
+    pwd->b[4]  = pwt->b[1];
+    pwd->b[6]  = pwt->b[5];
+    pwd->b[9]  = pws->b[11];
+    pwd->b[13] = pws->b[3];
+    pwd->b[1]  = pwt->b[11];
+    pwd->b[5]  = pwt->b[3];
+    pwd->b[11] = pws->b[15];
+    pwd->b[3]  = pwt->b[15];
+    pwd->b[15] = pws->b[7];
+    pwd->b[7]  = pwt->b[7];
+#else
+    pwd->b[15] = pws->b[14];
+    pwd->b[13] = pws->b[10];
+    pwd->b[11] = pws->b[6];
+    pwd->b[9]  = pws->b[2];
+    pwd->b[7]  = pwt->b[14];
+    pwd->b[5]  = pwt->b[10];
+    pwd->b[3]  = pwt->b[6];
+    pwd->b[1]  = pwt->b[2];
+    pwd->b[14] = pws->b[12];
+    pwd->b[10] = pws->b[4];
+    pwd->b[6]  = pwt->b[12];
+    pwd->b[2]  = pwt->b[4];
+    pwd->b[12] = pws->b[8];
+    pwd->b[4]  = pwt->b[8];
+    pwd->b[8]  = pws->b[0];
+    pwd->b[0]  = pwt->b[0];
+#endif
+}
+
+void helper_msa_pckev_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[4] = pws->h[5];
+    pwd->h[6] = pws->h[1];
+    pwd->h[0] = pwt->h[5];
+    pwd->h[2] = pwt->h[1];
+    pwd->h[5] = pws->h[7];
+    pwd->h[1] = pwt->h[7];
+    pwd->h[7] = pws->h[3];
+    pwd->h[3] = pwt->h[3];
+#else
+    pwd->h[7] = pws->h[6];
+    pwd->h[5] = pws->h[2];
+    pwd->h[3] = pwt->h[6];
+    pwd->h[1] = pwt->h[2];
+    pwd->h[6] = pws->h[4];
+    pwd->h[2] = pwt->h[4];
+    pwd->h[4] = pws->h[0];
+    pwd->h[0] = pwt->h[0];
+#endif
+}
+
+void helper_msa_pckev_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[2] = pws->w[3];
+    pwd->w[0] = pwt->w[3];
+    pwd->w[3] = pws->w[1];
+    pwd->w[1] = pwt->w[1];
+#else
+    pwd->w[3] = pws->w[2];
+    pwd->w[1] = pwt->w[2];
+    pwd->w[2] = pws->w[0];
+    pwd->w[0] = pwt->w[0];
+#endif
+}
+
+void helper_msa_pckev_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[1] = pws->d[0];
+    pwd->d[0] = pwt->d[0];
+}
+
+
+void helper_msa_pckod_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[7]  = pwt->b[6];
+    pwd->b[5]  = pwt->b[2];
+    pwd->b[3]  = pwt->b[14];
+    pwd->b[1]  = pwt->b[10];
+    pwd->b[15] = pws->b[6];
+    pwd->b[13] = pws->b[2];
+    pwd->b[11] = pws->b[14];
+    pwd->b[9]  = pws->b[10];
+    pwd->b[6]  = pwt->b[4];
+    pwd->b[2]  = pwt->b[12];
+    pwd->b[14] = pws->b[4];
+    pwd->b[10] = pws->b[12];
+    pwd->b[4]  = pwt->b[0];
+    pwd->b[12] = pws->b[0];
+    pwd->b[0]  = pwt->b[8];
+    pwd->b[8]  = pws->b[8];
+#else
+    pwd->b[0]  = pwt->b[1];
+    pwd->b[2]  = pwt->b[5];
+    pwd->b[4]  = pwt->b[9];
+    pwd->b[6]  = pwt->b[13];
+    pwd->b[8]  = pws->b[1];
+    pwd->b[10] = pws->b[5];
+    pwd->b[12] = pws->b[9];
+    pwd->b[14] = pws->b[13];
+    pwd->b[1]  = pwt->b[3];
+    pwd->b[5]  = pwt->b[11];
+    pwd->b[9]  = pws->b[3];
+    pwd->b[13] = pws->b[11];
+    pwd->b[3]  = pwt->b[7];
+    pwd->b[11] = pws->b[7];
+    pwd->b[7]  = pwt->b[15];
+    pwd->b[15] = pws->b[15];
+#endif
+
+}
+
+void helper_msa_pckod_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[3] = pwt->h[2];
+    pwd->h[1] = pwt->h[6];
+    pwd->h[7] = pws->h[2];
+    pwd->h[5] = pws->h[6];
+    pwd->h[2] = pwt->h[0];
+    pwd->h[6] = pws->h[0];
+    pwd->h[0] = pwt->h[4];
+    pwd->h[4] = pws->h[4];
+#else
+    pwd->h[0] = pwt->h[1];
+    pwd->h[2] = pwt->h[5];
+    pwd->h[4] = pws->h[1];
+    pwd->h[6] = pws->h[5];
+    pwd->h[1] = pwt->h[3];
+    pwd->h[5] = pws->h[3];
+    pwd->h[3] = pwt->h[7];
+    pwd->h[7] = pws->h[7];
+#endif
+}
+
+void helper_msa_pckod_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);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[1] = pwt->w[0];
+    pwd->w[3] = pws->w[0];
+    pwd->w[0] = pwt->w[2];
+    pwd->w[2] = pws->w[2];
+#else
+    pwd->w[0] = pwt->w[1];
+    pwd->w[2] = pws->w[1];
+    pwd->w[1] = pwt->w[3];
+    pwd->w[3] = pws->w[3];
+#endif
+}
+
+void helper_msa_pckod_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] = pwt->d[1];
+    pwd->d[1] = pws->d[1];
+}
 
 
 /*
@@ -4675,183 +4882,6 @@ MSA_FN_DF(vshf_df)
 #undef MSA_FN_DF
 
 
-void helper_msa_pckev_df(CPUMIPSState *env, uint32_t df, 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);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[8]  = pws->b[9];
-        pwd->b[10] = pws->b[13];
-        pwd->b[12] = pws->b[1];
-        pwd->b[14] = pws->b[5];
-        pwd->b[0]  = pwt->b[9];
-        pwd->b[2]  = pwt->b[13];
-        pwd->b[4]  = pwt->b[1];
-        pwd->b[6]  = pwt->b[5];
-        pwd->b[9]  = pws->b[11];
-        pwd->b[13] = pws->b[3];
-        pwd->b[1]  = pwt->b[11];
-        pwd->b[5]  = pwt->b[3];
-        pwd->b[11] = pws->b[15];
-        pwd->b[3]  = pwt->b[15];
-        pwd->b[15] = pws->b[7];
-        pwd->b[7]  = pwt->b[7];
-#else
-        pwd->b[15] = pws->b[14];
-        pwd->b[13] = pws->b[10];
-        pwd->b[11] = pws->b[6];
-        pwd->b[9]  = pws->b[2];
-        pwd->b[7]  = pwt->b[14];
-        pwd->b[5]  = pwt->b[10];
-        pwd->b[3]  = pwt->b[6];
-        pwd->b[1]  = pwt->b[2];
-        pwd->b[14] = pws->b[12];
-        pwd->b[10] = pws->b[4];
-        pwd->b[6]  = pwt->b[12];
-        pwd->b[2]  = pwt->b[4];
-        pwd->b[12] = pws->b[8];
-        pwd->b[4]  = pwt->b[8];
-        pwd->b[8]  = pws->b[0];
-        pwd->b[0]  = pwt->b[0];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[4] = pws->h[5];
-        pwd->h[6] = pws->h[1];
-        pwd->h[0] = pwt->h[5];
-        pwd->h[2] = pwt->h[1];
-        pwd->h[5] = pws->h[7];
-        pwd->h[1] = pwt->h[7];
-        pwd->h[7] = pws->h[3];
-        pwd->h[3] = pwt->h[3];
-#else
-        pwd->h[7] = pws->h[6];
-        pwd->h[5] = pws->h[2];
-        pwd->h[3] = pwt->h[6];
-        pwd->h[1] = pwt->h[2];
-        pwd->h[6] = pws->h[4];
-        pwd->h[2] = pwt->h[4];
-        pwd->h[4] = pws->h[0];
-        pwd->h[0] = pwt->h[0];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[2] = pws->w[3];
-        pwd->w[0] = pwt->w[3];
-        pwd->w[3] = pws->w[1];
-        pwd->w[1] = pwt->w[1];
-#else
-        pwd->w[3] = pws->w[2];
-        pwd->w[1] = pwt->w[2];
-        pwd->w[2] = pws->w[0];
-        pwd->w[0] = pwt->w[0];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[1] = pws->d[0];
-        pwd->d[0] = pwt->d[0];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-void helper_msa_pckod_df(CPUMIPSState *env, uint32_t df, 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);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[7]  = pwt->b[6];
-        pwd->b[5]  = pwt->b[2];
-        pwd->b[3]  = pwt->b[14];
-        pwd->b[1]  = pwt->b[10];
-        pwd->b[15] = pws->b[6];
-        pwd->b[13] = pws->b[2];
-        pwd->b[11] = pws->b[14];
-        pwd->b[9]  = pws->b[10];
-        pwd->b[6]  = pwt->b[4];
-        pwd->b[2]  = pwt->b[12];
-        pwd->b[14] = pws->b[4];
-        pwd->b[10] = pws->b[12];
-        pwd->b[4]  = pwt->b[0];
-        pwd->b[12] = pws->b[0];
-        pwd->b[0]  = pwt->b[8];
-        pwd->b[8]  = pws->b[8];
-#else
-        pwd->b[0]  = pwt->b[1];
-        pwd->b[2]  = pwt->b[5];
-        pwd->b[4]  = pwt->b[9];
-        pwd->b[6]  = pwt->b[13];
-        pwd->b[8]  = pws->b[1];
-        pwd->b[10] = pws->b[5];
-        pwd->b[12] = pws->b[9];
-        pwd->b[14] = pws->b[13];
-        pwd->b[1]  = pwt->b[3];
-        pwd->b[5]  = pwt->b[11];
-        pwd->b[9]  = pws->b[3];
-        pwd->b[13] = pws->b[11];
-        pwd->b[3]  = pwt->b[7];
-        pwd->b[11] = pws->b[7];
-        pwd->b[7]  = pwt->b[15];
-        pwd->b[15] = pws->b[15];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[3] = pwt->h[2];
-        pwd->h[1] = pwt->h[6];
-        pwd->h[7] = pws->h[2];
-        pwd->h[5] = pws->h[6];
-        pwd->h[2] = pwt->h[0];
-        pwd->h[6] = pws->h[0];
-        pwd->h[0] = pwt->h[4];
-        pwd->h[4] = pws->h[4];
-#else
-        pwd->h[0] = pwt->h[1];
-        pwd->h[2] = pwt->h[5];
-        pwd->h[4] = pws->h[1];
-        pwd->h[6] = pws->h[5];
-        pwd->h[1] = pwt->h[3];
-        pwd->h[5] = pws->h[3];
-        pwd->h[3] = pwt->h[7];
-        pwd->h[7] = pws->h[7];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[1] = pwt->w[0];
-        pwd->w[3] = pws->w[0];
-        pwd->w[0] = pwt->w[2];
-        pwd->w[2] = pws->w[2];
-#else
-        pwd->w[0] = pwt->w[1];
-        pwd->w[2] = pws->w[1];
-        pwd->w[1] = pwt->w[3];
-        pwd->w[3] = pws->w[3];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[0] = pwt->d[1];
-        pwd->d[1] = pws->d[1];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-
 void helper_msa_sldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
                         uint32_t ws, uint32_t n)
 {
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 7cdf68d21d..a57e0daeff 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28914,6 +28914,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_PCKEV_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_pckev_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_pckev_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_pckev_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_pckev_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_PCKOD_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_pckod_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_pckod_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_pckod_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_pckod_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_SLL_df:
         switch (df) {
         case DF_BYTE:
@@ -29024,15 +29056,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_MSUBV_df:
         gen_helper_msa_msubv_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_PCKEV_df:
-        gen_helper_msa_pckev_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUU_S_df:
         gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_PCKOD_df:
-        gen_helper_msa_pckod_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ASUB_S_df:
         gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt);
         break;