target/mips: msa: Split helpers for HADD_<S|U>.<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: <1571826227-10583-9-git-send-email-aleksandar.markovic@rt-rk.com>

3 files changed, 141 insertions, 32 deletions

diff --git a/target/mips/helper.h b/target/mips/helper.h
index ce01e972ba..f25ba90fc2 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -847,6 +847,14 @@ DEF_HELPER_4(msa_addv_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_addv_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_addv_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_hadd_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_s_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_hadd_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_u_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_ave_s_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_w, void, env, i32, i32, i32)
@@ -1024,8 +1032,6 @@ 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_srar_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srlr_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_hadd_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_hadd_u_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 c31f46cabf..f5d3737a77 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -1184,6 +1184,113 @@ void helper_msa_addv_d(CPUMIPSState *env,
 }
 
 
+#define SIGNED_EVEN(a, df) \
+        ((((int64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
+
+#define UNSIGNED_EVEN(a, df) \
+        ((((uint64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
+
+#define SIGNED_ODD(a, df) \
+        ((((int64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
+
+#define UNSIGNED_ODD(a, df) \
+        ((((uint64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
+
+
+static inline int64_t msa_hadd_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return SIGNED_ODD(arg1, df) + SIGNED_EVEN(arg2, df);
+}
+
+void helper_msa_hadd_s_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_hadd_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hadd_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hadd_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hadd_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hadd_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hadd_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hadd_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hadd_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hadd_s_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_hadd_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hadd_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hadd_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hadd_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hadd_s_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_hadd_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hadd_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_hadd_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return UNSIGNED_ODD(arg1, df) + UNSIGNED_EVEN(arg2, df);
+}
+
+void helper_msa_hadd_u_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_hadd_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hadd_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hadd_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hadd_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hadd_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hadd_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hadd_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hadd_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hadd_u_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_hadd_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hadd_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hadd_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hadd_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hadd_u_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_hadd_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hadd_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
 /*
  * Int Average
  * -----------
@@ -3727,18 +3834,6 @@ static inline int64_t msa_mulv_df(uint32_t df, int64_t arg1, int64_t arg2)
     return arg1 * arg2;
 }
 
-#define SIGNED_EVEN(a, df) \
-        ((((int64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
-
-#define UNSIGNED_EVEN(a, df) \
-        ((((uint64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
-
-#define SIGNED_ODD(a, df) \
-        ((((int64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
-
-#define UNSIGNED_ODD(a, df) \
-        ((((uint64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
-
 #define SIGNED_EXTRACT(e, o, a, df)     \
     do {                                \
         e = SIGNED_EVEN(a, df);         \
@@ -3815,16 +3910,6 @@ static inline void msa_sld_df(uint32_t df, wr_t *pwd,
     }
 }
 
-static inline int64_t msa_hadd_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return SIGNED_ODD(arg1, df) + SIGNED_EVEN(arg2, df);
-}
-
-static inline int64_t msa_hadd_u_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return UNSIGNED_ODD(arg1, df) + UNSIGNED_EVEN(arg2, df);
-}
-
 static inline int64_t msa_hsub_s_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     return SIGNED_ODD(arg1, df) - SIGNED_EVEN(arg2, df);
@@ -3925,8 +4010,6 @@ MSA_BINOP_DF(dotp_s)
 MSA_BINOP_DF(dotp_u)
 MSA_BINOP_DF(srar)
 MSA_BINOP_DF(srlr)
-MSA_BINOP_DF(hadd_s)
-MSA_BINOP_DF(hadd_u)
 MSA_BINOP_DF(hsub_s)
 MSA_BINOP_DF(hsub_u)
 
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 14f9891bca..9e8e973d91 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28990,6 +28990,32 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         switch (MASK_MSA_3R(ctx->opcode)) {
+        case OPC_HADD_S_df:
+            switch (df) {
+            case DF_HALF:
+                gen_helper_msa_hadd_s_h(cpu_env, twd, tws, twt);
+                break;
+            case DF_WORD:
+                gen_helper_msa_hadd_s_w(cpu_env, twd, tws, twt);
+                break;
+            case DF_DOUBLE:
+                gen_helper_msa_hadd_s_d(cpu_env, twd, tws, twt);
+                break;
+            }
+            break;
+        case OPC_HADD_U_df:
+            switch (df) {
+            case DF_HALF:
+                gen_helper_msa_hadd_u_h(cpu_env, twd, tws, twt);
+                break;
+            case DF_WORD:
+                gen_helper_msa_hadd_u_w(cpu_env, twd, tws, twt);
+                break;
+            case DF_DOUBLE:
+                gen_helper_msa_hadd_u_d(cpu_env, twd, tws, twt);
+                break;
+            }
+            break;
         case OPC_DOTP_S_df:
             gen_helper_msa_dotp_s_df(cpu_env, tdf, twd, tws, twt);
             break;
@@ -29005,15 +29031,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
         case OPC_DPSUB_S_df:
             gen_helper_msa_dpsub_s_df(cpu_env, tdf, twd, tws, twt);
             break;
-        case OPC_HADD_S_df:
-            gen_helper_msa_hadd_s_df(cpu_env, tdf, twd, tws, twt);
-            break;
         case OPC_DPSUB_U_df:
             gen_helper_msa_dpsub_u_df(cpu_env, tdf, twd, tws, twt);
             break;
-        case OPC_HADD_U_df:
-            gen_helper_msa_hadd_u_df(cpu_env, tdf, twd, tws, twt);
-            break;
         case OPC_HSUB_S_df:
             gen_helper_msa_hsub_s_df(cpu_env, tdf, twd, tws, twt);
             break;