target/mips: msa: Split helpers for HSUB_<S|U>.<H|W|D>

Achieves clearer code and slightly better performance.

Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Message-Id: <1571826227-10583-12-git-send-email-aleksandar.markovic@rt-rk.com>

1 files changed, 95 insertions, 13 deletions

diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 24006323c7..ae9e8e04f4 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -2888,7 +2888,101 @@ void helper_msa_mod_u_d(CPUMIPSState *env,
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Int Subtract group helpers here */
+/* TODO: insert the rest of Int Subtract group helpers here */
+
+
+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);
+}
+
+void helper_msa_hsub_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_hsub_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hsub_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hsub_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hsub_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hsub_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hsub_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hsub_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hsub_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hsub_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_hsub_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hsub_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hsub_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hsub_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hsub_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_hsub_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hsub_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_hsub_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return UNSIGNED_ODD(arg1, df) - UNSIGNED_EVEN(arg2, df);
+}
+
+void helper_msa_hsub_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_hsub_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hsub_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hsub_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hsub_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hsub_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hsub_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hsub_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hsub_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hsub_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_hsub_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hsub_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hsub_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hsub_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hsub_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_hsub_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hsub_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
 
 
 /*
@@ -4450,16 +4544,6 @@ static inline void msa_sld_df(uint32_t df, wr_t *pwd,
     }
 }
 
-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);
-}
-
-static inline int64_t msa_hsub_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_mul_q_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     int64_t q_min = DF_MIN_INT(df);
@@ -4545,8 +4629,6 @@ MSA_BINOP_DF(asub_u)
 MSA_BINOP_DF(mulv)
 MSA_BINOP_DF(dotp_s)
 MSA_BINOP_DF(dotp_u)
-MSA_BINOP_DF(hsub_s)
-MSA_BINOP_DF(hsub_u)
 
 MSA_BINOP_DF(mul_q)
 MSA_BINOP_DF(mulr_q)