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

Achieves clearer code and slightly better performance.

Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Reviewed-by: Aleksandar Rikalo <arikalo@wavecomp.com>
Message-Id: <1569415572-19635-12-git-send-email-aleksandar.markovic@rt-rk.com>

3 files changed, 267 insertions, 35 deletions

diff --git a/target/mips/helper.h b/target/mips/helper.h
index 27544a1..1411e0e 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -807,6 +807,21 @@ DEF_HELPER_4(msa_bmnz_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_bmz_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_bsel_v, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_bclr_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bclr_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bclr_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bclr_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_bneg_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bneg_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bneg_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bneg_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_bset_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bset_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bset_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_bset_d, void, env, i32, i32, i32)
+
 
 DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ori_b, void, env, i32, i32, i32)
@@ -846,9 +861,6 @@ DEF_HELPER_5(msa_srlri_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_sll_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_sra_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srl_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_bclr_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_bset_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_bneg_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsr_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_addv_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 82c8871..5177e41 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -523,7 +523,210 @@ void helper_msa_bsel_v(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t wt)
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Bit Set group helpers here */
+static inline int64_t msa_bclr_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 & (~(1LL << b_arg2)), df);
+}
+
+void helper_msa_bclr_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_bclr_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_bclr_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_bclr_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_bclr_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_bclr_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_bclr_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_bclr_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_bclr_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_bclr_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_bclr_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_bclr_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_bclr_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_bclr_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_bclr_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_bclr_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_bclr_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_bclr_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_bclr_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_bclr_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_bclr_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_bclr_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_bclr_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_bclr_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_bclr_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_bclr_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_bclr_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_bclr_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_bclr_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_bclr_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_bclr_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_bclr_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_bclr_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_bclr_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+static inline int64_t msa_bneg_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 ^ (1LL << b_arg2), df);
+}
+
+void helper_msa_bneg_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_bneg_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_bneg_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_bneg_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_bneg_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_bneg_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_bneg_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_bneg_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_bneg_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_bneg_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_bneg_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_bneg_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_bneg_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_bneg_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_bneg_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_bneg_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_bneg_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_bneg_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_bneg_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_bneg_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_bneg_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_bneg_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_bneg_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_bneg_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_bneg_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_bneg_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_bneg_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_bneg_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_bneg_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_bneg_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_bneg_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_bneg_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_bneg_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_bneg_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+static inline int64_t msa_bset_df(uint32_t df, int64_t arg1,
+        int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 | (1LL << b_arg2), df);
+}
+
+void helper_msa_bset_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_bset_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_bset_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_bset_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_bset_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_bset_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_bset_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_bset_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_bset_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_bset_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_bset_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_bset_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_bset_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_bset_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_bset_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_bset_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_bset_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_bset_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_bset_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_bset_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_bset_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_bset_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_bset_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_bset_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_bset_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_bset_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_bset_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_bset_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_bset_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_bset_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_bset_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_bset_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_bset_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_bset_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
 
 
 /*
@@ -1220,25 +1423,6 @@ static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2)
     return u_arg1 >> b_arg2;
 }
 
-static inline int64_t msa_bclr_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return UNSIGNED(arg1 & (~(1LL << b_arg2)), df);
-}
-
-static inline int64_t msa_bset_df(uint32_t df, int64_t arg1,
-        int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return UNSIGNED(arg1 | (1LL << b_arg2), df);
-}
-
-static inline int64_t msa_bneg_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return UNSIGNED(arg1 ^ (1LL << b_arg2), df);
-}
-
 static inline int64_t msa_sat_s_df(uint32_t df, int64_t arg, uint32_t m)
 {
     return arg < M_MIN_INT(m + 1) ? M_MIN_INT(m + 1) :
@@ -1734,9 +1918,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df,         \
 MSA_BINOP_DF(sll)
 MSA_BINOP_DF(sra)
 MSA_BINOP_DF(srl)
-MSA_BINOP_DF(bclr)
-MSA_BINOP_DF(bset)
-MSA_BINOP_DF(bneg)
 MSA_BINOP_DF(addv)
 MSA_BINOP_DF(subv)
 MSA_BINOP_DF(max_s)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 6080c72..1a87f79 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28418,6 +28418,54 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_BCLR_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_bclr_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_bclr_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_bclr_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_bclr_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_BNEG_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_bneg_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_bneg_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_bneg_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_bneg_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_BSET_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_bset_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_bset_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_bset_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_bset_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_SLL_df:
         gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28487,9 +28535,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SRLR_df:
         gen_helper_msa_srlr_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_BCLR_df:
-        gen_helper_msa_bclr_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_MAX_U_df:
         gen_helper_msa_max_u_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28505,9 +28550,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_PCKOD_df:
         gen_helper_msa_pckod_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_BSET_df:
-        gen_helper_msa_bset_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_MIN_S_df:
         gen_helper_msa_min_s_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28526,9 +28568,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_ILVL_df:
         gen_helper_msa_ilvl_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_BNEG_df:
-        gen_helper_msa_bneg_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_MIN_U_df:
         gen_helper_msa_min_u_df(cpu_env, tdf, twd, tws, twt);
         break;