@@ -955,6 +955,11 @@ 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_msubv_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_msubv_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_msubv_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_msubv_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)
@@ -1074,7 +1079,6 @@ 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_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)
DEF_HELPER_5(msa_dpadd_s_df, void, env, i32, i32, i32, i32)
@@ -2955,6 +2955,78 @@ void helper_msa_maddv_d(CPUMIPSState *env,
pwd->d[1] = msa_maddv_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]);
}
+static inline int64_t msa_msubv_df(uint32_t df, int64_t dest, int64_t arg1,
+ int64_t arg2)
+{
+ return dest - arg1 * arg2;
+}
+
+void helper_msa_msubv_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_msubv_df(DF_BYTE, pwt->b[0], pws->b[0], pwt->b[0]);
+ pwd->b[1] = msa_msubv_df(DF_BYTE, pwt->b[1], pws->b[1], pwt->b[1]);
+ pwd->b[2] = msa_msubv_df(DF_BYTE, pwt->b[2], pws->b[2], pwt->b[2]);
+ pwd->b[3] = msa_msubv_df(DF_BYTE, pwt->b[3], pws->b[3], pwt->b[3]);
+ pwd->b[4] = msa_msubv_df(DF_BYTE, pwt->b[4], pws->b[4], pwt->b[4]);
+ pwd->b[5] = msa_msubv_df(DF_BYTE, pwt->b[5], pws->b[5], pwt->b[5]);
+ pwd->b[6] = msa_msubv_df(DF_BYTE, pwt->b[6], pws->b[6], pwt->b[6]);
+ pwd->b[7] = msa_msubv_df(DF_BYTE, pwt->b[7], pws->b[7], pwt->b[7]);
+ pwd->b[8] = msa_msubv_df(DF_BYTE, pwt->b[8], pws->b[8], pwt->b[8]);
+ pwd->b[9] = msa_msubv_df(DF_BYTE, pwt->b[9], pws->b[9], pwt->b[9]);
+ pwd->b[10] = msa_msubv_df(DF_BYTE, pwt->b[10], pws->b[10], pwt->b[10]);
+ pwd->b[11] = msa_msubv_df(DF_BYTE, pwt->b[11], pws->b[11], pwt->b[11]);
+ pwd->b[12] = msa_msubv_df(DF_BYTE, pwt->b[12], pws->b[12], pwt->b[12]);
+ pwd->b[13] = msa_msubv_df(DF_BYTE, pwt->b[13], pws->b[13], pwt->b[13]);
+ pwd->b[14] = msa_msubv_df(DF_BYTE, pwt->b[14], pws->b[14], pwt->b[14]);
+ pwd->b[15] = msa_msubv_df(DF_BYTE, pwt->b[15], pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_msubv_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_msubv_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]);
+ pwd->h[1] = msa_msubv_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]);
+ pwd->h[2] = msa_msubv_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]);
+ pwd->h[3] = msa_msubv_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]);
+ pwd->h[4] = msa_msubv_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]);
+ pwd->h[5] = msa_msubv_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]);
+ pwd->h[6] = msa_msubv_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]);
+ pwd->h[7] = msa_msubv_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]);
+}
+
+void helper_msa_msubv_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_msubv_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]);
+ pwd->w[1] = msa_msubv_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]);
+ pwd->w[2] = msa_msubv_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]);
+ pwd->w[3] = msa_msubv_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]);
+}
+
+void helper_msa_msubv_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_msubv_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]);
+ pwd->d[1] = msa_msubv_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]);
+}
+
/*
* Int Subtract
@@ -4886,12 +4958,6 @@ 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_msubv_df(uint32_t df, int64_t dest, int64_t arg1,
- int64_t arg2)
-{
- return dest - arg1 * arg2;
-}
-
static inline int64_t msa_dpadd_s_df(uint32_t df, int64_t dest, int64_t arg1,
int64_t arg2)
{
@@ -5066,7 +5132,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd, \
} \
}
-MSA_TEROP_DF(msubv)
MSA_TEROP_DF(dpadd_s)
MSA_TEROP_DF(dpadd_u)
MSA_TEROP_DF(dpsub_s)
@@ -29073,6 +29073,22 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
break;
}
break;
+ case OPC_MSUBV_df:
+ switch (df) {
+ case DF_BYTE:
+ gen_helper_msa_msubv_b(cpu_env, twd, tws, twt);
+ break;
+ case DF_HALF:
+ gen_helper_msa_msubv_h(cpu_env, twd, tws, twt);
+ break;
+ case DF_WORD:
+ gen_helper_msa_msubv_w(cpu_env, twd, tws, twt);
+ break;
+ case DF_DOUBLE:
+ gen_helper_msa_msubv_d(cpu_env, twd, tws, twt);
+ break;
+ }
+ break;
case OPC_ASUB_S_df:
switch (df) {
case DF_BYTE:
@@ -29305,9 +29321,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
case OPC_SUBSUS_U_df:
gen_helper_msa_subsus_u_df(cpu_env, tdf, twd, tws, twt);
break;
- case OPC_MSUBV_df:
- gen_helper_msa_msubv_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;
Achieves clearer code and slightly better performance. Signed-off-by: Aleksandar Markovic <aleksandar.qemu.devel@gmail.com> --- target/mips/helper.h | 6 ++- target/mips/msa_helper.c | 79 ++++++++++++++++++++++++++++++++++++---- target/mips/translate.c | 19 ++++++++-- 3 files changed, 93 insertions(+), 11 deletions(-)