> From: Aleksandar Markovic <amarko...@wavecomp.com>
>
> Achieves clearer code and slightly better performance.
>
> Signed-off-by: Aleksandar Markovic <amarko...@wavecomp.com>
> ---
> target/mips/helper.h | 10 ++++-
> target/mips/msa_helper.c | 108
+++++++++++++++++++++++++++++++++++++++++------
> target/mips/translate.c | 32 +++++++++++---
> 3 files changed, 129 insertions(+), 21 deletions(-)
>
> diff --git a/target/mips/helper.h b/target/mips/helper.h
> index 7bb13d5..d7c4bbf 100644
> --- a/target/mips/helper.h
> +++ b/target/mips/helper.h
> @@ -945,6 +945,14 @@ DEF_HELPER_4(msa_mod_s_h, void, env, i32, i32, i32)
> DEF_HELPER_4(msa_mod_s_w, void, env, i32, i32, i32)
> DEF_HELPER_4(msa_mod_s_d, void, env, i32, i32, i32)
>
> +DEF_HELPER_4(msa_hsub_s_h, void, env, i32, i32, i32)
> +DEF_HELPER_4(msa_hsub_s_w, void, env, i32, i32, i32)
> +DEF_HELPER_4(msa_hsub_s_d, void, env, i32, i32, i32)
> +
> +DEF_HELPER_4(msa_hsub_u_h, void, env, i32, i32, i32)
> +DEF_HELPER_4(msa_hsub_u_w, void, env, i32, i32, i32)
> +DEF_HELPER_4(msa_hsub_u_d, void, env, i32, i32, i32)
> +
> DEF_HELPER_4(msa_ilvev_b, void, env, i32, i32, i32)
> DEF_HELPER_4(msa_ilvev_h, void, env, i32, i32, i32)
> DEF_HELPER_4(msa_ilvev_w, void, env, i32, i32, i32)
> @@ -1059,8 +1067,6 @@ 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_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)
>
> DEF_HELPER_5(msa_sldi_df, void, env, i32, i32, i32, i32)
> DEF_HELPER_5(msa_splati_df, void, env, i32, i32, i32, i32)
> diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
> index 2400632..ae9e8e0 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)
> diff --git a/target/mips/translate.c b/target/mips/translate.c
> index a57e0da..4c68c5b 100644
> --- a/target/mips/translate.c
> +++ b/target/mips/translate.c
> @@ -29107,6 +29107,32 @@ static void gen_msa_3r(CPUMIPSState *env,
DisasContext *ctx)
> break;
> }
> break;
> + case OPC_HSUB_S_df:
> + switch (df) {
> + case DF_HALF:
> + gen_helper_msa_hsub_s_h(cpu_env, twd, tws, twt);
> + break;
> + case DF_WORD:
> + gen_helper_msa_hsub_s_w(cpu_env, twd, tws, twt);
> + break;
> + case DF_DOUBLE:
> + gen_helper_msa_hsub_s_d(cpu_env, twd, tws, twt);
> + break;
> + }
> + break;
> + case OPC_HSUB_U_df:
> + switch (df) {
> + case DF_HALF:
> + gen_helper_msa_hsub_u_h(cpu_env, twd, tws, twt);
> + break;
> + case DF_WORD:
> + gen_helper_msa_hsub_u_w(cpu_env, twd, tws, twt);
> + break;
> + case DF_DOUBLE:
> + gen_helper_msa_hsub_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;
> @@ -29125,12 +29151,6 @@ static void gen_msa_3r(CPUMIPSState *env,
DisasContext *ctx)
> case OPC_DPSUB_U_df:
> gen_helper_msa_dpsub_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;
> - case OPC_HSUB_U_df:
> - gen_helper_msa_hsub_u_df(cpu_env, tdf, twd, tws, twt);
> - break;
> }
> break;
> default:
Reviewed-by: Aleksandar Rikalo <aleksandar.rik...@rt-rk.com>