From e8e01ef026c86bc8cbef22dd3b8e7c183949e5ba Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:37 +0200 Subject: target/mips: msa: Split helpers for _A. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-5-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index d615c83c54..cef4de6506 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -877,6 +877,15 @@ DEF_HELPER_4(msa_div_u_h, void, env, i32, i32, i32) DEF_HELPER_4(msa_div_u_w, void, env, i32, i32, i32) DEF_HELPER_4(msa_div_u_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_a_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_a_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_a_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_a_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_a_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_a_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_a_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_a_d, void, env, i32, i32, i32) + DEF_HELPER_4(msa_mod_u_b, void, env, i32, i32, i32) DEF_HELPER_4(msa_mod_u_h, void, env, i32, i32, i32) DEF_HELPER_4(msa_mod_u_w, void, env, i32, i32, i32) @@ -940,8 +949,6 @@ DEF_HELPER_5(msa_max_s_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_max_u_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_min_s_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_min_u_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_max_a_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_min_a_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32) -- cgit 1.4.1 From 2db26305a6a50832e2239c473ed1ced9c0eab706 Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:38 +0200 Subject: target/mips: msa: Split helpers for _. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-6-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 20 ++- target/mips/msa_helper.c | 320 ++++++++++++++++++++++++++++++++++++++++++----- target/mips/translate.c | 76 +++++++++-- 3 files changed, 372 insertions(+), 44 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index cef4de6506..6419bb8395 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -881,10 +881,26 @@ DEF_HELPER_4(msa_max_a_b, void, env, i32, i32, i32) DEF_HELPER_4(msa_max_a_h, void, env, i32, i32, i32) DEF_HELPER_4(msa_max_a_w, void, env, i32, i32, i32) DEF_HELPER_4(msa_max_a_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_s_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_s_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_max_u_d, void, env, i32, i32, i32) DEF_HELPER_4(msa_min_a_b, void, env, i32, i32, i32) DEF_HELPER_4(msa_min_a_h, void, env, i32, i32, i32) DEF_HELPER_4(msa_min_a_w, void, env, i32, i32, i32) DEF_HELPER_4(msa_min_a_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_s_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_s_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_min_u_d, void, env, i32, i32, i32) DEF_HELPER_4(msa_mod_u_b, void, env, i32, i32, i32) DEF_HELPER_4(msa_mod_u_h, void, env, i32, i32, i32) @@ -945,10 +961,6 @@ 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) DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_max_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_max_u_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_min_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_min_u_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32) diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index 3eb0ab1d6e..65df15df6e 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -1810,6 +1810,152 @@ void helper_msa_max_a_d(CPUMIPSState *env, } +static inline int64_t msa_max_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + return arg1 > arg2 ? arg1 : arg2; +} + +void helper_msa_max_s_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_max_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_max_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_max_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_max_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_max_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_max_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_max_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_max_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_max_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_max_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_max_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_max_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_max_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_max_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_max_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_max_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_max_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_max_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_max_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_max_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_max_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_max_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_max_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_max_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_max_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_max_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_max_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_max_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_max_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_max_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_max_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_max_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_max_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_max_u_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t u_arg2 = UNSIGNED(arg2, df); + return u_arg1 > u_arg2 ? arg1 : arg2; +} + +void helper_msa_max_u_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_max_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_max_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_max_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_max_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_max_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_max_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_max_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_max_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_max_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_max_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_max_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_max_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_max_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_max_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_max_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_max_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_max_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_max_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_max_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_max_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_max_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_max_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_max_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_max_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_max_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_max_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_max_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_max_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_max_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_max_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_max_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_max_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_max_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + static inline int64_t msa_min_a_df(uint32_t df, int64_t arg1, int64_t arg2) { uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1; @@ -1884,6 +2030,152 @@ void helper_msa_min_a_d(CPUMIPSState *env, } +static inline int64_t msa_min_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + return arg1 < arg2 ? arg1 : arg2; +} + +void helper_msa_min_s_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_min_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_min_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_min_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_min_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_min_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_min_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_min_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_min_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_min_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_min_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_min_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_min_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_min_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_min_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_min_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_min_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_min_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_min_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_min_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_min_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_min_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_min_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_min_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_min_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_min_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_min_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_min_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_min_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_min_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_min_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_min_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_min_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_min_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_min_u_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t u_arg2 = UNSIGNED(arg2, df); + return u_arg1 < u_arg2 ? arg1 : arg2; +} + +void helper_msa_min_u_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_min_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_min_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_min_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_min_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_min_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_min_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_min_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_min_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_min_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_min_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_min_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_min_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_min_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_min_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_min_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_min_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_min_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_min_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_min_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_min_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_min_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_min_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_min_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_min_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_min_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_min_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_min_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_min_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_min_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_min_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_min_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_min_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_min_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + /* * Int Modulo * ---------- @@ -2354,30 +2646,6 @@ static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2) return arg1 - arg2; } -static inline int64_t msa_max_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - return arg1 > arg2 ? arg1 : arg2; -} - -static inline int64_t msa_max_u_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t u_arg2 = UNSIGNED(arg2, df); - return u_arg1 > u_arg2 ? arg1 : arg2; -} - -static inline int64_t msa_min_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - return arg1 < arg2 ? arg1 : arg2; -} - -static inline int64_t msa_min_u_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t u_arg2 = UNSIGNED(arg2, df); - return u_arg1 < u_arg2 ? arg1 : arg2; -} - #define MSA_BINOP_IMM_DF(helper, func) \ void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df, \ uint32_t wd, uint32_t ws, int32_t u5) \ @@ -2900,10 +3168,6 @@ MSA_BINOP_DF(sra) MSA_BINOP_DF(srl) MSA_BINOP_DF(addv) MSA_BINOP_DF(subv) -MSA_BINOP_DF(max_s) -MSA_BINOP_DF(max_u) -MSA_BINOP_DF(min_s) -MSA_BINOP_DF(min_u) MSA_BINOP_DF(add_a) MSA_BINOP_DF(adds_a) MSA_BINOP_DF(adds_s) diff --git a/target/mips/translate.c b/target/mips/translate.c index 8e26548a91..7a35c26062 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28658,6 +28658,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_MAX_S_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_max_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_max_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_max_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_max_s_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_MAX_U_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_max_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_max_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_max_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_max_u_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_MIN_A_df: switch (df) { case DF_BYTE: @@ -28674,6 +28706,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_MIN_S_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_min_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_min_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_min_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_min_s_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_MIN_U_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_min_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_min_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_min_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_min_u_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_MOD_S_df: switch (df) { case DF_BYTE: @@ -28751,9 +28815,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SRL_df: gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_MAX_S_df: - gen_helper_msa_max_s_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_ADDS_S_df: gen_helper_msa_adds_s_df(cpu_env, tdf, twd, tws, twt); break; @@ -28769,9 +28830,6 @@ 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_MAX_U_df: - gen_helper_msa_max_u_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_ADDS_U_df: gen_helper_msa_adds_u_df(cpu_env, tdf, twd, tws, twt); break; @@ -28781,18 +28839,12 @@ 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_MIN_S_df: - gen_helper_msa_min_s_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_ASUB_S_df: gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt); break; case OPC_ILVL_df: gen_helper_msa_ilvl_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; case OPC_ASUB_U_df: gen_helper_msa_asub_u_df(cpu_env, tdf, twd, tws, twt); break; -- cgit 1.4.1 From fb5f59b4dca403293921fb1aec45bde935ee51a6 Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:39 +0200 Subject: target/mips: msa: Split helpers for ILV. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-7-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 21 +- target/mips/msa_helper.c | 768 +++++++++++++++++++++++++---------------------- target/mips/translate.c | 76 ++++- 3 files changed, 496 insertions(+), 369 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index 6419bb8395..f3df187c28 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -912,6 +912,23 @@ 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_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) +DEF_HELPER_4(msa_ilvev_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvod_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvod_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvod_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvod_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvl_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvl_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvl_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvl_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvr_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvr_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvr_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_ilvr_d, void, env, i32, i32, i32) + DEF_HELPER_4(msa_and_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32) @@ -984,10 +1001,6 @@ 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_pckev_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_ilvl_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_ilvr_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_ilvev_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_ilvod_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) diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index 65df15df6e..499fcdee52 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -2432,7 +2432,421 @@ void helper_msa_mod_u_d(CPUMIPSState *env, * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Interleave group helpers here */ + +void helper_msa_ilvev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[8] = pws->b[9]; + pwd->b[9] = pwt->b[9]; + pwd->b[10] = pws->b[11]; + pwd->b[11] = pwt->b[11]; + pwd->b[12] = pws->b[13]; + pwd->b[13] = pwt->b[13]; + pwd->b[14] = pws->b[15]; + pwd->b[15] = pwt->b[15]; + pwd->b[0] = pws->b[1]; + pwd->b[1] = pwt->b[1]; + pwd->b[2] = pws->b[3]; + pwd->b[3] = pwt->b[3]; + pwd->b[4] = pws->b[5]; + pwd->b[5] = pwt->b[5]; + pwd->b[6] = pws->b[7]; + pwd->b[7] = pwt->b[7]; +#else + pwd->b[15] = pws->b[14]; + pwd->b[14] = pwt->b[14]; + pwd->b[13] = pws->b[12]; + pwd->b[12] = pwt->b[12]; + pwd->b[11] = pws->b[10]; + pwd->b[10] = pwt->b[10]; + pwd->b[9] = pws->b[8]; + pwd->b[8] = pwt->b[8]; + pwd->b[7] = pws->b[6]; + pwd->b[6] = pwt->b[6]; + pwd->b[5] = pws->b[4]; + pwd->b[4] = pwt->b[4]; + pwd->b[3] = pws->b[2]; + pwd->b[2] = pwt->b[2]; + pwd->b[1] = pws->b[0]; + pwd->b[0] = pwt->b[0]; +#endif +} + +void helper_msa_ilvev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[4] = pws->h[5]; + pwd->h[5] = pwt->h[5]; + pwd->h[6] = pws->h[7]; + pwd->h[7] = pwt->h[7]; + pwd->h[0] = pws->h[1]; + pwd->h[1] = pwt->h[1]; + pwd->h[2] = pws->h[3]; + pwd->h[3] = pwt->h[3]; +#else + pwd->h[7] = pws->h[6]; + pwd->h[6] = pwt->h[6]; + pwd->h[5] = pws->h[4]; + pwd->h[4] = pwt->h[4]; + pwd->h[3] = pws->h[2]; + pwd->h[2] = pwt->h[2]; + pwd->h[1] = pws->h[0]; + pwd->h[0] = pwt->h[0]; +#endif +} + +void helper_msa_ilvev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[2] = pws->w[3]; + pwd->w[3] = pwt->w[3]; + pwd->w[0] = pws->w[1]; + pwd->w[1] = pwt->w[1]; +#else + pwd->w[3] = pws->w[2]; + pwd->w[2] = pwt->w[2]; + pwd->w[1] = pws->w[0]; + pwd->w[0] = pwt->w[0]; +#endif +} + +void helper_msa_ilvev_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[1] = pws->d[0]; + pwd->d[0] = pwt->d[0]; +} + + +void helper_msa_ilvod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[7] = pwt->b[6]; + pwd->b[6] = pws->b[6]; + pwd->b[5] = pwt->b[4]; + pwd->b[4] = pws->b[4]; + pwd->b[3] = pwt->b[2]; + pwd->b[2] = pws->b[2]; + pwd->b[1] = pwt->b[0]; + pwd->b[0] = pws->b[0]; + pwd->b[15] = pwt->b[14]; + pwd->b[14] = pws->b[14]; + pwd->b[13] = pwt->b[12]; + pwd->b[12] = pws->b[12]; + pwd->b[11] = pwt->b[10]; + pwd->b[10] = pws->b[10]; + pwd->b[9] = pwt->b[8]; + pwd->b[8] = pws->b[8]; +#else + pwd->b[0] = pwt->b[1]; + pwd->b[1] = pws->b[1]; + pwd->b[2] = pwt->b[3]; + pwd->b[3] = pws->b[3]; + pwd->b[4] = pwt->b[5]; + pwd->b[5] = pws->b[5]; + pwd->b[6] = pwt->b[7]; + pwd->b[7] = pws->b[7]; + pwd->b[8] = pwt->b[9]; + pwd->b[9] = pws->b[9]; + pwd->b[10] = pwt->b[11]; + pwd->b[11] = pws->b[11]; + pwd->b[12] = pwt->b[13]; + pwd->b[13] = pws->b[13]; + pwd->b[14] = pwt->b[15]; + pwd->b[15] = pws->b[15]; +#endif +} + +void helper_msa_ilvod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[3] = pwt->h[2]; + pwd->h[2] = pws->h[2]; + pwd->h[1] = pwt->h[0]; + pwd->h[0] = pws->h[0]; + pwd->h[7] = pwt->h[6]; + pwd->h[6] = pws->h[6]; + pwd->h[5] = pwt->h[4]; + pwd->h[4] = pws->h[4]; +#else + pwd->h[0] = pwt->h[1]; + pwd->h[1] = pws->h[1]; + pwd->h[2] = pwt->h[3]; + pwd->h[3] = pws->h[3]; + pwd->h[4] = pwt->h[5]; + pwd->h[5] = pws->h[5]; + pwd->h[6] = pwt->h[7]; + pwd->h[7] = pws->h[7]; +#endif +} + +void helper_msa_ilvod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[1] = pwt->w[0]; + pwd->w[0] = pws->w[0]; + pwd->w[3] = pwt->w[2]; + pwd->w[2] = pws->w[2]; +#else + pwd->w[0] = pwt->w[1]; + pwd->w[1] = pws->w[1]; + pwd->w[2] = pwt->w[3]; + pwd->w[3] = pws->w[3]; +#endif +} + +void helper_msa_ilvod_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] = pwt->d[1]; + pwd->d[1] = pws->d[1]; +} + + +void helper_msa_ilvl_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[7] = pwt->b[15]; + pwd->b[6] = pws->b[15]; + pwd->b[5] = pwt->b[14]; + pwd->b[4] = pws->b[14]; + pwd->b[3] = pwt->b[13]; + pwd->b[2] = pws->b[13]; + pwd->b[1] = pwt->b[12]; + pwd->b[0] = pws->b[12]; + pwd->b[15] = pwt->b[11]; + pwd->b[14] = pws->b[11]; + pwd->b[13] = pwt->b[10]; + pwd->b[12] = pws->b[10]; + pwd->b[11] = pwt->b[9]; + pwd->b[10] = pws->b[9]; + pwd->b[9] = pwt->b[8]; + pwd->b[8] = pws->b[8]; +#else + pwd->b[0] = pwt->b[8]; + pwd->b[1] = pws->b[8]; + pwd->b[2] = pwt->b[9]; + pwd->b[3] = pws->b[9]; + pwd->b[4] = pwt->b[10]; + pwd->b[5] = pws->b[10]; + pwd->b[6] = pwt->b[11]; + pwd->b[7] = pws->b[11]; + pwd->b[8] = pwt->b[12]; + pwd->b[9] = pws->b[12]; + pwd->b[10] = pwt->b[13]; + pwd->b[11] = pws->b[13]; + pwd->b[12] = pwt->b[14]; + pwd->b[13] = pws->b[14]; + pwd->b[14] = pwt->b[15]; + pwd->b[15] = pws->b[15]; +#endif +} + +void helper_msa_ilvl_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[3] = pwt->h[7]; + pwd->h[2] = pws->h[7]; + pwd->h[1] = pwt->h[6]; + pwd->h[0] = pws->h[6]; + pwd->h[7] = pwt->h[5]; + pwd->h[6] = pws->h[5]; + pwd->h[5] = pwt->h[4]; + pwd->h[4] = pws->h[4]; +#else + pwd->h[0] = pwt->h[4]; + pwd->h[1] = pws->h[4]; + pwd->h[2] = pwt->h[5]; + pwd->h[3] = pws->h[5]; + pwd->h[4] = pwt->h[6]; + pwd->h[5] = pws->h[6]; + pwd->h[6] = pwt->h[7]; + pwd->h[7] = pws->h[7]; +#endif +} + +void helper_msa_ilvl_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[1] = pwt->w[3]; + pwd->w[0] = pws->w[3]; + pwd->w[3] = pwt->w[2]; + pwd->w[2] = pws->w[2]; +#else + pwd->w[0] = pwt->w[2]; + pwd->w[1] = pws->w[2]; + pwd->w[2] = pwt->w[3]; + pwd->w[3] = pws->w[3]; +#endif +} + +void helper_msa_ilvl_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] = pwt->d[1]; + pwd->d[1] = pws->d[1]; +} + + +void helper_msa_ilvr_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[8] = pws->b[0]; + pwd->b[9] = pwt->b[0]; + pwd->b[10] = pws->b[1]; + pwd->b[11] = pwt->b[1]; + pwd->b[12] = pws->b[2]; + pwd->b[13] = pwt->b[2]; + pwd->b[14] = pws->b[3]; + pwd->b[15] = pwt->b[3]; + pwd->b[0] = pws->b[4]; + pwd->b[1] = pwt->b[4]; + pwd->b[2] = pws->b[5]; + pwd->b[3] = pwt->b[5]; + pwd->b[4] = pws->b[6]; + pwd->b[5] = pwt->b[6]; + pwd->b[6] = pws->b[7]; + pwd->b[7] = pwt->b[7]; +#else + pwd->b[15] = pws->b[7]; + pwd->b[14] = pwt->b[7]; + pwd->b[13] = pws->b[6]; + pwd->b[12] = pwt->b[6]; + pwd->b[11] = pws->b[5]; + pwd->b[10] = pwt->b[5]; + pwd->b[9] = pws->b[4]; + pwd->b[8] = pwt->b[4]; + pwd->b[7] = pws->b[3]; + pwd->b[6] = pwt->b[3]; + pwd->b[5] = pws->b[2]; + pwd->b[4] = pwt->b[2]; + pwd->b[3] = pws->b[1]; + pwd->b[2] = pwt->b[1]; + pwd->b[1] = pws->b[0]; + pwd->b[0] = pwt->b[0]; +#endif +} + +void helper_msa_ilvr_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[4] = pws->h[0]; + pwd->h[5] = pwt->h[0]; + pwd->h[6] = pws->h[1]; + pwd->h[7] = pwt->h[1]; + pwd->h[0] = pws->h[2]; + pwd->h[1] = pwt->h[2]; + pwd->h[2] = pws->h[3]; + pwd->h[3] = pwt->h[3]; +#else + pwd->h[7] = pws->h[3]; + pwd->h[6] = pwt->h[3]; + pwd->h[5] = pws->h[2]; + pwd->h[4] = pwt->h[2]; + pwd->h[3] = pws->h[1]; + pwd->h[2] = pwt->h[1]; + pwd->h[1] = pws->h[0]; + pwd->h[0] = pwt->h[0]; +#endif +} + +void helper_msa_ilvr_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[2] = pws->w[0]; + pwd->w[3] = pwt->w[0]; + pwd->w[0] = pws->w[1]; + pwd->w[1] = pwt->w[1]; +#else + pwd->w[3] = pws->w[1]; + pwd->w[2] = pwt->w[1]; + pwd->w[1] = pws->w[0]; + pwd->w[0] = pwt->w[0]; +#endif +} + +void helper_msa_ilvr_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[1] = pws->d[0]; + pwd->d[0] = pwt->d[0]; +} /* @@ -3522,358 +3936,6 @@ MSA_FN_DF(vshf_df) #undef MSA_FN_DF -void helper_msa_ilvev_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[8] = pws->b[9]; - pwd->b[9] = pwt->b[9]; - pwd->b[10] = pws->b[11]; - pwd->b[11] = pwt->b[11]; - pwd->b[12] = pws->b[13]; - pwd->b[13] = pwt->b[13]; - pwd->b[14] = pws->b[15]; - pwd->b[15] = pwt->b[15]; - pwd->b[0] = pws->b[1]; - pwd->b[1] = pwt->b[1]; - pwd->b[2] = pws->b[3]; - pwd->b[3] = pwt->b[3]; - pwd->b[4] = pws->b[5]; - pwd->b[5] = pwt->b[5]; - pwd->b[6] = pws->b[7]; - pwd->b[7] = pwt->b[7]; -#else - pwd->b[15] = pws->b[14]; - pwd->b[14] = pwt->b[14]; - pwd->b[13] = pws->b[12]; - pwd->b[12] = pwt->b[12]; - pwd->b[11] = pws->b[10]; - pwd->b[10] = pwt->b[10]; - pwd->b[9] = pws->b[8]; - pwd->b[8] = pwt->b[8]; - pwd->b[7] = pws->b[6]; - pwd->b[6] = pwt->b[6]; - pwd->b[5] = pws->b[4]; - pwd->b[4] = pwt->b[4]; - pwd->b[3] = pws->b[2]; - pwd->b[2] = pwt->b[2]; - pwd->b[1] = pws->b[0]; - pwd->b[0] = pwt->b[0]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[4] = pws->h[5]; - pwd->h[5] = pwt->h[5]; - pwd->h[6] = pws->h[7]; - pwd->h[7] = pwt->h[7]; - pwd->h[0] = pws->h[1]; - pwd->h[1] = pwt->h[1]; - pwd->h[2] = pws->h[3]; - pwd->h[3] = pwt->h[3]; -#else - pwd->h[7] = pws->h[6]; - pwd->h[6] = pwt->h[6]; - pwd->h[5] = pws->h[4]; - pwd->h[4] = pwt->h[4]; - pwd->h[3] = pws->h[2]; - pwd->h[2] = pwt->h[2]; - pwd->h[1] = pws->h[0]; - pwd->h[0] = pwt->h[0]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[2] = pws->w[3]; - pwd->w[3] = pwt->w[3]; - pwd->w[0] = pws->w[1]; - pwd->w[1] = pwt->w[1]; -#else - pwd->w[3] = pws->w[2]; - pwd->w[2] = pwt->w[2]; - pwd->w[1] = pws->w[0]; - pwd->w[0] = pwt->w[0]; -#endif - break; - case DF_DOUBLE: - pwd->d[1] = pws->d[0]; - pwd->d[0] = pwt->d[0]; - break; - default: - assert(0); - } -} - -void helper_msa_ilvod_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[7] = pwt->b[6]; - pwd->b[6] = pws->b[6]; - pwd->b[5] = pwt->b[4]; - pwd->b[4] = pws->b[4]; - pwd->b[3] = pwt->b[2]; - pwd->b[2] = pws->b[2]; - pwd->b[1] = pwt->b[0]; - pwd->b[0] = pws->b[0]; - pwd->b[15] = pwt->b[14]; - pwd->b[14] = pws->b[14]; - pwd->b[13] = pwt->b[12]; - pwd->b[12] = pws->b[12]; - pwd->b[11] = pwt->b[10]; - pwd->b[10] = pws->b[10]; - pwd->b[9] = pwt->b[8]; - pwd->b[8] = pws->b[8]; -#else - pwd->b[0] = pwt->b[1]; - pwd->b[1] = pws->b[1]; - pwd->b[2] = pwt->b[3]; - pwd->b[3] = pws->b[3]; - pwd->b[4] = pwt->b[5]; - pwd->b[5] = pws->b[5]; - pwd->b[6] = pwt->b[7]; - pwd->b[7] = pws->b[7]; - pwd->b[8] = pwt->b[9]; - pwd->b[9] = pws->b[9]; - pwd->b[10] = pwt->b[11]; - pwd->b[11] = pws->b[11]; - pwd->b[12] = pwt->b[13]; - pwd->b[13] = pws->b[13]; - pwd->b[14] = pwt->b[15]; - pwd->b[15] = pws->b[15]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[3] = pwt->h[2]; - pwd->h[2] = pws->h[2]; - pwd->h[1] = pwt->h[0]; - pwd->h[0] = pws->h[0]; - pwd->h[7] = pwt->h[6]; - pwd->h[6] = pws->h[6]; - pwd->h[5] = pwt->h[4]; - pwd->h[4] = pws->h[4]; -#else - pwd->h[0] = pwt->h[1]; - pwd->h[1] = pws->h[1]; - pwd->h[2] = pwt->h[3]; - pwd->h[3] = pws->h[3]; - pwd->h[4] = pwt->h[5]; - pwd->h[5] = pws->h[5]; - pwd->h[6] = pwt->h[7]; - pwd->h[7] = pws->h[7]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[1] = pwt->w[0]; - pwd->w[0] = pws->w[0]; - pwd->w[3] = pwt->w[2]; - pwd->w[2] = pws->w[2]; -#else - pwd->w[0] = pwt->w[1]; - pwd->w[1] = pws->w[1]; - pwd->w[2] = pwt->w[3]; - pwd->w[3] = pws->w[3]; -#endif - break; - case DF_DOUBLE: - pwd->d[0] = pwt->d[1]; - pwd->d[1] = pws->d[1]; - break; - default: - assert(0); - } -} - -void helper_msa_ilvl_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[7] = pwt->b[15]; - pwd->b[6] = pws->b[15]; - pwd->b[5] = pwt->b[14]; - pwd->b[4] = pws->b[14]; - pwd->b[3] = pwt->b[13]; - pwd->b[2] = pws->b[13]; - pwd->b[1] = pwt->b[12]; - pwd->b[0] = pws->b[12]; - pwd->b[15] = pwt->b[11]; - pwd->b[14] = pws->b[11]; - pwd->b[13] = pwt->b[10]; - pwd->b[12] = pws->b[10]; - pwd->b[11] = pwt->b[9]; - pwd->b[10] = pws->b[9]; - pwd->b[9] = pwt->b[8]; - pwd->b[8] = pws->b[8]; -#else - pwd->b[0] = pwt->b[8]; - pwd->b[1] = pws->b[8]; - pwd->b[2] = pwt->b[9]; - pwd->b[3] = pws->b[9]; - pwd->b[4] = pwt->b[10]; - pwd->b[5] = pws->b[10]; - pwd->b[6] = pwt->b[11]; - pwd->b[7] = pws->b[11]; - pwd->b[8] = pwt->b[12]; - pwd->b[9] = pws->b[12]; - pwd->b[10] = pwt->b[13]; - pwd->b[11] = pws->b[13]; - pwd->b[12] = pwt->b[14]; - pwd->b[13] = pws->b[14]; - pwd->b[14] = pwt->b[15]; - pwd->b[15] = pws->b[15]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[3] = pwt->h[7]; - pwd->h[2] = pws->h[7]; - pwd->h[1] = pwt->h[6]; - pwd->h[0] = pws->h[6]; - pwd->h[7] = pwt->h[5]; - pwd->h[6] = pws->h[5]; - pwd->h[5] = pwt->h[4]; - pwd->h[4] = pws->h[4]; -#else - pwd->h[0] = pwt->h[4]; - pwd->h[1] = pws->h[4]; - pwd->h[2] = pwt->h[5]; - pwd->h[3] = pws->h[5]; - pwd->h[4] = pwt->h[6]; - pwd->h[5] = pws->h[6]; - pwd->h[6] = pwt->h[7]; - pwd->h[7] = pws->h[7]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[1] = pwt->w[3]; - pwd->w[0] = pws->w[3]; - pwd->w[3] = pwt->w[2]; - pwd->w[2] = pws->w[2]; -#else - pwd->w[0] = pwt->w[2]; - pwd->w[1] = pws->w[2]; - pwd->w[2] = pwt->w[3]; - pwd->w[3] = pws->w[3]; -#endif - break; - case DF_DOUBLE: - pwd->d[0] = pwt->d[1]; - pwd->d[1] = pws->d[1]; - break; - default: - assert(0); - } -} - -void helper_msa_ilvr_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[8] = pws->b[0]; - pwd->b[9] = pwt->b[0]; - pwd->b[10] = pws->b[1]; - pwd->b[11] = pwt->b[1]; - pwd->b[12] = pws->b[2]; - pwd->b[13] = pwt->b[2]; - pwd->b[14] = pws->b[3]; - pwd->b[15] = pwt->b[3]; - pwd->b[0] = pws->b[4]; - pwd->b[1] = pwt->b[4]; - pwd->b[2] = pws->b[5]; - pwd->b[3] = pwt->b[5]; - pwd->b[4] = pws->b[6]; - pwd->b[5] = pwt->b[6]; - pwd->b[6] = pws->b[7]; - pwd->b[7] = pwt->b[7]; -#else - pwd->b[15] = pws->b[7]; - pwd->b[14] = pwt->b[7]; - pwd->b[13] = pws->b[6]; - pwd->b[12] = pwt->b[6]; - pwd->b[11] = pws->b[5]; - pwd->b[10] = pwt->b[5]; - pwd->b[9] = pws->b[4]; - pwd->b[8] = pwt->b[4]; - pwd->b[7] = pws->b[3]; - pwd->b[6] = pwt->b[3]; - pwd->b[5] = pws->b[2]; - pwd->b[4] = pwt->b[2]; - pwd->b[3] = pws->b[1]; - pwd->b[2] = pwt->b[1]; - pwd->b[1] = pws->b[0]; - pwd->b[0] = pwt->b[0]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[4] = pws->h[0]; - pwd->h[5] = pwt->h[0]; - pwd->h[6] = pws->h[1]; - pwd->h[7] = pwt->h[1]; - pwd->h[0] = pws->h[2]; - pwd->h[1] = pwt->h[2]; - pwd->h[2] = pws->h[3]; - pwd->h[3] = pwt->h[3]; -#else - pwd->h[7] = pws->h[3]; - pwd->h[6] = pwt->h[3]; - pwd->h[5] = pws->h[2]; - pwd->h[4] = pwt->h[2]; - pwd->h[3] = pws->h[1]; - pwd->h[2] = pwt->h[1]; - pwd->h[1] = pws->h[0]; - pwd->h[0] = pwt->h[0]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[2] = pws->w[0]; - pwd->w[3] = pwt->w[0]; - pwd->w[0] = pws->w[1]; - pwd->w[1] = pwt->w[1]; -#else - pwd->w[3] = pws->w[1]; - pwd->w[2] = pwt->w[1]; - pwd->w[1] = pws->w[0]; - pwd->w[0] = pwt->w[0]; -#endif - break; - case DF_DOUBLE: - pwd->d[1] = pws->d[0]; - pwd->d[0] = pwt->d[0]; - break; - default: - assert(0); - } -} - void helper_msa_pckev_df(CPUMIPSState *env, uint32_t df, uint32_t wd, uint32_t ws, uint32_t wt) { diff --git a/target/mips/translate.c b/target/mips/translate.c index 7a35c26062..ea8b8f43a9 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28770,6 +28770,70 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_ILVEV_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_ilvev_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_ilvev_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_ilvev_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_ilvev_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ILVOD_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_ilvod_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_ilvod_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_ilvod_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_ilvod_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ILVL_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_ilvl_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_ilvl_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_ilvl_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_ilvl_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ILVR_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_ilvr_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_ilvr_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_ilvr_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_ilvr_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_SLL_df: gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt); break; @@ -28842,21 +28906,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_ASUB_S_df: gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ILVL_df: - gen_helper_msa_ilvl_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_ASUB_U_df: gen_helper_msa_asub_u_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ILVR_df: - gen_helper_msa_ilvr_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_ILVEV_df: - gen_helper_msa_ilvev_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_ILVOD_df: - gen_helper_msa_ilvod_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_DOTP_S_df: case OPC_DOTP_U_df: -- cgit 1.4.1 From c65ca134d79bdb8d77e79791b7f49533827ca70d Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:40 +0200 Subject: target/mips: msa: Split helpers for ADD<_A|S_A|S_S|S_U|V>. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-8-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 30 +++- target/mips/msa_helper.c | 426 +++++++++++++++++++++++++++++++++++++++++------ target/mips/translate.c | 95 +++++++++-- 3 files changed, 482 insertions(+), 69 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index f3df187c28..ce01e972ba 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -822,6 +822,31 @@ 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_add_a_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_add_a_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_add_a_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_add_a_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_adds_a_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_a_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_a_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_a_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_adds_s_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_s_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_adds_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_adds_u_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_addv_b, void, env, i32, i32, i32) +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_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) @@ -976,12 +1001,7 @@ 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_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) DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_adds_u_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_subs_s_df, void, env, i32, i32, i32, i32) 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) diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index 499fcdee52..c31f46cabf 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -805,7 +805,383 @@ void helper_msa_bset_d(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t wt) * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Int Add group helpers here */ + +static inline int64_t msa_add_a_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1; + uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2; + return abs_arg1 + abs_arg2; +} + +void helper_msa_add_a_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_add_a_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_add_a_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_add_a_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_add_a_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_add_a_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_add_a_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_add_a_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_add_a_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_add_a_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_add_a_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_add_a_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_add_a_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_add_a_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_add_a_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_add_a_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_add_a_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_add_a_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_add_a_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_add_a_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_add_a_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_add_a_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_add_a_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_add_a_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_add_a_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_add_a_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_add_a_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_add_a_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_add_a_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_add_a_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_add_a_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_add_a_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_add_a_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_add_a_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_adds_a_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t max_int = (uint64_t)DF_MAX_INT(df); + uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1; + uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2; + if (abs_arg1 > max_int || abs_arg2 > max_int) { + return (int64_t)max_int; + } else { + return (abs_arg1 < max_int - abs_arg2) ? abs_arg1 + abs_arg2 : max_int; + } +} + +void helper_msa_adds_a_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_adds_a_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_adds_a_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_adds_a_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_adds_a_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_adds_a_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_adds_a_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_adds_a_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_adds_a_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_adds_a_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_adds_a_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_adds_a_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_adds_a_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_adds_a_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_adds_a_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_adds_a_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_adds_a_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_adds_a_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_adds_a_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_adds_a_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_adds_a_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_adds_a_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_adds_a_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_adds_a_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_adds_a_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_adds_a_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_adds_a_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_adds_a_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_adds_a_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_adds_a_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_adds_a_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_adds_a_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_adds_a_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_adds_a_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_adds_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int64_t max_int = DF_MAX_INT(df); + int64_t min_int = DF_MIN_INT(df); + if (arg1 < 0) { + return (min_int - arg1 < arg2) ? arg1 + arg2 : min_int; + } else { + return (arg2 < max_int - arg1) ? arg1 + arg2 : max_int; + } +} + +void helper_msa_adds_s_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_adds_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_adds_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_adds_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_adds_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_adds_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_adds_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_adds_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_adds_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_adds_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_adds_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_adds_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_adds_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_adds_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_adds_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_adds_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_adds_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_adds_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_adds_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_adds_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_adds_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_adds_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_adds_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_adds_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_adds_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_adds_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_adds_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_adds_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_adds_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_adds_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_adds_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_adds_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_adds_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_adds_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline uint64_t msa_adds_u_df(uint32_t df, uint64_t arg1, uint64_t arg2) +{ + uint64_t max_uint = DF_MAX_UINT(df); + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t u_arg2 = UNSIGNED(arg2, df); + return (u_arg1 < max_uint - u_arg2) ? u_arg1 + u_arg2 : max_uint; +} + +void helper_msa_adds_u_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_adds_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_adds_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_adds_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_adds_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_adds_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_adds_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_adds_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_adds_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_adds_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_adds_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_adds_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_adds_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_adds_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_adds_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_adds_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_adds_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_adds_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_adds_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_adds_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_adds_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_adds_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_adds_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_adds_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_adds_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_adds_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_adds_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_adds_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_adds_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_adds_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_adds_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_adds_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_adds_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_adds_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_addv_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + return arg1 + arg2; +} + +void helper_msa_addv_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_addv_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_addv_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_addv_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_addv_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_addv_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_addv_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_addv_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_addv_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_addv_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_addv_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_addv_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_addv_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_addv_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_addv_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_addv_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_addv_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_addv_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_addv_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_addv_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_addv_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_addv_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_addv_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_addv_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_addv_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_addv_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_addv_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_addv_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_addv_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_addv_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_addv_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_addv_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_addv_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_addv_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} /* @@ -3050,11 +3426,6 @@ void helper_msa_shf_df(CPUMIPSState *env, uint32_t df, uint32_t wd, msa_move_v(pwd, pwx); } -static inline int64_t msa_addv_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - return arg1 + arg2; -} - static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2) { return arg1 - arg2; @@ -3283,44 +3654,6 @@ MSA_TEROP_IMMU_DF(binsli, binsl) MSA_TEROP_IMMU_DF(binsri, binsr) #undef MSA_TEROP_IMMU_DF -static inline int64_t msa_add_a_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1; - uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2; - return abs_arg1 + abs_arg2; -} - -static inline int64_t msa_adds_a_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t max_int = (uint64_t)DF_MAX_INT(df); - uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1; - uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2; - if (abs_arg1 > max_int || abs_arg2 > max_int) { - return (int64_t)max_int; - } else { - return (abs_arg1 < max_int - abs_arg2) ? abs_arg1 + abs_arg2 : max_int; - } -} - -static inline int64_t msa_adds_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int64_t max_int = DF_MAX_INT(df); - int64_t min_int = DF_MIN_INT(df); - if (arg1 < 0) { - return (min_int - arg1 < arg2) ? arg1 + arg2 : min_int; - } else { - return (arg2 < max_int - arg1) ? arg1 + arg2 : max_int; - } -} - -static inline uint64_t msa_adds_u_df(uint32_t df, uint64_t arg1, uint64_t arg2) -{ - uint64_t max_uint = DF_MAX_UINT(df); - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t u_arg2 = UNSIGNED(arg2, df); - return (u_arg1 < max_uint - u_arg2) ? u_arg1 + u_arg2 : max_uint; -} - static inline int64_t msa_subs_s_df(uint32_t df, int64_t arg1, int64_t arg2) { int64_t max_int = DF_MAX_INT(df); @@ -3580,12 +3913,7 @@ 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(addv) MSA_BINOP_DF(subv) -MSA_BINOP_DF(add_a) -MSA_BINOP_DF(adds_a) -MSA_BINOP_DF(adds_s) -MSA_BINOP_DF(adds_u) MSA_BINOP_DF(subs_s) MSA_BINOP_DF(subs_u) MSA_BINOP_DF(subsus_u) diff --git a/target/mips/translate.c b/target/mips/translate.c index ea8b8f43a9..14f9891bca 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28466,6 +28466,86 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_ADD_A_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_add_a_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_add_a_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_add_a_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_add_a_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ADDS_A_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_adds_a_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_adds_a_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_adds_a_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_adds_a_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ADDS_S_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_adds_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_adds_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_adds_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_adds_s_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ADDS_U_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_adds_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_adds_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_adds_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_adds_u_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ADDV_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_addv_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_addv_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_addv_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_addv_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_AVE_S_df: switch (df) { case DF_BYTE: @@ -28837,12 +28917,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SLL_df: gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ADDV_df: - gen_helper_msa_addv_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_ADD_A_df: - gen_helper_msa_add_a_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_SUBS_S_df: gen_helper_msa_subs_s_df(cpu_env, tdf, twd, tws, twt); break; @@ -28861,9 +28935,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SUBV_df: gen_helper_msa_subv_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ADDS_A_df: - gen_helper_msa_adds_a_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_SUBS_U_df: gen_helper_msa_subs_u_df(cpu_env, tdf, twd, tws, twt); break; @@ -28879,9 +28950,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SRL_df: gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ADDS_S_df: - gen_helper_msa_adds_s_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_SUBSUS_U_df: gen_helper_msa_subsus_u_df(cpu_env, tdf, twd, tws, twt); break; @@ -28894,9 +28962,6 @@ 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_ADDS_U_df: - gen_helper_msa_adds_u_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; -- cgit 1.4.1 From dc0af9312b5e1b51d01714b29e1185d289b70dd8 Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:41 +0200 Subject: target/mips: msa: Split helpers for HADD_. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-9-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 10 +++- target/mips/msa_helper.c | 131 ++++++++++++++++++++++++++++++++++++++--------- target/mips/translate.c | 32 +++++++++--- 3 files changed, 141 insertions(+), 32 deletions(-) (limited to 'target/mips/helper.h') 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; -- cgit 1.4.1 From 4d52cc2bbc37897e94cdb0d93424c66d161ae7d8 Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:42 +0200 Subject: target/mips: msa: Split helpers for S. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-10-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 30 +++- target/mips/msa_helper.c | 424 +++++++++++++++++++++++++++++++++++++++++------ target/mips/translate.c | 91 ++++++++-- 3 files changed, 479 insertions(+), 66 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index f25ba90fc2..f779404826 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -967,6 +967,31 @@ DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_xor_v, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sll_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sll_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sll_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sll_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_sra_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sra_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sra_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_sra_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_srar_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srar_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srar_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srar_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_srl_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srl_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srl_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srl_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_srlr_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srlr_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srlr_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_srlr_d, void, env, i32, i32, i32) + DEF_HELPER_3(msa_move_v, void, env, i32, i32) DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32) @@ -1004,9 +1029,6 @@ DEF_HELPER_5(msa_sat_u_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_srari_df, void, env, i32, i32, i32, i32) 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_binsl_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_binsr_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32) @@ -1030,8 +1052,6 @@ DEF_HELPER_5(msa_splat_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_pckev_df, void, env, i32, i32, i32, i32) 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_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 f5d3737a77..38ff1da0dd 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -3461,7 +3461,382 @@ void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws) * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Shift group helpers here */ + +static inline int64_t msa_sll_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int32_t b_arg2 = BIT_POSITION(arg2, df); + return arg1 << b_arg2; +} + +void helper_msa_sll_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_sll_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_sll_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_sll_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_sll_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_sll_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_sll_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_sll_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_sll_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_sll_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_sll_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_sll_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_sll_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_sll_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_sll_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_sll_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_sll_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_sll_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_sll_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_sll_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_sll_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_sll_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_sll_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_sll_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_sll_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_sll_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_sll_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_sll_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_sll_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_sll_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_sll_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_sll_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_sll_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_sll_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_sra_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int32_t b_arg2 = BIT_POSITION(arg2, df); + return arg1 >> b_arg2; +} + +void helper_msa_sra_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_sra_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_sra_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_sra_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_sra_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_sra_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_sra_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_sra_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_sra_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_sra_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_sra_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_sra_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_sra_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_sra_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_sra_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_sra_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_sra_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_sra_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_sra_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_sra_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_sra_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_sra_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_sra_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_sra_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_sra_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_sra_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_sra_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_sra_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_sra_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_sra_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_sra_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_sra_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_sra_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_sra_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_srar_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int32_t b_arg2 = BIT_POSITION(arg2, df); + if (b_arg2 == 0) { + return arg1; + } else { + int64_t r_bit = (arg1 >> (b_arg2 - 1)) & 1; + return (arg1 >> b_arg2) + r_bit; + } +} + +void helper_msa_srar_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_srar_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_srar_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_srar_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_srar_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_srar_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_srar_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_srar_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_srar_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_srar_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_srar_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_srar_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_srar_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_srar_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_srar_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_srar_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_srar_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_srar_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_srar_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_srar_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_srar_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_srar_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_srar_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_srar_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_srar_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_srar_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_srar_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_srar_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_srar_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_srar_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_srar_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_srar_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_srar_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_srar_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + int32_t b_arg2 = BIT_POSITION(arg2, df); + return u_arg1 >> b_arg2; +} + +void helper_msa_srl_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_srl_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_srl_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_srl_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_srl_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_srl_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_srl_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_srl_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_srl_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_srl_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_srl_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_srl_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_srl_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_srl_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_srl_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_srl_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_srl_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_srl_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_srl_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_srl_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_srl_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_srl_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_srl_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_srl_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_srl_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_srl_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_srl_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_srl_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_srl_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_srl_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_srl_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_srl_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_srl_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_srl_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_srlr_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + int32_t b_arg2 = BIT_POSITION(arg2, df); + if (b_arg2 == 0) { + return u_arg1; + } else { + uint64_t r_bit = (u_arg1 >> (b_arg2 - 1)) & 1; + return (u_arg1 >> b_arg2) + r_bit; + } +} + +void helper_msa_srlr_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_srlr_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_srlr_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_srlr_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_srlr_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_srlr_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_srlr_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_srlr_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_srlr_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_srlr_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_srlr_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_srlr_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_srlr_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_srlr_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_srlr_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_srlr_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_srlr_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_srlr_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_srlr_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_srlr_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_srlr_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_srlr_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_srlr_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_srlr_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_srlr_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_srlr_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_srlr_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_srlr_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_srlr_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_srlr_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_srlr_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_srlr_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_srlr_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_srlr_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} #define MSA_FN_IMM8(FUNC, DEST, OPERATION) \ @@ -3617,25 +3992,6 @@ void helper_msa_ldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd, } } -static inline int64_t msa_sll_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int32_t b_arg2 = BIT_POSITION(arg2, df); - return arg1 << b_arg2; -} - -static inline int64_t msa_sra_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int32_t b_arg2 = BIT_POSITION(arg2, df); - return arg1 >> b_arg2; -} - -static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - int32_t b_arg2 = BIT_POSITION(arg2, df); - return u_arg1 >> b_arg2; -} - 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) : @@ -3650,29 +4006,6 @@ static inline int64_t msa_sat_u_df(uint32_t df, int64_t arg, uint32_t m) M_MAX_UINT(m + 1); } -static inline int64_t msa_srar_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int32_t b_arg2 = BIT_POSITION(arg2, df); - if (b_arg2 == 0) { - return arg1; - } else { - int64_t r_bit = (arg1 >> (b_arg2 - 1)) & 1; - return (arg1 >> b_arg2) + r_bit; - } -} - -static inline int64_t msa_srlr_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - int32_t b_arg2 = BIT_POSITION(arg2, df); - if (b_arg2 == 0) { - return u_arg1; - } else { - uint64_t r_bit = (u_arg1 >> (b_arg2 - 1)) & 1; - return (u_arg1 >> b_arg2) + r_bit; - } -} - #define MSA_BINOP_IMMU_DF(helper, func) \ void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd, \ uint32_t ws, uint32_t u5) \ @@ -3995,9 +4328,6 @@ 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(subv) MSA_BINOP_DF(subs_s) MSA_BINOP_DF(subs_u) @@ -4008,8 +4338,6 @@ MSA_BINOP_DF(asub_u) MSA_BINOP_DF(mulv) MSA_BINOP_DF(dotp_s) MSA_BINOP_DF(dotp_u) -MSA_BINOP_DF(srar) -MSA_BINOP_DF(srlr) MSA_BINOP_DF(hsub_s) MSA_BINOP_DF(hsub_u) diff --git a/target/mips/translate.c b/target/mips/translate.c index 9e8e973d91..7cdf68d21d 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28915,7 +28915,84 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) } break; case OPC_SLL_df: - gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_sll_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_sll_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_sll_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_sll_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_SRA_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_sra_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_sra_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_sra_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_sra_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_SRAR_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_srar_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_srar_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_srar_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_srar_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_SRL_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_srl_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_srl_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_srl_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_srl_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_SRLR_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_srlr_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_srlr_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_srlr_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_srlr_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_SUBS_S_df: gen_helper_msa_subs_s_df(cpu_env, tdf, twd, tws, twt); @@ -28929,9 +29006,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_VSHF_df: gen_helper_msa_vshf_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_SRA_df: - gen_helper_msa_sra_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_SUBV_df: gen_helper_msa_subv_df(cpu_env, tdf, twd, tws, twt); break; @@ -28944,12 +29018,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SPLAT_df: gen_helper_msa_splat_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_SRAR_df: - gen_helper_msa_srar_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_SRL_df: - gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_SUBSUS_U_df: gen_helper_msa_subsus_u_df(cpu_env, tdf, twd, tws, twt); break; @@ -28959,9 +29027,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_PCKEV_df: gen_helper_msa_pckev_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_SRLR_df: - gen_helper_msa_srlr_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; -- cgit 1.4.1 From 8a0ee3802f47365a8c2e3a80a21c2f0b40e1173a Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:43 +0200 Subject: target/mips: msa: Split helpers for PCK. Achieves clearer code and slightly better performance. Reviewed-by: Aleksandar Rikalo Signed-off-by: Aleksandar Markovic Message-Id: <1571826227-10583-11-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 11 +- target/mips/msa_helper.c | 386 +++++++++++++++++++++++++---------------------- target/mips/translate.c | 38 ++++- 3 files changed, 249 insertions(+), 186 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index f779404826..7bb13d5c3f 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -967,6 +967,15 @@ DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32) DEF_HELPER_4(msa_xor_v, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckev_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckev_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckev_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckev_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckod_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckod_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckod_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_pckod_d, void, env, i32, i32, i32) + DEF_HELPER_4(msa_sll_b, void, env, i32, i32, i32) DEF_HELPER_4(msa_sll_h, void, env, i32, i32, i32) DEF_HELPER_4(msa_sll_w, void, env, i32, i32, i32) @@ -1049,8 +1058,6 @@ DEF_HELPER_5(msa_dpsub_s_df, void, env, i32, i32, i32, i32) 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_pckev_df, void, env, i32, i32, i32, i32) -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_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 38ff1da0dd..24006323c7 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -3430,7 +3430,214 @@ void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws) * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Pack group helpers here */ + +void helper_msa_pckev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[8] = pws->b[9]; + pwd->b[10] = pws->b[13]; + pwd->b[12] = pws->b[1]; + pwd->b[14] = pws->b[5]; + pwd->b[0] = pwt->b[9]; + pwd->b[2] = pwt->b[13]; + pwd->b[4] = pwt->b[1]; + pwd->b[6] = pwt->b[5]; + pwd->b[9] = pws->b[11]; + pwd->b[13] = pws->b[3]; + pwd->b[1] = pwt->b[11]; + pwd->b[5] = pwt->b[3]; + pwd->b[11] = pws->b[15]; + pwd->b[3] = pwt->b[15]; + pwd->b[15] = pws->b[7]; + pwd->b[7] = pwt->b[7]; +#else + pwd->b[15] = pws->b[14]; + pwd->b[13] = pws->b[10]; + pwd->b[11] = pws->b[6]; + pwd->b[9] = pws->b[2]; + pwd->b[7] = pwt->b[14]; + pwd->b[5] = pwt->b[10]; + pwd->b[3] = pwt->b[6]; + pwd->b[1] = pwt->b[2]; + pwd->b[14] = pws->b[12]; + pwd->b[10] = pws->b[4]; + pwd->b[6] = pwt->b[12]; + pwd->b[2] = pwt->b[4]; + pwd->b[12] = pws->b[8]; + pwd->b[4] = pwt->b[8]; + pwd->b[8] = pws->b[0]; + pwd->b[0] = pwt->b[0]; +#endif +} + +void helper_msa_pckev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[4] = pws->h[5]; + pwd->h[6] = pws->h[1]; + pwd->h[0] = pwt->h[5]; + pwd->h[2] = pwt->h[1]; + pwd->h[5] = pws->h[7]; + pwd->h[1] = pwt->h[7]; + pwd->h[7] = pws->h[3]; + pwd->h[3] = pwt->h[3]; +#else + pwd->h[7] = pws->h[6]; + pwd->h[5] = pws->h[2]; + pwd->h[3] = pwt->h[6]; + pwd->h[1] = pwt->h[2]; + pwd->h[6] = pws->h[4]; + pwd->h[2] = pwt->h[4]; + pwd->h[4] = pws->h[0]; + pwd->h[0] = pwt->h[0]; +#endif +} + +void helper_msa_pckev_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[2] = pws->w[3]; + pwd->w[0] = pwt->w[3]; + pwd->w[3] = pws->w[1]; + pwd->w[1] = pwt->w[1]; +#else + pwd->w[3] = pws->w[2]; + pwd->w[1] = pwt->w[2]; + pwd->w[2] = pws->w[0]; + pwd->w[0] = pwt->w[0]; +#endif +} + +void helper_msa_pckev_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[1] = pws->d[0]; + pwd->d[0] = pwt->d[0]; +} + + +void helper_msa_pckod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->b[7] = pwt->b[6]; + pwd->b[5] = pwt->b[2]; + pwd->b[3] = pwt->b[14]; + pwd->b[1] = pwt->b[10]; + pwd->b[15] = pws->b[6]; + pwd->b[13] = pws->b[2]; + pwd->b[11] = pws->b[14]; + pwd->b[9] = pws->b[10]; + pwd->b[6] = pwt->b[4]; + pwd->b[2] = pwt->b[12]; + pwd->b[14] = pws->b[4]; + pwd->b[10] = pws->b[12]; + pwd->b[4] = pwt->b[0]; + pwd->b[12] = pws->b[0]; + pwd->b[0] = pwt->b[8]; + pwd->b[8] = pws->b[8]; +#else + pwd->b[0] = pwt->b[1]; + pwd->b[2] = pwt->b[5]; + pwd->b[4] = pwt->b[9]; + pwd->b[6] = pwt->b[13]; + pwd->b[8] = pws->b[1]; + pwd->b[10] = pws->b[5]; + pwd->b[12] = pws->b[9]; + pwd->b[14] = pws->b[13]; + pwd->b[1] = pwt->b[3]; + pwd->b[5] = pwt->b[11]; + pwd->b[9] = pws->b[3]; + pwd->b[13] = pws->b[11]; + pwd->b[3] = pwt->b[7]; + pwd->b[11] = pws->b[7]; + pwd->b[7] = pwt->b[15]; + pwd->b[15] = pws->b[15]; +#endif + +} + +void helper_msa_pckod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->h[3] = pwt->h[2]; + pwd->h[1] = pwt->h[6]; + pwd->h[7] = pws->h[2]; + pwd->h[5] = pws->h[6]; + pwd->h[2] = pwt->h[0]; + pwd->h[6] = pws->h[0]; + pwd->h[0] = pwt->h[4]; + pwd->h[4] = pws->h[4]; +#else + pwd->h[0] = pwt->h[1]; + pwd->h[2] = pwt->h[5]; + pwd->h[4] = pws->h[1]; + pwd->h[6] = pws->h[5]; + pwd->h[1] = pwt->h[3]; + pwd->h[5] = pws->h[3]; + pwd->h[3] = pwt->h[7]; + pwd->h[7] = pws->h[7]; +#endif +} + +void helper_msa_pckod_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); + +#if defined(HOST_WORDS_BIGENDIAN) + pwd->w[1] = pwt->w[0]; + pwd->w[3] = pws->w[0]; + pwd->w[0] = pwt->w[2]; + pwd->w[2] = pws->w[2]; +#else + pwd->w[0] = pwt->w[1]; + pwd->w[2] = pws->w[1]; + pwd->w[1] = pwt->w[3]; + pwd->w[3] = pws->w[3]; +#endif +} + +void helper_msa_pckod_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] = pwt->d[1]; + pwd->d[1] = pws->d[1]; +} /* @@ -4675,183 +4882,6 @@ MSA_FN_DF(vshf_df) #undef MSA_FN_DF -void helper_msa_pckev_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[8] = pws->b[9]; - pwd->b[10] = pws->b[13]; - pwd->b[12] = pws->b[1]; - pwd->b[14] = pws->b[5]; - pwd->b[0] = pwt->b[9]; - pwd->b[2] = pwt->b[13]; - pwd->b[4] = pwt->b[1]; - pwd->b[6] = pwt->b[5]; - pwd->b[9] = pws->b[11]; - pwd->b[13] = pws->b[3]; - pwd->b[1] = pwt->b[11]; - pwd->b[5] = pwt->b[3]; - pwd->b[11] = pws->b[15]; - pwd->b[3] = pwt->b[15]; - pwd->b[15] = pws->b[7]; - pwd->b[7] = pwt->b[7]; -#else - pwd->b[15] = pws->b[14]; - pwd->b[13] = pws->b[10]; - pwd->b[11] = pws->b[6]; - pwd->b[9] = pws->b[2]; - pwd->b[7] = pwt->b[14]; - pwd->b[5] = pwt->b[10]; - pwd->b[3] = pwt->b[6]; - pwd->b[1] = pwt->b[2]; - pwd->b[14] = pws->b[12]; - pwd->b[10] = pws->b[4]; - pwd->b[6] = pwt->b[12]; - pwd->b[2] = pwt->b[4]; - pwd->b[12] = pws->b[8]; - pwd->b[4] = pwt->b[8]; - pwd->b[8] = pws->b[0]; - pwd->b[0] = pwt->b[0]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[4] = pws->h[5]; - pwd->h[6] = pws->h[1]; - pwd->h[0] = pwt->h[5]; - pwd->h[2] = pwt->h[1]; - pwd->h[5] = pws->h[7]; - pwd->h[1] = pwt->h[7]; - pwd->h[7] = pws->h[3]; - pwd->h[3] = pwt->h[3]; -#else - pwd->h[7] = pws->h[6]; - pwd->h[5] = pws->h[2]; - pwd->h[3] = pwt->h[6]; - pwd->h[1] = pwt->h[2]; - pwd->h[6] = pws->h[4]; - pwd->h[2] = pwt->h[4]; - pwd->h[4] = pws->h[0]; - pwd->h[0] = pwt->h[0]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[2] = pws->w[3]; - pwd->w[0] = pwt->w[3]; - pwd->w[3] = pws->w[1]; - pwd->w[1] = pwt->w[1]; -#else - pwd->w[3] = pws->w[2]; - pwd->w[1] = pwt->w[2]; - pwd->w[2] = pws->w[0]; - pwd->w[0] = pwt->w[0]; -#endif - break; - case DF_DOUBLE: - pwd->d[1] = pws->d[0]; - pwd->d[0] = pwt->d[0]; - break; - default: - assert(0); - } -} - -void helper_msa_pckod_df(CPUMIPSState *env, uint32_t df, 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); - - switch (df) { - case DF_BYTE: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->b[7] = pwt->b[6]; - pwd->b[5] = pwt->b[2]; - pwd->b[3] = pwt->b[14]; - pwd->b[1] = pwt->b[10]; - pwd->b[15] = pws->b[6]; - pwd->b[13] = pws->b[2]; - pwd->b[11] = pws->b[14]; - pwd->b[9] = pws->b[10]; - pwd->b[6] = pwt->b[4]; - pwd->b[2] = pwt->b[12]; - pwd->b[14] = pws->b[4]; - pwd->b[10] = pws->b[12]; - pwd->b[4] = pwt->b[0]; - pwd->b[12] = pws->b[0]; - pwd->b[0] = pwt->b[8]; - pwd->b[8] = pws->b[8]; -#else - pwd->b[0] = pwt->b[1]; - pwd->b[2] = pwt->b[5]; - pwd->b[4] = pwt->b[9]; - pwd->b[6] = pwt->b[13]; - pwd->b[8] = pws->b[1]; - pwd->b[10] = pws->b[5]; - pwd->b[12] = pws->b[9]; - pwd->b[14] = pws->b[13]; - pwd->b[1] = pwt->b[3]; - pwd->b[5] = pwt->b[11]; - pwd->b[9] = pws->b[3]; - pwd->b[13] = pws->b[11]; - pwd->b[3] = pwt->b[7]; - pwd->b[11] = pws->b[7]; - pwd->b[7] = pwt->b[15]; - pwd->b[15] = pws->b[15]; -#endif - break; - case DF_HALF: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->h[3] = pwt->h[2]; - pwd->h[1] = pwt->h[6]; - pwd->h[7] = pws->h[2]; - pwd->h[5] = pws->h[6]; - pwd->h[2] = pwt->h[0]; - pwd->h[6] = pws->h[0]; - pwd->h[0] = pwt->h[4]; - pwd->h[4] = pws->h[4]; -#else - pwd->h[0] = pwt->h[1]; - pwd->h[2] = pwt->h[5]; - pwd->h[4] = pws->h[1]; - pwd->h[6] = pws->h[5]; - pwd->h[1] = pwt->h[3]; - pwd->h[5] = pws->h[3]; - pwd->h[3] = pwt->h[7]; - pwd->h[7] = pws->h[7]; -#endif - break; - case DF_WORD: -#if defined(HOST_WORDS_BIGENDIAN) - pwd->w[1] = pwt->w[0]; - pwd->w[3] = pws->w[0]; - pwd->w[0] = pwt->w[2]; - pwd->w[2] = pws->w[2]; -#else - pwd->w[0] = pwt->w[1]; - pwd->w[2] = pws->w[1]; - pwd->w[1] = pwt->w[3]; - pwd->w[3] = pws->w[3]; -#endif - break; - case DF_DOUBLE: - pwd->d[0] = pwt->d[1]; - pwd->d[1] = pws->d[1]; - break; - default: - assert(0); - } -} - - void helper_msa_sldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd, uint32_t ws, uint32_t n) { diff --git a/target/mips/translate.c b/target/mips/translate.c index 7cdf68d21d..a57e0daeff 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28914,6 +28914,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_PCKEV_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_pckev_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_pckev_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_pckev_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_pckev_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_PCKOD_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_pckod_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_pckod_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_pckod_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_pckod_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_SLL_df: switch (df) { case DF_BYTE: @@ -29024,15 +29056,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_MSUBV_df: gen_helper_msa_msubv_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_PCKEV_df: - gen_helper_msa_pckev_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; - case OPC_PCKOD_df: - gen_helper_msa_pckod_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_ASUB_S_df: gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt); break; -- cgit 1.4.1 From b24b9aec96d655710f3f862d412208e938fa0618 Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:44 +0200 Subject: target/mips: msa: Split helpers for HSUB_. Achieves clearer code and slightly better performance. Signed-off-by: Aleksandar Markovic Reviewed-by: Aleksandar Rikalo Message-Id: <1571826227-10583-12-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 10 ++++- target/mips/msa_helper.c | 108 +++++++++++++++++++++++++++++++++++++++++------ target/mips/translate.c | 32 +++++++++++--- 3 files changed, 129 insertions(+), 21 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index 7bb13d5c3f..d7c4bbf77a 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 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) diff --git a/target/mips/translate.c b/target/mips/translate.c index a57e0daeff..4c68c5b980 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: -- cgit 1.4.1 From f392d1344e40840ff03a1f4c9ed135551ee28d9d Mon Sep 17 00:00:00 2001 From: Aleksandar Markovic Date: Wed, 23 Oct 2019 12:23:45 +0200 Subject: target/mips: msa: Split helpers for ASUB_. Achieves clearer code and slightly better performance. Signed-off-by: Aleksandar Markovic Reviewed-by: Aleksandar Rikalo Message-Id: <1571826227-10583-13-git-send-email-aleksandar.markovic@rt-rk.com> --- target/mips/helper.h | 12 +++- target/mips/msa_helper.c | 169 ++++++++++++++++++++++++++++++++++++++++++----- target/mips/translate.c | 38 +++++++++-- 3 files changed, 193 insertions(+), 26 deletions(-) (limited to 'target/mips/helper.h') diff --git a/target/mips/helper.h b/target/mips/helper.h index d7c4bbf77a..7b8ad74d67 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -945,6 +945,16 @@ 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_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) +DEF_HELPER_4(msa_asub_s_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_asub_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_asub_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_asub_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_asub_u_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) @@ -1053,8 +1063,6 @@ DEF_HELPER_5(msa_subs_s_df, void, env, i32, i32, i32, i32) 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_asub_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_asub_u_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_mulv_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_maddv_df, void, env, i32, i32, i32, i32) DEF_HELPER_5(msa_msubv_df, void, env, i32, i32, i32, i32) diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index ae9e8e04f4..0e39016764 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -2888,6 +2888,157 @@ void helper_msa_mod_u_d(CPUMIPSState *env, * +---------------+----------------------------------------------------------+ */ + +static inline int64_t msa_asub_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + /* signed compare */ + return (arg1 < arg2) ? + (uint64_t)(arg2 - arg1) : (uint64_t)(arg1 - arg2); +} + +void helper_msa_asub_s_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_asub_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_asub_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_asub_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_asub_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_asub_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_asub_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_asub_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_asub_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_asub_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_asub_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_asub_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_asub_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_asub_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_asub_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_asub_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_asub_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_asub_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_asub_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_asub_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_asub_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_asub_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_asub_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_asub_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_asub_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_asub_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_asub_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_asub_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_asub_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_asub_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_asub_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_asub_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_asub_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_asub_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline uint64_t msa_asub_u_df(uint32_t df, uint64_t arg1, uint64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t u_arg2 = UNSIGNED(arg2, df); + /* unsigned compare */ + return (u_arg1 < u_arg2) ? + (uint64_t)(u_arg2 - u_arg1) : (uint64_t)(u_arg1 - u_arg2); +} + +void helper_msa_asub_u_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_asub_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_asub_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_asub_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_asub_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_asub_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_asub_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_asub_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_asub_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_asub_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_asub_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_asub_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_asub_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_asub_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_asub_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_asub_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_asub_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_asub_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_asub_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_asub_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_asub_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_asub_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_asub_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_asub_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_asub_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_asub_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_asub_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_asub_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_asub_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_asub_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_asub_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_asub_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_asub_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_asub_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + /* TODO: insert the rest of Int Subtract group helpers here */ @@ -4447,22 +4598,6 @@ static inline int64_t msa_subsuu_s_df(uint32_t df, int64_t arg1, int64_t arg2) } } -static inline int64_t msa_asub_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - /* signed compare */ - return (arg1 < arg2) ? - (uint64_t)(arg2 - arg1) : (uint64_t)(arg1 - arg2); -} - -static inline uint64_t msa_asub_u_df(uint32_t df, uint64_t arg1, uint64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t u_arg2 = UNSIGNED(arg2, df); - /* unsigned compare */ - return (u_arg1 < u_arg2) ? - (uint64_t)(u_arg2 - u_arg1) : (uint64_t)(u_arg1 - u_arg2); -} - static inline int64_t msa_mulv_df(uint32_t df, int64_t arg1, int64_t arg2) { return arg1 * arg2; @@ -4624,8 +4759,6 @@ MSA_BINOP_DF(subs_s) MSA_BINOP_DF(subs_u) MSA_BINOP_DF(subsus_u) MSA_BINOP_DF(subsuu_s) -MSA_BINOP_DF(asub_s) -MSA_BINOP_DF(asub_u) MSA_BINOP_DF(mulv) MSA_BINOP_DF(dotp_s) MSA_BINOP_DF(dotp_u) diff --git a/target/mips/translate.c b/target/mips/translate.c index 4c68c5b980..20c69d2802 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -28850,6 +28850,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_ASUB_S_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_asub_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_asub_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_asub_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_asub_s_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_ASUB_U_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_asub_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_asub_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_asub_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_asub_u_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_ILVEV_df: switch (df) { case DF_BYTE: @@ -29059,12 +29091,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) case OPC_SUBSUU_S_df: gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt); break; - case OPC_ASUB_S_df: - gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_ASUB_U_df: - gen_helper_msa_asub_u_df(cpu_env, tdf, twd, tws, twt); - break; case OPC_DOTP_S_df: case OPC_DOTP_U_df: -- cgit 1.4.1