diff options
Diffstat (limited to 'target/mips')
| -rw-r--r-- | target/mips/dsp_helper.c | 40 | ||||
| -rw-r--r-- | target/mips/lmi_helper.c | 8 | ||||
| -rw-r--r-- | target/mips/msa_helper.c | 542 | ||||
| -rw-r--r-- | target/mips/translate.c | 152 |
4 files changed, 616 insertions, 126 deletions
diff --git a/target/mips/dsp_helper.c b/target/mips/dsp_helper.c index 739b69dd45..8c58eeb0bf 100644 --- a/target/mips/dsp_helper.c +++ b/target/mips/dsp_helper.c @@ -22,8 +22,10 @@ #include "exec/helper-proto.h" #include "qemu/bitops.h" -/* As the byte ordering doesn't matter, i.e. all columns are treated - identically, these unions can be used directly. */ +/* + * As the byte ordering doesn't matter, i.e. all columns are treated + * identically, these unions can be used directly. + */ typedef union { uint8_t ub[4]; int8_t sb[4]; @@ -1445,9 +1447,15 @@ target_ulong helper_precr_ob_qh(target_ulong rs, target_ulong rt) return temp; } -#define PRECR_QH_PW(name, var) \ -target_ulong helper_precr_##name##_qh_pw(target_ulong rs, target_ulong rt, \ - uint32_t sa) \ + +/* + * In case sa == 0, use rt2, rt0, rs2, rs0. + * In case sa != 0, use rt3, rt1, rs3, rs1. + */ +#define PRECR_QH_PW(name, var) \ +target_ulong helper_precr_##name##_qh_pw(target_ulong rs, \ + target_ulong rt, \ + uint32_t sa) \ { \ uint16_t rs3, rs2, rs1, rs0; \ uint16_t rt3, rt2, rt1, rt0; \ @@ -1456,8 +1464,6 @@ target_ulong helper_precr_##name##_qh_pw(target_ulong rs, target_ulong rt, \ MIPSDSP_SPLIT64_16(rs, rs3, rs2, rs1, rs0); \ MIPSDSP_SPLIT64_16(rt, rt3, rt2, rt1, rt0); \ \ - /* When sa = 0, we use rt2, rt0, rs2, rs0; \ - * when sa != 0, we use rt3, rt1, rs3, rs1. */ \ if (sa == 0) { \ tempD = rt2 << var; \ tempC = rt0 << var; \ @@ -1965,7 +1971,8 @@ SHIFT_PH(shra_r, rnd16_rashift); #undef SHIFT_PH /** DSP Multiply Sub-class insns **/ -/* Return value made up by two 16bits value. +/* + * Return value made up by two 16bits value. * FIXME give the macro a better name. */ #define MUL_RETURN32_16_PH(name, func, \ @@ -3274,11 +3281,15 @@ target_ulong helper_dextr_l(target_ulong ac, target_ulong shift, CPUMIPSState *env) { uint64_t temp[3]; + target_ulong ret; shift = shift & 0x3F; mipsdsp_rndrashift_acc(temp, ac, shift, env); - return (temp[1] << 63) | (temp[0] >> 1); + + ret = (temp[1] << 63) | (temp[0] >> 1); + + return ret; } target_ulong helper_dextr_r_l(target_ulong ac, target_ulong shift, @@ -3286,6 +3297,7 @@ target_ulong helper_dextr_r_l(target_ulong ac, target_ulong shift, { uint64_t temp[3]; uint32_t temp128; + target_ulong ret; shift = shift & 0x3F; mipsdsp_rndrashift_acc(temp, ac, shift, env); @@ -3305,7 +3317,9 @@ target_ulong helper_dextr_r_l(target_ulong ac, target_ulong shift, set_DSPControl_overflow_flag(1, 23, env); } - return (temp[1] << 63) | (temp[0] >> 1); + ret = (temp[1] << 63) | (temp[0] >> 1); + + return ret; } target_ulong helper_dextr_rs_l(target_ulong ac, target_ulong shift, @@ -3313,6 +3327,7 @@ target_ulong helper_dextr_rs_l(target_ulong ac, target_ulong shift, { uint64_t temp[3]; uint32_t temp128; + target_ulong ret; shift = shift & 0x3F; mipsdsp_rndrashift_acc(temp, ac, shift, env); @@ -3338,7 +3353,10 @@ target_ulong helper_dextr_rs_l(target_ulong ac, target_ulong shift, } set_DSPControl_overflow_flag(1, 23, env); } - return (temp[1] << 63) | (temp[0] >> 1); + + ret = (temp[1] << 63) | (temp[0] >> 1); + + return ret; } #endif diff --git a/target/mips/lmi_helper.c b/target/mips/lmi_helper.c index fb1245b39d..6c645cf679 100644 --- a/target/mips/lmi_helper.c +++ b/target/mips/lmi_helper.c @@ -21,9 +21,11 @@ #include "cpu.h" #include "exec/helper-proto.h" -/* If the byte ordering doesn't matter, i.e. all columns are treated - identically, then this union can be used directly. If byte ordering - does matter, we generally ignore dumping to memory. */ +/* + * If the byte ordering doesn't matter, i.e. all columns are treated + * identically, then this union can be used directly. If byte ordering + * does matter, we generally ignore dumping to memory. + */ typedef union { uint8_t ub[8]; int8_t sb[8]; diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index ee1b1fa5f5..f6e16c2405 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -805,28 +805,45 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, \ 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); \ - uint32_t i; \ \ switch (df) { \ case DF_BYTE: \ - for (i = 0; i < DF_ELEMENTS(DF_BYTE); i++) { \ - pwd->b[i] = msa_ ## func ## _df(df, pws->b[i], pwt->b[i]); \ - } \ + pwd->b[0] = msa_ ## func ## _df(df, pws->b[0], pwt->b[0]); \ + pwd->b[1] = msa_ ## func ## _df(df, pws->b[1], pwt->b[1]); \ + pwd->b[2] = msa_ ## func ## _df(df, pws->b[2], pwt->b[2]); \ + pwd->b[3] = msa_ ## func ## _df(df, pws->b[3], pwt->b[3]); \ + pwd->b[4] = msa_ ## func ## _df(df, pws->b[4], pwt->b[4]); \ + pwd->b[5] = msa_ ## func ## _df(df, pws->b[5], pwt->b[5]); \ + pwd->b[6] = msa_ ## func ## _df(df, pws->b[6], pwt->b[6]); \ + pwd->b[7] = msa_ ## func ## _df(df, pws->b[7], pwt->b[7]); \ + pwd->b[8] = msa_ ## func ## _df(df, pws->b[8], pwt->b[8]); \ + pwd->b[9] = msa_ ## func ## _df(df, pws->b[9], pwt->b[9]); \ + pwd->b[10] = msa_ ## func ## _df(df, pws->b[10], pwt->b[10]); \ + pwd->b[11] = msa_ ## func ## _df(df, pws->b[11], pwt->b[11]); \ + pwd->b[12] = msa_ ## func ## _df(df, pws->b[12], pwt->b[12]); \ + pwd->b[13] = msa_ ## func ## _df(df, pws->b[13], pwt->b[13]); \ + pwd->b[14] = msa_ ## func ## _df(df, pws->b[14], pwt->b[14]); \ + pwd->b[15] = msa_ ## func ## _df(df, pws->b[15], pwt->b[15]); \ break; \ case DF_HALF: \ - for (i = 0; i < DF_ELEMENTS(DF_HALF); i++) { \ - pwd->h[i] = msa_ ## func ## _df(df, pws->h[i], pwt->h[i]); \ - } \ + pwd->h[0] = msa_ ## func ## _df(df, pws->h[0], pwt->h[0]); \ + pwd->h[1] = msa_ ## func ## _df(df, pws->h[1], pwt->h[1]); \ + pwd->h[2] = msa_ ## func ## _df(df, pws->h[2], pwt->h[2]); \ + pwd->h[3] = msa_ ## func ## _df(df, pws->h[3], pwt->h[3]); \ + pwd->h[4] = msa_ ## func ## _df(df, pws->h[4], pwt->h[4]); \ + pwd->h[5] = msa_ ## func ## _df(df, pws->h[5], pwt->h[5]); \ + pwd->h[6] = msa_ ## func ## _df(df, pws->h[6], pwt->h[6]); \ + pwd->h[7] = msa_ ## func ## _df(df, pws->h[7], pwt->h[7]); \ break; \ case DF_WORD: \ - for (i = 0; i < DF_ELEMENTS(DF_WORD); i++) { \ - pwd->w[i] = msa_ ## func ## _df(df, pws->w[i], pwt->w[i]); \ - } \ + pwd->w[0] = msa_ ## func ## _df(df, pws->w[0], pwt->w[0]); \ + pwd->w[1] = msa_ ## func ## _df(df, pws->w[1], pwt->w[1]); \ + pwd->w[2] = msa_ ## func ## _df(df, pws->w[2], pwt->w[2]); \ + pwd->w[3] = msa_ ## func ## _df(df, pws->w[3], pwt->w[3]); \ break; \ case DF_DOUBLE: \ - for (i = 0; i < DF_ELEMENTS(DF_DOUBLE); i++) { \ - pwd->d[i] = msa_ ## func ## _df(df, pws->d[i], pwt->d[i]); \ - } \ + pwd->d[0] = msa_ ## func ## _df(df, pws->d[0], pwt->d[0]); \ + pwd->d[1] = msa_ ## func ## _df(df, pws->d[1], pwt->d[1]); \ break; \ default: \ assert(0); \ @@ -1012,42 +1029,71 @@ static inline int64_t msa_msubr_q_df(uint32_t df, int64_t dest, int64_t arg1, } #define MSA_TEROP_DF(func) \ -void helper_msa_ ## func ## _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); \ - uint32_t i; \ - \ - switch (df) { \ - case DF_BYTE: \ - for (i = 0; i < DF_ELEMENTS(DF_BYTE); i++) { \ - pwd->b[i] = msa_ ## func ## _df(df, pwd->b[i], pws->b[i], \ - pwt->b[i]); \ - } \ - break; \ - case DF_HALF: \ - for (i = 0; i < DF_ELEMENTS(DF_HALF); i++) { \ - pwd->h[i] = msa_ ## func ## _df(df, pwd->h[i], pws->h[i], \ - pwt->h[i]); \ - } \ - break; \ - case DF_WORD: \ - for (i = 0; i < DF_ELEMENTS(DF_WORD); i++) { \ - pwd->w[i] = msa_ ## func ## _df(df, pwd->w[i], pws->w[i], \ - pwt->w[i]); \ - } \ - break; \ - case DF_DOUBLE: \ - for (i = 0; i < DF_ELEMENTS(DF_DOUBLE); i++) { \ - pwd->d[i] = msa_ ## func ## _df(df, pwd->d[i], pws->d[i], \ - pwt->d[i]); \ - } \ - break; \ - default: \ - assert(0); \ - } \ +void helper_msa_ ## func ## _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: \ + pwd->b[0] = msa_ ## func ## _df(df, pwd->b[0], pws->b[0], \ + pwt->b[0]); \ + pwd->b[1] = msa_ ## func ## _df(df, pwd->b[1], pws->b[1], \ + pwt->b[1]); \ + pwd->b[2] = msa_ ## func ## _df(df, pwd->b[2], pws->b[2], \ + pwt->b[2]); \ + pwd->b[3] = msa_ ## func ## _df(df, pwd->b[3], pws->b[3], \ + pwt->b[3]); \ + pwd->b[4] = msa_ ## func ## _df(df, pwd->b[4], pws->b[4], \ + pwt->b[4]); \ + pwd->b[5] = msa_ ## func ## _df(df, pwd->b[5], pws->b[5], \ + pwt->b[5]); \ + pwd->b[6] = msa_ ## func ## _df(df, pwd->b[6], pws->b[6], \ + pwt->b[6]); \ + pwd->b[7] = msa_ ## func ## _df(df, pwd->b[7], pws->b[7], \ + pwt->b[7]); \ + pwd->b[8] = msa_ ## func ## _df(df, pwd->b[8], pws->b[8], \ + pwt->b[8]); \ + pwd->b[9] = msa_ ## func ## _df(df, pwd->b[9], pws->b[9], \ + pwt->b[9]); \ + pwd->b[10] = msa_ ## func ## _df(df, pwd->b[10], pws->b[10], \ + pwt->b[10]); \ + pwd->b[11] = msa_ ## func ## _df(df, pwd->b[11], pws->b[11], \ + pwt->b[11]); \ + pwd->b[12] = msa_ ## func ## _df(df, pwd->b[12], pws->b[12], \ + pwt->b[12]); \ + pwd->b[13] = msa_ ## func ## _df(df, pwd->b[13], pws->b[13], \ + pwt->b[13]); \ + pwd->b[14] = msa_ ## func ## _df(df, pwd->b[14], pws->b[14], \ + pwt->b[14]); \ + pwd->b[15] = msa_ ## func ## _df(df, pwd->b[15], pws->b[15], \ + pwt->b[15]); \ + break; \ + case DF_HALF: \ + pwd->h[0] = msa_ ## func ## _df(df, pwd->h[0], pws->h[0], pwt->h[0]); \ + pwd->h[1] = msa_ ## func ## _df(df, pwd->h[1], pws->h[1], pwt->h[1]); \ + pwd->h[2] = msa_ ## func ## _df(df, pwd->h[2], pws->h[2], pwt->h[2]); \ + pwd->h[3] = msa_ ## func ## _df(df, pwd->h[3], pws->h[3], pwt->h[3]); \ + pwd->h[4] = msa_ ## func ## _df(df, pwd->h[4], pws->h[4], pwt->h[4]); \ + pwd->h[5] = msa_ ## func ## _df(df, pwd->h[5], pws->h[5], pwt->h[5]); \ + pwd->h[6] = msa_ ## func ## _df(df, pwd->h[6], pws->h[6], pwt->h[6]); \ + pwd->h[7] = msa_ ## func ## _df(df, pwd->h[7], pws->h[7], pwt->h[7]); \ + break; \ + case DF_WORD: \ + pwd->w[0] = msa_ ## func ## _df(df, pwd->w[0], pws->w[0], pwt->w[0]); \ + pwd->w[1] = msa_ ## func ## _df(df, pwd->w[1], pws->w[1], pwt->w[1]); \ + pwd->w[2] = msa_ ## func ## _df(df, pwd->w[2], pws->w[2], pwt->w[2]); \ + pwd->w[3] = msa_ ## func ## _df(df, pwd->w[3], pws->w[3], pwt->w[3]); \ + break; \ + case DF_DOUBLE: \ + pwd->d[0] = msa_ ## func ## _df(df, pwd->d[0], pws->d[0], pwt->d[0]); \ + pwd->d[1] = msa_ ## func ## _df(df, pwd->d[1], pws->d[1], pwt->d[1]); \ + break; \ + default: \ + assert(0); \ + } \ } MSA_TEROP_DF(maddv) @@ -1167,53 +1213,6 @@ void helper_msa_##FUNC(CPUMIPSState *env, uint32_t df, uint32_t wd, \ #define Rd(pwr, i) (pwr->d[i]) #define Ld(pwr, i) (pwr->d[i + DF_ELEMENTS(DF_DOUBLE)/2]) -#define MSA_DO(DF) \ - do { \ - R##DF(pwx, i) = pwt->DF[2*i]; \ - L##DF(pwx, i) = pws->DF[2*i]; \ - } while (0) -MSA_FN_DF(pckev_df) -#undef MSA_DO - -#define MSA_DO(DF) \ - do { \ - R##DF(pwx, i) = pwt->DF[2*i+1]; \ - L##DF(pwx, i) = pws->DF[2*i+1]; \ - } while (0) -MSA_FN_DF(pckod_df) -#undef MSA_DO - -#define MSA_DO(DF) \ - do { \ - pwx->DF[2*i] = L##DF(pwt, i); \ - pwx->DF[2*i+1] = L##DF(pws, i); \ - } while (0) -MSA_FN_DF(ilvl_df) -#undef MSA_DO - -#define MSA_DO(DF) \ - do { \ - pwx->DF[2*i] = R##DF(pwt, i); \ - pwx->DF[2*i+1] = R##DF(pws, i); \ - } while (0) -MSA_FN_DF(ilvr_df) -#undef MSA_DO - -#define MSA_DO(DF) \ - do { \ - pwx->DF[2*i] = pwt->DF[2*i]; \ - pwx->DF[2*i+1] = pws->DF[2*i]; \ - } while (0) -MSA_FN_DF(ilvev_df) -#undef MSA_DO - -#define MSA_DO(DF) \ - do { \ - pwx->DF[2*i] = pwt->DF[2*i+1]; \ - pwx->DF[2*i+1] = pws->DF[2*i+1]; \ - } while (0) -MSA_FN_DF(ilvod_df) -#undef MSA_DO #undef MSA_LOOP_COND #define MSA_LOOP_COND(DF) \ @@ -1231,6 +1230,314 @@ MSA_FN_DF(vshf_df) #undef MSA_LOOP_COND #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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[3] = pws->w[2]; + pwd->w[2] = pwt->w[2]; + pwd->w[1] = pws->w[0]; + pwd->w[0] = pwt->w[0]; + 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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[0] = pwt->w[1]; + pwd->w[1] = pws->w[1]; + pwd->w[2] = pwt->w[3]; + pwd->w[3] = pws->w[3]; + 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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[0] = pwt->w[2]; + pwd->w[1] = pws->w[2]; + pwd->w[2] = pwt->w[3]; + pwd->w[3] = pws->w[3]; + 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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[3] = pws->w[1]; + pwd->w[2] = pwt->w[1]; + pwd->w[1] = pws->w[0]; + pwd->w[0] = pwt->w[0]; + 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) +{ + 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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[3] = pws->w[2]; + pwd->w[1] = pwt->w[2]; + pwd->w[2] = pws->w[0]; + pwd->w[0] = pwt->w[0]; + 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: + 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]; + break; + case DF_HALF: + 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]; + break; + case DF_WORD: + pwd->w[0] = pwt->w[1]; + pwd->w[2] = pws->w[1]; + pwd->w[1] = pwt->w[3]; + pwd->w[3] = pws->w[3]; + 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) { @@ -1537,28 +1844,45 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, \ { \ wr_t *pwd = &(env->active_fpu.fpr[wd].wr); \ wr_t *pws = &(env->active_fpu.fpr[ws].wr); \ - uint32_t i; \ \ switch (df) { \ case DF_BYTE: \ - for (i = 0; i < DF_ELEMENTS(DF_BYTE); i++) { \ - pwd->b[i] = msa_ ## func ## _df(df, pws->b[i]); \ - } \ + pwd->b[0] = msa_ ## func ## _df(df, pws->b[0]); \ + pwd->b[1] = msa_ ## func ## _df(df, pws->b[1]); \ + pwd->b[2] = msa_ ## func ## _df(df, pws->b[2]); \ + pwd->b[3] = msa_ ## func ## _df(df, pws->b[3]); \ + pwd->b[4] = msa_ ## func ## _df(df, pws->b[4]); \ + pwd->b[5] = msa_ ## func ## _df(df, pws->b[5]); \ + pwd->b[6] = msa_ ## func ## _df(df, pws->b[6]); \ + pwd->b[7] = msa_ ## func ## _df(df, pws->b[7]); \ + pwd->b[8] = msa_ ## func ## _df(df, pws->b[8]); \ + pwd->b[9] = msa_ ## func ## _df(df, pws->b[9]); \ + pwd->b[10] = msa_ ## func ## _df(df, pws->b[10]); \ + pwd->b[11] = msa_ ## func ## _df(df, pws->b[11]); \ + pwd->b[12] = msa_ ## func ## _df(df, pws->b[12]); \ + pwd->b[13] = msa_ ## func ## _df(df, pws->b[13]); \ + pwd->b[14] = msa_ ## func ## _df(df, pws->b[14]); \ + pwd->b[15] = msa_ ## func ## _df(df, pws->b[15]); \ break; \ case DF_HALF: \ - for (i = 0; i < DF_ELEMENTS(DF_HALF); i++) { \ - pwd->h[i] = msa_ ## func ## _df(df, pws->h[i]); \ - } \ + pwd->h[0] = msa_ ## func ## _df(df, pws->h[0]); \ + pwd->h[1] = msa_ ## func ## _df(df, pws->h[1]); \ + pwd->h[2] = msa_ ## func ## _df(df, pws->h[2]); \ + pwd->h[3] = msa_ ## func ## _df(df, pws->h[3]); \ + pwd->h[4] = msa_ ## func ## _df(df, pws->h[4]); \ + pwd->h[5] = msa_ ## func ## _df(df, pws->h[5]); \ + pwd->h[6] = msa_ ## func ## _df(df, pws->h[6]); \ + pwd->h[7] = msa_ ## func ## _df(df, pws->h[7]); \ break; \ case DF_WORD: \ - for (i = 0; i < DF_ELEMENTS(DF_WORD); i++) { \ - pwd->w[i] = msa_ ## func ## _df(df, pws->w[i]); \ - } \ + pwd->w[0] = msa_ ## func ## _df(df, pws->w[0]); \ + pwd->w[1] = msa_ ## func ## _df(df, pws->w[1]); \ + pwd->w[2] = msa_ ## func ## _df(df, pws->w[2]); \ + pwd->w[3] = msa_ ## func ## _df(df, pws->w[3]); \ break; \ case DF_DOUBLE: \ - for (i = 0; i < DF_ELEMENTS(DF_DOUBLE); i++) { \ - pwd->d[i] = msa_ ## func ## _df(df, pws->d[i]); \ - } \ + pwd->d[0] = msa_ ## func ## _df(df, pws->d[0]); \ + pwd->d[1] = msa_ ## func ## _df(df, pws->d[1]); \ break; \ default: \ assert(0); \ diff --git a/target/mips/translate.c b/target/mips/translate.c index 70552fe543..e37722dfff 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -24357,6 +24357,146 @@ static void decode_opc_special(CPUMIPSState *env, DisasContext *ctx) * PEXTUW */ +/* + * PCPYH rd, rt + * + * Parallel Copy Halfword + * + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-----------+---------+---------+---------+---------+-----------+ + * | MMI |0 0 0 0 0| rt | rd | PCPYH | MMI3 | + * +-----------+---------+---------+---------+---------+-----------+ + */ +static void gen_mmi_pcpyh(DisasContext *ctx) +{ + uint32_t pd, rt, rd; + uint32_t opcode; + + opcode = ctx->opcode; + + pd = extract32(opcode, 21, 5); + rt = extract32(opcode, 16, 5); + rd = extract32(opcode, 11, 5); + + if (unlikely(pd != 0)) { + generate_exception_end(ctx, EXCP_RI); + } else if (rd == 0) { + /* nop */ + } else if (rt == 0) { + tcg_gen_movi_i64(cpu_gpr[rd], 0); + tcg_gen_movi_i64(cpu_mmr[rd], 0); + } else { + TCGv_i64 t0 = tcg_temp_new(); + TCGv_i64 t1 = tcg_temp_new(); + uint64_t mask = (1ULL << 16) - 1; + + tcg_gen_andi_i64(t0, cpu_gpr[rt], mask); + tcg_gen_movi_i64(t1, 0); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + + tcg_gen_mov_i64(cpu_gpr[rd], t1); + + tcg_gen_andi_i64(t0, cpu_mmr[rt], mask); + tcg_gen_movi_i64(t1, 0); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + tcg_gen_shli_i64(t0, t0, 16); + tcg_gen_or_i64(t1, t0, t1); + + tcg_gen_mov_i64(cpu_mmr[rd], t1); + + tcg_temp_free(t0); + tcg_temp_free(t1); + } +} + +/* + * PCPYLD rd, rs, rt + * + * Parallel Copy Lower Doubleword + * + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-----------+---------+---------+---------+---------+-----------+ + * | MMI | rs | rt | rd | PCPYLD | MMI2 | + * +-----------+---------+---------+---------+---------+-----------+ + */ +static void gen_mmi_pcpyld(DisasContext *ctx) +{ + uint32_t rs, rt, rd; + uint32_t opcode; + + opcode = ctx->opcode; + + rs = extract32(opcode, 21, 5); + rt = extract32(opcode, 16, 5); + rd = extract32(opcode, 11, 5); + + if (rd == 0) { + /* nop */ + } else { + if (rs == 0) { + tcg_gen_movi_i64(cpu_mmr[rd], 0); + } else { + tcg_gen_mov_i64(cpu_mmr[rd], cpu_gpr[rs]); + } + if (rt == 0) { + tcg_gen_movi_i64(cpu_gpr[rd], 0); + } else { + if (rd != rt) { + tcg_gen_mov_i64(cpu_gpr[rd], cpu_gpr[rt]); + } + } + } +} + +/* + * PCPYUD rd, rs, rt + * + * Parallel Copy Upper Doubleword + * + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * +-----------+---------+---------+---------+---------+-----------+ + * | MMI | rs | rt | rd | PCPYUD | MMI3 | + * +-----------+---------+---------+---------+---------+-----------+ + */ +static void gen_mmi_pcpyud(DisasContext *ctx) +{ + uint32_t rs, rt, rd; + uint32_t opcode; + + opcode = ctx->opcode; + + rs = extract32(opcode, 21, 5); + rt = extract32(opcode, 16, 5); + rd = extract32(opcode, 11, 5); + + if (rd == 0) { + /* nop */ + } else { + if (rs == 0) { + tcg_gen_movi_i64(cpu_gpr[rd], 0); + } else { + tcg_gen_mov_i64(cpu_gpr[rd], cpu_mmr[rs]); + } + if (rt == 0) { + tcg_gen_movi_i64(cpu_mmr[rd], 0); + } else { + if (rd != rt) { + tcg_gen_mov_i64(cpu_mmr[rd], cpu_mmr[rt]); + } + } + } +} + #endif @@ -27371,7 +27511,6 @@ static void decode_mmi2(CPUMIPSState *env, DisasContext *ctx) case MMI_OPC_2_PINTH: /* TODO: MMI_OPC_2_PINTH */ case MMI_OPC_2_PMULTW: /* TODO: MMI_OPC_2_PMULTW */ case MMI_OPC_2_PDIVW: /* TODO: MMI_OPC_2_PDIVW */ - case MMI_OPC_2_PCPYLD: /* TODO: MMI_OPC_2_PCPYLD */ case MMI_OPC_2_PMADDH: /* TODO: MMI_OPC_2_PMADDH */ case MMI_OPC_2_PHMADH: /* TODO: MMI_OPC_2_PHMADH */ case MMI_OPC_2_PAND: /* TODO: MMI_OPC_2_PAND */ @@ -27386,6 +27525,9 @@ static void decode_mmi2(CPUMIPSState *env, DisasContext *ctx) case MMI_OPC_2_PROT3W: /* TODO: MMI_OPC_2_PROT3W */ generate_exception_end(ctx, EXCP_RI); /* TODO: MMI_OPC_CLASS_MMI2 */ break; + case MMI_OPC_2_PCPYLD: + gen_mmi_pcpyld(ctx); + break; default: MIPS_INVAL("TX79 MMI class MMI2"); generate_exception_end(ctx, EXCP_RI); @@ -27405,14 +27547,18 @@ static void decode_mmi3(CPUMIPSState *env, DisasContext *ctx) case MMI_OPC_3_PINTEH: /* TODO: MMI_OPC_3_PINTEH */ case MMI_OPC_3_PMULTUW: /* TODO: MMI_OPC_3_PMULTUW */ case MMI_OPC_3_PDIVUW: /* TODO: MMI_OPC_3_PDIVUW */ - case MMI_OPC_3_PCPYUD: /* TODO: MMI_OPC_3_PCPYUD */ case MMI_OPC_3_POR: /* TODO: MMI_OPC_3_POR */ case MMI_OPC_3_PNOR: /* TODO: MMI_OPC_3_PNOR */ case MMI_OPC_3_PEXCH: /* TODO: MMI_OPC_3_PEXCH */ - case MMI_OPC_3_PCPYH: /* TODO: MMI_OPC_3_PCPYH */ case MMI_OPC_3_PEXCW: /* TODO: MMI_OPC_3_PEXCW */ generate_exception_end(ctx, EXCP_RI); /* TODO: MMI_OPC_CLASS_MMI3 */ break; + case MMI_OPC_3_PCPYH: + gen_mmi_pcpyh(ctx); + break; + case MMI_OPC_3_PCPYUD: + gen_mmi_pcpyud(ctx); + break; default: MIPS_INVAL("TX79 MMI class MMI3"); generate_exception_end(ctx, EXCP_RI); |