diff options
| -rw-r--r-- | MAINTAINERS | 8 | ||||
| -rw-r--r-- | po/sv.po | 75 | ||||
| -rw-r--r-- | target/mips/helper.h | 73 | ||||
| -rw-r--r-- | target/mips/mips-defs.h | 8 | ||||
| -rw-r--r-- | target/mips/msa_helper.c | 1116 | ||||
| -rw-r--r-- | target/mips/translate.c | 213 |
6 files changed, 1274 insertions, 219 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 9ec50e165d..b0549a556a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -296,7 +296,7 @@ F: tests/tcg/s390x/ L: qemu-s390x@nongnu.org SH4 TCG CPUs -M: Aurelien Jarno <aurelien@aurel32.net> +M: Yoshinori Sato <ysato@users.sourceforge.jp> S: Odd Fixes F: target/sh4/ F: hw/sh4/ @@ -1253,14 +1253,16 @@ F: include/hw/riscv/opentitan.h SH4 Machines ------------ R2D -M: Magnus Damm <magnus.damm@gmail.com> +M: Yoshinori Sato <ysato@users.sourceforge.jp> +R: Magnus Damm <magnus.damm@gmail.com> S: Maintained F: hw/sh4/r2d.c F: hw/intc/sh_intc.c F: hw/timer/sh_timer.c Shix -M: Magnus Damm <magnus.damm@gmail.com> +M: Yoshinori Sato <ysato@users.sourceforge.jp> +R: Magnus Damm <magnus.damm@gmail.com> S: Odd Fixes F: hw/sh4/shix.c diff --git a/po/sv.po b/po/sv.po new file mode 100644 index 0000000000..1e430edd65 --- /dev/null +++ b/po/sv.po @@ -0,0 +1,75 @@ +# Swedish translation of qemu po-file. +# This file is put in the public domain. +# Sebastian Rasmussen <sebras@gmail.com>, 2019. +# +msgid "" +msgstr "" +"Project-Id-Version: QEMU 2.12.91\n" +"Report-Msgid-Bugs-To: qemu-devel@nongnu.org\n" +"POT-Creation-Date: 2018-07-18 07:56+0200\n" +"PO-Revision-Date: 2019-08-16 21:19+0200\n" +"Last-Translator: Sebastian Rasmussen <sebras@gmail.com>\n" +"Language-Team: Swedish <tp-sv@listor.tp-sv.se>\n" +"Language: sv\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=UTF-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=2; plural=(n != 1);\n" +"X-Generator: Poedit 2.2.3\n" + +msgid " - Press Ctrl+Alt+G to release grab" +msgstr " - Tryck Ctrl+Alt+G för att sluta fånga" + +msgid " [Paused]" +msgstr " [Pausad]" + +msgid "_Pause" +msgstr "_Paus" + +msgid "_Reset" +msgstr "_Starta om" + +msgid "Power _Down" +msgstr "Stäng _ner" + +msgid "_Quit" +msgstr "_Avsluta" + +msgid "_Fullscreen" +msgstr "_Helskärm" + +msgid "_Copy" +msgstr "_Kopiera" + +msgid "Zoom _In" +msgstr "Zooma _in" + +msgid "Zoom _Out" +msgstr "Zooma _ut" + +msgid "Best _Fit" +msgstr "Anpassad _storlek" + +msgid "Zoom To _Fit" +msgstr "Zooma ti_ll anpassad storlek" + +msgid "Grab On _Hover" +msgstr "Fånga vi_d hovring" + +msgid "_Grab Input" +msgstr "Fån_ga inmatning" + +msgid "Show _Tabs" +msgstr "Visa _flika" + +msgid "Detach Tab" +msgstr "Frigör flik" + +msgid "Show Menubar" +msgstr "Visa menyrad" + +msgid "_Machine" +msgstr "_Maskin" + +msgid "_View" +msgstr "_Visa" diff --git a/target/mips/helper.h b/target/mips/helper.h index 84fdd9fd27..e97655dc0e 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -950,6 +950,21 @@ 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_maddv_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_maddv_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_maddv_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_maddv_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_msubv_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_msubv_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_msubv_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_msubv_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_mulv_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_mulv_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_mulv_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_mulv_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) @@ -968,6 +983,31 @@ 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_subs_s_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_s_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_subs_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subs_u_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_subsus_u_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsus_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsus_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsus_u_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_subsuu_s_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsuu_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsuu_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subsuu_s_d, void, env, i32, i32, i32) + +DEF_HELPER_4(msa_subv_b, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subv_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subv_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_subv_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) @@ -1063,20 +1103,25 @@ DEF_HELPER_5(msa_srlri_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) -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_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) -DEF_HELPER_5(msa_dotp_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_dotp_u_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_dpadd_s_df, void, env, i32, i32, i32, i32) -DEF_HELPER_5(msa_dpadd_u_df, void, env, i32, i32, i32, i32) -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_4(msa_dotp_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dotp_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dotp_s_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dotp_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dotp_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dotp_u_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_s_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpadd_u_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_s_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_s_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_s_d, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_u_h, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_u_w, void, env, i32, i32, i32) +DEF_HELPER_4(msa_dpsub_u_d, void, env, 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) diff --git a/target/mips/mips-defs.h b/target/mips/mips-defs.h index 0c129106c8..ed6a7a9e54 100644 --- a/target/mips/mips-defs.h +++ b/target/mips/mips-defs.h @@ -57,9 +57,13 @@ /* * bits 52-63: vendor-specific ASEs */ +/* MultiMedia Instructions defined by R5900 */ #define ASE_MMI 0x0010000000000000ULL +/* MIPS eXtension/enhanced Unit defined by Ingenic */ #define ASE_MXU 0x0020000000000000ULL +/* Loongson MultiMedia Instructions */ #define ASE_LMMI 0x0040000000000000ULL +/* Loongson EXTensions */ #define ASE_LEXT 0x0080000000000000ULL /* MIPS CPU defines. */ @@ -70,7 +74,7 @@ #define CPU_VR54XX (CPU_MIPS4 | INSN_VR54XX) #define CPU_R5900 (CPU_MIPS3 | INSN_R5900) #define CPU_LOONGSON2E (CPU_MIPS3 | INSN_LOONGSON2E) -#define CPU_LOONGSON2F (CPU_MIPS3 | INSN_LOONGSON2F) +#define CPU_LOONGSON2F (CPU_MIPS3 | INSN_LOONGSON2F | ASE_LMMI) #define CPU_MIPS5 (CPU_MIPS4 | ISA_MIPS5) @@ -97,7 +101,7 @@ /* Wave Computing: "nanoMIPS" */ #define CPU_NANOMIPS32 (CPU_MIPS32R6 | ISA_NANOMIPS32) -#define CPU_LOONGSON3A (CPU_MIPS64R2 | INSN_LOONGSON3A) +#define CPU_LOONGSON3A (CPU_MIPS64R2 | INSN_LOONGSON3A | ASE_LMMI | ASE_LEXT) /* * Strictly follow the architecture standard: diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index c3b271934a..6865addaf6 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -2224,7 +2224,339 @@ void helper_msa_div_u_d(CPUMIPSState *env, * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Int Dot Product group helpers here */ +#define SIGNED_EXTRACT(e, o, a, df) \ + do { \ + e = SIGNED_EVEN(a, df); \ + o = SIGNED_ODD(a, df); \ + } while (0) + +#define UNSIGNED_EXTRACT(e, o, a, df) \ + do { \ + e = UNSIGNED_EVEN(a, df); \ + o = UNSIGNED_ODD(a, df); \ + } while (0) + + +static inline int64_t msa_dotp_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); +} + +void helper_msa_dotp_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_dotp_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dotp_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dotp_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dotp_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dotp_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dotp_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dotp_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dotp_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_dotp_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_dotp_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dotp_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dotp_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dotp_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_dotp_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_dotp_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dotp_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_dotp_u_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); +} + +void helper_msa_dotp_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_dotp_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dotp_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dotp_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dotp_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dotp_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dotp_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dotp_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dotp_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_dotp_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_dotp_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dotp_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dotp_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dotp_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_dotp_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_dotp_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dotp_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_dpadd_s_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return dest + (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); +} + +void helper_msa_dpadd_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_dpadd_s_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dpadd_s_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dpadd_s_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dpadd_s_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dpadd_s_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dpadd_s_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dpadd_s_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dpadd_s_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_dpadd_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_dpadd_s_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dpadd_s_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dpadd_s_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dpadd_s_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_dpadd_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_dpadd_s_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dpadd_s_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_dpadd_u_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return dest + (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); +} + +void helper_msa_dpadd_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_dpadd_u_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dpadd_u_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dpadd_u_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dpadd_u_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dpadd_u_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dpadd_u_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dpadd_u_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dpadd_u_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_dpadd_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_dpadd_u_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dpadd_u_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dpadd_u_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dpadd_u_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_dpadd_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_dpadd_u_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dpadd_u_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_dpsub_s_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return dest - ((even_arg1 * even_arg2) + (odd_arg1 * odd_arg2)); +} + +void helper_msa_dpsub_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_dpsub_s_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dpsub_s_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dpsub_s_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dpsub_s_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dpsub_s_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dpsub_s_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dpsub_s_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dpsub_s_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_dpsub_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_dpsub_s_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dpsub_s_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dpsub_s_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dpsub_s_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_dpsub_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_dpsub_s_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dpsub_s_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_dpsub_u_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + int64_t even_arg1; + int64_t even_arg2; + int64_t odd_arg1; + int64_t odd_arg2; + UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); + UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); + return dest - ((even_arg1 * even_arg2) + (odd_arg1 * odd_arg2)); +} + +void helper_msa_dpsub_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_dpsub_u_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_dpsub_u_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_dpsub_u_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_dpsub_u_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_dpsub_u_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_dpsub_u_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_dpsub_u_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_dpsub_u_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_dpsub_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_dpsub_u_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_dpsub_u_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_dpsub_u_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_dpsub_u_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_dpsub_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_dpsub_u_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_dpsub_u_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} /* @@ -2883,7 +3215,221 @@ void helper_msa_mod_u_d(CPUMIPSState *env, * +---------------+----------------------------------------------------------+ */ -/* TODO: insert Int Multiply group helpers here */ +static inline int64_t msa_maddv_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + return dest + arg1 * arg2; +} + +void helper_msa_maddv_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_maddv_df(DF_BYTE, pwt->b[0], pws->b[0], pwt->b[0]); + pwd->b[1] = msa_maddv_df(DF_BYTE, pwt->b[1], pws->b[1], pwt->b[1]); + pwd->b[2] = msa_maddv_df(DF_BYTE, pwt->b[2], pws->b[2], pwt->b[2]); + pwd->b[3] = msa_maddv_df(DF_BYTE, pwt->b[3], pws->b[3], pwt->b[3]); + pwd->b[4] = msa_maddv_df(DF_BYTE, pwt->b[4], pws->b[4], pwt->b[4]); + pwd->b[5] = msa_maddv_df(DF_BYTE, pwt->b[5], pws->b[5], pwt->b[5]); + pwd->b[6] = msa_maddv_df(DF_BYTE, pwt->b[6], pws->b[6], pwt->b[6]); + pwd->b[7] = msa_maddv_df(DF_BYTE, pwt->b[7], pws->b[7], pwt->b[7]); + pwd->b[8] = msa_maddv_df(DF_BYTE, pwt->b[8], pws->b[8], pwt->b[8]); + pwd->b[9] = msa_maddv_df(DF_BYTE, pwt->b[9], pws->b[9], pwt->b[9]); + pwd->b[10] = msa_maddv_df(DF_BYTE, pwt->b[10], pws->b[10], pwt->b[10]); + pwd->b[11] = msa_maddv_df(DF_BYTE, pwt->b[11], pws->b[11], pwt->b[11]); + pwd->b[12] = msa_maddv_df(DF_BYTE, pwt->b[12], pws->b[12], pwt->b[12]); + pwd->b[13] = msa_maddv_df(DF_BYTE, pwt->b[13], pws->b[13], pwt->b[13]); + pwd->b[14] = msa_maddv_df(DF_BYTE, pwt->b[14], pws->b[14], pwt->b[14]); + pwd->b[15] = msa_maddv_df(DF_BYTE, pwt->b[15], pws->b[15], pwt->b[15]); +} + +void helper_msa_maddv_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_maddv_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_maddv_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_maddv_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_maddv_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_maddv_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_maddv_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_maddv_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_maddv_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_maddv_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_maddv_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_maddv_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_maddv_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_maddv_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_maddv_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_maddv_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_maddv_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} + +static inline int64_t msa_msubv_df(uint32_t df, int64_t dest, int64_t arg1, + int64_t arg2) +{ + return dest - arg1 * arg2; +} + +void helper_msa_msubv_b(CPUMIPSState *env, + uint32_t wd, uint32_t ws, uint32_t wt) +{ + wr_t *pwd = &(env->active_fpu.fpr[wd].wr); + wr_t *pws = &(env->active_fpu.fpr[ws].wr); + wr_t *pwt = &(env->active_fpu.fpr[wt].wr); + + pwd->b[0] = msa_msubv_df(DF_BYTE, pwt->b[0], pws->b[0], pwt->b[0]); + pwd->b[1] = msa_msubv_df(DF_BYTE, pwt->b[1], pws->b[1], pwt->b[1]); + pwd->b[2] = msa_msubv_df(DF_BYTE, pwt->b[2], pws->b[2], pwt->b[2]); + pwd->b[3] = msa_msubv_df(DF_BYTE, pwt->b[3], pws->b[3], pwt->b[3]); + pwd->b[4] = msa_msubv_df(DF_BYTE, pwt->b[4], pws->b[4], pwt->b[4]); + pwd->b[5] = msa_msubv_df(DF_BYTE, pwt->b[5], pws->b[5], pwt->b[5]); + pwd->b[6] = msa_msubv_df(DF_BYTE, pwt->b[6], pws->b[6], pwt->b[6]); + pwd->b[7] = msa_msubv_df(DF_BYTE, pwt->b[7], pws->b[7], pwt->b[7]); + pwd->b[8] = msa_msubv_df(DF_BYTE, pwt->b[8], pws->b[8], pwt->b[8]); + pwd->b[9] = msa_msubv_df(DF_BYTE, pwt->b[9], pws->b[9], pwt->b[9]); + pwd->b[10] = msa_msubv_df(DF_BYTE, pwt->b[10], pws->b[10], pwt->b[10]); + pwd->b[11] = msa_msubv_df(DF_BYTE, pwt->b[11], pws->b[11], pwt->b[11]); + pwd->b[12] = msa_msubv_df(DF_BYTE, pwt->b[12], pws->b[12], pwt->b[12]); + pwd->b[13] = msa_msubv_df(DF_BYTE, pwt->b[13], pws->b[13], pwt->b[13]); + pwd->b[14] = msa_msubv_df(DF_BYTE, pwt->b[14], pws->b[14], pwt->b[14]); + pwd->b[15] = msa_msubv_df(DF_BYTE, pwt->b[15], pws->b[15], pwt->b[15]); +} + +void helper_msa_msubv_h(CPUMIPSState *env, + uint32_t wd, uint32_t ws, uint32_t wt) +{ + wr_t *pwd = &(env->active_fpu.fpr[wd].wr); + wr_t *pws = &(env->active_fpu.fpr[ws].wr); + wr_t *pwt = &(env->active_fpu.fpr[wt].wr); + + pwd->h[0] = msa_msubv_df(DF_HALF, pwd->h[0], pws->h[0], pwt->h[0]); + pwd->h[1] = msa_msubv_df(DF_HALF, pwd->h[1], pws->h[1], pwt->h[1]); + pwd->h[2] = msa_msubv_df(DF_HALF, pwd->h[2], pws->h[2], pwt->h[2]); + pwd->h[3] = msa_msubv_df(DF_HALF, pwd->h[3], pws->h[3], pwt->h[3]); + pwd->h[4] = msa_msubv_df(DF_HALF, pwd->h[4], pws->h[4], pwt->h[4]); + pwd->h[5] = msa_msubv_df(DF_HALF, pwd->h[5], pws->h[5], pwt->h[5]); + pwd->h[6] = msa_msubv_df(DF_HALF, pwd->h[6], pws->h[6], pwt->h[6]); + pwd->h[7] = msa_msubv_df(DF_HALF, pwd->h[7], pws->h[7], pwt->h[7]); +} + +void helper_msa_msubv_w(CPUMIPSState *env, + uint32_t wd, uint32_t ws, uint32_t wt) +{ + wr_t *pwd = &(env->active_fpu.fpr[wd].wr); + wr_t *pws = &(env->active_fpu.fpr[ws].wr); + wr_t *pwt = &(env->active_fpu.fpr[wt].wr); + + pwd->w[0] = msa_msubv_df(DF_WORD, pwd->w[0], pws->w[0], pwt->w[0]); + pwd->w[1] = msa_msubv_df(DF_WORD, pwd->w[1], pws->w[1], pwt->w[1]); + pwd->w[2] = msa_msubv_df(DF_WORD, pwd->w[2], pws->w[2], pwt->w[2]); + pwd->w[3] = msa_msubv_df(DF_WORD, pwd->w[3], pws->w[3], pwt->w[3]); +} + +void helper_msa_msubv_d(CPUMIPSState *env, + uint32_t wd, uint32_t ws, uint32_t wt) +{ + wr_t *pwd = &(env->active_fpu.fpr[wd].wr); + wr_t *pws = &(env->active_fpu.fpr[ws].wr); + wr_t *pwt = &(env->active_fpu.fpr[wt].wr); + + pwd->d[0] = msa_msubv_df(DF_DOUBLE, pwd->d[0], pws->d[0], pwt->d[0]); + pwd->d[1] = msa_msubv_df(DF_DOUBLE, pwd->d[1], pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_mulv_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + return arg1 * arg2; +} + +void helper_msa_mulv_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_mulv_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_mulv_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_mulv_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_mulv_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_mulv_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_mulv_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_mulv_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_mulv_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_mulv_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_mulv_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_mulv_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_mulv_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_mulv_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_mulv_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_mulv_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_mulv_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_mulv_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_mulv_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_mulv_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_mulv_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_mulv_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_mulv_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_mulv_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_mulv_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_mulv_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_mulv_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_mulv_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_mulv_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_mulv_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_mulv_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_mulv_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_mulv_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_mulv_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} /* @@ -3079,9 +3625,6 @@ void helper_msa_asub_u_d(CPUMIPSState *env, } -/* 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); @@ -3176,6 +3719,398 @@ void helper_msa_hsub_u_d(CPUMIPSState *env, } +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); + int64_t min_int = DF_MIN_INT(df); + if (arg2 > 0) { + return (min_int + arg2 < arg1) ? arg1 - arg2 : min_int; + } else { + return (arg1 < max_int + arg2) ? arg1 - arg2 : max_int; + } +} + +void helper_msa_subs_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_subs_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_subs_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_subs_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_subs_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_subs_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_subs_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_subs_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_subs_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_subs_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_subs_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_subs_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_subs_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_subs_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_subs_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_subs_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_subs_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_subs_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_subs_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_subs_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_subs_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_subs_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_subs_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_subs_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_subs_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_subs_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_subs_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_subs_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_subs_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_subs_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_subs_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_subs_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_subs_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_subs_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_subs_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) ? u_arg1 - u_arg2 : 0; +} + +void helper_msa_subs_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_subs_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_subs_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_subs_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_subs_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_subs_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_subs_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_subs_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_subs_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_subs_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_subs_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_subs_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_subs_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_subs_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_subs_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_subs_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_subs_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_subs_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_subs_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_subs_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_subs_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_subs_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_subs_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_subs_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_subs_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_subs_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_subs_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_subs_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_subs_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_subs_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_subs_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_subs_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_subs_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_subs_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_subsus_u_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t max_uint = DF_MAX_UINT(df); + if (arg2 >= 0) { + uint64_t u_arg2 = (uint64_t)arg2; + return (u_arg1 > u_arg2) ? + (int64_t)(u_arg1 - u_arg2) : + 0; + } else { + uint64_t u_arg2 = (uint64_t)(-arg2); + return (u_arg1 < max_uint - u_arg2) ? + (int64_t)(u_arg1 + u_arg2) : + (int64_t)max_uint; + } +} + +void helper_msa_subsus_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_subsus_u_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_subsus_u_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_subsus_u_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_subsus_u_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_subsus_u_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_subsus_u_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_subsus_u_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_subsus_u_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_subsus_u_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_subsus_u_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_subsus_u_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_subsus_u_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_subsus_u_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_subsus_u_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_subsus_u_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_subsus_u_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_subsus_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_subsus_u_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_subsus_u_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_subsus_u_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_subsus_u_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_subsus_u_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_subsus_u_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_subsus_u_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_subsus_u_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_subsus_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_subsus_u_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_subsus_u_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_subsus_u_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_subsus_u_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_subsus_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_subsus_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_subsus_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_subsuu_s_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + uint64_t u_arg1 = UNSIGNED(arg1, df); + uint64_t u_arg2 = UNSIGNED(arg2, df); + int64_t max_int = DF_MAX_INT(df); + int64_t min_int = DF_MIN_INT(df); + if (u_arg1 > u_arg2) { + return u_arg1 - u_arg2 < (uint64_t)max_int ? + (int64_t)(u_arg1 - u_arg2) : + max_int; + } else { + return u_arg2 - u_arg1 < (uint64_t)(-min_int) ? + (int64_t)(u_arg1 - u_arg2) : + min_int; + } +} + +void helper_msa_subsuu_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_subsuu_s_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_subsuu_s_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_subsuu_s_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_subsuu_s_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_subsuu_s_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_subsuu_s_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_subsuu_s_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_subsuu_s_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_subsuu_s_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_subsuu_s_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_subsuu_s_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_subsuu_s_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_subsuu_s_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_subsuu_s_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_subsuu_s_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_subsuu_s_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_subsuu_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_subsuu_s_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_subsuu_s_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_subsuu_s_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_subsuu_s_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_subsuu_s_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_subsuu_s_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_subsuu_s_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_subsuu_s_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_subsuu_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_subsuu_s_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_subsuu_s_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_subsuu_s_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_subsuu_s_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_subsuu_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_subsuu_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_subsuu_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + +static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2) +{ + return arg1 - arg2; +} + +void helper_msa_subv_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_subv_df(DF_BYTE, pws->b[0], pwt->b[0]); + pwd->b[1] = msa_subv_df(DF_BYTE, pws->b[1], pwt->b[1]); + pwd->b[2] = msa_subv_df(DF_BYTE, pws->b[2], pwt->b[2]); + pwd->b[3] = msa_subv_df(DF_BYTE, pws->b[3], pwt->b[3]); + pwd->b[4] = msa_subv_df(DF_BYTE, pws->b[4], pwt->b[4]); + pwd->b[5] = msa_subv_df(DF_BYTE, pws->b[5], pwt->b[5]); + pwd->b[6] = msa_subv_df(DF_BYTE, pws->b[6], pwt->b[6]); + pwd->b[7] = msa_subv_df(DF_BYTE, pws->b[7], pwt->b[7]); + pwd->b[8] = msa_subv_df(DF_BYTE, pws->b[8], pwt->b[8]); + pwd->b[9] = msa_subv_df(DF_BYTE, pws->b[9], pwt->b[9]); + pwd->b[10] = msa_subv_df(DF_BYTE, pws->b[10], pwt->b[10]); + pwd->b[11] = msa_subv_df(DF_BYTE, pws->b[11], pwt->b[11]); + pwd->b[12] = msa_subv_df(DF_BYTE, pws->b[12], pwt->b[12]); + pwd->b[13] = msa_subv_df(DF_BYTE, pws->b[13], pwt->b[13]); + pwd->b[14] = msa_subv_df(DF_BYTE, pws->b[14], pwt->b[14]); + pwd->b[15] = msa_subv_df(DF_BYTE, pws->b[15], pwt->b[15]); +} + +void helper_msa_subv_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_subv_df(DF_HALF, pws->h[0], pwt->h[0]); + pwd->h[1] = msa_subv_df(DF_HALF, pws->h[1], pwt->h[1]); + pwd->h[2] = msa_subv_df(DF_HALF, pws->h[2], pwt->h[2]); + pwd->h[3] = msa_subv_df(DF_HALF, pws->h[3], pwt->h[3]); + pwd->h[4] = msa_subv_df(DF_HALF, pws->h[4], pwt->h[4]); + pwd->h[5] = msa_subv_df(DF_HALF, pws->h[5], pwt->h[5]); + pwd->h[6] = msa_subv_df(DF_HALF, pws->h[6], pwt->h[6]); + pwd->h[7] = msa_subv_df(DF_HALF, pws->h[7], pwt->h[7]); +} + +void helper_msa_subv_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_subv_df(DF_WORD, pws->w[0], pwt->w[0]); + pwd->w[1] = msa_subv_df(DF_WORD, pws->w[1], pwt->w[1]); + pwd->w[2] = msa_subv_df(DF_WORD, pws->w[2], pwt->w[2]); + pwd->w[3] = msa_subv_df(DF_WORD, pws->w[3], pwt->w[3]); +} + +void helper_msa_subv_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_subv_df(DF_DOUBLE, pws->d[0], pwt->d[0]); + pwd->d[1] = msa_subv_df(DF_DOUBLE, pws->d[1], pwt->d[1]); +} + + /* * Interleave * ---------- @@ -4400,11 +5335,6 @@ void helper_msa_shf_df(CPUMIPSState *env, uint32_t df, uint32_t wd, msa_move_v(pwd, pwx); } -static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - return 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) \ @@ -4586,97 +5516,6 @@ MSA_TEROP_IMMU_DF(binsli, binsl) MSA_TEROP_IMMU_DF(binsri, binsr) #undef MSA_TEROP_IMMU_DF -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); - int64_t min_int = DF_MIN_INT(df); - if (arg2 > 0) { - return (min_int + arg2 < arg1) ? arg1 - arg2 : min_int; - } else { - return (arg1 < max_int + arg2) ? arg1 - arg2 : max_int; - } -} - -static inline int64_t msa_subs_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) ? u_arg1 - u_arg2 : 0; -} - -static inline int64_t msa_subsus_u_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t max_uint = DF_MAX_UINT(df); - if (arg2 >= 0) { - uint64_t u_arg2 = (uint64_t)arg2; - return (u_arg1 > u_arg2) ? - (int64_t)(u_arg1 - u_arg2) : - 0; - } else { - uint64_t u_arg2 = (uint64_t)(-arg2); - return (u_arg1 < max_uint - u_arg2) ? - (int64_t)(u_arg1 + u_arg2) : - (int64_t)max_uint; - } -} - -static inline int64_t msa_subsuu_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - uint64_t u_arg1 = UNSIGNED(arg1, df); - uint64_t u_arg2 = UNSIGNED(arg2, df); - int64_t max_int = DF_MAX_INT(df); - int64_t min_int = DF_MIN_INT(df); - if (u_arg1 > u_arg2) { - return u_arg1 - u_arg2 < (uint64_t)max_int ? - (int64_t)(u_arg1 - u_arg2) : - max_int; - } else { - return u_arg2 - u_arg1 < (uint64_t)(-min_int) ? - (int64_t)(u_arg1 - u_arg2) : - min_int; - } -} - -static inline int64_t msa_mulv_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - return arg1 * arg2; -} - -#define SIGNED_EXTRACT(e, o, a, df) \ - do { \ - e = SIGNED_EVEN(a, df); \ - o = SIGNED_ODD(a, df); \ - } while (0) - -#define UNSIGNED_EXTRACT(e, o, a, df) \ - do { \ - e = UNSIGNED_EVEN(a, df); \ - o = UNSIGNED_ODD(a, df); \ - } while (0) - -static inline int64_t msa_dotp_s_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); -} - -static inline int64_t msa_dotp_u_df(uint32_t df, int64_t arg1, int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); -} - #define CONCATENATE_AND_SLIDE(s, k) \ do { \ for (i = 0; i < s; i++) { \ @@ -4794,15 +5633,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, \ } \ } -MSA_BINOP_DF(subv) -MSA_BINOP_DF(subs_s) -MSA_BINOP_DF(subs_u) -MSA_BINOP_DF(subsus_u) -MSA_BINOP_DF(subsuu_s) -MSA_BINOP_DF(mulv) -MSA_BINOP_DF(dotp_s) -MSA_BINOP_DF(dotp_u) - MSA_BINOP_DF(mul_q) MSA_BINOP_DF(mulr_q) #undef MSA_BINOP_DF @@ -4816,66 +5646,6 @@ void helper_msa_sld_df(CPUMIPSState *env, uint32_t df, uint32_t wd, msa_sld_df(df, pwd, pws, env->active_tc.gpr[rt]); } -static inline int64_t msa_maddv_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - return dest + arg1 * arg2; -} - -static inline int64_t msa_msubv_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - return dest - arg1 * arg2; -} - -static inline int64_t msa_dpadd_s_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return dest + (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); -} - -static inline int64_t msa_dpadd_u_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return dest + (even_arg1 * even_arg2) + (odd_arg1 * odd_arg2); -} - -static inline int64_t msa_dpsub_s_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - SIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - SIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return dest - ((even_arg1 * even_arg2) + (odd_arg1 * odd_arg2)); -} - -static inline int64_t msa_dpsub_u_df(uint32_t df, int64_t dest, int64_t arg1, - int64_t arg2) -{ - int64_t even_arg1; - int64_t even_arg2; - int64_t odd_arg1; - int64_t odd_arg2; - UNSIGNED_EXTRACT(even_arg1, odd_arg1, arg1, df); - UNSIGNED_EXTRACT(even_arg2, odd_arg2, arg2, df); - return dest - ((even_arg1 * even_arg2) + (odd_arg1 * odd_arg2)); -} - static inline int64_t msa_madd_q_df(uint32_t df, int64_t dest, int64_t arg1, int64_t arg2) { @@ -5002,12 +5772,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd, \ } \ } -MSA_TEROP_DF(maddv) -MSA_TEROP_DF(msubv) -MSA_TEROP_DF(dpadd_s) -MSA_TEROP_DF(dpadd_u) -MSA_TEROP_DF(dpsub_s) -MSA_TEROP_DF(dpsub_u) MSA_TEROP_DF(binsl) MSA_TEROP_DF(binsr) MSA_TEROP_DF(madd_q) diff --git a/target/mips/translate.c b/target/mips/translate.c index 2caf4cba5a..9fad58ea2c 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -1046,7 +1046,7 @@ enum { OPC_BC2NEZ = (0x0D << 21) | OPC_CP2, }; -#define MASK_LMI(op) (MASK_OP_MAJOR(op) | (op & (0x1F << 21)) | (op & 0x1F)) +#define MASK_LMMI(op) (MASK_OP_MAJOR(op) | (op & (0x1F << 21)) | (op & 0x1F)) enum { OPC_PADDSH = (24 << 21) | (0x00) | OPC_CP2, @@ -3421,7 +3421,8 @@ static void gen_ld(DisasContext *ctx, uint32_t opc, TCGv t0, t1, t2; int mem_idx = ctx->mem_idx; - if (rt == 0 && ctx->insn_flags & (INSN_LOONGSON2E | INSN_LOONGSON2F)) { + if (rt == 0 && ctx->insn_flags & (INSN_LOONGSON2E | INSN_LOONGSON2F | + INSN_LOONGSON3A)) { /* * Loongson CPU uses a load to zero register for prefetch. * We emulate it as a NOP. On other CPU we must perform the @@ -5531,7 +5532,7 @@ static void gen_loongson_multimedia(DisasContext *ctx, int rd, int rs, int rt) TCGv_i64 t0, t1; TCGCond cond; - opc = MASK_LMI(ctx->opcode); + opc = MASK_LMMI(ctx->opcode); switch (opc) { case OPC_ADD_CP2: case OPC_SUB_CP2: @@ -27161,7 +27162,7 @@ static void decode_opc_special2_legacy(CPUMIPSState *env, DisasContext *ctx) case OPC_MULTU_G_2F: case OPC_MOD_G_2F: case OPC_MODU_G_2F: - check_insn(ctx, INSN_LOONGSON2F); + check_insn(ctx, INSN_LOONGSON2F | ASE_LEXT); gen_loongson_integer(ctx, op1, rd, rs, rt); break; case OPC_CLO: @@ -27194,7 +27195,7 @@ static void decode_opc_special2_legacy(CPUMIPSState *env, DisasContext *ctx) case OPC_DDIVU_G_2F: case OPC_DMOD_G_2F: case OPC_DMODU_G_2F: - check_insn(ctx, INSN_LOONGSON2F); + check_insn(ctx, INSN_LOONGSON2F | ASE_LEXT); gen_loongson_integer(ctx, op1, rd, rs, rt); break; #endif @@ -29057,6 +29058,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) break; } break; + case OPC_MADDV_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_maddv_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_maddv_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_maddv_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_maddv_d(cpu_env, twd, tws, twt); + break; + } + break; + case OPC_MSUBV_df: + switch (df) { + case DF_BYTE: + gen_helper_msa_msubv_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_msubv_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_msubv_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_msubv_d(cpu_env, twd, tws, twt); + break; + } + break; case OPC_ASUB_S_df: switch (df) { case DF_BYTE: @@ -29266,10 +29299,36 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) } break; case OPC_SUBS_S_df: - gen_helper_msa_subs_s_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_subs_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_subs_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_subs_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_subs_s_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_MULV_df: - gen_helper_msa_mulv_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_mulv_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_mulv_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_mulv_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_mulv_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_SLD_df: gen_helper_msa_sld_df(cpu_env, tdf, twd, tws, twt); @@ -29278,25 +29337,71 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) gen_helper_msa_vshf_df(cpu_env, tdf, twd, tws, twt); break; case OPC_SUBV_df: - gen_helper_msa_subv_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_subv_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_subv_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_subv_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_subv_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_SUBS_U_df: - gen_helper_msa_subs_u_df(cpu_env, tdf, twd, tws, twt); - break; - case OPC_MADDV_df: - gen_helper_msa_maddv_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_subs_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_subs_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_subs_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_subs_u_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_SPLAT_df: gen_helper_msa_splat_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; - case OPC_MSUBV_df: - gen_helper_msa_msubv_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_subsus_u_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_subsus_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_subsus_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_subsus_u_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_SUBSUU_S_df: - gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_BYTE: + gen_helper_msa_subsuu_s_b(cpu_env, twd, tws, twt); + break; + case DF_HALF: + gen_helper_msa_subsuu_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_subsuu_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_subsuu_s_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DOTP_S_df: @@ -29367,22 +29472,82 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx) } break; case OPC_DOTP_S_df: - gen_helper_msa_dotp_s_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dotp_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dotp_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dotp_s_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DOTP_U_df: - gen_helper_msa_dotp_u_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dotp_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dotp_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dotp_u_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DPADD_S_df: - gen_helper_msa_dpadd_s_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dpadd_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dpadd_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dpadd_s_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DPADD_U_df: - gen_helper_msa_dpadd_u_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dpadd_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dpadd_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dpadd_u_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DPSUB_S_df: - gen_helper_msa_dpsub_s_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dpsub_s_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dpsub_s_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dpsub_s_d(cpu_env, twd, tws, twt); + break; + } break; case OPC_DPSUB_U_df: - gen_helper_msa_dpsub_u_df(cpu_env, tdf, twd, tws, twt); + switch (df) { + case DF_HALF: + gen_helper_msa_dpsub_u_h(cpu_env, twd, tws, twt); + break; + case DF_WORD: + gen_helper_msa_dpsub_u_w(cpu_env, twd, tws, twt); + break; + case DF_DOUBLE: + gen_helper_msa_dpsub_u_d(cpu_env, twd, tws, twt); + break; + } break; } break; @@ -30641,7 +30806,7 @@ static void decode_opc(CPUMIPSState *env, DisasContext *ctx) } break; case OPC_CP2: - check_insn(ctx, INSN_LOONGSON2F); + check_insn(ctx, ASE_LMMI); /* Note that these instructions use different fields. */ gen_loongson_multimedia(ctx, sa, rd, rt); break; |