riscv
/
qemu
mirror of https://gitea.goldendeliverer.com/riscv/qemu.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

target/mips: msa: Split helpers for CLE_<S|U>.<B|H|W|D> 

Achieves clearer code and slightly better performance.

Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Reviewed-by: Aleksandar Rikalo <arikalo@wavecomp.com>
Message-Id: <1569415572-19635-16-git-send-email-aleksandar.markovic@rt-rk.com>
pull/82/head
Aleksandar Markovic 7 years ago
parent
ade7e788e1
commit
0501bb1a66
3 changed files with 186 additions and 22 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 12
      target/mips/helper.h
  2. 158
      target/mips/msa_helper.c
  3. 38
      target/mips/translate.c

12
target/mips/helper.h
View File

@ -847,6 +847,16 @@ DEF_HELPER_4(msa_ceq_h, void, env, i32, i32, i32)
DEF_HELPER_4(msa_ceq_w, void, env, i32, i32, i32)
DEF_HELPER_4(msa_ceq_d, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_s_b, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_s_h, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_s_w, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_s_d, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_u_b, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_u_h, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_u_w, void, env, i32, i32, i32)
DEF_HELPER_4(msa_cle_u_d, void, env, i32, i32, i32)
DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32)
DEF_HELPER_4(msa_ori_b, void, env, i32, i32, i32)
@ -898,8 +908,6 @@ 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_clt_s_df, void, env, i32, i32, i32, i32)
DEF_HELPER_5(msa_clt_u_df, void, env, i32, i32, i32, i32)
DEF_HELPER_5(msa_cle_s_df, void, env, i32, i32, i32, i32)
DEF_HELPER_5(msa_cle_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)

158
target/mips/msa_helper.c
View File

@ -1220,6 +1220,150 @@ void helper_msa_ceq_d(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t wt)
pwd->d[1] = msa_ceq_df(DF_DOUBLE, pws->d[1], pwt->d[1]);
}
static inline int64_t msa_cle_s_df(uint32_t df, int64_t arg1, int64_t arg2)
{
return arg1 <= arg2 ? -1 : 0;
}
void helper_msa_cle_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_cle_s_df(DF_BYTE, pws->b[0], pwt->b[0]);
pwd->b[1] = msa_cle_s_df(DF_BYTE, pws->b[1], pwt->b[1]);
pwd->b[2] = msa_cle_s_df(DF_BYTE, pws->b[2], pwt->b[2]);
pwd->b[3] = msa_cle_s_df(DF_BYTE, pws->b[3], pwt->b[3]);
pwd->b[4] = msa_cle_s_df(DF_BYTE, pws->b[4], pwt->b[4]);
pwd->b[5] = msa_cle_s_df(DF_BYTE, pws->b[5], pwt->b[5]);
pwd->b[6] = msa_cle_s_df(DF_BYTE, pws->b[6], pwt->b[6]);
pwd->b[7] = msa_cle_s_df(DF_BYTE, pws->b[7], pwt->b[7]);
pwd->b[8] = msa_cle_s_df(DF_BYTE, pws->b[8], pwt->b[8]);
pwd->b[9] = msa_cle_s_df(DF_BYTE, pws->b[9], pwt->b[9]);
pwd->b[10] = msa_cle_s_df(DF_BYTE, pws->b[10], pwt->b[10]);
pwd->b[11] = msa_cle_s_df(DF_BYTE, pws->b[11], pwt->b[11]);
pwd->b[12] = msa_cle_s_df(DF_BYTE, pws->b[12], pwt->b[12]);
pwd->b[13] = msa_cle_s_df(DF_BYTE, pws->b[13], pwt->b[13]);
pwd->b[14] = msa_cle_s_df(DF_BYTE, pws->b[14], pwt->b[14]);
pwd->b[15] = msa_cle_s_df(DF_BYTE, pws->b[15], pwt->b[15]);
}
void helper_msa_cle_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_cle_s_df(DF_HALF, pws->h[0], pwt->h[0]);
pwd->h[1] = msa_cle_s_df(DF_HALF, pws->h[1], pwt->h[1]);
pwd->h[2] = msa_cle_s_df(DF_HALF, pws->h[2], pwt->h[2]);
pwd->h[3] = msa_cle_s_df(DF_HALF, pws->h[3], pwt->h[3]);
pwd->h[4] = msa_cle_s_df(DF_HALF, pws->h[4], pwt->h[4]);
pwd->h[5] = msa_cle_s_df(DF_HALF, pws->h[5], pwt->h[5]);
pwd->h[6] = msa_cle_s_df(DF_HALF, pws->h[6], pwt->h[6]);
pwd->h[7] = msa_cle_s_df(DF_HALF, pws->h[7], pwt->h[7]);
}
void helper_msa_cle_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_cle_s_df(DF_WORD, pws->w[0], pwt->w[0]);
pwd->w[1] = msa_cle_s_df(DF_WORD, pws->w[1], pwt->w[1]);
pwd->w[2] = msa_cle_s_df(DF_WORD, pws->w[2], pwt->w[2]);
pwd->w[3] = msa_cle_s_df(DF_WORD, pws->w[3], pwt->w[3]);
}
void helper_msa_cle_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_cle_s_df(DF_DOUBLE, pws->d[0], pwt->d[0]);
pwd->d[1] = msa_cle_s_df(DF_DOUBLE, pws->d[1], pwt->d[1]);
}
static inline int64_t msa_cle_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 ? -1 : 0;
}
void helper_msa_cle_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_cle_u_df(DF_BYTE, pws->b[0], pwt->b[0]);
pwd->b[1] = msa_cle_u_df(DF_BYTE, pws->b[1], pwt->b[1]);
pwd->b[2] = msa_cle_u_df(DF_BYTE, pws->b[2], pwt->b[2]);
pwd->b[3] = msa_cle_u_df(DF_BYTE, pws->b[3], pwt->b[3]);
pwd->b[4] = msa_cle_u_df(DF_BYTE, pws->b[4], pwt->b[4]);
pwd->b[5] = msa_cle_u_df(DF_BYTE, pws->b[5], pwt->b[5]);
pwd->b[6] = msa_cle_u_df(DF_BYTE, pws->b[6], pwt->b[6]);
pwd->b[7] = msa_cle_u_df(DF_BYTE, pws->b[7], pwt->b[7]);
pwd->b[8] = msa_cle_u_df(DF_BYTE, pws->b[8], pwt->b[8]);
pwd->b[9] = msa_cle_u_df(DF_BYTE, pws->b[9], pwt->b[9]);
pwd->b[10] = msa_cle_u_df(DF_BYTE, pws->b[10], pwt->b[10]);
pwd->b[11] = msa_cle_u_df(DF_BYTE, pws->b[11], pwt->b[11]);
pwd->b[12] = msa_cle_u_df(DF_BYTE, pws->b[12], pwt->b[12]);
pwd->b[13] = msa_cle_u_df(DF_BYTE, pws->b[13], pwt->b[13]);
pwd->b[14] = msa_cle_u_df(DF_BYTE, pws->b[14], pwt->b[14]);
pwd->b[15] = msa_cle_u_df(DF_BYTE, pws->b[15], pwt->b[15]);
}
void helper_msa_cle_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_cle_u_df(DF_HALF, pws->h[0], pwt->h[0]);
pwd->h[1] = msa_cle_u_df(DF_HALF, pws->h[1], pwt->h[1]);
pwd->h[2] = msa_cle_u_df(DF_HALF, pws->h[2], pwt->h[2]);
pwd->h[3] = msa_cle_u_df(DF_HALF, pws->h[3], pwt->h[3]);
pwd->h[4] = msa_cle_u_df(DF_HALF, pws->h[4], pwt->h[4]);
pwd->h[5] = msa_cle_u_df(DF_HALF, pws->h[5], pwt->h[5]);
pwd->h[6] = msa_cle_u_df(DF_HALF, pws->h[6], pwt->h[6]);
pwd->h[7] = msa_cle_u_df(DF_HALF, pws->h[7], pwt->h[7]);
}
void helper_msa_cle_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_cle_u_df(DF_WORD, pws->w[0], pwt->w[0]);
pwd->w[1] = msa_cle_u_df(DF_WORD, pws->w[1], pwt->w[1]);
pwd->w[2] = msa_cle_u_df(DF_WORD, pws->w[2], pwt->w[2]);
pwd->w[3] = msa_cle_u_df(DF_WORD, pws->w[3], pwt->w[3]);
}
void helper_msa_cle_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_cle_u_df(DF_DOUBLE, pws->d[0], pwt->d[0]);
pwd->d[1] = msa_cle_u_df(DF_DOUBLE, pws->d[1], pwt->d[1]);
}
/*
* Int Divide
@ -1627,18 +1771,6 @@ static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2)
return arg1 - arg2;
}
static inline int64_t msa_cle_s_df(uint32_t df, int64_t arg1, int64_t arg2)
{
return arg1 <= arg2 ? -1 : 0;
}
static inline int64_t msa_cle_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 ? -1 : 0;
}
static inline int64_t msa_clt_s_df(uint32_t df, int64_t arg1, int64_t arg2)
{
return arg1 < arg2 ? -1 : 0;
@ -2250,8 +2382,6 @@ MSA_BINOP_DF(max_a)
MSA_BINOP_DF(min_a)
MSA_BINOP_DF(clt_s)
MSA_BINOP_DF(clt_u)
MSA_BINOP_DF(cle_s)
MSA_BINOP_DF(cle_u)
MSA_BINOP_DF(add_a)
MSA_BINOP_DF(adds_a)
MSA_BINOP_DF(adds_s)

38
target/mips/translate.c
View File

@ -28546,6 +28546,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
break;
}
break;
case OPC_CLE_S_df:
switch (df) {
case DF_BYTE:
gen_helper_msa_cle_s_b(cpu_env, twd, tws, twt);
break;
case DF_HALF:
gen_helper_msa_cle_s_h(cpu_env, twd, tws, twt);
break;
case DF_WORD:
gen_helper_msa_cle_s_w(cpu_env, twd, tws, twt);
break;
case DF_DOUBLE:
gen_helper_msa_cle_s_d(cpu_env, twd, tws, twt);
break;
}
break;
case OPC_CLE_U_df:
switch (df) {
case DF_BYTE:
gen_helper_msa_cle_u_b(cpu_env, twd, tws, twt);
break;
case DF_HALF:
gen_helper_msa_cle_u_h(cpu_env, twd, tws, twt);
break;
case DF_WORD:
gen_helper_msa_cle_u_w(cpu_env, twd, tws, twt);
break;
case DF_DOUBLE:
gen_helper_msa_cle_u_d(cpu_env, twd, tws, twt);
break;
}
break;
case OPC_SLL_df:
gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
break;
@ -28630,9 +28662,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
case OPC_MIN_S_df:
gen_helper_msa_min_s_df(cpu_env, tdf, twd, tws, twt);
break;
case OPC_CLE_S_df:
gen_helper_msa_cle_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;
@ -28645,9 +28674,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
case OPC_MIN_U_df:
gen_helper_msa_min_u_df(cpu_env, tdf, twd, tws, twt);
break;
case OPC_CLE_U_df:
gen_helper_msa_cle_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;

Write Preview
Loading…
Cancel
Save