target-mips: add MSA ELM format instructions

add MSA ELM format instructions

Signed-off-by: Yongbok Kim <yongbok.kim@imgtec.com>
Signed-off-by: Leon Alrae <leon.alrae@imgtec.com>

3 files changed, 290 insertions, 0 deletions

diff --git a/target-mips/helper.h b/target-mips/helper.h
index 4297d4a668..c9e033bdaa 100644
--- a/target-mips/helper.h
+++ b/target-mips/helper.h
@@ -848,3 +848,13 @@ DEF_HELPER_5(msa_hadd_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hadd_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_u_df, void, env, i32, i32, i32, i32)
+
+DEF_HELPER_5(msa_sldi_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_splati_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_copy_s_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_copy_u_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_insert_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_insve_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_3(msa_ctcmsa, void, env, tl, i32)
+DEF_HELPER_2(msa_cfcmsa, tl, env, i32)
+DEF_HELPER_3(msa_move_v, void, env, i32, i32)
diff --git a/target-mips/msa_helper.c b/target-mips/msa_helper.c
index f879cc7808..3a909e6b45 100644
--- a/target-mips/msa_helper.c
+++ b/target-mips/msa_helper.c
@@ -1108,3 +1108,165 @@ MSA_FN_DF(vshf_df)
 #undef MSA_DO
 #undef MSA_LOOP_COND
 #undef MSA_FN_DF
+
+void helper_msa_sldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
+                        uint32_t ws, uint32_t n)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    msa_sld_df(df, pwd, pws, n);
+}
+
+void helper_msa_splati_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
+                          uint32_t ws, uint32_t n)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    msa_splat_df(df, pwd, pws, n);
+}
+
+void helper_msa_copy_s_df(CPUMIPSState *env, uint32_t df, uint32_t rd,
+                          uint32_t ws, uint32_t n)
+{
+    n %= DF_ELEMENTS(df);
+
+    switch (df) {
+    case DF_BYTE:
+        env->active_tc.gpr[rd] = (int8_t)env->active_fpu.fpr[ws].wr.b[n];
+        break;
+    case DF_HALF:
+        env->active_tc.gpr[rd] = (int16_t)env->active_fpu.fpr[ws].wr.h[n];
+        break;
+    case DF_WORD:
+        env->active_tc.gpr[rd] = (int32_t)env->active_fpu.fpr[ws].wr.w[n];
+        break;
+#ifdef TARGET_MIPS64
+    case DF_DOUBLE:
+        env->active_tc.gpr[rd] = (int64_t)env->active_fpu.fpr[ws].wr.d[n];
+        break;
+#endif
+    default:
+        assert(0);
+    }
+}
+
+void helper_msa_copy_u_df(CPUMIPSState *env, uint32_t df, uint32_t rd,
+                          uint32_t ws, uint32_t n)
+{
+    n %= DF_ELEMENTS(df);
+
+    switch (df) {
+    case DF_BYTE:
+        env->active_tc.gpr[rd] = (uint8_t)env->active_fpu.fpr[ws].wr.b[n];
+        break;
+    case DF_HALF:
+        env->active_tc.gpr[rd] = (uint16_t)env->active_fpu.fpr[ws].wr.h[n];
+        break;
+    case DF_WORD:
+        env->active_tc.gpr[rd] = (uint32_t)env->active_fpu.fpr[ws].wr.w[n];
+        break;
+#ifdef TARGET_MIPS64
+    case DF_DOUBLE:
+        env->active_tc.gpr[rd] = (uint64_t)env->active_fpu.fpr[ws].wr.d[n];
+        break;
+#endif
+    default:
+        assert(0);
+    }
+}
+
+void helper_msa_insert_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
+                          uint32_t rs_num, uint32_t n)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    target_ulong rs = env->active_tc.gpr[rs_num];
+
+    switch (df) {
+    case DF_BYTE:
+        pwd->b[n] = (int8_t)rs;
+        break;
+    case DF_HALF:
+        pwd->h[n] = (int16_t)rs;
+        break;
+    case DF_WORD:
+        pwd->w[n] = (int32_t)rs;
+        break;
+    case DF_DOUBLE:
+        pwd->d[n] = (int64_t)rs;
+        break;
+    default:
+        assert(0);
+    }
+}
+
+void helper_msa_insve_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
+                         uint32_t ws, uint32_t n)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    switch (df) {
+    case DF_BYTE:
+        pwd->b[n] = (int8_t)pws->b[0];
+        break;
+    case DF_HALF:
+        pwd->h[n] = (int16_t)pws->h[0];
+        break;
+    case DF_WORD:
+        pwd->w[n] = (int32_t)pws->w[0];
+        break;
+    case DF_DOUBLE:
+        pwd->d[n] = (int64_t)pws->d[0];
+        break;
+    default:
+        assert(0);
+    }
+}
+
+void helper_msa_ctcmsa(CPUMIPSState *env, target_ulong elm, uint32_t cd)
+{
+    switch (cd) {
+    case 0:
+        break;
+    case 1:
+        env->active_tc.msacsr = (int32_t)elm & MSACSR_MASK;
+        /* set float_status rounding mode */
+        set_float_rounding_mode(
+            ieee_rm[(env->active_tc.msacsr & MSACSR_RM_MASK) >> MSACSR_RM],
+            &env->active_tc.msa_fp_status);
+        /* set float_status flush modes */
+        set_flush_to_zero(
+          (env->active_tc.msacsr & MSACSR_FS_MASK) != 0 ? 1 : 0,
+          &env->active_tc.msa_fp_status);
+        set_flush_inputs_to_zero(
+          (env->active_tc.msacsr & MSACSR_FS_MASK) != 0 ? 1 : 0,
+          &env->active_tc.msa_fp_status);
+        /* check exception */
+        if ((GET_FP_ENABLE(env->active_tc.msacsr) | FP_UNIMPLEMENTED)
+            & GET_FP_CAUSE(env->active_tc.msacsr)) {
+            helper_raise_exception(env, EXCP_MSAFPE);
+        }
+        break;
+    }
+}
+
+target_ulong helper_msa_cfcmsa(CPUMIPSState *env, uint32_t cs)
+{
+    switch (cs) {
+    case 0:
+        return env->msair;
+    case 1:
+        return env->active_tc.msacsr & MSACSR_MASK;
+    }
+    return 0;
+}
+
+void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+
+    msa_move_v(pwd, pws);
+}
diff --git a/target-mips/translate.c b/target-mips/translate.c
index 0d5a054021..31a56b6a44 100644
--- a/target-mips/translate.c
+++ b/target-mips/translate.c
@@ -17780,6 +17780,121 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     tcg_temp_free_i32(tdf);
 }
 
+static void gen_msa_elm_3e(CPUMIPSState *env, DisasContext *ctx)
+{
+#define MASK_MSA_ELM_DF3E(op)   (MASK_MSA_MINOR(op) | (op & (0x3FF << 16)))
+    uint8_t source = (ctx->opcode >> 11) & 0x1f;
+    uint8_t dest = (ctx->opcode >> 6) & 0x1f;
+    TCGv telm = tcg_temp_new();
+    TCGv_i32 tsr = tcg_const_i32(source);
+    TCGv_i32 tdt = tcg_const_i32(dest);
+
+    switch (MASK_MSA_ELM_DF3E(ctx->opcode)) {
+    case OPC_CTCMSA:
+        gen_load_gpr(telm, source);
+        gen_helper_msa_ctcmsa(cpu_env, telm, tdt);
+        break;
+    case OPC_CFCMSA:
+        gen_helper_msa_cfcmsa(telm, cpu_env, tsr);
+        gen_store_gpr(telm, dest);
+        break;
+    case OPC_MOVE_V:
+        gen_helper_msa_move_v(cpu_env, tdt, tsr);
+        break;
+    default:
+        MIPS_INVAL("MSA instruction");
+        generate_exception(ctx, EXCP_RI);
+        break;
+    }
+
+    tcg_temp_free(telm);
+    tcg_temp_free_i32(tdt);
+    tcg_temp_free_i32(tsr);
+}
+
+static void gen_msa_elm_df(CPUMIPSState *env, DisasContext *ctx, uint32_t df,
+        uint32_t n)
+{
+#define MASK_MSA_ELM(op)    (MASK_MSA_MINOR(op) | (op & (0xf << 22)))
+    uint8_t ws = (ctx->opcode >> 11) & 0x1f;
+    uint8_t wd = (ctx->opcode >> 6) & 0x1f;
+
+    TCGv_i32 tws = tcg_const_i32(ws);
+    TCGv_i32 twd = tcg_const_i32(wd);
+    TCGv_i32 tn  = tcg_const_i32(n);
+    TCGv_i32 tdf = tcg_const_i32(df);
+
+    switch (MASK_MSA_ELM(ctx->opcode)) {
+    case OPC_SLDI_df:
+        gen_helper_msa_sldi_df(cpu_env, tdf, twd, tws, tn);
+        break;
+    case OPC_SPLATI_df:
+        gen_helper_msa_splati_df(cpu_env, tdf, twd, tws, tn);
+        break;
+    case OPC_INSVE_df:
+        gen_helper_msa_insve_df(cpu_env, tdf, twd, tws, tn);
+        break;
+    case OPC_COPY_S_df:
+    case OPC_COPY_U_df:
+    case OPC_INSERT_df:
+#if !defined(TARGET_MIPS64)
+        /* Double format valid only for MIPS64 */
+        if (df == DF_DOUBLE) {
+            generate_exception(ctx, EXCP_RI);
+            break;
+        }
+#endif
+        switch (MASK_MSA_ELM(ctx->opcode)) {
+        case OPC_COPY_S_df:
+            gen_helper_msa_copy_s_df(cpu_env, tdf, twd, tws, tn);
+            break;
+        case OPC_COPY_U_df:
+            gen_helper_msa_copy_u_df(cpu_env, tdf, twd, tws, tn);
+            break;
+        case OPC_INSERT_df:
+            gen_helper_msa_insert_df(cpu_env, tdf, twd, tws, tn);
+            break;
+        }
+        break;
+    default:
+        MIPS_INVAL("MSA instruction");
+        generate_exception(ctx, EXCP_RI);
+    }
+    tcg_temp_free_i32(twd);
+    tcg_temp_free_i32(tws);
+    tcg_temp_free_i32(tn);
+    tcg_temp_free_i32(tdf);
+}
+
+static void gen_msa_elm(CPUMIPSState *env, DisasContext *ctx)
+{
+    uint8_t dfn = (ctx->opcode >> 16) & 0x3f;
+    uint32_t df = 0, n = 0;
+
+    if ((dfn & 0x30) == 0x00) {
+        n = dfn & 0x0f;
+        df = DF_BYTE;
+    } else if ((dfn & 0x38) == 0x20) {
+        n = dfn & 0x07;
+        df = DF_HALF;
+    } else if ((dfn & 0x3c) == 0x30) {
+        n = dfn & 0x03;
+        df = DF_WORD;
+    } else if ((dfn & 0x3e) == 0x38) {
+        n = dfn & 0x01;
+        df = DF_DOUBLE;
+    } else if (dfn == 0x3E) {
+        /* CTCMSA, CFCMSA, MOVE.V */
+        gen_msa_elm_3e(env, ctx);
+        return;
+    } else {
+        generate_exception(ctx, EXCP_RI);
+        return;
+    }
+
+    gen_msa_elm_df(env, ctx, df, n);
+}
+
 static void gen_msa(CPUMIPSState *env, DisasContext *ctx)
 {
     uint32_t opcode = ctx->opcode;
@@ -17811,6 +17926,9 @@ static void gen_msa(CPUMIPSState *env, DisasContext *ctx)
     case OPC_MSA_3R_15:
         gen_msa_3r(env, ctx);
         break;
+    case OPC_MSA_ELM:
+        gen_msa_elm(env, ctx);
+        break;
     default:
         MIPS_INVAL("MSA instruction");
         generate_exception(ctx, EXCP_RI);