From: Stefan Markovic <smarko...@wavecomp.com>
Add emulation of DSP ASE instructions for nanoMIPS - part 4.
Signed-off-by: Aleksandar Markovic <amarko...@wavecomp.com>
Signed-off-by: Stefan Markovic <smarko...@wavecomp.com>
---
target/mips/translate.c | 366 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 366 insertions(+)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index e597b35..bbc7788 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -17039,6 +17039,368 @@ static void
gen_pool32axf_1_nanomips_insn(DisasContext *ctx, uint32_t opc,
tcg_temp_free(v1_t);
}
+static void gen_pool32axf_2_multiply(DisasContext *ctx, uint32_t opc,
+ int ret, int v1, int v2)
+{
+ TCGv_i32 t0;
+ TCGv v0_t;
+ TCGv v1_t;
+
+ t0 = tcg_temp_new_i32();
+
+ v0_t = tcg_temp_new();
+ v1_t = tcg_temp_new();
+
+ tcg_gen_movi_i32(t0, v2 >> 3);
+
+ gen_load_gpr(v0_t, ret);
+ gen_load_gpr(v1_t, v1);
+
+ switch (opc) {
+ case NM_POOL32AXF_2_0_7:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPA_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpa_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPAQ_S_W_PH:
+ check_dsp(ctx);
+ gen_helper_dpaq_s_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPS_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dps_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPSQ_S_W_PH:
+ check_dsp(ctx);
+ gen_helper_dpsq_s_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_8_15:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAX_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpax_w_ph(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPAQ_SA_L_W:
+ check_dsp(ctx);
+ gen_helper_dpaq_sa_l_w(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPSX_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpsx_w_ph(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPSQ_SA_L_W:
+ check_dsp(ctx);
+ gen_helper_dpsq_sa_l_w(t0, v0_t, v1_t, cpu_env);
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_16_23:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAU_H_QBL:
+ check_dsp(ctx);
+ gen_helper_dpau_h_qbl(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPAQX_S_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpaqx_s_w_ph(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPSU_H_QBL:
+ check_dsp(ctx);
+ gen_helper_dpsu_h_qbl(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_DPSQX_S_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpsqx_s_w_ph(t0, v0_t, v1_t, cpu_env);
+ break;
+ case NM_MULSA_W_PH:
+ check_dspr2(ctx);
+ gen_helper_mulsa_w_ph(t0, v0_t, v1_t, cpu_env);
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_24_31:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAU_H_QBR:
+ check_dsp(ctx);
+ gen_helper_dpau_h_qbr(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPAQX_SA_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpaqx_sa_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPSU_H_QBR:
+ check_dsp(ctx);
+ gen_helper_dpsu_h_qbr(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_DPSQX_SA_W_PH:
+ check_dspr2(ctx);
+ gen_helper_dpsqx_sa_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ case NM_MULSAQ_S_W_PH:
+ check_dsp(ctx);
+ gen_helper_mulsaq_s_w_ph(t0, v1_t, v0_t, cpu_env);
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+
+ tcg_temp_free_i32(t0);
+
+ tcg_temp_free(v0_t);
+ tcg_temp_free(v1_t);
+}
+
+static void gen_pool32axf_2_nanomips_insn(DisasContext *ctx, uint32_t opc,
+ int ret, int v1, int v2)
+{
+ TCGv t0;
+ TCGv t1;
+
+ TCGv v0_t;
+ TCGv v1_t;
+
+ t0 = tcg_temp_new();
+ t1 = tcg_temp_new();
+
+ v0_t = tcg_temp_new();
+ v1_t = tcg_temp_new();
+
+ gen_load_gpr(v0_t, ret);
+ gen_load_gpr(v1_t, v1);
+
+ switch (opc) {
+ case NM_POOL32AXF_2_0_7:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPA_W_PH:
+ case NM_DPAQ_S_W_PH:
+ case NM_DPS_W_PH:
+ case NM_DPSQ_S_W_PH:
+ gen_pool32axf_2_multiply(ctx, opc, ret, v1, v2);
+ break;
+ case NM_BALIGN:
+ gen_load_gpr(t0, v1);
+ v2 &= 3;
+ if (v2 != 0 && v2 != 2) {
+ tcg_gen_shli_tl(cpu_gpr[ret], cpu_gpr[ret], 8 * v2);
+ tcg_gen_ext32u_tl(t0, t0);
+ tcg_gen_shri_tl(t0, t0, 8 * (4 - v2));
+ tcg_gen_or_tl(cpu_gpr[ret], cpu_gpr[ret], t0);
+ }
+ tcg_gen_ext32s_tl(cpu_gpr[ret], cpu_gpr[ret]);
+ break;
+ case NM_MADD:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ gen_load_gpr(t0, ret);
+ gen_load_gpr(t1, v1);
+ TCGv_i64 t2 = tcg_temp_new_i64();
+ TCGv_i64 t3 = tcg_temp_new_i64();
+
+ tcg_gen_ext_tl_i64(t2, t0);
+ tcg_gen_ext_tl_i64(t3, t1);
+ tcg_gen_mul_i64(t2, t2, t3);
+ tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]);
+ tcg_gen_add_i64(t2, t2, t3);
+ tcg_temp_free_i64(t3);
+ gen_move_low32(cpu_LO[acc], t2);
+ gen_move_high32(cpu_HI[acc], t2);
+ tcg_temp_free_i64(t2);
+ }
+ break;
+ case NM_MULT:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ gen_load_gpr(t0, v1);
+ gen_load_gpr(t1, ret);
+
+ TCGv_i32 t2 = tcg_temp_new_i32();
+ TCGv_i32 t3 = tcg_temp_new_i32();
+ tcg_gen_trunc_tl_i32(t2, t0);
+ tcg_gen_trunc_tl_i32(t3, t1);
+ tcg_gen_muls2_i32(t2, t3, t2, t3);
+ tcg_gen_ext_i32_tl(cpu_LO[acc], t2);
+ tcg_gen_ext_i32_tl(cpu_HI[acc], t3);
+ tcg_temp_free_i32(t2);
+ tcg_temp_free_i32(t3);
+ }
+ break;
+ case NM_EXTRV_W:
+ gen_load_gpr(v1_t, v1);
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extr_w(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_8_15:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAX_W_PH:
+ case NM_DPAQ_SA_L_W:
+ case NM_DPSX_W_PH:
+ case NM_DPSQ_SA_L_W:
+ gen_pool32axf_2_multiply(ctx, opc, ret, v1, v2);
+ break;
+ case NM_MADDU:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ TCGv_i64 t2 = tcg_temp_new_i64();
+ TCGv_i64 t3 = tcg_temp_new_i64();
+
+ gen_load_gpr(t0, v1);
+ gen_load_gpr(t1, ret);
+
+ tcg_gen_ext32u_tl(t0, t0);
+ tcg_gen_ext32u_tl(t1, t1);
+ tcg_gen_extu_tl_i64(t2, t0);
+ tcg_gen_extu_tl_i64(t3, t1);
+ tcg_gen_mul_i64(t2, t2, t3);
+ tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]);
+ tcg_gen_add_i64(t2, t2, t3);
+ tcg_temp_free_i64(t3);
+ gen_move_low32(cpu_LO[acc], t2);
+ gen_move_high32(cpu_HI[acc], t2);
+ tcg_temp_free_i64(t2);
+ }
+ break;
+ case NM_MULTU:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ TCGv_i32 t2 = tcg_temp_new_i32();
+ TCGv_i32 t3 = tcg_temp_new_i32();
+
+ gen_load_gpr(t0, v1);
+ gen_load_gpr(t1, ret);
+
+ tcg_gen_trunc_tl_i32(t2, t0);
+ tcg_gen_trunc_tl_i32(t3, t1);
+ tcg_gen_mulu2_i32(t2, t3, t2, t3);
+ tcg_gen_ext_i32_tl(cpu_LO[acc], t2);
+ tcg_gen_ext_i32_tl(cpu_HI[acc], t3);
+ tcg_temp_free_i32(t2);
+ tcg_temp_free_i32(t3);
+ }
+ break;
+ case NM_EXTRV_R_W:
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extr_r_w(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_16_23:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAU_H_QBL:
+ case NM_DPAQX_S_W_PH:
+ case NM_DPSU_H_QBL:
+ case NM_DPSQX_S_W_PH:
+ case NM_MULSA_W_PH:
+ gen_pool32axf_2_multiply(ctx, opc, ret, v1, v2);
+ break;
+ case NM_EXTPV:
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extp(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ case NM_MSUB:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ TCGv_i64 t2 = tcg_temp_new_i64();
+ TCGv_i64 t3 = tcg_temp_new_i64();
+
+ gen_load_gpr(t0, v1);
+ gen_load_gpr(t1, ret);
+
+ tcg_gen_ext_tl_i64(t2, t0);
+ tcg_gen_ext_tl_i64(t3, t1);
+ tcg_gen_mul_i64(t2, t2, t3);
+ tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]);
+ tcg_gen_sub_i64(t2, t3, t2);
+ tcg_temp_free_i64(t3);
+ gen_move_low32(cpu_LO[acc], t2);
+ gen_move_high32(cpu_HI[acc], t2);
+ tcg_temp_free_i64(t2);
+ }
+ break;
+ case NM_EXTRV_RS_W:
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extr_rs_w(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ }
+ break;
+ case NM_POOL32AXF_2_24_31:
+ switch (extract32(ctx->opcode, 9, 3)) {
+ case NM_DPAU_H_QBR:
+ case NM_DPAQX_SA_W_PH:
+ case NM_DPSU_H_QBR:
+ case NM_DPSQX_SA_W_PH:
+ case NM_MULSAQ_S_W_PH:
+ gen_pool32axf_2_multiply(ctx, opc, ret, v1, v2);
+ break;
+ case NM_EXTPDPV:
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extpdp(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ case NM_MSUBU:
+ {
+ int acc = extract32(ctx->opcode, 14, 2);
+
+ TCGv_i64 t2 = tcg_temp_new_i64();
+ TCGv_i64 t3 = tcg_temp_new_i64();
+
+ gen_load_gpr(t0, v1);
+ gen_load_gpr(t1, ret);
+
+ tcg_gen_ext32u_tl(t0, t0);
+ tcg_gen_ext32u_tl(t1, t1);
+ tcg_gen_extu_tl_i64(t2, t0);
+ tcg_gen_extu_tl_i64(t3, t1);
+ tcg_gen_mul_i64(t2, t2, t3);
+ tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]);
+ tcg_gen_sub_i64(t2, t3, t2);
+ tcg_temp_free_i64(t3);
+ gen_move_low32(cpu_LO[acc], t2);
+ gen_move_high32(cpu_HI[acc], t2);
+ tcg_temp_free_i64(t2);
+ }
+ break;
+ case NM_EXTRV_S_H:
+ tcg_gen_movi_tl(t0, v2 >> 3);
+ gen_helper_extr_s_h(cpu_gpr[ret], t0, v1_t, cpu_env);
+ break;
+ }
+ break;
+ default:
+ generate_exception_end(ctx, EXCP_RI);
+ break;
+ }
+
+ tcg_temp_free(t0);
+ tcg_temp_free(t1);
+
+ tcg_temp_free(v0_t);
+ tcg_temp_free(v1_t);
+}
+
static void gen_pool32axf_nanomips_insn(CPUMIPSState *env, DisasContext *ctx)
{
@@ -17054,6 +17416,10 @@ static void gen_pool32axf_nanomips_insn(CPUMIPSState
*env, DisasContext *ctx)
}
break;
case NM_POOL32AXF_2:
+ {
+ int32_t op1 = (ctx->opcode >> 12) & 0x03;
+ gen_pool32axf_2_nanomips_insn(ctx, op1, rt, rs, rd);
+ }
break;
case NM_POOL32AXF_4:
break;
--
2.7.4
