From 3fb763cb55c282a686e22b7639ff6615d527bb10 Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Thu, 16 Oct 2014 21:07:29 +0100 Subject: [PATCH 1/9] target-tricore: Add instructions of BOL opcode format Add instructions of BOL opcode format. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/translate.c | 48 ++++++++++++++++++++++++++++++++ target-tricore/tricore-opcodes.h | 4 ++- 2 files changed, 51 insertions(+), 1 deletion(-) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index d5a95969bb..28e268e8ee 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -2279,6 +2279,46 @@ static void decode_bo_addrmode_ldmst_bitreverse_circular(CPUTriCoreState *env, tcg_temp_free(temp3); } +static void decode_bol_opc(CPUTriCoreState *env, DisasContext *ctx, int32_t op1) +{ + int r1, r2; + int32_t address; + TCGv temp; + + r1 = MASK_OP_BOL_S1D(ctx->opcode); + r2 = MASK_OP_BOL_S2(ctx->opcode); + address = MASK_OP_BOL_OFF16_SEXT(ctx->opcode); + + switch (op1) { + case OPC1_32_BOL_LD_A_LONGOFF: + temp = tcg_temp_new(); + tcg_gen_addi_tl(temp, cpu_gpr_a[r2], address); + tcg_gen_qemu_ld_tl(cpu_gpr_a[r1], temp, ctx->mem_idx, MO_LEUL); + tcg_temp_free(temp); + break; + case OPC1_32_BOL_LD_W_LONFOFF: + temp = tcg_temp_new(); + tcg_gen_addi_tl(temp, cpu_gpr_a[r2], address); + tcg_gen_qemu_ld_tl(cpu_gpr_d[r1], temp, ctx->mem_idx, MO_LEUL); + tcg_temp_free(temp); + break; + case OPC1_32_BOL_LEA_LONGOFF: + tcg_gen_addi_tl(cpu_gpr_a[r1], cpu_gpr_a[r2], address); + break; + case OPC1_32_BOL_ST_A_LONGOFF: + if (tricore_feature(env, TRICORE_FEATURE_16)) { + gen_offset_st(ctx, cpu_gpr_a[r1], cpu_gpr_a[r2], address, MO_LEUL); + } else { + /* raise illegal opcode trap */ + } + break; + case OPC1_32_BOL_ST_W_LONGOFF: + gen_offset_st(ctx, cpu_gpr_d[r1], cpu_gpr_a[r2], address, MO_LEUL); + break; + } + +} + static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) { int op1; @@ -2405,6 +2445,14 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) case OPCM_32_BO_ADDRMODE_LDMST_BITREVERSE_CIRCULAR: decode_bo_addrmode_ldmst_bitreverse_circular(env, ctx); break; +/* BOL-format */ + case OPC1_32_BOL_LD_A_LONGOFF: + case OPC1_32_BOL_LD_W_LONFOFF: + case OPC1_32_BOL_LEA_LONGOFF: + case OPC1_32_BOL_ST_W_LONGOFF: + case OPC1_32_BOL_ST_A_LONGOFF: + decode_bol_opc(env, ctx, op1); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index 7e6f33bd62..ba07d85222 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -115,7 +115,9 @@ #define MASK_OP_BOL_OFF16(op) ((MASK_BITS_SHIFT(op, 16, 21) + \ (MASK_BITS_SHIFT(op, 28, 31) << 6)) + \ (MASK_BITS_SHIFT(op, 22, 27) >> 10)) - +#define MASK_OP_BOL_OFF16_SEXT(op) ((MASK_BITS_SHIFT(op, 16, 21) + \ + (MASK_BITS_SHIFT(op, 28, 31) << 6)) + \ + (MASK_BITS_SHIFT_SEXT(op, 22, 27) << 10)) #define MASK_OP_BOL_S2(op) MASK_BITS_SHIFT(op, 12, 15) #define MASK_OP_BOL_S1D(op) MASK_BITS_SHIFT(op, 8, 11) From fc2ef4a391c39688d35c7f78cec6a20d552e5a3b Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Fri, 17 Oct 2014 17:29:01 +0100 Subject: [PATCH 2/9] target-tricore: Add instructions of BRC opcode format Add instructions of BRC opcode format. Fixed OP2_BRC_JGE -> OP2_32_BRC_JGE Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/translate.c | 53 +++++++++++++++++++++++++++++++- target-tricore/tricore-opcodes.h | 6 ++-- 2 files changed, 56 insertions(+), 3 deletions(-) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 28e268e8ee..789f005088 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -665,6 +665,47 @@ static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1, tcg_gen_movi_tl(cpu_gpr_a[11], ctx->next_pc); gen_goto_tb(ctx, 0, ctx->pc + offset * 2); break; +/* BOL format */ + case OPCM_32_BRC_EQ_NEQ: + if (MASK_OP_BRC_OP2(ctx->opcode) == OPC2_32_BRC_JEQ) { + gen_branch_condi(ctx, TCG_COND_EQ, cpu_gpr_d[r1], constant, offset); + } else { + gen_branch_condi(ctx, TCG_COND_NE, cpu_gpr_d[r1], constant, offset); + } + break; + case OPCM_32_BRC_GE: + if (MASK_OP_BRC_OP2(ctx->opcode) == OP2_32_BRC_JGE) { + gen_branch_condi(ctx, TCG_COND_GE, cpu_gpr_d[r1], constant, offset); + } else { + constant = MASK_OP_BRC_CONST4(ctx->opcode); + gen_branch_condi(ctx, TCG_COND_GEU, cpu_gpr_d[r1], constant, + offset); + } + break; + case OPCM_32_BRC_JLT: + if (MASK_OP_BRC_OP2(ctx->opcode) == OPC2_32_BRC_JLT) { + gen_branch_condi(ctx, TCG_COND_LT, cpu_gpr_d[r1], constant, offset); + } else { + constant = MASK_OP_BRC_CONST4(ctx->opcode); + gen_branch_condi(ctx, TCG_COND_LTU, cpu_gpr_d[r1], constant, + offset); + } + break; + case OPCM_32_BRC_JNE: + temp = tcg_temp_new(); + if (MASK_OP_BRC_OP2(ctx->opcode) == OPC2_32_BRC_JNED) { + tcg_gen_mov_tl(temp, cpu_gpr_d[r1]); + /* subi is unconditional */ + tcg_gen_subi_tl(cpu_gpr_d[r1], cpu_gpr_d[r1], 1); + gen_branch_condi(ctx, TCG_COND_NE, temp, constant, offset); + } else { + tcg_gen_mov_tl(temp, cpu_gpr_d[r1]); + /* addi is unconditional */ + tcg_gen_addi_tl(cpu_gpr_d[r1], cpu_gpr_d[r1], 1); + gen_branch_condi(ctx, TCG_COND_NE, temp, constant, offset); + } + tcg_temp_free(temp); + break; default: printf("Branch Error at %x\n", ctx->pc); } @@ -2324,7 +2365,7 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) int op1; int32_t r1; int32_t address; - int8_t b; + int8_t b, const4; int32_t bpos; TCGv temp, temp2; @@ -2453,6 +2494,16 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) case OPC1_32_BOL_ST_A_LONGOFF: decode_bol_opc(env, ctx, op1); break; +/* BRC Format */ + case OPCM_32_BRC_EQ_NEQ: + case OPCM_32_BRC_GE: + case OPCM_32_BRC_JLT: + case OPCM_32_BRC_JNE: + const4 = MASK_OP_BRC_CONST4_SEXT(ctx->opcode); + address = MASK_OP_BRC_DISP15_SEXT(ctx->opcode); + r1 = MASK_OP_BRC_S1(ctx->opcode); + gen_compute_branch(ctx, op1, r1, 0, const4, address); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index ba07d85222..2d18624bef 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -124,7 +124,9 @@ /* BRC Format */ #define MASK_OP_BRC_OP2(op) MASK_BITS_SHIFT(op, 31, 31) #define MASK_OP_BRC_DISP15(op) MASK_BITS_SHIFT(op, 16, 30) +#define MASK_OP_BRC_DISP15_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 16, 30) #define MASK_OP_BRC_CONST4(op) MASK_BITS_SHIFT(op, 12, 15) +#define MASK_OP_BRC_CONST4_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 12, 15) #define MASK_OP_BRC_S1(op) MASK_BITS_SHIFT(op, 8, 11) /* BRN Format */ @@ -765,8 +767,8 @@ enum { }; /* OPCM_32_BRC_GE */ enum { - OP2_BRC_JGE = 0x00, - OPC_BRC_JGE_U = 0x01, + OP2_32_BRC_JGE = 0x00, + OPC_32_BRC_JGE_U = 0x01, }; /* OPCM_32_BRC_JLT */ enum { From 83c1bb1868848912f3d5516880e937cb247dfcd1 Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Fri, 17 Oct 2014 17:46:29 +0100 Subject: [PATCH 3/9] target-tricore: Add instructions of BRN opcode format Add instructions of BRN opcode format. Add MASK_OP_BRN_DISP15_SEXT. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/translate.c | 26 ++++++++++++++++++++++++++ target-tricore/tricore-opcodes.h | 1 + 2 files changed, 27 insertions(+) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 789f005088..428a41e8e8 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -568,6 +568,7 @@ static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1, int r2 , int32_t constant , int32_t offset) { TCGv temp; + int n; switch (opc) { /* SB-format jumps */ @@ -706,6 +707,20 @@ static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1, } tcg_temp_free(temp); break; +/* BRN format */ + case OPCM_32_BRN_JTT: + n = MASK_OP_BRN_N(ctx->opcode); + + temp = tcg_temp_new(); + tcg_gen_andi_tl(temp, cpu_gpr_d[r1], (1 << n)); + + if (MASK_OP_BRN_OP2(ctx->opcode) == OPC2_32_BRN_JNZ_T) { + gen_branch_condi(ctx, TCG_COND_NE, temp, 0, offset); + } else { + gen_branch_condi(ctx, TCG_COND_EQ, temp, 0, offset); + } + tcg_temp_free(temp); + break; default: printf("Branch Error at %x\n", ctx->pc); } @@ -2371,6 +2386,11 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) op1 = MASK_OP_MAJOR(ctx->opcode); + /* handle JNZ.T opcode only being 6 bit long */ + if (unlikely((op1 & 0x3f) == OPCM_32_BRN_JTT)) { + op1 = OPCM_32_BRN_JTT; + } + switch (op1) { /* ABS-format */ case OPCM_32_ABS_LDW: @@ -2504,6 +2524,12 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) r1 = MASK_OP_BRC_S1(ctx->opcode); gen_compute_branch(ctx, op1, r1, 0, const4, address); break; +/* BRN Format */ + case OPCM_32_BRN_JTT: + address = MASK_OP_BRN_DISP15_SEXT(ctx->opcode); + r1 = MASK_OP_BRN_S1(ctx->opcode); + gen_compute_branch(ctx, op1, r1, 0, 0, address); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index 2d18624bef..3622d388e2 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -132,6 +132,7 @@ /* BRN Format */ #define MASK_OP_BRN_OP2(op) MASK_BITS_SHIFT(op, 31, 31) #define MASK_OP_BRN_DISP15(op) MASK_BITS_SHIFT(op, 16, 30) +#define MASK_OP_BRN_DISP15_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 16, 30) #define MASK_OP_BRN_N(op) (MASK_BITS_SHIFT(op, 12, 15) + \ (MASK_BITS_SHIFT(op, 7, 7) << 4)) #define MASK_OP_BRN_S1(op) MASK_BITS_SHIFT(op, 8, 11) From a68e0d547f042f1d75f4d56ca5b6c4cc719d7077 Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Thu, 23 Oct 2014 12:18:02 +0100 Subject: [PATCH 4/9] target-tricore: Add instructions of BRR opcode format Add instructions of BRR opcode format. Add MASK_OP_BRR_DISP15_SEXT. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/translate.c | 90 +++++++++++++++++++++++++++++++- target-tricore/tricore-opcodes.h | 1 + 2 files changed, 89 insertions(+), 2 deletions(-) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 428a41e8e8..84dd47db00 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -567,7 +567,7 @@ static void gen_loop(DisasContext *ctx, int r1, int32_t offset) static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1, int r2 , int32_t constant , int32_t offset) { - TCGv temp; + TCGv temp, temp2; int n; switch (opc) { @@ -721,6 +721,79 @@ static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1, } tcg_temp_free(temp); break; +/* BRR Format */ + case OPCM_32_BRR_EQ_NEQ: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_JEQ) { + gen_branch_cond(ctx, TCG_COND_EQ, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } else { + gen_branch_cond(ctx, TCG_COND_NE, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } + break; + case OPCM_32_BRR_ADDR_EQ_NEQ: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_JEQ_A) { + gen_branch_cond(ctx, TCG_COND_EQ, cpu_gpr_a[r1], cpu_gpr_a[r2], + offset); + } else { + gen_branch_cond(ctx, TCG_COND_NE, cpu_gpr_a[r1], cpu_gpr_a[r2], + offset); + } + break; + case OPCM_32_BRR_GE: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_JGE) { + gen_branch_cond(ctx, TCG_COND_GE, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } else { + gen_branch_cond(ctx, TCG_COND_GEU, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } + break; + case OPCM_32_BRR_JLT: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_JLT) { + gen_branch_cond(ctx, TCG_COND_LT, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } else { + gen_branch_cond(ctx, TCG_COND_LTU, cpu_gpr_d[r1], cpu_gpr_d[r2], + offset); + } + break; + case OPCM_32_BRR_LOOP: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_LOOP) { + gen_loop(ctx, r1, offset * 2); + } else { + /* OPC2_32_BRR_LOOPU */ + gen_goto_tb(ctx, 0, ctx->pc + offset * 2); + } + break; + case OPCM_32_BRR_JNE: + temp = tcg_temp_new(); + temp2 = tcg_temp_new(); + if (MASK_OP_BRC_OP2(ctx->opcode) == OPC2_32_BRR_JNED) { + tcg_gen_mov_tl(temp, cpu_gpr_d[r1]); + /* also save r2, in case of r1 == r2, so r2 is not decremented */ + tcg_gen_mov_tl(temp2, cpu_gpr_d[r2]); + /* subi is unconditional */ + tcg_gen_subi_tl(cpu_gpr_d[r1], cpu_gpr_d[r1], 1); + gen_branch_cond(ctx, TCG_COND_NE, temp, temp2, offset); + } else { + tcg_gen_mov_tl(temp, cpu_gpr_d[r1]); + /* also save r2, in case of r1 == r2, so r2 is not decremented */ + tcg_gen_mov_tl(temp2, cpu_gpr_d[r2]); + /* addi is unconditional */ + tcg_gen_addi_tl(cpu_gpr_d[r1], cpu_gpr_d[r1], 1); + gen_branch_cond(ctx, TCG_COND_NE, temp, temp2, offset); + } + tcg_temp_free(temp); + tcg_temp_free(temp2); + break; + case OPCM_32_BRR_JNZ: + if (MASK_OP_BRR_OP2(ctx->opcode) == OPC2_32_BRR_JNZ_A) { + gen_branch_condi(ctx, TCG_COND_NE, cpu_gpr_a[r1], 0, offset); + } else { + gen_branch_condi(ctx, TCG_COND_EQ, cpu_gpr_a[r1], 0, offset); + } + break; default: printf("Branch Error at %x\n", ctx->pc); } @@ -2378,7 +2451,7 @@ static void decode_bol_opc(CPUTriCoreState *env, DisasContext *ctx, int32_t op1) static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) { int op1; - int32_t r1; + int32_t r1, r2; int32_t address; int8_t b, const4; int32_t bpos; @@ -2530,6 +2603,19 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) r1 = MASK_OP_BRN_S1(ctx->opcode); gen_compute_branch(ctx, op1, r1, 0, 0, address); break; +/* BRR Format */ + case OPCM_32_BRR_EQ_NEQ: + case OPCM_32_BRR_ADDR_EQ_NEQ: + case OPCM_32_BRR_GE: + case OPCM_32_BRR_JLT: + case OPCM_32_BRR_JNE: + case OPCM_32_BRR_JNZ: + case OPCM_32_BRR_LOOP: + address = MASK_OP_BRR_DISP15_SEXT(ctx->opcode); + r2 = MASK_OP_BRR_S2(ctx->opcode); + r1 = MASK_OP_BRR_S1(ctx->opcode); + gen_compute_branch(ctx, op1, r1, r2, 0, address); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index 3622d388e2..7d35e3e04d 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -139,6 +139,7 @@ /* BRR Format */ #define MASK_OP_BRR_OP2(op) MASK_BITS_SHIFT(op, 31, 31) #define MASK_OP_BRR_DISP15(op) MASK_BITS_SHIFT(op, 16, 30) +#define MASK_OP_BRR_DISP15_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 16, 30) #define MASK_OP_BRR_S2(op) MASK_BITS_SHIFT(op, 12, 15) #define MASK_OP_BRR_S1(op) MASK_BITS_SHIFT(op, 8, 11) From 0974257ed58ff3e9512d74ffa5b4039bbec49b2d Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Sun, 26 Oct 2014 21:49:41 +0000 Subject: [PATCH 5/9] target-tricore: Add instructions of RC opcode format Add instructions of RC opcode format. Add helper for mul, sha, absdif with signed saturation on overflow. Add helper for add, sub, mul with unsigned saturation on overflow. Add microcode generator functions: * gen_add_CC, which calculates the carry bit. * gen_addc_CC, which adds the carry bit to the add and calculates the carry bit. * gen_absdif, which calculates the absolute difference. * gen_mul_i64s/u, which mul two 32 bits val into one 64bit reg. * gen_sh_hi, which shifts two 16bit words in one reg. * gen_sha_hi, which does a arithmetic shift on two 16bit words. * gen_sh_cond, which shifts left a reg by one and writes the result of cond into the lsb. * gen_accumulating_cond, which ands/ors/xors the result of cond of the lsbs with the lsb of the result. * gen_eqany_bi/hi, which checks ever byte/hword on equality. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/helper.h | 6 + target-tricore/op_helper.c | 99 +++++ target-tricore/translate.c | 693 +++++++++++++++++++++++++++++++ target-tricore/tricore-opcodes.h | 1 + 4 files changed, 799 insertions(+) diff --git a/target-tricore/helper.h b/target-tricore/helper.h index b3fc33ceae..4893060245 100644 --- a/target-tricore/helper.h +++ b/target-tricore/helper.h @@ -17,7 +17,13 @@ /* Arithmetic */ DEF_HELPER_3(add_ssov, i32, env, i32, i32) +DEF_HELPER_3(add_suov, i32, env, i32, i32) DEF_HELPER_3(sub_ssov, i32, env, i32, i32) +DEF_HELPER_3(sub_suov, i32, env, i32, i32) +DEF_HELPER_3(mul_ssov, i32, env, i32, i32) +DEF_HELPER_3(mul_suov, i32, env, i32, i32) +DEF_HELPER_3(sha_ssov, i32, env, i32, i32) +DEF_HELPER_3(absdif_ssov, i32, env, i32, i32) /* CSA */ DEF_HELPER_2(call, void, env, i32) DEF_HELPER_1(ret, void, env) diff --git a/target-tricore/op_helper.c b/target-tricore/op_helper.c index a36988aa1b..d8d57b0687 100644 --- a/target-tricore/op_helper.c +++ b/target-tricore/op_helper.c @@ -77,6 +77,27 @@ uint32_t helper_circ_update(uint32_t reg, uint32_t off) env->PSW_USB_SAV |= env->PSW_USB_AV; \ } while (0) +#define SUOV(env, ret, arg, len) do { \ + int64_t max_pos = UINT##len ##_MAX; \ + if (arg > max_pos) { \ + env->PSW_USB_V = (1 << 31); \ + env->PSW_USB_SV = (1 << 31); \ + ret = (target_ulong)max_pos; \ + } else { \ + if (arg < 0) { \ + env->PSW_USB_V = (1 << 31); \ + env->PSW_USB_SV = (1 << 31); \ + ret = 0; \ + } else { \ + env->PSW_USB_V = 0; \ + ret = (target_ulong)arg; \ + } \ + } \ + env->PSW_USB_AV = arg ^ arg * 2u; \ + env->PSW_USB_SAV |= env->PSW_USB_AV; \ +} while (0) + + target_ulong helper_add_ssov(CPUTriCoreState *env, target_ulong r1, target_ulong r2) { @@ -88,6 +109,17 @@ target_ulong helper_add_ssov(CPUTriCoreState *env, target_ulong r1, return ret; } +target_ulong helper_add_suov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = extract64(r1, 0, 32); + int64_t t2 = extract64(r2, 0, 32); + int64_t result = t1 + t2; + SUOV(env, ret, result, 32); + return ret; +} + target_ulong helper_sub_ssov(CPUTriCoreState *env, target_ulong r1, target_ulong r2) { @@ -99,6 +131,73 @@ target_ulong helper_sub_ssov(CPUTriCoreState *env, target_ulong r1, return ret; } +target_ulong helper_sub_suov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = extract64(r1, 0, 32); + int64_t t2 = extract64(r2, 0, 32); + int64_t result = t1 - t2; + SUOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_mul_ssov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t2 = sextract64(r2, 0, 32); + int64_t result = t1 * t2; + SSOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_mul_suov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = extract64(r1, 0, 32); + int64_t t2 = extract64(r2, 0, 32); + int64_t result = t1 * t2; + SUOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_sha_ssov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = sextract64(r1, 0, 32); + int32_t t2 = sextract64(r2, 0, 6); + int64_t result; + if (t2 == 0) { + result = t1; + } else if (t2 > 0) { + result = t1 << t2; + } else { + result = t1 >> -t2; + } + SSOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_absdif_ssov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2) +{ + target_ulong ret; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t2 = sextract64(r2, 0, 32); + int64_t result; + + if (t1 > t2) { + result = t1 - t2; + } else { + result = t2 - t1; + } + SSOV(env, ret, result, 32); + return ret; +} /* context save area (CSA) related helpers */ static int cdc_increment(target_ulong *psw) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 84dd47db00..1daf26d20e 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -265,6 +265,76 @@ static inline void gen_addi_d(TCGv ret, TCGv r1, target_ulong r2) gen_add_d(ret, r1, temp); tcg_temp_free(temp); } +/* calculate the carry bit too */ +static inline void gen_add_CC(TCGv ret, TCGv r1, TCGv r2) +{ + TCGv t0 = tcg_temp_new_i32(); + TCGv result = tcg_temp_new_i32(); + + tcg_gen_movi_tl(t0, 0); + /* Addition and set C/V/SV bits */ + tcg_gen_add2_i32(result, cpu_PSW_C, r1, t0, r2, t0); + /* calc V bit */ + tcg_gen_xor_tl(cpu_PSW_V, result, r1); + tcg_gen_xor_tl(t0, r1, r2); + tcg_gen_andc_tl(cpu_PSW_V, cpu_PSW_V, t0); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, result, result); + tcg_gen_xor_tl(cpu_PSW_AV, result, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + /* write back result */ + tcg_gen_mov_tl(ret, result); + + tcg_temp_free(result); + tcg_temp_free(t0); +} + +static inline void gen_addi_CC(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_add_CC(ret, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_addc_CC(TCGv ret, TCGv r1, TCGv r2) +{ + TCGv carry = tcg_temp_new_i32(); + TCGv t0 = tcg_temp_new_i32(); + TCGv result = tcg_temp_new_i32(); + + tcg_gen_movi_tl(t0, 0); + tcg_gen_setcondi_tl(TCG_COND_NE, carry, cpu_PSW_C, 0); + /* Addition, carry and set C/V/SV bits */ + tcg_gen_add2_i32(result, cpu_PSW_C, r1, t0, carry, t0); + tcg_gen_add2_i32(result, cpu_PSW_C, result, cpu_PSW_C, r2, t0); + /* calc V bit */ + tcg_gen_xor_tl(cpu_PSW_V, result, r1); + tcg_gen_xor_tl(t0, r1, r2); + tcg_gen_andc_tl(cpu_PSW_V, cpu_PSW_V, t0); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, result, result); + tcg_gen_xor_tl(cpu_PSW_AV, result, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + /* write back result */ + tcg_gen_mov_tl(ret, result); + + tcg_temp_free(result); + tcg_temp_free(t0); + tcg_temp_free(carry); +} + +static inline void gen_addci_CC(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_addc_CC(ret, r1, temp); + tcg_temp_free(temp); +} static inline void gen_cond_add(TCGCond cond, TCGv r1, TCGv r2, TCGv r3, TCGv r4) @@ -337,6 +407,49 @@ static inline void gen_sub_d(TCGv ret, TCGv r1, TCGv r2) tcg_temp_free(result); } +static inline void gen_absdif(TCGv ret, TCGv r1, TCGv r2) +{ + TCGv temp = tcg_temp_new_i32(); + TCGv result = tcg_temp_new_i32(); + + tcg_gen_sub_tl(result, r1, r2); + tcg_gen_sub_tl(temp, r2, r1); + tcg_gen_movcond_tl(TCG_COND_GT, result, r1, r2, result, temp); + + /* calc V bit */ + tcg_gen_xor_tl(cpu_PSW_V, result, r1); + tcg_gen_xor_tl(temp, result, r2); + tcg_gen_movcond_tl(TCG_COND_GT, cpu_PSW_V, r1, r2, cpu_PSW_V, temp); + tcg_gen_xor_tl(temp, r1, r2); + tcg_gen_and_tl(cpu_PSW_V, cpu_PSW_V, temp); + /* calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV bit */ + tcg_gen_add_tl(cpu_PSW_AV, result, result); + tcg_gen_xor_tl(cpu_PSW_AV, result, cpu_PSW_AV); + /* calc SAV bit */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + /* write back result */ + tcg_gen_mov_tl(ret, result); + + tcg_temp_free(temp); + tcg_temp_free(result); +} + +static inline void gen_absdifi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_absdif(ret, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_absdifsi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_absdif_ssov(ret, cpu_env, r1, temp); + tcg_temp_free(temp); +} + static inline void gen_mul_i32s(TCGv ret, TCGv r1, TCGv r2) { TCGv high = tcg_temp_new(); @@ -360,6 +473,71 @@ static inline void gen_mul_i32s(TCGv ret, TCGv r1, TCGv r2) tcg_temp_free(low); } +static inline void gen_muli_i32s(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_mul_i32s(ret, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_mul_i64s(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2) +{ + tcg_gen_muls2_tl(ret_low, ret_high, r1, r2); + /* clear V bit */ + tcg_gen_movi_tl(cpu_PSW_V, 0); + /* calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV bit */ + tcg_gen_add_tl(cpu_PSW_AV, ret_high, ret_high); + tcg_gen_xor_tl(cpu_PSW_AV, ret_high, cpu_PSW_AV); + /* calc SAV bit */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); +} + +static inline void gen_muli_i64s(TCGv ret_low, TCGv ret_high, TCGv r1, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_mul_i64s(ret_low, ret_high, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_mul_i64u(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2) +{ + tcg_gen_mulu2_tl(ret_low, ret_high, r1, r2); + /* clear V bit */ + tcg_gen_movi_tl(cpu_PSW_V, 0); + /* calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV bit */ + tcg_gen_add_tl(cpu_PSW_AV, ret_high, ret_high); + tcg_gen_xor_tl(cpu_PSW_AV, ret_high, cpu_PSW_AV); + /* calc SAV bit */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); +} + +static inline void gen_muli_i64u(TCGv ret_low, TCGv ret_high, TCGv r1, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_mul_i64u(ret_low, ret_high, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_mulsi_i32(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_mul_ssov(ret, cpu_env, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_mulsui_i32(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_mul_suov(ret, cpu_env, r1, temp); + tcg_temp_free(temp); +} + static void gen_saturate(TCGv ret, TCGv arg, int32_t up, int32_t low) { TCGv sat_neg = tcg_const_i32(low); @@ -394,6 +572,27 @@ static void gen_shi(TCGv ret, TCGv r1, int32_t shift_count) } } +static void gen_sh_hi(TCGv ret, TCGv r1, int32_t shiftcount) +{ + TCGv temp_low, temp_high; + + if (shiftcount == -16) { + tcg_gen_movi_tl(ret, 0); + } else { + temp_high = tcg_temp_new(); + temp_low = tcg_temp_new(); + + tcg_gen_andi_tl(temp_low, r1, 0xffff); + tcg_gen_andi_tl(temp_high, r1, 0xffff0000); + gen_shi(temp_low, temp_low, shiftcount); + gen_shi(ret, temp_high, shiftcount); + tcg_gen_deposit_tl(ret, ret, temp_low, 0, 16); + + tcg_temp_free(temp_low); + tcg_temp_free(temp_high); + } +} + static void gen_shaci(TCGv ret, TCGv r1, int32_t shift_count) { uint32_t msk, msk_start; @@ -453,16 +652,100 @@ static void gen_shaci(TCGv ret, TCGv r1, int32_t shift_count) tcg_temp_free(t_0); } +static void gen_shas(TCGv ret, TCGv r1, TCGv r2) +{ + gen_helper_sha_ssov(ret, cpu_env, r1, r2); +} + +static void gen_shasi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_shas(ret, r1, temp); + tcg_temp_free(temp); +} + +static void gen_sha_hi(TCGv ret, TCGv r1, int32_t shift_count) +{ + TCGv low, high; + + if (shift_count == 0) { + tcg_gen_mov_tl(ret, r1); + } else if (shift_count > 0) { + low = tcg_temp_new(); + high = tcg_temp_new(); + + tcg_gen_andi_tl(high, r1, 0xffff0000); + tcg_gen_shli_tl(low, r1, shift_count); + tcg_gen_shli_tl(ret, high, shift_count); + tcg_gen_deposit_tl(ret, ret, low, 0, 16); + + tcg_temp_free(low); + tcg_temp_free(high); + } else { + low = tcg_temp_new(); + high = tcg_temp_new(); + + tcg_gen_ext16s_tl(low, r1); + tcg_gen_sari_tl(low, low, -shift_count); + tcg_gen_sari_tl(ret, r1, -shift_count); + tcg_gen_deposit_tl(ret, ret, low, 0, 16); + + tcg_temp_free(low); + tcg_temp_free(high); + } + +} + +/* ret = {ret[30:0], (r1 cond r2)}; */ +static void gen_sh_cond(int cond, TCGv ret, TCGv r1, TCGv r2) +{ + TCGv temp = tcg_temp_new(); + TCGv temp2 = tcg_temp_new(); + + tcg_gen_shli_tl(temp, ret, 1); + tcg_gen_setcond_tl(cond, temp2, r1, r2); + tcg_gen_or_tl(ret, temp, temp2); + + tcg_temp_free(temp); + tcg_temp_free(temp2); +} + +static void gen_sh_condi(int cond, TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_sh_cond(cond, ret, r1, temp); + tcg_temp_free(temp); +} + static inline void gen_adds(TCGv ret, TCGv r1, TCGv r2) { gen_helper_add_ssov(ret, cpu_env, r1, r2); } +static inline void gen_addsi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_add_ssov(ret, cpu_env, r1, temp); + tcg_temp_free(temp); +} + +static inline void gen_addsui(TCGv ret, TCGv r1, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_add_suov(ret, cpu_env, r1, temp); + tcg_temp_free(temp); +} + static inline void gen_subs(TCGv ret, TCGv r1, TCGv r2) { gen_helper_sub_ssov(ret, cpu_env, r1, r2); } +static inline void gen_subsu(TCGv ret, TCGv r1, TCGv r2) +{ + gen_helper_sub_suov(ret, cpu_env, r1, r2); +} + static inline void gen_bit_2op(TCGv ret, TCGv r1, TCGv r2, int pos1, int pos2, void(*op1)(TCGv, TCGv, TCGv), @@ -506,6 +789,88 @@ static inline void gen_bit_1op(TCGv ret, TCGv r1, TCGv r2, tcg_temp_free(temp2); } +static inline void gen_accumulating_cond(int cond, TCGv ret, TCGv r1, TCGv r2, + void(*op)(TCGv, TCGv, TCGv)) +{ + TCGv temp = tcg_temp_new(); + TCGv temp2 = tcg_temp_new(); + /* temp = (arg1 cond arg2 )*/ + tcg_gen_setcond_tl(cond, temp, r1, r2); + /* temp2 = ret[0]*/ + tcg_gen_andi_tl(temp2, ret, 0x1); + /* temp = temp insn temp2 */ + (*op)(temp, temp, temp2); + /* ret = {ret[31:1], temp} */ + tcg_gen_deposit_tl(ret, ret, temp, 0, 1); + + tcg_temp_free(temp); + tcg_temp_free(temp2); +} + +static inline void +gen_accumulating_condi(int cond, TCGv ret, TCGv r1, int32_t con, + void(*op)(TCGv, TCGv, TCGv)) +{ + TCGv temp = tcg_const_i32(con); + gen_accumulating_cond(cond, ret, r1, temp, op); + tcg_temp_free(temp); +} + +static inline void gen_eqany_bi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv b0 = tcg_temp_new(); + TCGv b1 = tcg_temp_new(); + TCGv b2 = tcg_temp_new(); + TCGv b3 = tcg_temp_new(); + + /* byte 0 */ + tcg_gen_andi_tl(b0, r1, 0xff); + tcg_gen_setcondi_tl(TCG_COND_EQ, b0, b0, con & 0xff); + + /* byte 1 */ + tcg_gen_andi_tl(b1, r1, 0xff00); + tcg_gen_setcondi_tl(TCG_COND_EQ, b1, b1, con & 0xff00); + + /* byte 2 */ + tcg_gen_andi_tl(b2, r1, 0xff0000); + tcg_gen_setcondi_tl(TCG_COND_EQ, b2, b2, con & 0xff0000); + + /* byte 3 */ + tcg_gen_andi_tl(b3, r1, 0xff000000); + tcg_gen_setcondi_tl(TCG_COND_EQ, b3, b3, con & 0xff000000); + + /* combine them */ + tcg_gen_or_tl(ret, b0, b1); + tcg_gen_or_tl(ret, ret, b2); + tcg_gen_or_tl(ret, ret, b3); + + tcg_temp_free(b0); + tcg_temp_free(b1); + tcg_temp_free(b2); + tcg_temp_free(b3); +} + +static inline void gen_eqany_hi(TCGv ret, TCGv r1, int32_t con) +{ + TCGv h0 = tcg_temp_new(); + TCGv h1 = tcg_temp_new(); + + /* halfword 0 */ + tcg_gen_andi_tl(h0, r1, 0xffff); + tcg_gen_setcondi_tl(TCG_COND_EQ, h0, h0, con & 0xffff); + + /* halfword 1 */ + tcg_gen_andi_tl(h1, r1, 0xffff0000); + tcg_gen_setcondi_tl(TCG_COND_EQ, h1, h1, con & 0xffff0000); + + /* combine them */ + tcg_gen_or_tl(ret, h0, h1); + + tcg_temp_free(h0); + tcg_temp_free(h1); +} + + /* helpers for generating program flow micro-ops */ static inline void gen_save_pc(target_ulong pc) @@ -2448,6 +2813,321 @@ static void decode_bol_opc(CPUTriCoreState *env, DisasContext *ctx, int32_t op1) } +/* RC format */ +static void decode_rc_logical_shift(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r2; + int32_t const9; + TCGv temp; + + r2 = MASK_OP_RC_D(ctx->opcode); + r1 = MASK_OP_RC_S1(ctx->opcode); + const9 = MASK_OP_RC_CONST9(ctx->opcode); + op2 = MASK_OP_RC_OP2(ctx->opcode); + + temp = tcg_temp_new(); + + switch (op2) { + case OPC2_32_RC_AND: + tcg_gen_andi_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ANDN: + tcg_gen_andi_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], ~const9); + break; + case OPC2_32_RC_NAND: + tcg_gen_movi_tl(temp, const9); + tcg_gen_nand_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_NOR: + tcg_gen_movi_tl(temp, const9); + tcg_gen_nor_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_OR: + tcg_gen_ori_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ORN: + tcg_gen_ori_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], ~const9); + break; + case OPC2_32_RC_SH: + const9 = sextract32(const9, 0, 6); + gen_shi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_H: + const9 = sextract32(const9, 0, 5); + gen_sh_hi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SHA: + const9 = sextract32(const9, 0, 6); + gen_shaci(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SHA_H: + const9 = sextract32(const9, 0, 5); + gen_sha_hi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SHAS: + gen_shasi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_XNOR: + tcg_gen_xori_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + tcg_gen_not_tl(cpu_gpr_d[r2], cpu_gpr_d[r2]); + break; + case OPC2_32_RC_XOR: + tcg_gen_xori_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + } + tcg_temp_free(temp); +} + +static void decode_rc_accumulator(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r2; + int16_t const9; + + TCGv temp; + + r2 = MASK_OP_RC_D(ctx->opcode); + r1 = MASK_OP_RC_S1(ctx->opcode); + const9 = MASK_OP_RC_CONST9_SEXT(ctx->opcode); + + op2 = MASK_OP_RC_OP2(ctx->opcode); + + temp = tcg_temp_new(); + + switch (op2) { + case OPC2_32_RC_ABSDIF: + gen_absdifi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ABSDIFS: + gen_absdifsi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ADD: + gen_addi_d(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ADDC: + gen_addci_CC(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ADDS: + gen_addsi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ADDS_U: + gen_addsui(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_ADDX: + gen_addi_CC(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_AND_EQ: + gen_accumulating_condi(TCG_COND_EQ, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_AND_GE: + gen_accumulating_condi(TCG_COND_GE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_AND_GE_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_GEU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_AND_LT: + gen_accumulating_condi(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_AND_LT_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_AND_NE: + gen_accumulating_condi(TCG_COND_NE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_and_tl); + break; + case OPC2_32_RC_EQ: + tcg_gen_setcondi_tl(TCG_COND_EQ, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_EQANY_B: + gen_eqany_bi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_EQANY_H: + gen_eqany_hi(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_GE: + tcg_gen_setcondi_tl(TCG_COND_GE, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_GE_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + tcg_gen_setcondi_tl(TCG_COND_GEU, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_LT: + tcg_gen_setcondi_tl(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_LT_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + tcg_gen_setcondi_tl(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_MAX: + tcg_gen_movi_tl(temp, const9); + tcg_gen_movcond_tl(TCG_COND_GT, cpu_gpr_d[r2], cpu_gpr_d[r1], temp, + cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_MAX_U: + tcg_gen_movi_tl(temp, MASK_OP_RC_CONST9(ctx->opcode)); + tcg_gen_movcond_tl(TCG_COND_GTU, cpu_gpr_d[r2], cpu_gpr_d[r1], temp, + cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_MIN: + tcg_gen_movi_tl(temp, const9); + tcg_gen_movcond_tl(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], temp, + cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_MIN_U: + tcg_gen_movi_tl(temp, MASK_OP_RC_CONST9(ctx->opcode)); + tcg_gen_movcond_tl(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], temp, + cpu_gpr_d[r1], temp); + break; + case OPC2_32_RC_NE: + tcg_gen_setcondi_tl(TCG_COND_NE, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_OR_EQ: + gen_accumulating_condi(TCG_COND_EQ, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_OR_GE: + gen_accumulating_condi(TCG_COND_GE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_OR_GE_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_GEU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_OR_LT: + gen_accumulating_condi(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_OR_LT_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_OR_NE: + gen_accumulating_condi(TCG_COND_NE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_or_tl); + break; + case OPC2_32_RC_RSUB: + tcg_gen_movi_tl(temp, const9); + gen_sub_d(cpu_gpr_d[r2], temp, cpu_gpr_d[r1]); + break; + case OPC2_32_RC_RSUBS: + tcg_gen_movi_tl(temp, const9); + gen_subs(cpu_gpr_d[r2], temp, cpu_gpr_d[r1]); + break; + case OPC2_32_RC_RSUBS_U: + tcg_gen_movi_tl(temp, const9); + gen_subsu(cpu_gpr_d[r2], temp, cpu_gpr_d[r1]); + break; + case OPC2_32_RC_SH_EQ: + gen_sh_condi(TCG_COND_EQ, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_GE: + gen_sh_condi(TCG_COND_GE, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_GE_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_sh_condi(TCG_COND_GEU, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_LT: + gen_sh_condi(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_LT_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_sh_condi(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_SH_NE: + gen_sh_condi(TCG_COND_NE, cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_XOR_EQ: + gen_accumulating_condi(TCG_COND_EQ, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + case OPC2_32_RC_XOR_GE: + gen_accumulating_condi(TCG_COND_GE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + case OPC2_32_RC_XOR_GE_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_GEU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + case OPC2_32_RC_XOR_LT: + gen_accumulating_condi(TCG_COND_LT, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + case OPC2_32_RC_XOR_LT_U: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_accumulating_condi(TCG_COND_LTU, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + case OPC2_32_RC_XOR_NE: + gen_accumulating_condi(TCG_COND_NE, cpu_gpr_d[r2], cpu_gpr_d[r1], + const9, &tcg_gen_xor_tl); + break; + } + tcg_temp_free(temp); +} + +static void decode_rc_serviceroutine(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + uint32_t const9; + + op2 = MASK_OP_RC_OP2(ctx->opcode); + const9 = MASK_OP_RC_CONST9(ctx->opcode); + + switch (op2) { + case OPC2_32_RC_BISR: + gen_helper_1arg(bisr, const9); + break; + case OPC2_32_RC_SYSCALL: + /* TODO: Add exception generation */ + break; + } +} + +static void decode_rc_mul(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r2; + int16_t const9; + + r2 = MASK_OP_RC_D(ctx->opcode); + r1 = MASK_OP_RC_S1(ctx->opcode); + const9 = MASK_OP_RC_CONST9_SEXT(ctx->opcode); + + op2 = MASK_OP_RC_OP2(ctx->opcode); + + switch (op2) { + case OPC2_32_RC_MUL_32: + gen_muli_i32s(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_MUL_64: + gen_muli_i64s(cpu_gpr_d[r2], cpu_gpr_d[r2+1], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_MULS_32: + gen_mulsi_i32(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_MUL_U_64: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_muli_i64u(cpu_gpr_d[r2], cpu_gpr_d[r2+1], cpu_gpr_d[r1], const9); + break; + case OPC2_32_RC_MULS_U_32: + const9 = MASK_OP_RC_CONST9(ctx->opcode); + gen_mulsui_i32(cpu_gpr_d[r2], cpu_gpr_d[r1], const9); + break; + } +} + static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) { int op1; @@ -2616,6 +3296,19 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) r1 = MASK_OP_BRR_S1(ctx->opcode); gen_compute_branch(ctx, op1, r1, r2, 0, address); break; +/* RC Format */ + case OPCM_32_RC_LOGICAL_SHIFT: + decode_rc_logical_shift(env, ctx); + break; + case OPCM_32_RC_ACCUMULATOR: + decode_rc_accumulator(env, ctx); + break; + case OPCM_32_RC_SERVICEROUTINE: + decode_rc_serviceroutine(env, ctx); + break; + case OPCM_32_RC_MUL: + decode_rc_mul(env, ctx); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index 7d35e3e04d..9b042e4b37 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -151,6 +151,7 @@ #define MASK_OP_RC_D(op) MASK_OP_META_D(op) #define MASK_OP_RC_OP2(op) MASK_BITS_SHIFT(op, 21, 27) #define MASK_OP_RC_CONST9(op) MASK_BITS_SHIFT(op, 12, 20) +#define MASK_OP_RC_CONST9_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 12, 20) #define MASK_OP_RC_S1(op) MASK_OP_META_S1(op) /* RCPW Format */ From 47e04430ed3e6ab835f023a5c84381ca2ce9f4d8 Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Thu, 13 Nov 2014 14:17:08 +0000 Subject: [PATCH 6/9] target-tricore: Make TRICORE_FEATURES implying others. Since all the TriCore instructionsets are subsets of each other (1.3 C 1.3.1 C 1.6), make the features implying each other, e.g 1.6 also has 1.3.1 and 1.3. This way we only need to check our features for the instructionset, where a instruction was first introduced. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/cpu.c | 9 +++++++++ target-tricore/translate.c | 6 +++--- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/target-tricore/cpu.c b/target-tricore/cpu.c index 7bf041afb9..abe16fa7e6 100644 --- a/target-tricore/cpu.c +++ b/target-tricore/cpu.c @@ -63,8 +63,17 @@ static bool tricore_cpu_has_work(CPUState *cs) static void tricore_cpu_realizefn(DeviceState *dev, Error **errp) { CPUState *cs = CPU(dev); + TriCoreCPU *cpu = TRICORE_CPU(dev); TriCoreCPUClass *tcc = TRICORE_CPU_GET_CLASS(dev); + CPUTriCoreState *env = &cpu->env; + /* Some features automatically imply others */ + if (tricore_feature(env, TRICORE_FEATURE_16)) { + set_feature(env, TRICORE_FEATURE_131); + } + if (tricore_feature(env, TRICORE_FEATURE_131)) { + set_feature(env, TRICORE_FEATURE_13); + } cpu_reset(cs); qemu_init_vcpu(cs); diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 1daf26d20e..3775374b38 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -2206,17 +2206,17 @@ static void decode_bo_addrmode_post_pre_base(CPUTriCoreState *env, case OPC2_32_BO_CACHEI_WI_SHORTOFF: case OPC2_32_BO_CACHEI_W_SHORTOFF: /* TODO: Raise illegal opcode trap, - if tricore_feature(TRICORE_FEATURE_13) */ + if !tricore_feature(TRICORE_FEATURE_131) */ break; case OPC2_32_BO_CACHEI_W_POSTINC: case OPC2_32_BO_CACHEI_WI_POSTINC: - if (!tricore_feature(env, TRICORE_FEATURE_13)) { + if (tricore_feature(env, TRICORE_FEATURE_131)) { tcg_gen_addi_tl(cpu_gpr_d[r2], cpu_gpr_d[r2], off10); } /* TODO: else raise illegal opcode trap */ break; case OPC2_32_BO_CACHEI_W_PREINC: case OPC2_32_BO_CACHEI_WI_PREINC: - if (!tricore_feature(env, TRICORE_FEATURE_13)) { + if (tricore_feature(env, TRICORE_FEATURE_131)) { tcg_gen_addi_tl(cpu_gpr_d[r2], cpu_gpr_d[r2], off10); } /* TODO: else raise illegal opcode trap */ break; From ed51626066ea40092335f653780b6d1ca22c574a Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Wed, 29 Oct 2014 19:48:18 +0000 Subject: [PATCH 7/9] target-tricore: Add instructions of RCPW, RCRR and RCRW opcode format Add instructions of RCPW, RCRR and RCRW opcode format. Add microcode generator function gen_insert. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/translate.c | 132 ++++++++++++++++++++++++++++++++++++- 1 file changed, 129 insertions(+), 3 deletions(-) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 3775374b38..689596f985 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -869,7 +869,28 @@ static inline void gen_eqany_hi(TCGv ret, TCGv r1, int32_t con) tcg_temp_free(h0); tcg_temp_free(h1); } +/* mask = ((1 << width) -1) << pos; + ret = (r1 & ~mask) | (r2 << pos) & mask); */ +static inline void gen_insert(TCGv ret, TCGv r1, TCGv r2, TCGv width, TCGv pos) +{ + TCGv mask = tcg_temp_new(); + TCGv temp = tcg_temp_new(); + TCGv temp2 = tcg_temp_new(); + tcg_gen_movi_tl(mask, 1); + tcg_gen_shl_tl(mask, mask, width); + tcg_gen_subi_tl(mask, mask, 1); + tcg_gen_shl_tl(mask, mask, pos); + + tcg_gen_shl_tl(temp, r2, pos); + tcg_gen_and_tl(temp, temp, mask); + tcg_gen_andc_tl(temp2, r1, mask); + tcg_gen_or_tl(ret, temp, temp2); + + tcg_temp_free(mask); + tcg_temp_free(temp); + tcg_temp_free(temp2); +} /* helpers for generating program flow micro-ops */ @@ -3128,14 +3149,92 @@ static void decode_rc_mul(CPUTriCoreState *env, DisasContext *ctx) } } +/* RCPW format */ +static void decode_rcpw_insert(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r2; + int32_t pos, width, const4; + + TCGv temp; + + op2 = MASK_OP_RCPW_OP2(ctx->opcode); + r1 = MASK_OP_RCPW_S1(ctx->opcode); + r2 = MASK_OP_RCPW_D(ctx->opcode); + const4 = MASK_OP_RCPW_CONST4(ctx->opcode); + width = MASK_OP_RCPW_WIDTH(ctx->opcode); + pos = MASK_OP_RCPW_POS(ctx->opcode); + + switch (op2) { + case OPC2_32_RCPW_IMASK: + /* if pos + width > 31 undefined result */ + if (pos + width <= 31) { + tcg_gen_movi_tl(cpu_gpr_d[r2+1], ((1u << width) - 1) << pos); + tcg_gen_movi_tl(cpu_gpr_d[r2], (const4 << pos)); + } + break; + case OPC2_32_RCPW_INSERT: + /* if pos + width > 32 undefined result */ + if (pos + width <= 32) { + temp = tcg_const_i32(const4); + tcg_gen_deposit_tl(cpu_gpr_d[r2], cpu_gpr_d[r1], temp, pos, width); + tcg_temp_free(temp); + } + break; + } +} + +/* RCRW format */ + +static void decode_rcrw_insert(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r3, r4; + int32_t width, const4; + + TCGv temp, temp2, temp3; + + op2 = MASK_OP_RCRW_OP2(ctx->opcode); + r1 = MASK_OP_RCRW_S1(ctx->opcode); + r3 = MASK_OP_RCRW_S3(ctx->opcode); + r4 = MASK_OP_RCRW_D(ctx->opcode); + width = MASK_OP_RCRW_WIDTH(ctx->opcode); + const4 = MASK_OP_RCRW_CONST4(ctx->opcode); + + temp = tcg_temp_new(); + temp2 = tcg_temp_new(); + + switch (op2) { + case OPC2_32_RCRW_IMASK: + tcg_gen_andi_tl(temp, cpu_gpr_d[r4], 0x1f); + tcg_gen_movi_tl(temp2, (1 << width) - 1); + tcg_gen_shl_tl(cpu_gpr_d[r3 + 1], temp2, temp); + tcg_gen_movi_tl(temp2, const4); + tcg_gen_shl_tl(cpu_gpr_d[r3], temp2, temp); + break; + case OPC2_32_RCRW_INSERT: + temp3 = tcg_temp_new(); + + tcg_gen_movi_tl(temp, width); + tcg_gen_movi_tl(temp2, const4); + tcg_gen_andi_tl(temp3, cpu_gpr_d[r4], 0x1f); + gen_insert(cpu_gpr_d[r3], cpu_gpr_d[r1], temp2, temp, temp3); + + tcg_temp_free(temp3); + break; + } + tcg_temp_free(temp); + tcg_temp_free(temp2); +} + static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) { int op1; - int32_t r1, r2; - int32_t address; + int32_t r1, r2, r3; + int32_t address, const16; int8_t b, const4; int32_t bpos; - TCGv temp, temp2; + TCGv temp, temp2, temp3; op1 = MASK_OP_MAJOR(ctx->opcode); @@ -3309,6 +3408,33 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) case OPCM_32_RC_MUL: decode_rc_mul(env, ctx); break; +/* RCPW Format */ + case OPCM_32_RCPW_MASK_INSERT: + decode_rcpw_insert(env, ctx); + break; +/* RCRR Format */ + case OPC1_32_RCRR_INSERT: + r1 = MASK_OP_RCRR_S1(ctx->opcode); + r2 = MASK_OP_RCRR_S3(ctx->opcode); + r3 = MASK_OP_RCRR_D(ctx->opcode); + const16 = MASK_OP_RCRR_CONST4(ctx->opcode); + temp = tcg_const_i32(const16); + temp2 = tcg_temp_new(); /* width*/ + temp3 = tcg_temp_new(); /* pos */ + + tcg_gen_andi_tl(temp2, cpu_gpr_d[r3+1], 0x1f); + tcg_gen_andi_tl(temp3, cpu_gpr_d[r3], 0x1f); + + gen_insert(cpu_gpr_d[r2], cpu_gpr_d[r1], temp, temp2, temp3); + + tcg_temp_free(temp); + tcg_temp_free(temp2); + tcg_temp_free(temp3); + break; +/* RCRW Format */ + case OPCM_32_RCRW_MASK_INSERT: + decode_rcrw_insert(env, ctx); + break; } } From 2b2f7d97d856a4e7020d881ec1e6e60be64d0ab6 Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Thu, 30 Oct 2014 12:06:53 +0000 Subject: [PATCH 8/9] target-tricore: Add instructions of RLC opcode format Add instructions of RLC opcode format. Add helper psw_write/read. Add microcode generator gen_mtcr/mfcr, which loads/stores a value to a core special function register, which are defined in csfr.def Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/csfr.def | 124 +++++++++++++++++++++++++++++++ target-tricore/helper.h | 3 + target-tricore/op_helper.c | 11 +++ target-tricore/translate.c | 113 ++++++++++++++++++++++++++++ target-tricore/tricore-opcodes.h | 1 + 5 files changed, 252 insertions(+) create mode 100644 target-tricore/csfr.def diff --git a/target-tricore/csfr.def b/target-tricore/csfr.def new file mode 100644 index 0000000000..5b219b4bf1 --- /dev/null +++ b/target-tricore/csfr.def @@ -0,0 +1,124 @@ +/* A(ll) access permited + R(ead only) access + E(nd init protected) access + + A|R|E(offset, register, feature introducing reg) + + NOTE: PSW is handled as a special case in gen_mtcr/mfcr */ + +A(0xfe00, PCXI, TRICORE_FEATURE_13) +A(0xfe08, PC, TRICORE_FEATURE_13) +A(0xfe14, SYSCON, TRICORE_FEATURE_13) +R(0xfe18, CPU_ID, TRICORE_FEATURE_13) +E(0xfe20, BIV, TRICORE_FEATURE_13) +E(0xfe24, BTV, TRICORE_FEATURE_13) +E(0xfe28, ISP, TRICORE_FEATURE_13) +A(0xfe2c, ICR, TRICORE_FEATURE_13) +A(0xfe38, FCX, TRICORE_FEATURE_13) +A(0xfe3c, LCX, TRICORE_FEATURE_13) +E(0x9400, COMPAT, TRICORE_FEATURE_131) +/* memory protection register */ +A(0xC000, DPR0_0L, TRICORE_FEATURE_13) +A(0xC004, DPR0_0U, TRICORE_FEATURE_13) +A(0xC008, DPR0_1L, TRICORE_FEATURE_13) +A(0xC00C, DPR0_1U, TRICORE_FEATURE_13) +A(0xC010, DPR0_2L, TRICORE_FEATURE_13) +A(0xC014, DPR0_2U, TRICORE_FEATURE_13) +A(0xC018, DPR0_3L, TRICORE_FEATURE_13) +A(0xC01C, DPR0_3U, TRICORE_FEATURE_13) +A(0xC400, DPR1_0L, TRICORE_FEATURE_13) +A(0xC404, DPR1_0U, TRICORE_FEATURE_13) +A(0xC408, DPR1_1L, TRICORE_FEATURE_13) +A(0xC40C, DPR1_1U, TRICORE_FEATURE_13) +A(0xC410, DPR1_2L, TRICORE_FEATURE_13) +A(0xC414, DPR1_2U, TRICORE_FEATURE_13) +A(0xC418, DPR1_3L, TRICORE_FEATURE_13) +A(0xC41C, DPR1_3U, TRICORE_FEATURE_13) +A(0xC800, DPR2_0L, TRICORE_FEATURE_13) +A(0xC804, DPR2_0U, TRICORE_FEATURE_13) +A(0xC808, DPR2_1L, TRICORE_FEATURE_13) +A(0xC80C, DPR2_1U, TRICORE_FEATURE_13) +A(0xC810, DPR2_2L, TRICORE_FEATURE_13) +A(0xC814, DPR2_2U, TRICORE_FEATURE_13) +A(0xC818, DPR2_3L, TRICORE_FEATURE_13) +A(0xC81C, DPR2_3U, TRICORE_FEATURE_13) +A(0xCC00, DPR3_0L, TRICORE_FEATURE_13) +A(0xCC04, DPR3_0U, TRICORE_FEATURE_13) +A(0xCC08, DPR3_1L, TRICORE_FEATURE_13) +A(0xCC0C, DPR3_1U, TRICORE_FEATURE_13) +A(0xCC10, DPR3_2L, TRICORE_FEATURE_13) +A(0xCC14, DPR3_2U, TRICORE_FEATURE_13) +A(0xCC18, DPR3_3L, TRICORE_FEATURE_13) +A(0xCC1C, DPR3_3U, TRICORE_FEATURE_13) +A(0xD000, CPR0_0L, TRICORE_FEATURE_13) +A(0xD004, CPR0_0U, TRICORE_FEATURE_13) +A(0xD008, CPR0_1L, TRICORE_FEATURE_13) +A(0xD00C, CPR0_1U, TRICORE_FEATURE_13) +A(0xD010, CPR0_2L, TRICORE_FEATURE_13) +A(0xD014, CPR0_2U, TRICORE_FEATURE_13) +A(0xD018, CPR0_3L, TRICORE_FEATURE_13) +A(0xD01C, CPR0_3U, TRICORE_FEATURE_13) +A(0xD400, CPR1_0L, TRICORE_FEATURE_13) +A(0xD404, CPR1_0U, TRICORE_FEATURE_13) +A(0xD408, CPR1_1L, TRICORE_FEATURE_13) +A(0xD40C, CPR1_1U, TRICORE_FEATURE_13) +A(0xD410, CPR1_2L, TRICORE_FEATURE_13) +A(0xD414, CPR1_2U, TRICORE_FEATURE_13) +A(0xD418, CPR1_3L, TRICORE_FEATURE_13) +A(0xD41C, CPR1_3U, TRICORE_FEATURE_13) +A(0xD800, CPR2_0L, TRICORE_FEATURE_13) +A(0xD804, CPR2_0U, TRICORE_FEATURE_13) +A(0xD808, CPR2_1L, TRICORE_FEATURE_13) +A(0xD80C, CPR2_1U, TRICORE_FEATURE_13) +A(0xD810, CPR2_2L, TRICORE_FEATURE_13) +A(0xD814, CPR2_2U, TRICORE_FEATURE_13) +A(0xD818, CPR2_3L, TRICORE_FEATURE_13) +A(0xD81C, CPR2_3U, TRICORE_FEATURE_13) +A(0xDC00, CPR3_0L, TRICORE_FEATURE_13) +A(0xDC04, CPR3_0U, TRICORE_FEATURE_13) +A(0xDC08, CPR3_1L, TRICORE_FEATURE_13) +A(0xDC0C, CPR3_1U, TRICORE_FEATURE_13) +A(0xDC10, CPR3_2L, TRICORE_FEATURE_13) +A(0xDC14, CPR3_2U, TRICORE_FEATURE_13) +A(0xDC18, CPR3_3L, TRICORE_FEATURE_13) +A(0xDC1C, CPR3_3U, TRICORE_FEATURE_13) +A(0xE000, DPM0, TRICORE_FEATURE_13) +A(0xE080, DPM1, TRICORE_FEATURE_13) +A(0xE100, DPM2, TRICORE_FEATURE_13) +A(0xE180, DPM3, TRICORE_FEATURE_13) +A(0xE200, CPM0, TRICORE_FEATURE_13) +A(0xE280, CPM1, TRICORE_FEATURE_13) +A(0xE300, CPM2, TRICORE_FEATURE_13) +A(0xE380, CPM3, TRICORE_FEATURE_13) +/* memory Managment Registers */ +A(0x8000, MMU_CON, TRICORE_FEATURE_13) +A(0x8004, MMU_ASI, TRICORE_FEATURE_13) +A(0x800C, MMU_TVA, TRICORE_FEATURE_13) +A(0x8010, MMU_TPA, TRICORE_FEATURE_13) +A(0x8014, MMU_TPX, TRICORE_FEATURE_13) +A(0x8018, MMU_TFA, TRICORE_FEATURE_13) +E(0x9004, BMACON, TRICORE_FEATURE_131) +E(0x900C, SMACON, TRICORE_FEATURE_131) +A(0x9020, DIEAR, TRICORE_FEATURE_131) +A(0x9024, DIETR, TRICORE_FEATURE_131) +A(0x9028, CCDIER, TRICORE_FEATURE_131) +E(0x9044, MIECON, TRICORE_FEATURE_131) +A(0x9210, PIEAR, TRICORE_FEATURE_131) +A(0x9214, PIETR, TRICORE_FEATURE_131) +A(0x9218, CCPIER, TRICORE_FEATURE_131) +/* debug registers */ +A(0xFD00, DBGSR, TRICORE_FEATURE_13) +A(0xFD08, EXEVT, TRICORE_FEATURE_13) +A(0xFD0C, CREVT, TRICORE_FEATURE_13) +A(0xFD10, SWEVT, TRICORE_FEATURE_13) +A(0xFD20, TR0EVT, TRICORE_FEATURE_13) +A(0xFD24, TR1EVT, TRICORE_FEATURE_13) +A(0xFD40, DMS, TRICORE_FEATURE_13) +A(0xFD44, DCX, TRICORE_FEATURE_13) +A(0xFD48, DBGTCR, TRICORE_FEATURE_131) +A(0xFC00, CCTRL, TRICORE_FEATURE_131) +A(0xFC04, CCNT, TRICORE_FEATURE_131) +A(0xFC08, ICNT, TRICORE_FEATURE_131) +A(0xFC0C, M1CNT, TRICORE_FEATURE_131) +A(0xFC10, M2CNT, TRICORE_FEATURE_131) +A(0xFC14, M3CNT, TRICORE_FEATURE_131) diff --git a/target-tricore/helper.h b/target-tricore/helper.h index 4893060245..2eb33ea21b 100644 --- a/target-tricore/helper.h +++ b/target-tricore/helper.h @@ -36,3 +36,6 @@ DEF_HELPER_2(stucx, void, env, i32) /* Address mode helper */ DEF_HELPER_1(br_update, i32, i32) DEF_HELPER_2(circ_update, i32, i32, i32) +/* PSW cache helper */ +DEF_HELPER_2(psw_write, void, env, i32) +DEF_HELPER_1(psw_read, i32, env) diff --git a/target-tricore/op_helper.c b/target-tricore/op_helper.c index d8d57b0687..0b6b47155a 100644 --- a/target-tricore/op_helper.c +++ b/target-tricore/op_helper.c @@ -536,6 +536,17 @@ void helper_stucx(CPUTriCoreState *env, uint32_t ea) save_context_upper(env, ea); } +void helper_psw_write(CPUTriCoreState *env, uint32_t arg) +{ + psw_write(env, arg); +} + +uint32_t helper_psw_read(CPUTriCoreState *env) +{ + return psw_read(env); +} + + static inline void QEMU_NORETURN do_raise_exception_err(CPUTriCoreState *env, uint32_t exception, int error_code, diff --git a/target-tricore/translate.c b/target-tricore/translate.c index 689596f985..fdc9ade428 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -233,6 +233,63 @@ static void gen_swap(DisasContext *ctx, int reg, TCGv ea) tcg_temp_free(temp); } +/* We generate loads and store to core special function register (csfr) through + the function gen_mfcr and gen_mtcr. To handle access permissions, we use 3 + makros R, A and E, which allow read-only, all and endinit protected access. + These makros also specify in which ISA version the csfr was introduced. */ +#define R(ADDRESS, REG, FEATURE) \ + case ADDRESS: \ + if (tricore_feature(env, FEATURE)) { \ + tcg_gen_ld_tl(ret, cpu_env, offsetof(CPUTriCoreState, REG)); \ + } \ + break; +#define A(ADDRESS, REG, FEATURE) R(ADDRESS, REG, FEATURE) +#define E(ADDRESS, REG, FEATURE) R(ADDRESS, REG, FEATURE) +static inline void gen_mfcr(CPUTriCoreState *env, TCGv ret, int32_t offset) +{ + /* since we're caching PSW make this a special case */ + if (offset == 0xfe04) { + gen_helper_psw_read(ret, cpu_env); + } else { + switch (offset) { +#include "csfr.def" + } + } +} +#undef R +#undef A +#undef E + +#define R(ADDRESS, REG, FEATURE) /* don't gen writes to read-only reg, + since no execption occurs */ +#define A(ADDRESS, REG, FEATURE) R(ADDRESS, REG, FEATURE) \ + case ADDRESS: \ + if (tricore_feature(env, FEATURE)) { \ + tcg_gen_st_tl(r1, cpu_env, offsetof(CPUTriCoreState, REG)); \ + } \ + break; +/* Endinit protected registers + TODO: Since the endinit bit is in a register of a not yet implemented + watchdog device, we handle endinit protected registers like + all-access registers for now. */ +#define E(ADDRESS, REG, FEATURE) A(ADDRESS, REG, FEATURE) +static inline void gen_mtcr(CPUTriCoreState *env, DisasContext *ctx, TCGv r1, + int32_t offset) +{ + if (ctx->hflags & TRICORE_HFLAG_SM) { + /* since we're caching PSW make this a special case */ + if (offset == 0xfe04) { + gen_helper_psw_write(cpu_env, r1); + } else { + switch (offset) { +#include "csfr.def" + } + } + } else { + /* generate privilege trap */ + } +} + /* Functions for arithmetic instructions */ static inline void gen_add_d(TCGv ret, TCGv r1, TCGv r2) @@ -3227,6 +3284,50 @@ static void decode_rcrw_insert(CPUTriCoreState *env, DisasContext *ctx) tcg_temp_free(temp2); } +/* RLC format */ + +static void decode_rlc_opc(CPUTriCoreState *env, DisasContext *ctx, + uint32_t op1) +{ + int32_t const16; + int r1, r2; + + const16 = MASK_OP_RLC_CONST16_SEXT(ctx->opcode); + r1 = MASK_OP_RLC_S1(ctx->opcode); + r2 = MASK_OP_RLC_D(ctx->opcode); + + switch (op1) { + case OPC1_32_RLC_ADDI: + gen_addi_CC(cpu_gpr_d[r2], cpu_gpr_d[r1], const16); + break; + case OPC1_32_RLC_ADDIH: + gen_addi_CC(cpu_gpr_d[r2], cpu_gpr_d[r1], const16 << 16); + break; + case OPC1_32_RLC_ADDIH_A: + tcg_gen_addi_tl(cpu_gpr_a[r2], cpu_gpr_a[r1], const16 << 16); + break; + case OPC1_32_RLC_MFCR: + gen_mfcr(env, cpu_gpr_d[r2], const16); + break; + case OPC1_32_RLC_MOV: + tcg_gen_movi_tl(cpu_gpr_d[r2], const16); + break; + case OPC1_32_RLC_MOV_U: + const16 = MASK_OP_RLC_CONST16(ctx->opcode); + tcg_gen_movi_tl(cpu_gpr_d[r2], const16); + break; + case OPC1_32_RLC_MOV_H: + tcg_gen_movi_tl(cpu_gpr_d[r2], const16 << 16); + break; + case OPC1_32_RLC_MOVH_A: + tcg_gen_movi_tl(cpu_gpr_a[r2], const16 << 16); + break; + case OPC1_32_RLC_MTCR: + gen_mtcr(env, ctx, cpu_gpr_d[r2], const16); + break; + } +} + static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) { int op1; @@ -3435,6 +3536,18 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) case OPCM_32_RCRW_MASK_INSERT: decode_rcrw_insert(env, ctx); break; +/* RLC Format */ + case OPC1_32_RLC_ADDI: + case OPC1_32_RLC_ADDIH: + case OPC1_32_RLC_ADDIH_A: + case OPC1_32_RLC_MFCR: + case OPC1_32_RLC_MOV: + case OPC1_32_RLC_MOV_U: + case OPC1_32_RLC_MOV_H: + case OPC1_32_RLC_MOVH_A: + case OPC1_32_RLC_MTCR: + decode_rlc_opc(env, ctx, op1); + break; } } diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index 9b042e4b37..bafc8fba46 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -192,6 +192,7 @@ #define MASK_OP_RLC_D(op) MASK_OP_META_D(op) #define MASK_OP_RLC_CONST16(op) MASK_BITS_SHIFT(op, 12, 27) +#define MASK_OP_RLC_CONST16_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 12, 27) #define MASK_OP_RLC_S1(op) MASK_OP_META_S1(op) /* RR Format */ From 328f1f0f08f1aa303eef7493bd7c3d97a8d9636a Mon Sep 17 00:00:00 2001 From: Bastian Koppelmann Date: Sun, 2 Nov 2014 17:31:45 +0000 Subject: [PATCH 9/9] target-tricore: Add instructions of RCR opcode format Add instructions of RCR opcode format. Add helper for madd32/64_ssov and madd32/64_suov. Add helper for msub32/64_ssov and msub32/64_suov. Add microcode generator function madd/msub for 32bit and 64bit, which calculate a mul and a add/sub. OPC2_32_RCR_MSUB_U_32 -> OPC2_32_RCR_MSUB_U_32. Signed-off-by: Bastian Koppelmann Reviewed-by: Richard Henderson --- target-tricore/helper.h | 8 + target-tricore/op_helper.c | 168 +++++++++++ target-tricore/translate.c | 479 +++++++++++++++++++++++++++++++ target-tricore/tricore-opcodes.h | 3 +- 4 files changed, 657 insertions(+), 1 deletion(-) diff --git a/target-tricore/helper.h b/target-tricore/helper.h index 2eb33ea21b..6c07bd7f28 100644 --- a/target-tricore/helper.h +++ b/target-tricore/helper.h @@ -24,6 +24,14 @@ DEF_HELPER_3(mul_ssov, i32, env, i32, i32) DEF_HELPER_3(mul_suov, i32, env, i32, i32) DEF_HELPER_3(sha_ssov, i32, env, i32, i32) DEF_HELPER_3(absdif_ssov, i32, env, i32, i32) +DEF_HELPER_4(madd32_ssov, i32, env, i32, i32, i32) +DEF_HELPER_4(madd32_suov, i32, env, i32, i32, i32) +DEF_HELPER_4(madd64_ssov, i64, env, i32, i64, i32) +DEF_HELPER_4(madd64_suov, i64, env, i32, i64, i32) +DEF_HELPER_4(msub32_ssov, i32, env, i32, i32, i32) +DEF_HELPER_4(msub32_suov, i32, env, i32, i32, i32) +DEF_HELPER_4(msub64_ssov, i64, env, i32, i64, i32) +DEF_HELPER_4(msub64_suov, i64, env, i32, i64, i32) /* CSA */ DEF_HELPER_2(call, void, env, i32) DEF_HELPER_1(ret, void, env) diff --git a/target-tricore/op_helper.c b/target-tricore/op_helper.c index 0b6b47155a..4da76ff232 100644 --- a/target-tricore/op_helper.c +++ b/target-tricore/op_helper.c @@ -198,6 +198,174 @@ target_ulong helper_absdif_ssov(CPUTriCoreState *env, target_ulong r1, SSOV(env, ret, result, 32); return ret; } + +target_ulong helper_madd32_ssov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2, target_ulong r3) +{ + target_ulong ret; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t2 = sextract64(r2, 0, 32); + int64_t t3 = sextract64(r3, 0, 32); + int64_t result; + + result = t2 + (t1 * t3); + SSOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_madd32_suov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2, target_ulong r3) +{ + target_ulong ret; + uint64_t t1 = extract64(r1, 0, 32); + uint64_t t2 = extract64(r2, 0, 32); + uint64_t t3 = extract64(r3, 0, 32); + int64_t result; + + result = t2 + (t1 * t3); + SUOV(env, ret, result, 32); + return ret; +} + +uint64_t helper_madd64_ssov(CPUTriCoreState *env, target_ulong r1, + uint64_t r2, target_ulong r3) +{ + uint64_t ret, ovf; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t3 = sextract64(r3, 0, 32); + int64_t mul; + + mul = t1 * t3; + ret = mul + r2; + ovf = (ret ^ mul) & ~(mul ^ r2); + + if ((int64_t)ovf < 0) { + env->PSW_USB_V = (1 << 31); + env->PSW_USB_SV = (1 << 31); + /* ext_ret > MAX_INT */ + if (mul >= 0) { + ret = INT64_MAX; + /* ext_ret < MIN_INT */ + } else { + ret = INT64_MIN; + } + } else { + env->PSW_USB_V = 0; + } + t1 = ret >> 32; + env->PSW_USB_AV = t1 ^ t1 * 2u; + env->PSW_USB_SAV |= env->PSW_USB_AV; + + return ret; +} + +uint64_t helper_madd64_suov(CPUTriCoreState *env, target_ulong r1, + uint64_t r2, target_ulong r3) +{ + uint64_t ret, mul; + uint64_t t1 = extract64(r1, 0, 32); + uint64_t t3 = extract64(r3, 0, 32); + + mul = t1 * t3; + ret = mul + r2; + + if (ret < r2) { + env->PSW_USB_V = (1 << 31); + env->PSW_USB_SV = (1 << 31); + /* saturate */ + ret = UINT64_MAX; + } else { + env->PSW_USB_V = 0; + } + t1 = ret >> 32; + env->PSW_USB_AV = t1 ^ t1 * 2u; + env->PSW_USB_SAV |= env->PSW_USB_AV; + return ret; +} + +target_ulong helper_msub32_ssov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2, target_ulong r3) +{ + target_ulong ret; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t2 = sextract64(r2, 0, 32); + int64_t t3 = sextract64(r3, 0, 32); + int64_t result; + + result = t2 - (t1 * t3); + SSOV(env, ret, result, 32); + return ret; +} + +target_ulong helper_msub32_suov(CPUTriCoreState *env, target_ulong r1, + target_ulong r2, target_ulong r3) +{ + target_ulong ret; + int64_t t1 = extract64(r1, 0, 32); + int64_t t2 = extract64(r2, 0, 32); + int64_t t3 = extract64(r3, 0, 32); + int64_t result; + + result = t2 - (t1 * t3); + SUOV(env, ret, result, 32); + return ret; +} + +uint64_t helper_msub64_ssov(CPUTriCoreState *env, target_ulong r1, + uint64_t r2, target_ulong r3) +{ + uint64_t ret, ovf; + int64_t t1 = sextract64(r1, 0, 32); + int64_t t3 = sextract64(r3, 0, 32); + int64_t mul; + + mul = t1 * t3; + ret = r2 - mul; + ovf = (ret ^ r2) & (mul ^ r2); + + if ((int64_t)ovf < 0) { + env->PSW_USB_V = (1 << 31); + env->PSW_USB_SV = (1 << 31); + /* ext_ret > MAX_INT */ + if (mul < 0) { + ret = INT64_MAX; + /* ext_ret < MIN_INT */ + } else { + ret = INT64_MIN; + } + } else { + env->PSW_USB_V = 0; + } + t1 = ret >> 32; + env->PSW_USB_AV = t1 ^ t1 * 2u; + env->PSW_USB_SAV |= env->PSW_USB_AV; + return ret; +} + +uint64_t helper_msub64_suov(CPUTriCoreState *env, target_ulong r1, + uint64_t r2, target_ulong r3) +{ + uint64_t ret, mul; + uint64_t t1 = extract64(r1, 0, 32); + uint64_t t3 = extract64(r3, 0, 32); + + mul = t1 * t3; + ret = r2 - mul; + + if (ret > r2) { + env->PSW_USB_V = (1 << 31); + env->PSW_USB_SV = (1 << 31); + /* saturate */ + ret = 0; + } else { + env->PSW_USB_V = 0; + } + t1 = ret >> 32; + env->PSW_USB_AV = t1 ^ t1 * 2u; + env->PSW_USB_SAV |= env->PSW_USB_AV; + return ret; +} + /* context save area (CSA) related helpers */ static int cdc_increment(target_ulong *psw) diff --git a/target-tricore/translate.c b/target-tricore/translate.c index fdc9ade428..65abf453f0 100644 --- a/target-tricore/translate.c +++ b/target-tricore/translate.c @@ -316,6 +316,261 @@ static inline void gen_add_d(TCGv ret, TCGv r1, TCGv r2) tcg_temp_free(t0); } +/* ret = r2 + (r1 * r3); */ +static inline void gen_madd32_d(TCGv ret, TCGv r1, TCGv r2, TCGv r3) +{ + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + tcg_gen_ext_i32_i64(t1, r1); + tcg_gen_ext_i32_i64(t2, r2); + tcg_gen_ext_i32_i64(t3, r3); + + tcg_gen_mul_i64(t1, t1, t3); + tcg_gen_add_i64(t1, t2, t1); + + tcg_gen_trunc_i64_i32(ret, t1); + /* calc V + t1 > 0x7fffffff */ + tcg_gen_setcondi_i64(TCG_COND_GT, t3, t1, 0x7fffffffLL); + /* t1 < -0x80000000 */ + tcg_gen_setcondi_i64(TCG_COND_LT, t2, t1, -0x80000000LL); + tcg_gen_or_i64(t2, t2, t3); + tcg_gen_trunc_i64_i32(cpu_PSW_V, t2); + tcg_gen_shli_tl(cpu_PSW_V, cpu_PSW_V, 31); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, ret, ret); + tcg_gen_xor_tl(cpu_PSW_AV, ret, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + tcg_temp_free_i64(t3); +} + +static inline void gen_maddi32_d(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_madd32_d(ret, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void +gen_madd64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + TCGv r3) +{ + TCGv t1 = tcg_temp_new(); + TCGv t2 = tcg_temp_new(); + TCGv t3 = tcg_temp_new(); + TCGv t4 = tcg_temp_new(); + + tcg_gen_muls2_tl(t1, t2, r1, r3); + /* only the add can overflow */ + tcg_gen_add2_tl(t3, t4, r2_low, r2_high, t1, t2); + /* calc V bit */ + tcg_gen_xor_tl(cpu_PSW_V, t4, r2_high); + tcg_gen_xor_tl(t1, r2_high, t2); + tcg_gen_andc_tl(cpu_PSW_V, cpu_PSW_V, t1); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, t4, t4); + tcg_gen_xor_tl(cpu_PSW_AV, t4, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + /* write back the result */ + tcg_gen_mov_tl(ret_low, t3); + tcg_gen_mov_tl(ret_high, t4); + + tcg_temp_free(t1); + tcg_temp_free(t2); + tcg_temp_free(t3); + tcg_temp_free(t4); +} + +static inline void +gen_maddu64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + TCGv r3) +{ + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + tcg_gen_extu_i32_i64(t1, r1); + tcg_gen_concat_i32_i64(t2, r2_low, r2_high); + tcg_gen_extu_i32_i64(t3, r3); + + tcg_gen_mul_i64(t1, t1, t3); + tcg_gen_add_i64(t2, t2, t1); + /* write back result */ + tcg_gen_extr_i64_i32(ret_low, ret_high, t2); + /* only the add overflows, if t2 < t1 + calc V bit */ + tcg_gen_setcond_i64(TCG_COND_LTU, t2, t2, t1); + tcg_gen_trunc_i64_i32(cpu_PSW_V, t2); + tcg_gen_shli_tl(cpu_PSW_V, cpu_PSW_V, 31); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, ret_high, ret_high); + tcg_gen_xor_tl(cpu_PSW_AV, ret_high, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + tcg_temp_free_i64(t3); +} + +static inline void +gen_maddi64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_madd64_d(ret_low, ret_high, r1, r2_low, r2_high, temp); + tcg_temp_free(temp); +} + +static inline void +gen_maddui64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_maddu64_d(ret_low, ret_high, r1, r2_low, r2_high, temp); + tcg_temp_free(temp); +} + +/* ret = r2 - (r1 * r3); */ +static inline void gen_msub32_d(TCGv ret, TCGv r1, TCGv r2, TCGv r3) +{ + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + tcg_gen_ext_i32_i64(t1, r1); + tcg_gen_ext_i32_i64(t2, r2); + tcg_gen_ext_i32_i64(t3, r3); + + tcg_gen_mul_i64(t1, t1, t3); + tcg_gen_sub_i64(t1, t2, t1); + + tcg_gen_trunc_i64_i32(ret, t1); + /* calc V + t2 > 0x7fffffff */ + tcg_gen_setcondi_i64(TCG_COND_GT, t3, t1, 0x7fffffffLL); + /* result < -0x80000000 */ + tcg_gen_setcondi_i64(TCG_COND_LT, t2, t1, -0x80000000LL); + tcg_gen_or_i64(t2, t2, t3); + tcg_gen_trunc_i64_i32(cpu_PSW_V, t2); + tcg_gen_shli_tl(cpu_PSW_V, cpu_PSW_V, 31); + + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, ret, ret); + tcg_gen_xor_tl(cpu_PSW_AV, ret, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + tcg_temp_free_i64(t3); +} + +static inline void gen_msubi32_d(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_msub32_d(ret, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void +gen_msub64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + TCGv r3) +{ + TCGv t1 = tcg_temp_new(); + TCGv t2 = tcg_temp_new(); + TCGv t3 = tcg_temp_new(); + TCGv t4 = tcg_temp_new(); + + tcg_gen_muls2_tl(t1, t2, r1, r3); + /* only the sub can overflow */ + tcg_gen_sub2_tl(t3, t4, r2_low, r2_high, t1, t2); + /* calc V bit */ + tcg_gen_xor_tl(cpu_PSW_V, t4, r2_high); + tcg_gen_xor_tl(t1, r2_high, t2); + tcg_gen_and_tl(cpu_PSW_V, cpu_PSW_V, t1); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, t4, t4); + tcg_gen_xor_tl(cpu_PSW_AV, t4, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + /* write back the result */ + tcg_gen_mov_tl(ret_low, t3); + tcg_gen_mov_tl(ret_high, t4); + + tcg_temp_free(t1); + tcg_temp_free(t2); + tcg_temp_free(t3); + tcg_temp_free(t4); +} + +static inline void +gen_msubi64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_msub64_d(ret_low, ret_high, r1, r2_low, r2_high, temp); + tcg_temp_free(temp); +} + +static inline void +gen_msubu64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + TCGv r3) +{ + TCGv_i64 t1 = tcg_temp_new_i64(); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + tcg_gen_extu_i32_i64(t1, r1); + tcg_gen_concat_i32_i64(t2, r2_low, r2_high); + tcg_gen_extu_i32_i64(t3, r3); + + tcg_gen_mul_i64(t1, t1, t3); + tcg_gen_sub_i64(t3, t2, t1); + tcg_gen_extr_i64_i32(ret_low, ret_high, t3); + /* calc V bit, only the sub can overflow, if t1 > t2 */ + tcg_gen_setcond_i64(TCG_COND_GTU, t1, t1, t2); + tcg_gen_trunc_i64_i32(cpu_PSW_V, t1); + tcg_gen_shli_tl(cpu_PSW_V, cpu_PSW_V, 31); + /* Calc SV bit */ + tcg_gen_or_tl(cpu_PSW_SV, cpu_PSW_SV, cpu_PSW_V); + /* Calc AV/SAV bits */ + tcg_gen_add_tl(cpu_PSW_AV, ret_high, ret_high); + tcg_gen_xor_tl(cpu_PSW_AV, ret_high, cpu_PSW_AV); + /* calc SAV */ + tcg_gen_or_tl(cpu_PSW_SAV, cpu_PSW_SAV, cpu_PSW_AV); + + tcg_temp_free_i64(t1); + tcg_temp_free_i64(t2); + tcg_temp_free_i64(t3); +} + +static inline void +gen_msubui64_d(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_msubu64_d(ret_low, ret_high, r1, r2_low, r2_high, temp); + tcg_temp_free(temp); +} + static inline void gen_addi_d(TCGv ret, TCGv r1, target_ulong r2) { TCGv temp = tcg_const_i32(r2); @@ -594,6 +849,86 @@ static inline void gen_mulsui_i32(TCGv ret, TCGv r1, int32_t con) gen_helper_mul_suov(ret, cpu_env, r1, temp); tcg_temp_free(temp); } +/* gen_maddsi_32(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); */ +static inline void gen_maddsi_32(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_madd32_ssov(ret, cpu_env, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void gen_maddsui_32(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_madd32_suov(ret, cpu_env, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void +gen_maddsi_64(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + TCGv_i64 temp64 = tcg_temp_new_i64(); + tcg_gen_concat_i32_i64(temp64, r2_low, r2_high); + gen_helper_madd64_ssov(temp64, cpu_env, r1, temp64, temp); + tcg_gen_extr_i64_i32(ret_low, ret_high, temp64); + tcg_temp_free(temp); + tcg_temp_free_i64(temp64); +} + +static inline void +gen_maddsui_64(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + TCGv_i64 temp64 = tcg_temp_new_i64(); + tcg_gen_concat_i32_i64(temp64, r2_low, r2_high); + gen_helper_madd64_suov(temp64, cpu_env, r1, temp64, temp); + tcg_gen_extr_i64_i32(ret_low, ret_high, temp64); + tcg_temp_free(temp); + tcg_temp_free_i64(temp64); +} + +static inline void gen_msubsi_32(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_msub32_ssov(ret, cpu_env, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void gen_msubsui_32(TCGv ret, TCGv r1, TCGv r2, int32_t con) +{ + TCGv temp = tcg_const_i32(con); + gen_helper_msub32_suov(ret, cpu_env, r1, r2, temp); + tcg_temp_free(temp); +} + +static inline void +gen_msubsi_64(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + TCGv_i64 temp64 = tcg_temp_new_i64(); + tcg_gen_concat_i32_i64(temp64, r2_low, r2_high); + gen_helper_msub64_ssov(temp64, cpu_env, r1, temp64, temp); + tcg_gen_extr_i64_i32(ret_low, ret_high, temp64); + tcg_temp_free(temp); + tcg_temp_free_i64(temp64); +} + +static inline void +gen_msubsui_64(TCGv ret_low, TCGv ret_high, TCGv r1, TCGv r2_low, TCGv r2_high, + int32_t con) +{ + TCGv temp = tcg_const_i32(con); + TCGv_i64 temp64 = tcg_temp_new_i64(); + tcg_gen_concat_i32_i64(temp64, r2_low, r2_high); + gen_helper_msub64_suov(temp64, cpu_env, r1, temp64, temp); + tcg_gen_extr_i64_i32(ret_low, ret_high, temp64); + tcg_temp_free(temp); + tcg_temp_free_i64(temp64); +} static void gen_saturate(TCGv ret, TCGv arg, int32_t up, int32_t low) { @@ -3284,6 +3619,140 @@ static void decode_rcrw_insert(CPUTriCoreState *env, DisasContext *ctx) tcg_temp_free(temp2); } +/* RCR format */ + +static void decode_rcr_cond_select(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r3, r4; + int32_t const9; + + TCGv temp, temp2; + + op2 = MASK_OP_RCR_OP2(ctx->opcode); + r1 = MASK_OP_RCR_S1(ctx->opcode); + const9 = MASK_OP_RCR_CONST9_SEXT(ctx->opcode); + r3 = MASK_OP_RCR_S3(ctx->opcode); + r4 = MASK_OP_RCR_D(ctx->opcode); + + switch (op2) { + case OPC2_32_RCR_CADD: + gen_condi_add(TCG_COND_NE, cpu_gpr_d[r1], const9, cpu_gpr_d[r3], + cpu_gpr_d[r4]); + break; + case OPC2_32_RCR_CADDN: + gen_condi_add(TCG_COND_EQ, cpu_gpr_d[r1], const9, cpu_gpr_d[r3], + cpu_gpr_d[r4]); + break; + case OPC2_32_RCR_SEL: + temp = tcg_const_i32(0); + temp2 = tcg_const_i32(const9); + tcg_gen_movcond_tl(TCG_COND_NE, cpu_gpr_d[r3], cpu_gpr_d[r4], temp, + cpu_gpr_d[r1], temp2); + tcg_temp_free(temp); + tcg_temp_free(temp2); + break; + case OPC2_32_RCR_SELN: + temp = tcg_const_i32(0); + temp2 = tcg_const_i32(const9); + tcg_gen_movcond_tl(TCG_COND_EQ, cpu_gpr_d[r3], cpu_gpr_d[r4], temp, + cpu_gpr_d[r1], temp2); + tcg_temp_free(temp); + tcg_temp_free(temp2); + break; + } +} + +static void decode_rcr_madd(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r3, r4; + int32_t const9; + + + op2 = MASK_OP_RCR_OP2(ctx->opcode); + r1 = MASK_OP_RCR_S1(ctx->opcode); + const9 = MASK_OP_RCR_CONST9_SEXT(ctx->opcode); + r3 = MASK_OP_RCR_S3(ctx->opcode); + r4 = MASK_OP_RCR_D(ctx->opcode); + + switch (op2) { + case OPC2_32_RCR_MADD_32: + gen_maddi32_d(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MADD_64: + gen_maddi64_d(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MADDS_32: + gen_maddsi_32(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MADDS_64: + gen_maddsi_64(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MADD_U_64: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_maddui64_d(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MADDS_U_32: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_maddsui_32(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MADDS_U_64: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_maddsui_64(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + } +} + +static void decode_rcr_msub(CPUTriCoreState *env, DisasContext *ctx) +{ + uint32_t op2; + int r1, r3, r4; + int32_t const9; + + + op2 = MASK_OP_RCR_OP2(ctx->opcode); + r1 = MASK_OP_RCR_S1(ctx->opcode); + const9 = MASK_OP_RCR_CONST9_SEXT(ctx->opcode); + r3 = MASK_OP_RCR_S3(ctx->opcode); + r4 = MASK_OP_RCR_D(ctx->opcode); + + switch (op2) { + case OPC2_32_RCR_MSUB_32: + gen_msubi32_d(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MSUB_64: + gen_msubi64_d(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MSUBS_32: + gen_msubsi_32(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MSUBS_64: + gen_msubsi_64(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MSUB_U_64: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_msubui64_d(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + case OPC2_32_RCR_MSUBS_U_32: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_msubsui_32(cpu_gpr_d[r4], cpu_gpr_d[r1], cpu_gpr_d[r3], const9); + break; + case OPC2_32_RCR_MSUBS_U_64: + const9 = MASK_OP_RCR_CONST9(ctx->opcode); + gen_msubsui_64(cpu_gpr_d[r4], cpu_gpr_d[r4+1], cpu_gpr_d[r1], + cpu_gpr_d[r3], cpu_gpr_d[r3+1], const9); + break; + } +} + /* RLC format */ static void decode_rlc_opc(CPUTriCoreState *env, DisasContext *ctx, @@ -3536,6 +4005,16 @@ static void decode_32Bit_opc(CPUTriCoreState *env, DisasContext *ctx) case OPCM_32_RCRW_MASK_INSERT: decode_rcrw_insert(env, ctx); break; +/* RCR Format */ + case OPCM_32_RCR_COND_SELECT: + decode_rcr_cond_select(env, ctx); + break; + case OPCM_32_RCR_MADD: + decode_rcr_madd(env, ctx); + break; + case OPCM_32_RCR_MSUB: + decode_rcr_msub(env, ctx); + break; /* RLC Format */ case OPC1_32_RLC_ADDI: case OPC1_32_RLC_ADDIH: diff --git a/target-tricore/tricore-opcodes.h b/target-tricore/tricore-opcodes.h index bafc8fba46..0a9122cfb9 100644 --- a/target-tricore/tricore-opcodes.h +++ b/target-tricore/tricore-opcodes.h @@ -169,6 +169,7 @@ #define MASK_OP_RCR_S3(op) MASK_BITS_SHIFT(op, 24, 27) #define MASK_OP_RCR_OP2(op) MASK_BITS_SHIFT(op, 21, 23) #define MASK_OP_RCR_CONST9(op) MASK_BITS_SHIFT(op, 12, 20) +#define MASK_OP_RCR_CONST9_SEXT(op) MASK_BITS_SHIFT_SEXT(op, 12, 20) #define MASK_OP_RCR_S1(op) MASK_OP_META_S1(op) /* RCRR Format */ @@ -945,7 +946,7 @@ enum { OPC2_32_RCR_MSUB_64 = 0x03, OPC2_32_RCR_MSUBS_32 = 0x05, OPC2_32_RCR_MSUBS_64 = 0x07, - OPC2_32_RCR_MSUB_U_32 = 0x02, + OPC2_32_RCR_MSUB_U_64 = 0x02, OPC2_32_RCR_MSUBS_U_32 = 0x04, OPC2_32_RCR_MSUBS_U_64 = 0x06, };