Merge remote-tracking branch 'remotes/bkoppelmann/tags/pull-tricore-2017-01-11-2' into staging

TriCore FPU patches

# gpg: Signature made Wed 11 Jan 2017 13:40:11 GMT
# gpg:                using RSA key 0x0AD2C6396B69CA14
# gpg: Good signature from "Bastian Koppelmann <kbastian@mail.uni-paderborn.de>"
# Primary key fingerprint: 6E63 6A7E 83F2 DD0C FA6E  6E37 0AD2 C639 6B69 CA14

* remotes/bkoppelmann/tags/pull-tricore-2017-01-11-2:
  target-tricore: Add updfl instruction
  target-tricore: Added new JNE instruction variant
  target-tricore: Added new MOV instruction variant
  target-tricore: Added MADD.F and MSUB.F instructions
  target-tricore: Added FTOUZ instruction

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 188 insertions, 1 deletions

diff --git a/target/tricore/fpu_helper.c b/target/tricore/fpu_helper.c
index 98fe947..7979bb6 100644
--- a/target/tricore/fpu_helper.c
+++ b/target/tricore/fpu_helper.c
@@ -21,7 +21,8 @@
 #include "cpu.h"
 #include "exec/helper-proto.h"
 
-#define ADD_NAN   0x7cf00001
+#define QUIET_NAN 0x7fc00000
+#define ADD_NAN   0x7fc00001
 #define DIV_NAN   0x7fc00008
 #define MUL_NAN   0x7fc00002
 #define FPU_FS PSW_USB_C
@@ -47,6 +48,42 @@ static inline bool f_is_denormal(float32 arg)
     return float32_is_zero_or_denormal(arg) && !float32_is_zero(arg);
 }
 
+static inline float32 f_maddsub_nan_result(float32 arg1, float32 arg2,
+                                           float32 arg3, float32 result,
+                                           uint32_t muladd_negate_c)
+{
+    uint32_t aSign, bSign, cSign;
+    uint32_t aExp, bExp, cExp;
+
+    if (float32_is_any_nan(arg1) || float32_is_any_nan(arg2) ||
+        float32_is_any_nan(arg3)) {
+        return QUIET_NAN;
+    } else if (float32_is_infinity(arg1) && float32_is_zero(arg2)) {
+        return MUL_NAN;
+    } else if (float32_is_zero(arg1) && float32_is_infinity(arg2)) {
+        return MUL_NAN;
+    } else {
+        aSign = arg1 >> 31;
+        bSign = arg2 >> 31;
+        cSign = arg3 >> 31;
+
+        aExp = (arg1 >> 23) & 0xff;
+        bExp = (arg2 >> 23) & 0xff;
+        cExp = (arg3 >> 23) & 0xff;
+
+        if (muladd_negate_c) {
+            cSign ^= 1;
+        }
+        if (((aExp == 0xff) || (bExp == 0xff)) && (cExp == 0xff)) {
+            if (aSign ^ bSign ^ cSign) {
+                return ADD_NAN;
+            }
+        }
+    }
+
+    return result;
+}
+
 static void f_update_psw_flags(CPUTriCoreState *env, uint8_t flags)
 {
     uint8_t some_excp = 0;
@@ -159,6 +196,60 @@ uint32_t helper_fdiv(CPUTriCoreState *env, uint32_t r1, uint32_t r2)
     return (uint32_t)f_result;
 }
 
+uint32_t helper_fmadd(CPUTriCoreState *env, uint32_t r1,
+                      uint32_t r2, uint32_t r3)
+{
+    uint32_t flags;
+    float32 arg1 = make_float32(r1);
+    float32 arg2 = make_float32(r2);
+    float32 arg3 = make_float32(r3);
+    float32 f_result;
+
+    f_result = float32_muladd(arg1, arg2, arg3, 0, &env->fp_status);
+
+    flags = f_get_excp_flags(env);
+    if (flags) {
+        if (flags & float_flag_invalid) {
+            arg1 = float32_squash_input_denormal(arg1, &env->fp_status);
+            arg2 = float32_squash_input_denormal(arg2, &env->fp_status);
+            arg3 = float32_squash_input_denormal(arg3, &env->fp_status);
+            f_result = f_maddsub_nan_result(arg1, arg2, arg3, f_result, 0);
+        }
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+    return (uint32_t)f_result;
+}
+
+uint32_t helper_fmsub(CPUTriCoreState *env, uint32_t r1,
+                      uint32_t r2, uint32_t r3)
+{
+    uint32_t flags;
+    float32 arg1 = make_float32(r1);
+    float32 arg2 = make_float32(r2);
+    float32 arg3 = make_float32(r3);
+    float32 f_result;
+
+    f_result = float32_muladd(arg1, arg2, arg3, float_muladd_negate_product,
+                              &env->fp_status);
+
+    flags = f_get_excp_flags(env);
+    if (flags) {
+        if (flags & float_flag_invalid) {
+            arg1 = float32_squash_input_denormal(arg1, &env->fp_status);
+            arg2 = float32_squash_input_denormal(arg2, &env->fp_status);
+            arg3 = float32_squash_input_denormal(arg3, &env->fp_status);
+
+            f_result = f_maddsub_nan_result(arg1, arg2, arg3, f_result, 1);
+        }
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+    return (uint32_t)f_result;
+}
+
 uint32_t helper_fcmp(CPUTriCoreState *env, uint32_t r1, uint32_t r2)
 {
     uint32_t result, flags;
@@ -215,3 +306,44 @@ uint32_t helper_itof(CPUTriCoreState *env, uint32_t arg)
     }
     return (uint32_t)f_result;
 }
+
+uint32_t helper_ftouz(CPUTriCoreState *env, uint32_t arg)
+{
+    float32 f_arg = make_float32(arg);
+    uint32_t result;
+    int32_t flags;
+
+    result = float32_to_uint32_round_to_zero(f_arg, &env->fp_status);
+
+    flags = f_get_excp_flags(env);
+    if (flags & float_flag_invalid) {
+        flags &= ~float_flag_inexact;
+        if (float32_is_any_nan(f_arg)) {
+            result = 0;
+        }
+    } else if (float32_lt_quiet(f_arg, 0, &env->fp_status)) {
+        flags = float_flag_invalid;
+        result = 0;
+    }
+
+    if (flags) {
+        f_update_psw_flags(env, flags);
+    } else {
+        env->FPU_FS = 0;
+    }
+    return result;
+}
+
+void helper_updfl(CPUTriCoreState *env, uint32_t arg)
+{
+    env->FPU_FS =  extract32(arg, 7, 1) & extract32(arg, 15, 1);
+    env->FPU_FI = (extract32(arg, 6, 1) & extract32(arg, 14, 1)) << 31;
+    env->FPU_FV = (extract32(arg, 5, 1) & extract32(arg, 13, 1)) << 31;
+    env->FPU_FZ = (extract32(arg, 4, 1) & extract32(arg, 12, 1)) << 31;
+    env->FPU_FU = (extract32(arg, 3, 1) & extract32(arg, 11, 1)) << 31;
+    /* clear FX and RM */
+    env->PSW &= ~(extract32(arg, 10, 1) << 26);
+    env->PSW |= (extract32(arg, 2, 1) & extract32(arg, 10, 1)) << 26;
+
+    fpu_set_state(env);
+}
diff --git a/target/tricore/helper.h b/target/tricore/helper.h
index d215349..e634d0c 100644
--- a/target/tricore/helper.h
+++ b/target/tricore/helper.h
@@ -106,9 +106,13 @@ DEF_HELPER_3(fadd, i32, env, i32, i32)
 DEF_HELPER_3(fsub, i32, env, i32, i32)
 DEF_HELPER_3(fmul, i32, env, i32, i32)
 DEF_HELPER_3(fdiv, i32, env, i32, i32)
+DEF_HELPER_4(fmadd, i32, env, i32, i32, i32)
+DEF_HELPER_4(fmsub, i32, env, i32, i32, i32)
 DEF_HELPER_3(fcmp, i32, env, i32, i32)
 DEF_HELPER_2(ftoi, i32, env, i32)
 DEF_HELPER_2(itof, i32, env, i32)
+DEF_HELPER_2(ftouz, i32, env, i32)
+DEF_HELPER_2(updfl, void, env, i32)
 /* dvinit */
 DEF_HELPER_3(dvinit_b_13, i64, env, i32, i32)
 DEF_HELPER_3(dvinit_b_131, i64, env, i32, i32)
diff --git a/target/tricore/translate.c b/target/tricore/translate.c
index 41b1d27..ddd2dd0 100644
--- a/target/tricore/translate.c
+++ b/target/tricore/translate.c
@@ -3362,9 +3362,17 @@ static void gen_compute_branch(DisasContext *ctx, uint32_t opc, int r1,
     case OPC1_16_SBC_JEQ:
         gen_branch_condi(ctx, TCG_COND_EQ, cpu_gpr_d[15], constant, offset);
         break;
+    case OPC1_16_SBC_JEQ2:
+        gen_branch_condi(ctx, TCG_COND_EQ, cpu_gpr_d[15], constant,
+                         offset + 16);
+        break;
     case OPC1_16_SBC_JNE:
         gen_branch_condi(ctx, TCG_COND_NE, cpu_gpr_d[15], constant, offset);
         break;
+    case OPC1_16_SBC_JNE2:
+        gen_branch_condi(ctx, TCG_COND_NE, cpu_gpr_d[15],
+                         constant, offset + 16);
+        break;
 /* SBRN-format jumps */
     case OPC1_16_SBRN_JZ_T:
         temp = tcg_temp_new();
@@ -4097,6 +4105,16 @@ static void decode_16Bit_opc(CPUTriCoreState *env, DisasContext *ctx)
         const16 = MASK_OP_SBC_CONST4_SEXT(ctx->opcode);
         gen_compute_branch(ctx, op1, 0, 0, const16, address);
         break;
+    case OPC1_16_SBC_JEQ2:
+    case OPC1_16_SBC_JNE2:
+        if (tricore_feature(env, TRICORE_FEATURE_16)) {
+            address = MASK_OP_SBC_DISP4(ctx->opcode);
+            const16 = MASK_OP_SBC_CONST4_SEXT(ctx->opcode);
+            gen_compute_branch(ctx, op1, 0, 0, const16, address);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
+        break;
 /* SBRN-format */
     case OPC1_16_SBRN_JNZ_T:
     case OPC1_16_SBRN_JZ_T:
@@ -6034,6 +6052,8 @@ static void decode_rr_accumulator(CPUTriCoreState *env, DisasContext *ctx)
     uint32_t op2;
     int r3, r2, r1;
 
+    TCGv temp;
+
     r3 = MASK_OP_RR_D(ctx->opcode);
     r2 = MASK_OP_RR_S2(ctx->opcode);
     r1 = MASK_OP_RR_S1(ctx->opcode);
@@ -6224,6 +6244,20 @@ static void decode_rr_accumulator(CPUTriCoreState *env, DisasContext *ctx)
     case OPC2_32_RR_MOV:
         tcg_gen_mov_tl(cpu_gpr_d[r3], cpu_gpr_d[r2]);
         break;
+    case OPC2_32_RR_MOV_64:
+        if (tricore_feature(env, TRICORE_FEATURE_16)) {
+            temp = tcg_temp_new();
+
+            CHECK_REG_PAIR(r3);
+            tcg_gen_mov_tl(temp, cpu_gpr_d[r1]);
+            tcg_gen_mov_tl(cpu_gpr_d[r3], cpu_gpr_d[r2]);
+            tcg_gen_mov_tl(cpu_gpr_d[r3 + 1], temp);
+
+            tcg_temp_free(temp);
+        } else {
+            generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
+        }
+        break;
     case OPC2_32_RR_NE:
         tcg_gen_setcond_tl(TCG_COND_NE, cpu_gpr_d[r3], cpu_gpr_d[r1],
                            cpu_gpr_d[r2]);
@@ -6699,6 +6733,12 @@ static void decode_rr_divide(CPUTriCoreState *env, DisasContext *ctx)
     case OPC2_32_RR_ITOF:
         gen_helper_itof(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
         break;
+    case OPC2_32_RR_FTOUZ:
+        gen_helper_ftouz(cpu_gpr_d[r3], cpu_env, cpu_gpr_d[r1]);
+        break;
+    case OPC2_32_RR_UPDFL:
+        gen_helper_updfl(cpu_env, cpu_gpr_d[r1]);
+        break;
     default:
         generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
     }
@@ -7094,6 +7134,14 @@ static void decode_rrr_divide(CPUTriCoreState *env, DisasContext *ctx)
     case OPC2_32_RRR_SUB_F:
         gen_helper_fsub(cpu_gpr_d[r4], cpu_env, cpu_gpr_d[r1], cpu_gpr_d[r3]);
         break;
+    case OPC2_32_RRR_MADD_F:
+        gen_helper_fmadd(cpu_gpr_d[r4], cpu_env, cpu_gpr_d[r1],
+                         cpu_gpr_d[r2], cpu_gpr_d[r3]);
+        break;
+    case OPC2_32_RRR_MSUB_F:
+        gen_helper_fmsub(cpu_gpr_d[r4], cpu_env, cpu_gpr_d[r1],
+                         cpu_gpr_d[r2], cpu_gpr_d[r3]);
+        break;
     default:
         generate_trap(ctx, TRAPC_INSN_ERR, TIN2_IOPC);
     }
diff --git a/target/tricore/tricore-opcodes.h b/target/tricore/tricore-opcodes.h
index df666b0..08394b8 100644
--- a/target/tricore/tricore-opcodes.h
+++ b/target/tricore/tricore-opcodes.h
@@ -311,6 +311,7 @@ enum {
     OPC1_16_SRR_EQ                                   = 0x3a,
     OPC1_16_SB_J                                     = 0x3c,
     OPC1_16_SBC_JEQ                                  = 0x1e,
+    OPC1_16_SBC_JEQ2                                 = 0x9e,
     OPC1_16_SBR_JEQ                                  = 0x3e,
     OPC1_16_SBR_JGEZ                                 = 0xce,
     OPC1_16_SBR_JGTZ                                 = 0x4e,
@@ -318,6 +319,7 @@ enum {
     OPC1_16_SBR_JLEZ                                 = 0x8e,
     OPC1_16_SBR_JLTZ                                 = 0x0e,
     OPC1_16_SBC_JNE                                  = 0x5e,
+    OPC1_16_SBC_JNE2                                 = 0xde,
     OPC1_16_SBR_JNE                                  = 0x7e,
     OPC1_16_SB_JNZ                                   = 0xee,
     OPC1_16_SBR_JNZ                                  = 0xf6,
@@ -1062,6 +1064,7 @@ enum {
     OPC2_32_RR_MIN_H                             = 0x78,
     OPC2_32_RR_MIN_HU                            = 0x79,
     OPC2_32_RR_MOV                               = 0x1f,
+    OPC2_32_RR_MOV_64                            = 0x81,
     OPC2_32_RR_NE                                = 0x11,
     OPC2_32_RR_OR_EQ                             = 0x27,
     OPC2_32_RR_OR_GE                             = 0x2b,