diff options
Diffstat (limited to 'target')
| -rw-r--r-- | target/i386/cpu.c | 92 | ||||
| -rw-r--r-- | target/i386/cpu.h | 26 | ||||
| -rw-r--r-- | target/i386/kvm.c | 78 | ||||
| -rw-r--r-- | target/i386/machine.c | 38 | ||||
| -rw-r--r-- | target/m68k/fpu_helper.c | 61 | ||||
| -rw-r--r-- | target/m68k/helper.h | 11 | ||||
| -rw-r--r-- | target/m68k/softfloat.c | 1637 | ||||
| -rw-r--r-- | target/m68k/softfloat.h | 11 | ||||
| -rw-r--r-- | target/m68k/softfloat_fpsp_tables.h | 267 | ||||
| -rw-r--r-- | target/m68k/translate.c | 38 |
10 files changed, 2257 insertions, 2 deletions
diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 01607dd046..6bb4ce8719 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -174,7 +174,32 @@ #define L2_ITLB_4K_ASSOC 4 #define L2_ITLB_4K_ENTRIES 512 - +/* CPUID Leaf 0x14 constants: */ +#define INTEL_PT_MAX_SUBLEAF 0x1 +/* + * bit[00]: IA32_RTIT_CTL.CR3 filter can be set to 1 and IA32_RTIT_CR3_MATCH + * MSR can be accessed; + * bit[01]: Support Configurable PSB and Cycle-Accurate Mode; + * bit[02]: Support IP Filtering, TraceStop filtering, and preservation + * of Intel PT MSRs across warm reset; + * bit[03]: Support MTC timing packet and suppression of COFI-based packets; + */ +#define INTEL_PT_MINIMAL_EBX 0xf +/* + * bit[00]: Tracing can be enabled with IA32_RTIT_CTL.ToPA = 1 and + * IA32_RTIT_OUTPUT_BASE and IA32_RTIT_OUTPUT_MASK_PTRS MSRs can be + * accessed; + * bit[01]: ToPA tables can hold any number of output entries, up to the + * maximum allowed by the MaskOrTableOffset field of + * IA32_RTIT_OUTPUT_MASK_PTRS; + * bit[02]: Support Single-Range Output scheme; + */ +#define INTEL_PT_MINIMAL_ECX 0x7 +#define INTEL_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable address ranges */ +#define INTEL_PT_ADDR_RANGES_NUM_MASK 0x3 +#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */ +#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */ +#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */ static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, uint32_t vendor2, uint32_t vendor3) @@ -360,6 +385,20 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .cpuid_eax = KVM_CPUID_FEATURES, .cpuid_reg = R_EAX, .tcg_features = TCG_KVM_FEATURES, }, + [FEAT_KVM_HINTS] = { + .feat_names = { + "kvm-hint-dedicated", NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, + }, + .cpuid_eax = KVM_CPUID_FEATURES, .cpuid_reg = R_EDX, + .tcg_features = TCG_KVM_FEATURES, + }, [FEAT_HYPERV_EAX] = { .feat_names = { NULL /* hv_msr_vp_runtime_access */, NULL /* hv_msr_time_refcount_access */, @@ -429,7 +468,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { NULL, NULL, "mpx", NULL, "avx512f", "avx512dq", "rdseed", "adx", "smap", "avx512ifma", "pcommit", "clflushopt", - "clwb", NULL, "avx512pf", "avx512er", + "clwb", "intel-pt", "avx512pf", "avx512er", "avx512cd", "sha-ni", "avx512bw", "avx512vl", }, .cpuid_eax = 7, @@ -3454,6 +3493,27 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, } break; } + case 0x14: { + /* Intel Processor Trace Enumeration */ + *eax = 0; + *ebx = 0; + *ecx = 0; + *edx = 0; + if (!(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) || + !kvm_enabled()) { + break; + } + + if (count == 0) { + *eax = INTEL_PT_MAX_SUBLEAF; + *ebx = INTEL_PT_MINIMAL_EBX; + *ecx = INTEL_PT_MINIMAL_ECX; + } else if (count == 1) { + *eax = INTEL_PT_MTC_BITMAP | INTEL_PT_ADDR_RANGES_NUM; + *ebx = INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP; + } + break; + } case 0x40000000: /* * CPUID code in kvm_arch_init_vcpu() ignores stuff @@ -4097,6 +4157,34 @@ static int x86_cpu_filter_features(X86CPU *cpu) } } + if ((env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) && + kvm_enabled()) { + KVMState *s = CPU(cpu)->kvm_state; + uint32_t eax_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EAX); + uint32_t ebx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EBX); + uint32_t ecx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_ECX); + uint32_t eax_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EAX); + uint32_t ebx_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EBX); + + if (!eax_0 || + ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) || + ((ecx_0 & INTEL_PT_MINIMAL_ECX) != INTEL_PT_MINIMAL_ECX) || + ((eax_1 & INTEL_PT_MTC_BITMAP) != INTEL_PT_MTC_BITMAP) || + ((eax_1 & INTEL_PT_ADDR_RANGES_NUM_MASK) < + INTEL_PT_ADDR_RANGES_NUM) || + ((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) != + (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) { + /* + * Processor Trace capabilities aren't configurable, so if the + * host can't emulate the capabilities we report on + * cpu_x86_cpuid(), intel-pt can't be enabled on the current host. + */ + env->features[FEAT_7_0_EBX] &= ~CPUID_7_0_EBX_INTEL_PT; + cpu->filtered_features[FEAT_7_0_EBX] |= CPUID_7_0_EBX_INTEL_PT; + rv = 1; + } + } + return rv; } diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 254e557bb8..2e2bab5ff3 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -417,6 +417,21 @@ typedef enum X86Seg { #define MSR_MC0_ADDR 0x402 #define MSR_MC0_MISC 0x403 +#define MSR_IA32_RTIT_OUTPUT_BASE 0x560 +#define MSR_IA32_RTIT_OUTPUT_MASK 0x561 +#define MSR_IA32_RTIT_CTL 0x570 +#define MSR_IA32_RTIT_STATUS 0x571 +#define MSR_IA32_RTIT_CR3_MATCH 0x572 +#define MSR_IA32_RTIT_ADDR0_A 0x580 +#define MSR_IA32_RTIT_ADDR0_B 0x581 +#define MSR_IA32_RTIT_ADDR1_A 0x582 +#define MSR_IA32_RTIT_ADDR1_B 0x583 +#define MSR_IA32_RTIT_ADDR2_A 0x584 +#define MSR_IA32_RTIT_ADDR2_B 0x585 +#define MSR_IA32_RTIT_ADDR3_A 0x586 +#define MSR_IA32_RTIT_ADDR3_B 0x587 +#define MAX_RTIT_ADDRS 8 + #define MSR_EFER 0xc0000080 #define MSR_EFER_SCE (1 << 0) @@ -473,6 +488,7 @@ typedef enum FeatureWord { FEAT_8000_0008_EBX, /* CPUID[8000_0008].EBX */ FEAT_C000_0001_EDX, /* CPUID[C000_0001].EDX */ FEAT_KVM, /* CPUID[4000_0001].EAX (KVM_CPUID_FEATURES) */ + FEAT_KVM_HINTS, /* CPUID[4000_0001].EDX */ FEAT_HYPERV_EAX, /* CPUID[4000_0003].EAX */ FEAT_HYPERV_EBX, /* CPUID[4000_0003].EBX */ FEAT_HYPERV_EDX, /* CPUID[4000_0003].EDX */ @@ -642,6 +658,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; #define CPUID_7_0_EBX_PCOMMIT (1U << 22) /* Persistent Commit */ #define CPUID_7_0_EBX_CLFLUSHOPT (1U << 23) /* Flush a Cache Line Optimized */ #define CPUID_7_0_EBX_CLWB (1U << 24) /* Cache Line Write Back */ +#define CPUID_7_0_EBX_INTEL_PT (1U << 25) /* Intel Processor Trace */ #define CPUID_7_0_EBX_AVX512PF (1U << 26) /* AVX-512 Prefetch */ #define CPUID_7_0_EBX_AVX512ER (1U << 27) /* AVX-512 Exponential and Reciprocal */ #define CPUID_7_0_EBX_AVX512CD (1U << 28) /* AVX-512 Conflict Detection */ @@ -668,6 +685,8 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; #define CPUID_7_0_EDX_AVX512_4FMAPS (1U << 3) /* AVX512 Multiply Accumulation Single Precision */ #define CPUID_7_0_EDX_SPEC_CTRL (1U << 26) /* Speculation Control */ +#define KVM_HINTS_DEDICATED (1U << 0) + #define CPUID_8000_0008_EBX_IBPB (1U << 12) /* Indirect Branch Prediction Barrier */ #define CPUID_XSAVE_XSAVEOPT (1U << 0) @@ -1156,6 +1175,13 @@ typedef struct CPUX86State { uint64_t msr_hv_stimer_config[HV_STIMER_COUNT]; uint64_t msr_hv_stimer_count[HV_STIMER_COUNT]; + uint64_t msr_rtit_ctrl; + uint64_t msr_rtit_status; + uint64_t msr_rtit_output_base; + uint64_t msr_rtit_output_mask; + uint64_t msr_rtit_cr3_match; + uint64_t msr_rtit_addrs[MAX_RTIT_ADDRS]; + /* exception/interrupt handling */ int error_code; int exception_is_int; diff --git a/target/i386/kvm.c b/target/i386/kvm.c index a53735f266..d23fff12f5 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -384,6 +384,9 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, if (!kvm_irqchip_in_kernel()) { ret &= ~(1U << KVM_FEATURE_PV_UNHALT); } + } else if (function == KVM_CPUID_FEATURES && reg == R_EDX) { + ret |= KVM_HINTS_DEDICATED; + found = 1; } /* fallback for older kernels */ @@ -802,6 +805,7 @@ int kvm_arch_init_vcpu(CPUState *cs) c = &cpuid_data.entries[cpuid_i++]; c->function = KVM_CPUID_FEATURES | kvm_base; c->eax = env->features[FEAT_KVM]; + c->edx = env->features[FEAT_KVM_HINTS]; } cpu_x86_cpuid(env, 0, 0, &limit, &unused, &unused, &unused); @@ -866,6 +870,29 @@ int kvm_arch_init_vcpu(CPUState *cs) c = &cpuid_data.entries[cpuid_i++]; } break; + case 0x14: { + uint32_t times; + + c->function = i; + c->index = 0; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + times = c->eax; + + for (j = 1; j <= times; ++j) { + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + fprintf(stderr, "cpuid_data is full, no space for " + "cpuid(eax:0x14,ecx:0x%x)\n", j); + abort(); + } + c = &cpuid_data.entries[cpuid_i++]; + c->function = i; + c->index = j; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + } + break; + } default: c->function = i; c->flags = 0; @@ -1795,6 +1822,25 @@ static int kvm_put_msrs(X86CPU *cpu, int level) kvm_msr_entry_add(cpu, MSR_MTRRphysMask(i), mask); } } + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { + int addr_num = kvm_arch_get_supported_cpuid(kvm_state, + 0x14, 1, R_EAX) & 0x7; + + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CTL, + env->msr_rtit_ctrl); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_STATUS, + env->msr_rtit_status); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_BASE, + env->msr_rtit_output_base); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_MASK, + env->msr_rtit_output_mask); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CR3_MATCH, + env->msr_rtit_cr3_match); + for (i = 0; i < addr_num; i++) { + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_ADDR0_A + i, + env->msr_rtit_addrs[i]); + } + } /* Note: MSR_IA32_FEATURE_CONTROL is written separately, see * kvm_put_msr_feature_control. */ @@ -2111,6 +2157,20 @@ static int kvm_get_msrs(X86CPU *cpu) } } + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { + int addr_num = + kvm_arch_get_supported_cpuid(kvm_state, 0x14, 1, R_EAX) & 0x7; + + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CTL, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_STATUS, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_BASE, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_MASK, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CR3_MATCH, 0); + for (i = 0; i < addr_num; i++) { + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_ADDR0_A + i, 0); + } + } + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, cpu->kvm_msr_buf); if (ret < 0) { return ret; @@ -2354,6 +2414,24 @@ static int kvm_get_msrs(X86CPU *cpu) case MSR_IA32_SPEC_CTRL: env->spec_ctrl = msrs[i].data; break; + case MSR_IA32_RTIT_CTL: + env->msr_rtit_ctrl = msrs[i].data; + break; + case MSR_IA32_RTIT_STATUS: + env->msr_rtit_status = msrs[i].data; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + env->msr_rtit_output_base = msrs[i].data; + break; + case MSR_IA32_RTIT_OUTPUT_MASK: + env->msr_rtit_output_mask = msrs[i].data; + break; + case MSR_IA32_RTIT_CR3_MATCH: + env->msr_rtit_cr3_match = msrs[i].data; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + env->msr_rtit_addrs[index - MSR_IA32_RTIT_ADDR0_A] = msrs[i].data; + break; } } diff --git a/target/i386/machine.c b/target/i386/machine.c index 9432496cbd..bd2d82e91b 100644 --- a/target/i386/machine.c +++ b/target/i386/machine.c @@ -856,6 +856,43 @@ static const VMStateDescription vmstate_spec_ctrl = { } }; +static bool intel_pt_enable_needed(void *opaque) +{ + X86CPU *cpu = opaque; + CPUX86State *env = &cpu->env; + int i; + + if (env->msr_rtit_ctrl || env->msr_rtit_status || + env->msr_rtit_output_base || env->msr_rtit_output_mask || + env->msr_rtit_cr3_match) { + return true; + } + + for (i = 0; i < MAX_RTIT_ADDRS; i++) { + if (env->msr_rtit_addrs[i]) { + return true; + } + } + + return false; +} + +static const VMStateDescription vmstate_msr_intel_pt = { + .name = "cpu/intel_pt", + .version_id = 1, + .minimum_version_id = 1, + .needed = intel_pt_enable_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(env.msr_rtit_ctrl, X86CPU), + VMSTATE_UINT64(env.msr_rtit_status, X86CPU), + VMSTATE_UINT64(env.msr_rtit_output_base, X86CPU), + VMSTATE_UINT64(env.msr_rtit_output_mask, X86CPU), + VMSTATE_UINT64(env.msr_rtit_cr3_match, X86CPU), + VMSTATE_UINT64_ARRAY(env.msr_rtit_addrs, X86CPU, MAX_RTIT_ADDRS), + VMSTATE_END_OF_LIST() + } +}; + VMStateDescription vmstate_x86_cpu = { .name = "cpu", .version_id = 12, @@ -977,6 +1014,7 @@ VMStateDescription vmstate_x86_cpu = { #endif &vmstate_spec_ctrl, &vmstate_mcg_ext_ctl, + &vmstate_msr_intel_pt, NULL } }; diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c index 62cbb0dff1..6eeffdf9bb 100644 --- a/target/m68k/fpu_helper.c +++ b/target/m68k/fpu_helper.c @@ -592,3 +592,64 @@ void HELPER(ftentox)(CPUM68KState *env, FPReg *res, FPReg *val) { res->d = floatx80_tentox(val->d, &env->fp_status); } + +void HELPER(ftan)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_tan(val->d, &env->fp_status); +} + +void HELPER(fsin)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_sin(val->d, &env->fp_status); +} + +void HELPER(fcos)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_cos(val->d, &env->fp_status); +} + +void HELPER(fsincos)(CPUM68KState *env, FPReg *res0, FPReg *res1, FPReg *val) +{ + floatx80 a = val->d; + /* If res0 and res1 specify the same floating-point data register, + * the sine result is stored in the register, and the cosine + * result is discarded. + */ + res1->d = floatx80_cos(a, &env->fp_status); + res0->d = floatx80_sin(a, &env->fp_status); +} + +void HELPER(fatan)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_atan(val->d, &env->fp_status); +} + +void HELPER(fasin)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_asin(val->d, &env->fp_status); +} + +void HELPER(facos)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_acos(val->d, &env->fp_status); +} + +void HELPER(fatanh)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_atanh(val->d, &env->fp_status); +} + +void HELPER(ftanh)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_tanh(val->d, &env->fp_status); +} + +void HELPER(fsinh)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_sinh(val->d, &env->fp_status); +} + +void HELPER(fcosh)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_cosh(val->d, &env->fp_status); +} diff --git a/target/m68k/helper.h b/target/m68k/helper.h index 9a9734c196..feee7be626 100644 --- a/target/m68k/helper.h +++ b/target/m68k/helper.h @@ -75,6 +75,17 @@ DEF_HELPER_3(flog2, void, env, fp, fp) DEF_HELPER_3(fetox, void, env, fp, fp) DEF_HELPER_3(ftwotox, void, env, fp, fp) DEF_HELPER_3(ftentox, void, env, fp, fp) +DEF_HELPER_3(ftan, void, env, fp, fp) +DEF_HELPER_3(fsin, void, env, fp, fp) +DEF_HELPER_3(fcos, void, env, fp, fp) +DEF_HELPER_4(fsincos, void, env, fp, fp, fp) +DEF_HELPER_3(fatan, void, env, fp, fp) +DEF_HELPER_3(fasin, void, env, fp, fp) +DEF_HELPER_3(facos, void, env, fp, fp) +DEF_HELPER_3(fatanh, void, env, fp, fp) +DEF_HELPER_3(ftanh, void, env, fp, fp) +DEF_HELPER_3(fsinh, void, env, fp, fp) +DEF_HELPER_3(fcosh, void, env, fp, fp) DEF_HELPER_3(mac_move, void, env, i32, i32) DEF_HELPER_3(macmulf, i64, env, i32, i32) diff --git a/target/m68k/softfloat.c b/target/m68k/softfloat.c index 4bd5b9e6b7..dffb371c71 100644 --- a/target/m68k/softfloat.c +++ b/target/m68k/softfloat.c @@ -23,6 +23,10 @@ #include "fpu/softfloat-macros.h" #include "softfloat_fpsp_tables.h" +#define pi_exp 0x4000 +#define piby2_exp 0x3FFF +#define pi_sig LIT64(0xc90fdaa22168c235) + static floatx80 propagateFloatx80NaNOneArg(floatx80 a, float_status *status) { if (floatx80_is_signaling_nan(a, status)) { @@ -1266,3 +1270,1636 @@ floatx80 floatx80_tentox(floatx80 a, float_status *status) return a; } } + +/*---------------------------------------------------------------------------- + | Tangent + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_tan(floatx80 a, float_status *status) +{ + flag aSign, xSign; + int32_t aExp, xExp; + uint64_t aSig, xSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact, l, n, j; + floatx80 fp0, fp1, fp2, fp3, fp4, fp5, invtwopi, twopi1, twopi2; + float32 twoto63; + flag endflag; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + fp0 = a; + + if (compact < 0x3FD78000 || compact > 0x4004BC7E) { + /* 2^(-40) > |X| > 15 PI */ + if (compact > 0x3FFF8000) { /* |X| >= 15 PI */ + /* REDUCEX */ + fp1 = packFloatx80(0, 0, 0); + if (compact == 0x7FFEFFFF) { + twopi1 = packFloatx80(aSign ^ 1, 0x7FFE, + LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(aSign ^ 1, 0x7FDC, + LIT64(0x85A308D300000000)); + fp0 = floatx80_add(fp0, twopi1, status); + fp1 = fp0; + fp0 = floatx80_add(fp0, twopi2, status); + fp1 = floatx80_sub(fp1, fp0, status); + fp1 = floatx80_add(fp1, twopi2, status); + } + loop: + xSign = extractFloatx80Sign(fp0); + xExp = extractFloatx80Exp(fp0); + xExp -= 0x3FFF; + if (xExp <= 28) { + l = 0; + endflag = 1; + } else { + l = xExp - 27; + endflag = 0; + } + invtwopi = packFloatx80(0, 0x3FFE - l, + LIT64(0xA2F9836E4E44152A)); /* INVTWOPI */ + twopi1 = packFloatx80(0, 0x3FFF + l, LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(0, 0x3FDD + l, LIT64(0x85A308D300000000)); + + /* SIGN(INARG)*2^63 IN SGL */ + twoto63 = packFloat32(xSign, 0xBE, 0); + + fp2 = floatx80_mul(fp0, invtwopi, status); + fp2 = floatx80_add(fp2, float32_to_floatx80(twoto63, status), + status); /* THE FRACT PART OF FP2 IS ROUNDED */ + fp2 = floatx80_sub(fp2, float32_to_floatx80(twoto63, status), + status); /* FP2 is N */ + fp4 = floatx80_mul(twopi1, fp2, status); /* W = N*P1 */ + fp5 = floatx80_mul(twopi2, fp2, status); /* w = N*P2 */ + fp3 = floatx80_add(fp4, fp5, status); /* FP3 is P */ + fp4 = floatx80_sub(fp4, fp3, status); /* W-P */ + fp0 = floatx80_sub(fp0, fp3, status); /* FP0 is A := R - P */ + fp4 = floatx80_add(fp4, fp5, status); /* FP4 is p = (W-P)+w */ + fp3 = fp0; /* FP3 is A */ + fp1 = floatx80_sub(fp1, fp4, status); /* FP1 is a := r - p */ + fp0 = floatx80_add(fp0, fp1, status); /* FP0 is R := A+a */ + + if (endflag > 0) { + n = floatx80_to_int32(fp2, status); + goto tancont; + } + fp3 = floatx80_sub(fp3, fp0, status); /* A-R */ + fp1 = floatx80_add(fp1, fp3, status); /* FP1 is r := (A-R)+a */ + goto loop; + } else { + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_move(a, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } else { + fp1 = floatx80_mul(fp0, float64_to_floatx80( + make_float64(0x3FE45F306DC9C883), status), + status); /* X*2/PI */ + + n = floatx80_to_int32(fp1, status); + j = 32 + n; + + fp0 = floatx80_sub(fp0, pi_tbl[j], status); /* X-Y1 */ + fp0 = floatx80_sub(fp0, float32_to_floatx80(pi_tbl2[j], status), + status); /* FP0 IS R = (X-Y1)-Y2 */ + + tancont: + if (n & 1) { + /* NODD */ + fp1 = fp0; /* R */ + fp0 = floatx80_mul(fp0, fp0, status); /* S = R*R */ + fp3 = float64_to_floatx80(make_float64(0x3EA0B759F50F8688), + status); /* Q4 */ + fp2 = float64_to_floatx80(make_float64(0xBEF2BAA5A8924F04), + status); /* P3 */ + fp3 = floatx80_mul(fp3, fp0, status); /* SQ4 */ + fp2 = floatx80_mul(fp2, fp0, status); /* SP3 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBF346F59B39BA65F), status), + status); /* Q3+SQ4 */ + fp4 = packFloatx80(0, 0x3FF6, LIT64(0xE073D3FC199C4A00)); + fp2 = floatx80_add(fp2, fp4, status); /* P2+SP3 */ + fp3 = floatx80_mul(fp3, fp0, status); /* S(Q3+SQ4) */ + fp2 = floatx80_mul(fp2, fp0, status); /* S(P2+SP3) */ + fp4 = packFloatx80(0, 0x3FF9, LIT64(0xD23CD68415D95FA1)); + fp3 = floatx80_add(fp3, fp4, status); /* Q2+S(Q3+SQ4) */ + fp4 = packFloatx80(1, 0x3FFC, LIT64(0x8895A6C5FB423BCA)); + fp2 = floatx80_add(fp2, fp4, status); /* P1+S(P2+SP3) */ + fp3 = floatx80_mul(fp3, fp0, status); /* S(Q2+S(Q3+SQ4)) */ + fp2 = floatx80_mul(fp2, fp0, status); /* S(P1+S(P2+SP3)) */ + fp4 = packFloatx80(1, 0x3FFD, LIT64(0xEEF57E0DA84BC8CE)); + fp3 = floatx80_add(fp3, fp4, status); /* Q1+S(Q2+S(Q3+SQ4)) */ + fp2 = floatx80_mul(fp2, fp1, status); /* RS(P1+S(P2+SP3)) */ + fp0 = floatx80_mul(fp0, fp3, status); /* S(Q1+S(Q2+S(Q3+SQ4))) */ + fp1 = floatx80_add(fp1, fp2, status); /* R+RS(P1+S(P2+SP3)) */ + fp0 = floatx80_add(fp0, float32_to_floatx80( + make_float32(0x3F800000), status), + status); /* 1+S(Q1+S(Q2+S(Q3+SQ4))) */ + + xSign = extractFloatx80Sign(fp1); + xExp = extractFloatx80Exp(fp1); + xSig = extractFloatx80Frac(fp1); + xSign ^= 1; + fp1 = packFloatx80(xSign, xExp, xSig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_div(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + fp1 = floatx80_mul(fp0, fp0, status); /* S = R*R */ + fp3 = float64_to_floatx80(make_float64(0x3EA0B759F50F8688), + status); /* Q4 */ + fp2 = float64_to_floatx80(make_float64(0xBEF2BAA5A8924F04), + status); /* P3 */ + fp3 = floatx80_mul(fp3, fp1, status); /* SQ4 */ + fp2 = floatx80_mul(fp2, fp1, status); /* SP3 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBF346F59B39BA65F), status), + status); /* Q3+SQ4 */ + fp4 = packFloatx80(0, 0x3FF6, LIT64(0xE073D3FC199C4A00)); + fp2 = floatx80_add(fp2, fp4, status); /* P2+SP3 */ + fp3 = floatx80_mul(fp3, fp1, status); /* S(Q3+SQ4) */ + fp2 = floatx80_mul(fp2, fp1, status); /* S(P2+SP3) */ + fp4 = packFloatx80(0, 0x3FF9, LIT64(0xD23CD68415D95FA1)); + fp3 = floatx80_add(fp3, fp4, status); /* Q2+S(Q3+SQ4) */ + fp4 = packFloatx80(1, 0x3FFC, LIT64(0x8895A6C5FB423BCA)); + fp2 = floatx80_add(fp2, fp4, status); /* P1+S(P2+SP3) */ + fp3 = floatx80_mul(fp3, fp1, status); /* S(Q2+S(Q3+SQ4)) */ + fp2 = floatx80_mul(fp2, fp1, status); /* S(P1+S(P2+SP3)) */ + fp4 = packFloatx80(1, 0x3FFD, LIT64(0xEEF57E0DA84BC8CE)); + fp3 = floatx80_add(fp3, fp4, status); /* Q1+S(Q2+S(Q3+SQ4)) */ + fp2 = floatx80_mul(fp2, fp0, status); /* RS(P1+S(P2+SP3)) */ + fp1 = floatx80_mul(fp1, fp3, status); /* S(Q1+S(Q2+S(Q3+SQ4))) */ + fp0 = floatx80_add(fp0, fp2, status); /* R+RS(P1+S(P2+SP3)) */ + fp1 = floatx80_add(fp1, float32_to_floatx80( + make_float32(0x3F800000), status), + status); /* 1+S(Q1+S(Q2+S(Q3+SQ4))) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_div(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } +} + +/*---------------------------------------------------------------------------- + | Sine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_sin(floatx80 a, float_status *status) +{ + flag aSign, xSign; + int32_t aExp, xExp; + uint64_t aSig, xSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact, l, n, j; + floatx80 fp0, fp1, fp2, fp3, fp4, fp5, x, invtwopi, twopi1, twopi2; + float32 posneg1, twoto63; + flag adjn, endflag; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + adjn = 0; + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + fp0 = a; + + if (compact < 0x3FD78000 || compact > 0x4004BC7E) { + /* 2^(-40) > |X| > 15 PI */ + if (compact > 0x3FFF8000) { /* |X| >= 15 PI */ + /* REDUCEX */ + fp1 = packFloatx80(0, 0, 0); + if (compact == 0x7FFEFFFF) { + twopi1 = packFloatx80(aSign ^ 1, 0x7FFE, + LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(aSign ^ 1, 0x7FDC, + LIT64(0x85A308D300000000)); + fp0 = floatx80_add(fp0, twopi1, status); + fp1 = fp0; + fp0 = floatx80_add(fp0, twopi2, status); + fp1 = floatx80_sub(fp1, fp0, status); + fp1 = floatx80_add(fp1, twopi2, status); + } + loop: + xSign = extractFloatx80Sign(fp0); + xExp = extractFloatx80Exp(fp0); + xExp -= 0x3FFF; + if (xExp <= 28) { + l = 0; + endflag = 1; + } else { + l = xExp - 27; + endflag = 0; + } + invtwopi = packFloatx80(0, 0x3FFE - l, + LIT64(0xA2F9836E4E44152A)); /* INVTWOPI */ + twopi1 = packFloatx80(0, 0x3FFF + l, LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(0, 0x3FDD + l, LIT64(0x85A308D300000000)); + + /* SIGN(INARG)*2^63 IN SGL */ + twoto63 = packFloat32(xSign, 0xBE, 0); + + fp2 = floatx80_mul(fp0, invtwopi, status); + fp2 = floatx80_add(fp2, float32_to_floatx80(twoto63, status), + status); /* THE FRACT PART OF FP2 IS ROUNDED */ + fp2 = floatx80_sub(fp2, float32_to_floatx80(twoto63, status), + status); /* FP2 is N */ + fp4 = floatx80_mul(twopi1, fp2, status); /* W = N*P1 */ + fp5 = floatx80_mul(twopi2, fp2, status); /* w = N*P2 */ + fp3 = floatx80_add(fp4, fp5, status); /* FP3 is P */ + fp4 = floatx80_sub(fp4, fp3, status); /* W-P */ + fp0 = floatx80_sub(fp0, fp3, status); /* FP0 is A := R - P */ + fp4 = floatx80_add(fp4, fp5, status); /* FP4 is p = (W-P)+w */ + fp3 = fp0; /* FP3 is A */ + fp1 = floatx80_sub(fp1, fp4, status); /* FP1 is a := r - p */ + fp0 = floatx80_add(fp0, fp1, status); /* FP0 is R := A+a */ + + if (endflag > 0) { + n = floatx80_to_int32(fp2, status); + goto sincont; + } + fp3 = floatx80_sub(fp3, fp0, status); /* A-R */ + fp1 = floatx80_add(fp1, fp3, status); /* FP1 is r := (A-R)+a */ + goto loop; + } else { + /* SINSM */ + fp0 = float32_to_floatx80(make_float32(0x3F800000), + status); /* 1 */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + if (adjn) { + /* COSTINY */ + a = floatx80_sub(fp0, float32_to_floatx80( + make_float32(0x00800000), status), status); + } else { + /* SINTINY */ + a = floatx80_move(a, status); + } + float_raise(float_flag_inexact, status); + + return a; + } + } else { + fp1 = floatx80_mul(fp0, float64_to_floatx80( + make_float64(0x3FE45F306DC9C883), status), + status); /* X*2/PI */ + + n = floatx80_to_int32(fp1, status); + j = 32 + n; + + fp0 = floatx80_sub(fp0, pi_tbl[j], status); /* X-Y1 */ + fp0 = floatx80_sub(fp0, float32_to_floatx80(pi_tbl2[j], status), + status); /* FP0 IS R = (X-Y1)-Y2 */ + + sincont: + if ((n + adjn) & 1) { + /* COSPOLY */ + fp0 = floatx80_mul(fp0, fp0, status); /* FP0 IS S */ + fp1 = floatx80_mul(fp0, fp0, status); /* FP1 IS T */ + fp2 = float64_to_floatx80(make_float64(0x3D2AC4D0D6011EE3), + status); /* B8 */ + fp3 = float64_to_floatx80(make_float64(0xBDA9396F9F45AC19), + status); /* B7 */ + + xSign = extractFloatx80Sign(fp0); /* X IS S */ + xExp = extractFloatx80Exp(fp0); + xSig = extractFloatx80Frac(fp0); + + if (((n + adjn) >> 1) & 1) { + xSign ^= 1; + posneg1 = make_float32(0xBF800000); /* -1 */ + } else { + xSign ^= 0; + posneg1 = make_float32(0x3F800000); /* 1 */ + } /* X IS NOW R'= SGN*R */ + + fp2 = floatx80_mul(fp2, fp1, status); /* TB8 */ + fp3 = floatx80_mul(fp3, fp1, status); /* TB7 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3E21EED90612C972), status), + status); /* B6+TB8 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBE927E4FB79D9FCF), status), + status); /* B5+TB7 */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(B6+TB8) */ + fp3 = floatx80_mul(fp3, fp1, status); /* T(B5+TB7) */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3EFA01A01A01D423), status), + status); /* B4+T(B6+TB8) */ + fp4 = packFloatx80(1, 0x3FF5, LIT64(0xB60B60B60B61D438)); + fp3 = floatx80_add(fp3, fp4, status); /* B3+T(B5+TB7) */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(B4+T(B6+TB8)) */ + fp1 = floatx80_mul(fp1, fp3, status); /* T(B3+T(B5+TB7)) */ + fp4 = packFloatx80(0, 0x3FFA, LIT64(0xAAAAAAAAAAAAAB5E)); + fp2 = floatx80_add(fp2, fp4, status); /* B2+T(B4+T(B6+TB8)) */ + fp1 = floatx80_add(fp1, float32_to_floatx80( + make_float32(0xBF000000), status), + status); /* B1+T(B3+T(B5+TB7)) */ + fp0 = floatx80_mul(fp0, fp2, status); /* S(B2+T(B4+T(B6+TB8))) */ + fp0 = floatx80_add(fp0, fp1, status); /* [B1+T(B3+T(B5+TB7))]+ + * [S(B2+T(B4+T(B6+TB8)))] + */ + + x = packFloatx80(xSign, xExp, xSig); + fp0 = floatx80_mul(fp0, x, status); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, float32_to_floatx80(posneg1, status), status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + /* SINPOLY */ + xSign = extractFloatx80Sign(fp0); /* X IS R */ + xExp = extractFloatx80Exp(fp0); + xSig = extractFloatx80Frac(fp0); + + xSign ^= ((n + adjn) >> 1) & 1; /* X IS NOW R'= SGN*R */ + + fp0 = floatx80_mul(fp0, fp0, status); /* FP0 IS S */ + fp1 = floatx80_mul(fp0, fp0, status); /* FP1 IS T */ + fp3 = float64_to_floatx80(make_float64(0xBD6AAA77CCC994F5), + status); /* A7 */ + fp2 = float64_to_floatx80(make_float64(0x3DE612097AAE8DA1), + status); /* A6 */ + fp3 = floatx80_mul(fp3, fp1, status); /* T*A7 */ + fp2 = floatx80_mul(fp2, fp1, status); /* T*A6 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBE5AE6452A118AE4), status), + status); /* A5+T*A7 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3EC71DE3A5341531), status), + status); /* A4+T*A6 */ + fp3 = floatx80_mul(fp3, fp1, status); /* T(A5+TA7) */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(A4+TA6) */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBF2A01A01A018B59), status), + status); /* A3+T(A5+TA7) */ + fp4 = packFloatx80(0, 0x3FF8, LIT64(0x88888888888859AF)); + fp2 = floatx80_add(fp2, fp4, status); /* A2+T(A4+TA6) */ + fp1 = floatx80_mul(fp1, fp3, status); /* T(A3+T(A5+TA7)) */ + fp2 = floatx80_mul(fp2, fp0, status); /* S(A2+T(A4+TA6)) */ + fp4 = packFloatx80(1, 0x3FFC, LIT64(0xAAAAAAAAAAAAAA99)); + fp1 = floatx80_add(fp1, fp4, status); /* A1+T(A3+T(A5+TA7)) */ + fp1 = floatx80_add(fp1, fp2, + status); /* [A1+T(A3+T(A5+TA7))]+ + * [S(A2+T(A4+TA6))] + */ + + x = packFloatx80(xSign, xExp, xSig); + fp0 = floatx80_mul(fp0, x, status); /* R'*S */ + fp0 = floatx80_mul(fp0, fp1, status); /* SIN(R')-R' */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, x, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } +} + +/*---------------------------------------------------------------------------- + | Cosine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_cos(floatx80 a, float_status *status) +{ + flag aSign, xSign; + int32_t aExp, xExp; + uint64_t aSig, xSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact, l, n, j; + floatx80 fp0, fp1, fp2, fp3, fp4, fp5, x, invtwopi, twopi1, twopi2; + float32 posneg1, twoto63; + flag adjn, endflag; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(0, one_exp, one_sig); + } + + adjn = 1; + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + fp0 = a; + + if (compact < 0x3FD78000 || compact > 0x4004BC7E) { + /* 2^(-40) > |X| > 15 PI */ + if (compact > 0x3FFF8000) { /* |X| >= 15 PI */ + /* REDUCEX */ + fp1 = packFloatx80(0, 0, 0); + if (compact == 0x7FFEFFFF) { + twopi1 = packFloatx80(aSign ^ 1, 0x7FFE, + LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(aSign ^ 1, 0x7FDC, + LIT64(0x85A308D300000000)); + fp0 = floatx80_add(fp0, twopi1, status); + fp1 = fp0; + fp0 = floatx80_add(fp0, twopi2, status); + fp1 = floatx80_sub(fp1, fp0, status); + fp1 = floatx80_add(fp1, twopi2, status); + } + loop: + xSign = extractFloatx80Sign(fp0); + xExp = extractFloatx80Exp(fp0); + xExp -= 0x3FFF; + if (xExp <= 28) { + l = 0; + endflag = 1; + } else { + l = xExp - 27; + endflag = 0; + } + invtwopi = packFloatx80(0, 0x3FFE - l, + LIT64(0xA2F9836E4E44152A)); /* INVTWOPI */ + twopi1 = packFloatx80(0, 0x3FFF + l, LIT64(0xC90FDAA200000000)); + twopi2 = packFloatx80(0, 0x3FDD + l, LIT64(0x85A308D300000000)); + + /* SIGN(INARG)*2^63 IN SGL */ + twoto63 = packFloat32(xSign, 0xBE, 0); + + fp2 = floatx80_mul(fp0, invtwopi, status); + fp2 = floatx80_add(fp2, float32_to_floatx80(twoto63, status), + status); /* THE FRACT PART OF FP2 IS ROUNDED */ + fp2 = floatx80_sub(fp2, float32_to_floatx80(twoto63, status), + status); /* FP2 is N */ + fp4 = floatx80_mul(twopi1, fp2, status); /* W = N*P1 */ + fp5 = floatx80_mul(twopi2, fp2, status); /* w = N*P2 */ + fp3 = floatx80_add(fp4, fp5, status); /* FP3 is P */ + fp4 = floatx80_sub(fp4, fp3, status); /* W-P */ + fp0 = floatx80_sub(fp0, fp3, status); /* FP0 is A := R - P */ + fp4 = floatx80_add(fp4, fp5, status); /* FP4 is p = (W-P)+w */ + fp3 = fp0; /* FP3 is A */ + fp1 = floatx80_sub(fp1, fp4, status); /* FP1 is a := r - p */ + fp0 = floatx80_add(fp0, fp1, status); /* FP0 is R := A+a */ + + if (endflag > 0) { + n = floatx80_to_int32(fp2, status); + goto sincont; + } + fp3 = floatx80_sub(fp3, fp0, status); /* A-R */ + fp1 = floatx80_add(fp1, fp3, status); /* FP1 is r := (A-R)+a */ + goto loop; + } else { + /* SINSM */ + fp0 = float32_to_floatx80(make_float32(0x3F800000), status); /* 1 */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + if (adjn) { + /* COSTINY */ + a = floatx80_sub(fp0, float32_to_floatx80( + make_float32(0x00800000), status), + status); + } else { + /* SINTINY */ + a = floatx80_move(a, status); + } + float_raise(float_flag_inexact, status); + + return a; + } + } else { + fp1 = floatx80_mul(fp0, float64_to_floatx80( + make_float64(0x3FE45F306DC9C883), status), + status); /* X*2/PI */ + + n = floatx80_to_int32(fp1, status); + j = 32 + n; + + fp0 = floatx80_sub(fp0, pi_tbl[j], status); /* X-Y1 */ + fp0 = floatx80_sub(fp0, float32_to_floatx80(pi_tbl2[j], status), + status); /* FP0 IS R = (X-Y1)-Y2 */ + + sincont: + if ((n + adjn) & 1) { + /* COSPOLY */ + fp0 = floatx80_mul(fp0, fp0, status); /* FP0 IS S */ + fp1 = floatx80_mul(fp0, fp0, status); /* FP1 IS T */ + fp2 = float64_to_floatx80(make_float64(0x3D2AC4D0D6011EE3), + status); /* B8 */ + fp3 = float64_to_floatx80(make_float64(0xBDA9396F9F45AC19), + status); /* B7 */ + + xSign = extractFloatx80Sign(fp0); /* X IS S */ + xExp = extractFloatx80Exp(fp0); + xSig = extractFloatx80Frac(fp0); + + if (((n + adjn) >> 1) & 1) { + xSign ^= 1; + posneg1 = make_float32(0xBF800000); /* -1 */ + } else { + xSign ^= 0; + posneg1 = make_float32(0x3F800000); /* 1 */ + } /* X IS NOW R'= SGN*R */ + + fp2 = floatx80_mul(fp2, fp1, status); /* TB8 */ + fp3 = floatx80_mul(fp3, fp1, status); /* TB7 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3E21EED90612C972), status), + status); /* B6+TB8 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBE927E4FB79D9FCF), status), + status); /* B5+TB7 */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(B6+TB8) */ + fp3 = floatx80_mul(fp3, fp1, status); /* T(B5+TB7) */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3EFA01A01A01D423), status), + status); /* B4+T(B6+TB8) */ + fp4 = packFloatx80(1, 0x3FF5, LIT64(0xB60B60B60B61D438)); + fp3 = floatx80_add(fp3, fp4, status); /* B3+T(B5+TB7) */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(B4+T(B6+TB8)) */ + fp1 = floatx80_mul(fp1, fp3, status); /* T(B3+T(B5+TB7)) */ + fp4 = packFloatx80(0, 0x3FFA, LIT64(0xAAAAAAAAAAAAAB5E)); + fp2 = floatx80_add(fp2, fp4, status); /* B2+T(B4+T(B6+TB8)) */ + fp1 = floatx80_add(fp1, float32_to_floatx80( + make_float32(0xBF000000), status), + status); /* B1+T(B3+T(B5+TB7)) */ + fp0 = floatx80_mul(fp0, fp2, status); /* S(B2+T(B4+T(B6+TB8))) */ + fp0 = floatx80_add(fp0, fp1, status); + /* [B1+T(B3+T(B5+TB7))]+[S(B2+T(B4+T(B6+TB8)))] */ + + x = packFloatx80(xSign, xExp, xSig); + fp0 = floatx80_mul(fp0, x, status); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, float32_to_floatx80(posneg1, status), status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + /* SINPOLY */ + xSign = extractFloatx80Sign(fp0); /* X IS R */ + xExp = extractFloatx80Exp(fp0); + xSig = extractFloatx80Frac(fp0); + + xSign ^= ((n + adjn) >> 1) & 1; /* X IS NOW R'= SGN*R */ + + fp0 = floatx80_mul(fp0, fp0, status); /* FP0 IS S */ + fp1 = floatx80_mul(fp0, fp0, status); /* FP1 IS T */ + fp3 = float64_to_floatx80(make_float64(0xBD6AAA77CCC994F5), + status); /* A7 */ + fp2 = float64_to_floatx80(make_float64(0x3DE612097AAE8DA1), + status); /* A6 */ + fp3 = floatx80_mul(fp3, fp1, status); /* T*A7 */ + fp2 = floatx80_mul(fp2, fp1, status); /* T*A6 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBE5AE6452A118AE4), status), + status); /* A5+T*A7 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3EC71DE3A5341531), status), + status); /* A4+T*A6 */ + fp3 = floatx80_mul(fp3, fp1, status); /* T(A5+TA7) */ + fp2 = floatx80_mul(fp2, fp1, status); /* T(A4+TA6) */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBF2A01A01A018B59), status), + status); /* A3+T(A5+TA7) */ + fp4 = packFloatx80(0, 0x3FF8, LIT64(0x88888888888859AF)); + fp2 = floatx80_add(fp2, fp4, status); /* A2+T(A4+TA6) */ + fp1 = floatx80_mul(fp1, fp3, status); /* T(A3+T(A5+TA7)) */ + fp2 = floatx80_mul(fp2, fp0, status); /* S(A2+T(A4+TA6)) */ + fp4 = packFloatx80(1, 0x3FFC, LIT64(0xAAAAAAAAAAAAAA99)); + fp1 = floatx80_add(fp1, fp4, status); /* A1+T(A3+T(A5+TA7)) */ + fp1 = floatx80_add(fp1, fp2, status); + /* [A1+T(A3+T(A5+TA7))]+[S(A2+T(A4+TA6))] */ + + x = packFloatx80(xSign, xExp, xSig); + fp0 = floatx80_mul(fp0, x, status); /* R'*S */ + fp0 = floatx80_mul(fp0, fp1, status); /* SIN(R')-R' */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, x, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } +} + +/*---------------------------------------------------------------------------- + | Arc tangent + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_atan(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact, tbl_index; + floatx80 fp0, fp1, fp2, fp3, xsave; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + a = packFloatx80(aSign, piby2_exp, pi_sig); + float_raise(float_flag_inexact, status); + return floatx80_move(a, status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + compact = floatx80_make_compact(aExp, aSig); + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + if (compact < 0x3FFB8000 || compact > 0x4002FFFF) { + /* |X| >= 16 or |X| < 1/16 */ + if (compact > 0x3FFF8000) { /* |X| >= 16 */ + if (compact > 0x40638000) { /* |X| > 2^(100) */ + fp0 = packFloatx80(aSign, piby2_exp, pi_sig); + fp1 = packFloatx80(aSign, 0x0001, one_sig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_sub(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + fp0 = a; + fp1 = packFloatx80(1, one_exp, one_sig); /* -1 */ + fp1 = floatx80_div(fp1, fp0, status); /* X' = -1/X */ + xsave = fp1; + fp0 = floatx80_mul(fp1, fp1, status); /* Y = X'*X' */ + fp1 = floatx80_mul(fp0, fp0, status); /* Z = Y*Y */ + fp3 = float64_to_floatx80(make_float64(0xBFB70BF398539E6A), + status); /* C5 */ + fp2 = float64_to_floatx80(make_float64(0x3FBC7187962D1D7D), + status); /* C4 */ + fp3 = floatx80_mul(fp3, fp1, status); /* Z*C5 */ + fp2 = floatx80_mul(fp2, fp1, status); /* Z*C4 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBFC24924827107B8), status), + status); /* C3+Z*C5 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3FC999999996263E), status), + status); /* C2+Z*C4 */ + fp1 = floatx80_mul(fp1, fp3, status); /* Z*(C3+Z*C5) */ + fp2 = floatx80_mul(fp2, fp0, status); /* Y*(C2+Z*C4) */ + fp1 = floatx80_add(fp1, float64_to_floatx80( + make_float64(0xBFD5555555555536), status), + status); /* C1+Z*(C3+Z*C5) */ + fp0 = floatx80_mul(fp0, xsave, status); /* X'*Y */ + /* [Y*(C2+Z*C4)]+[C1+Z*(C3+Z*C5)] */ + fp1 = floatx80_add(fp1, fp2, status); + /* X'*Y*([B1+Z*(B3+Z*B5)]+[Y*(B2+Z*(B4+Z*B6))]) ?? */ + fp0 = floatx80_mul(fp0, fp1, status); + fp0 = floatx80_add(fp0, xsave, status); + fp1 = packFloatx80(aSign, piby2_exp, pi_sig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } else { /* |X| < 1/16 */ + if (compact < 0x3FD78000) { /* |X| < 2^(-40) */ + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_move(a, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + fp0 = a; + xsave = a; + fp0 = floatx80_mul(fp0, fp0, status); /* Y = X*X */ + fp1 = floatx80_mul(fp0, fp0, status); /* Z = Y*Y */ + fp2 = float64_to_floatx80(make_float64(0x3FB344447F876989), + status); /* B6 */ + fp3 = float64_to_floatx80(make_float64(0xBFB744EE7FAF45DB), + status); /* B5 */ + fp2 = floatx80_mul(fp2, fp1, status); /* Z*B6 */ + fp3 = floatx80_mul(fp3, fp1, status); /* Z*B5 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3FBC71C646940220), status), + status); /* B4+Z*B6 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0xBFC24924921872F9), + status), status); /* B3+Z*B5 */ + fp2 = floatx80_mul(fp2, fp1, status); /* Z*(B4+Z*B6) */ + fp1 = floatx80_mul(fp1, fp3, status); /* Z*(B3+Z*B5) */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3FC9999999998FA9), status), + status); /* B2+Z*(B4+Z*B6) */ + fp1 = floatx80_add(fp1, float64_to_floatx80( + make_float64(0xBFD5555555555555), status), + status); /* B1+Z*(B3+Z*B5) */ + fp2 = floatx80_mul(fp2, fp0, status); /* Y*(B2+Z*(B4+Z*B6)) */ + fp0 = floatx80_mul(fp0, xsave, status); /* X*Y */ + /* [B1+Z*(B3+Z*B5)]+[Y*(B2+Z*(B4+Z*B6))] */ + fp1 = floatx80_add(fp1, fp2, status); + /* X*Y*([B1+Z*(B3+Z*B5)]+[Y*(B2+Z*(B4+Z*B6))]) */ + fp0 = floatx80_mul(fp0, fp1, status); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, xsave, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } + } else { + aSig &= LIT64(0xF800000000000000); + aSig |= LIT64(0x0400000000000000); + xsave = packFloatx80(aSign, aExp, aSig); /* F */ + fp0 = a; + fp1 = a; /* X */ + fp2 = packFloatx80(0, one_exp, one_sig); /* 1 */ + fp1 = floatx80_mul(fp1, xsave, status); /* X*F */ + fp0 = floatx80_sub(fp0, xsave, status); /* X-F */ + fp1 = floatx80_add(fp1, fp2, status); /* 1 + X*F */ + fp0 = floatx80_div(fp0, fp1, status); /* U = (X-F)/(1+X*F) */ + + tbl_index = compact; + + tbl_index &= 0x7FFF0000; + tbl_index -= 0x3FFB0000; + tbl_index >>= 1; + tbl_index += compact & 0x00007800; + tbl_index >>= 11; + + fp3 = atan_tbl[tbl_index]; + + fp3.high |= aSign ? 0x8000 : 0; /* ATAN(F) */ + + fp1 = floatx80_mul(fp0, fp0, status); /* V = U*U */ + fp2 = float64_to_floatx80(make_float64(0xBFF6687E314987D8), + status); /* A3 */ + fp2 = floatx80_add(fp2, fp1, status); /* A3+V */ + fp2 = floatx80_mul(fp2, fp1, status); /* V*(A3+V) */ + fp1 = floatx80_mul(fp1, fp0, status); /* U*V */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x4002AC6934A26DB3), status), + status); /* A2+V*(A3+V) */ + fp1 = floatx80_mul(fp1, float64_to_floatx80( + make_float64(0xBFC2476F4E1DA28E), status), + status); /* A1+U*V */ + fp1 = floatx80_mul(fp1, fp2, status); /* A1*U*V*(A2+V*(A3+V)) */ + fp0 = floatx80_add(fp0, fp1, status); /* ATAN(U) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, fp3, status); /* ATAN(X) */ + + float_raise(float_flag_inexact, status); + + return a; + } +} + +/*---------------------------------------------------------------------------- + | Arc sine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_asin(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1, fp2, one; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF && (uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + compact = floatx80_make_compact(aExp, aSig); + + if (compact >= 0x3FFF8000) { /* |X| >= 1 */ + if (aExp == one_exp && aSig == one_sig) { /* |X| == 1 */ + float_raise(float_flag_inexact, status); + a = packFloatx80(aSign, piby2_exp, pi_sig); + return floatx80_move(a, status); + } else { /* |X| > 1 */ + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + + } /* |X| < 1 */ + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + one = packFloatx80(0, one_exp, one_sig); + fp0 = a; + + fp1 = floatx80_sub(one, fp0, status); /* 1 - X */ + fp2 = floatx80_add(one, fp0, status); /* 1 + X */ + fp1 = floatx80_mul(fp2, fp1, status); /* (1+X)*(1-X) */ + fp1 = floatx80_sqrt(fp1, status); /* SQRT((1+X)*(1-X)) */ + fp0 = floatx80_div(fp0, fp1, status); /* X/SQRT((1+X)*(1-X)) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_atan(fp0, status); /* ATAN(X/SQRT((1+X)*(1-X))) */ + + float_raise(float_flag_inexact, status); + + return a; +} + +/*---------------------------------------------------------------------------- + | Arc cosine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_acos(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1, one; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF && (uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + if (aExp == 0 && aSig == 0) { + float_raise(float_flag_inexact, status); + return roundAndPackFloatx80(status->floatx80_rounding_precision, 0, + piby2_exp, pi_sig, 0, status); + } + + compact = floatx80_make_compact(aExp, aSig); + + if (compact >= 0x3FFF8000) { /* |X| >= 1 */ + if (aExp == one_exp && aSig == one_sig) { /* |X| == 1 */ + if (aSign) { /* X == -1 */ + a = packFloatx80(0, pi_exp, pi_sig); + float_raise(float_flag_inexact, status); + return floatx80_move(a, status); + } else { /* X == +1 */ + return packFloatx80(0, 0, 0); + } + } else { /* |X| > 1 */ + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + } /* |X| < 1 */ + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + one = packFloatx80(0, one_exp, one_sig); + fp0 = a; + + fp1 = floatx80_add(one, fp0, status); /* 1 + X */ + fp0 = floatx80_sub(one, fp0, status); /* 1 - X */ + fp0 = floatx80_div(fp0, fp1, status); /* (1-X)/(1+X) */ + fp0 = floatx80_sqrt(fp0, status); /* SQRT((1-X)/(1+X)) */ + fp0 = floatx80_atan(fp0, status); /* ATAN(SQRT((1-X)/(1+X))) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, fp0, status); /* 2 * ATAN(SQRT((1-X)/(1+X))) */ + + float_raise(float_flag_inexact, status); + + return a; +} + +/*---------------------------------------------------------------------------- + | Hyperbolic arc tangent + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_atanh(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1, fp2, one; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF && (uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + compact = floatx80_make_compact(aExp, aSig); + + if (compact >= 0x3FFF8000) { /* |X| >= 1 */ + if (aExp == one_exp && aSig == one_sig) { /* |X| == 1 */ + float_raise(float_flag_divbyzero, status); + return packFloatx80(aSign, floatx80_infinity.high, + floatx80_infinity.low); + } else { /* |X| > 1 */ + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + } /* |X| < 1 */ + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + one = packFloatx80(0, one_exp, one_sig); + fp2 = packFloatx80(aSign, 0x3FFE, one_sig); /* SIGN(X) * (1/2) */ + fp0 = packFloatx80(0, aExp, aSig); /* Y = |X| */ + fp1 = packFloatx80(1, aExp, aSig); /* -Y */ + fp0 = floatx80_add(fp0, fp0, status); /* 2Y */ + fp1 = floatx80_add(fp1, one, status); /* 1-Y */ + fp0 = floatx80_div(fp0, fp1, status); /* Z = 2Y/(1-Y) */ + fp0 = floatx80_lognp1(fp0, status); /* LOG1P(Z) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, fp2, + status); /* ATANH(X) = SIGN(X) * (1/2) * LOG1P(Z) */ + + float_raise(float_flag_inexact, status); + + return a; +} + +/*---------------------------------------------------------------------------- + | e to x minus 1 + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_etoxm1(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact, n, j, m, m1; + floatx80 fp0, fp1, fp2, fp3, l2, sc, onebysc; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + if (aSign) { + return packFloatx80(aSign, one_exp, one_sig); + } + return packFloatx80(0, floatx80_infinity.high, + floatx80_infinity.low); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + if (aExp >= 0x3FFD) { /* |X| >= 1/4 */ + compact = floatx80_make_compact(aExp, aSig); + + if (compact <= 0x4004C215) { /* |X| <= 70 log2 */ + fp0 = a; + fp1 = a; + fp0 = floatx80_mul(fp0, float32_to_floatx80( + make_float32(0x42B8AA3B), status), + status); /* 64/log2 * X */ + n = floatx80_to_int32(fp0, status); /* int(64/log2*X) */ + fp0 = int32_to_floatx80(n, status); + + j = n & 0x3F; /* J = N mod 64 */ + m = n / 64; /* NOTE: this is really arithmetic right shift by 6 */ + if (n < 0 && j) { + /* arithmetic right shift is division and + * round towards minus infinity + */ + m--; + } + m1 = -m; + /*m += 0x3FFF; // biased exponent of 2^(M) */ + /*m1 += 0x3FFF; // biased exponent of -2^(-M) */ + + fp2 = fp0; /* N */ + fp0 = floatx80_mul(fp0, float32_to_floatx80( + make_float32(0xBC317218), status), + status); /* N * L1, L1 = lead(-log2/64) */ + l2 = packFloatx80(0, 0x3FDC, LIT64(0x82E308654361C4C6)); + fp2 = floatx80_mul(fp2, l2, status); /* N * L2, L1+L2 = -log2/64 */ + fp0 = floatx80_add(fp0, fp1, status); /* X + N*L1 */ + fp0 = floatx80_add(fp0, fp2, status); /* R */ + + fp1 = floatx80_mul(fp0, fp0, status); /* S = R*R */ + fp2 = float32_to_floatx80(make_float32(0x3950097B), + status); /* A6 */ + fp2 = floatx80_mul(fp2, fp1, status); /* fp2 is S*A6 */ + fp3 = floatx80_mul(float32_to_floatx80(make_float32(0x3AB60B6A), + status), fp1, status); /* fp3 is S*A5 */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3F81111111174385), status), + status); /* fp2 IS A4+S*A6 */ + fp3 = floatx80_add(fp3, float64_to_floatx80( + make_float64(0x3FA5555555554F5A), status), + status); /* fp3 is A3+S*A5 */ + fp2 = floatx80_mul(fp2, fp1, status); /* fp2 IS S*(A4+S*A6) */ + fp3 = floatx80_mul(fp3, fp1, status); /* fp3 IS S*(A3+S*A5) */ + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3FC5555555555555), status), + status); /* fp2 IS A2+S*(A4+S*A6) */ + fp3 = floatx80_add(fp3, float32_to_floatx80( + make_float32(0x3F000000), status), + status); /* fp3 IS A1+S*(A3+S*A5) */ + fp2 = floatx80_mul(fp2, fp1, + status); /* fp2 IS S*(A2+S*(A4+S*A6)) */ + fp1 = floatx80_mul(fp1, fp3, + status); /* fp1 IS S*(A1+S*(A3+S*A5)) */ + fp2 = floatx80_mul(fp2, fp0, + status); /* fp2 IS R*S*(A2+S*(A4+S*A6)) */ + fp0 = floatx80_add(fp0, fp1, + status); /* fp0 IS R+S*(A1+S*(A3+S*A5)) */ + fp0 = floatx80_add(fp0, fp2, status); /* fp0 IS EXP(R) - 1 */ + + fp0 = floatx80_mul(fp0, exp_tbl[j], + status); /* 2^(J/64)*(Exp(R)-1) */ + + if (m >= 64) { + fp1 = float32_to_floatx80(exp_tbl2[j], status); + onebysc = packFloatx80(1, m1 + 0x3FFF, one_sig); /* -2^(-M) */ + fp1 = floatx80_add(fp1, onebysc, status); + fp0 = floatx80_add(fp0, fp1, status); + fp0 = floatx80_add(fp0, exp_tbl[j], status); + } else if (m < -3) { + fp0 = floatx80_add(fp0, float32_to_floatx80(exp_tbl2[j], + status), status); + fp0 = floatx80_add(fp0, exp_tbl[j], status); + onebysc = packFloatx80(1, m1 + 0x3FFF, one_sig); /* -2^(-M) */ + fp0 = floatx80_add(fp0, onebysc, status); + } else { /* -3 <= m <= 63 */ + fp1 = exp_tbl[j]; + fp0 = floatx80_add(fp0, float32_to_floatx80(exp_tbl2[j], + status), status); + onebysc = packFloatx80(1, m1 + 0x3FFF, one_sig); /* -2^(-M) */ + fp1 = floatx80_add(fp1, onebysc, status); + fp0 = floatx80_add(fp0, fp1, status); + } + + sc = packFloatx80(0, m + 0x3FFF, one_sig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, sc, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { /* |X| > 70 log2 */ + if (aSign) { + fp0 = float32_to_floatx80(make_float32(0xBF800000), + status); /* -1 */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, float32_to_floatx80( + make_float32(0x00800000), status), + status); /* -1 + 2^(-126) */ + + float_raise(float_flag_inexact, status); + + return a; + } else { + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + return floatx80_etox(a, status); + } + } + } else { /* |X| < 1/4 */ + if (aExp >= 0x3FBE) { + fp0 = a; + fp0 = floatx80_mul(fp0, fp0, status); /* S = X*X */ + fp1 = float32_to_floatx80(make_float32(0x2F30CAA8), + status); /* B12 */ + fp1 = floatx80_mul(fp1, fp0, status); /* S * B12 */ + fp2 = float32_to_floatx80(make_float32(0x310F8290), + status); /* B11 */ + fp1 = floatx80_add(fp1, float32_to_floatx80( + make_float32(0x32D73220), status), + status); /* B10 */ + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, fp0, status); + fp2 = floatx80_add(fp2, float32_to_floatx80( + make_float32(0x3493F281), status), + status); /* B9 */ + fp1 = floatx80_add(fp1, float64_to_floatx80( + make_float64(0x3EC71DE3A5774682), status), + status); /* B8 */ + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, fp0, status); + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3EFA01A019D7CB68), status), + status); /* B7 */ + fp1 = floatx80_add(fp1, float64_to_floatx80( + make_float64(0x3F2A01A01A019DF3), status), + status); /* B6 */ + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, fp0, status); + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3F56C16C16C170E2), status), + status); /* B5 */ + fp1 = floatx80_add(fp1, float64_to_floatx80( + make_float64(0x3F81111111111111), status), + status); /* B4 */ + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, fp0, status); + fp2 = floatx80_add(fp2, float64_to_floatx80( + make_float64(0x3FA5555555555555), status), + status); /* B3 */ + fp3 = packFloatx80(0, 0x3FFC, LIT64(0xAAAAAAAAAAAAAAAB)); + fp1 = floatx80_add(fp1, fp3, status); /* B2 */ + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, fp0, status); + + fp2 = floatx80_mul(fp2, fp0, status); + fp1 = floatx80_mul(fp1, a, status); + + fp0 = floatx80_mul(fp0, float32_to_floatx80( + make_float32(0x3F000000), status), + status); /* S*B1 */ + fp1 = floatx80_add(fp1, fp2, status); /* Q */ + fp0 = floatx80_add(fp0, fp1, status); /* S*B1+Q */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, a, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { /* |X| < 2^(-65) */ + sc = packFloatx80(1, 1, one_sig); + fp0 = a; + + if (aExp < 0x0033) { /* |X| < 2^(-16382) */ + fp0 = floatx80_mul(fp0, float64_to_floatx80( + make_float64(0x48B0000000000000), status), + status); + fp0 = floatx80_add(fp0, sc, status); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, float64_to_floatx80( + make_float64(0x3730000000000000), status), + status); + } else { + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, sc, status); + } + + float_raise(float_flag_inexact, status); + + return a; + } + } +} + +/*---------------------------------------------------------------------------- + | Hyperbolic tangent + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_tanh(floatx80 a, float_status *status) +{ + flag aSign, vSign; + int32_t aExp, vExp; + uint64_t aSig, vSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1; + uint32_t sign; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + return packFloatx80(aSign, one_exp, one_sig); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + if (compact < 0x3FD78000 || compact > 0x3FFFDDCE) { + /* TANHBORS */ + if (compact < 0x3FFF8000) { + /* TANHSM */ + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_move(a, status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + if (compact > 0x40048AA1) { + /* TANHHUGE */ + sign = 0x3F800000; + sign |= aSign ? 0x80000000 : 0x00000000; + fp0 = float32_to_floatx80(make_float32(sign), status); + sign &= 0x80000000; + sign ^= 0x80800000; /* -SIGN(X)*EPS */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, float32_to_floatx80(make_float32(sign), + status), status); + + float_raise(float_flag_inexact, status); + + return a; + } else { + fp0 = packFloatx80(0, aExp + 1, aSig); /* Y = 2|X| */ + fp0 = floatx80_etox(fp0, status); /* FP0 IS EXP(Y) */ + fp0 = floatx80_add(fp0, float32_to_floatx80( + make_float32(0x3F800000), + status), status); /* EXP(Y)+1 */ + sign = aSign ? 0x80000000 : 0x00000000; + fp1 = floatx80_div(float32_to_floatx80(make_float32( + sign ^ 0xC0000000), status), fp0, + status); /* -SIGN(X)*2 / [EXP(Y)+1] */ + fp0 = float32_to_floatx80(make_float32(sign | 0x3F800000), + status); /* SIGN */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp1, fp0, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } + } else { /* 2**(-40) < |X| < (5/2)LOG2 */ + fp0 = packFloatx80(0, aExp + 1, aSig); /* Y = 2|X| */ + fp0 = floatx80_etoxm1(fp0, status); /* FP0 IS Z = EXPM1(Y) */ + fp1 = floatx80_add(fp0, float32_to_floatx80(make_float32(0x40000000), + status), + status); /* Z+2 */ + + vSign = extractFloatx80Sign(fp1); + vExp = extractFloatx80Exp(fp1); + vSig = extractFloatx80Frac(fp1); + + fp1 = packFloatx80(vSign ^ aSign, vExp, vSig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_div(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } +} + +/*---------------------------------------------------------------------------- + | Hyperbolic sine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_sinh(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1, fp2; + float32 fact; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + return packFloatx80(aSign, floatx80_infinity.high, + floatx80_infinity.low); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + if (compact > 0x400CB167) { + /* SINHBIG */ + if (compact > 0x400CB2B3) { + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + return roundAndPackFloatx80(status->floatx80_rounding_precision, + aSign, 0x8000, aSig, 0, status); + } else { + fp0 = floatx80_abs(a); /* Y = |X| */ + fp0 = floatx80_sub(fp0, float64_to_floatx80( + make_float64(0x40C62D38D3D64634), status), + status); /* (|X|-16381LOG2_LEAD) */ + fp0 = floatx80_sub(fp0, float64_to_floatx80( + make_float64(0x3D6F90AEB1E75CC7), status), + status); /* |X| - 16381 LOG2, ACCURATE */ + fp0 = floatx80_etox(fp0, status); + fp2 = packFloatx80(aSign, 0x7FFB, one_sig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, fp2, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } else { /* |X| < 16380 LOG2 */ + fp0 = floatx80_abs(a); /* Y = |X| */ + fp0 = floatx80_etoxm1(fp0, status); /* FP0 IS Z = EXPM1(Y) */ + fp1 = floatx80_add(fp0, float32_to_floatx80(make_float32(0x3F800000), + status), status); /* 1+Z */ + fp2 = fp0; + fp0 = floatx80_div(fp0, fp1, status); /* Z/(1+Z) */ + fp0 = floatx80_add(fp0, fp2, status); + + fact = packFloat32(aSign, 0x7E, 0); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, float32_to_floatx80(fact, status), status); + + float_raise(float_flag_inexact, status); + + return a; + } +} + +/*---------------------------------------------------------------------------- + | Hyperbolic cosine + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_cosh(floatx80 a, float_status *status) +{ + int32_t aExp; + uint64_t aSig; + + int8_t user_rnd_mode, user_rnd_prec; + + int32_t compact; + floatx80 fp0, fp1; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaNOneArg(a, status); + } + return packFloatx80(0, floatx80_infinity.high, + floatx80_infinity.low); + } + + if (aExp == 0 && aSig == 0) { + return packFloatx80(0, one_exp, one_sig); + } + + user_rnd_mode = status->float_rounding_mode; + user_rnd_prec = status->floatx80_rounding_precision; + status->float_rounding_mode = float_round_nearest_even; + status->floatx80_rounding_precision = 80; + + compact = floatx80_make_compact(aExp, aSig); + + if (compact > 0x400CB167) { + if (compact > 0x400CB2B3) { + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + return roundAndPackFloatx80(status->floatx80_rounding_precision, 0, + 0x8000, one_sig, 0, status); + } else { + fp0 = packFloatx80(0, aExp, aSig); + fp0 = floatx80_sub(fp0, float64_to_floatx80( + make_float64(0x40C62D38D3D64634), status), + status); + fp0 = floatx80_sub(fp0, float64_to_floatx80( + make_float64(0x3D6F90AEB1E75CC7), status), + status); + fp0 = floatx80_etox(fp0, status); + fp1 = packFloatx80(0, 0x7FFB, one_sig); + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_mul(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; + } + } + + fp0 = packFloatx80(0, aExp, aSig); /* |X| */ + fp0 = floatx80_etox(fp0, status); /* EXP(|X|) */ + fp0 = floatx80_mul(fp0, float32_to_floatx80(make_float32(0x3F000000), + status), status); /* (1/2)*EXP(|X|) */ + fp1 = float32_to_floatx80(make_float32(0x3E800000), status); /* 1/4 */ + fp1 = floatx80_div(fp1, fp0, status); /* 1/(2*EXP(|X|)) */ + + status->float_rounding_mode = user_rnd_mode; + status->floatx80_rounding_precision = user_rnd_prec; + + a = floatx80_add(fp0, fp1, status); + + float_raise(float_flag_inexact, status); + + return a; +} diff --git a/target/m68k/softfloat.h b/target/m68k/softfloat.h index d28e49fe9f..602661d5a8 100644 --- a/target/m68k/softfloat.h +++ b/target/m68k/softfloat.h @@ -34,4 +34,15 @@ floatx80 floatx80_log2(floatx80 a, float_status *status); floatx80 floatx80_etox(floatx80 a, float_status *status); floatx80 floatx80_twotox(floatx80 a, float_status *status); floatx80 floatx80_tentox(floatx80 a, float_status *status); +floatx80 floatx80_tan(floatx80 a, float_status *status); +floatx80 floatx80_sin(floatx80 a, float_status *status); +floatx80 floatx80_cos(floatx80 a, float_status *status); +floatx80 floatx80_atan(floatx80 a, float_status *status); +floatx80 floatx80_asin(floatx80 a, float_status *status); +floatx80 floatx80_acos(floatx80 a, float_status *status); +floatx80 floatx80_atanh(floatx80 a, float_status *status); +floatx80 floatx80_etoxm1(floatx80 a, float_status *status); +floatx80 floatx80_tanh(floatx80 a, float_status *status); +floatx80 floatx80_sinh(floatx80 a, float_status *status); +floatx80 floatx80_cosh(floatx80 a, float_status *status); #endif diff --git a/target/m68k/softfloat_fpsp_tables.h b/target/m68k/softfloat_fpsp_tables.h index dd76dc0373..3f1419ee6e 100644 --- a/target/m68k/softfloat_fpsp_tables.h +++ b/target/m68k/softfloat_fpsp_tables.h @@ -371,4 +371,271 @@ static const uint32_t exp2_tbl2[64] = { 0xBFBDBF4A, 0x3FBEC01A, 0x3FBE8CAC, 0xBFBCBB3F, 0x3FBEF73A, 0xBFB8B795, 0x3FBEF84B, 0xBFBEF581 }; + +static const floatx80 pi_tbl[65] = { + make_floatx80_init(0xC004, 0xC90FDAA22168C235), + make_floatx80_init(0xC004, 0xC2C75BCD105D7C23), + make_floatx80_init(0xC004, 0xBC7EDCF7FF523611), + make_floatx80_init(0xC004, 0xB6365E22EE46F000), + make_floatx80_init(0xC004, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0xC004, 0xA9A56078CC3063DD), + make_floatx80_init(0xC004, 0xA35CE1A3BB251DCB), + make_floatx80_init(0xC004, 0x9D1462CEAA19D7B9), + make_floatx80_init(0xC004, 0x96CBE3F9990E91A8), + make_floatx80_init(0xC004, 0x9083652488034B96), + make_floatx80_init(0xC004, 0x8A3AE64F76F80584), + make_floatx80_init(0xC004, 0x83F2677A65ECBF73), + make_floatx80_init(0xC003, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0xC003, 0xEEC2D3A087AC669F), + make_floatx80_init(0xC003, 0xE231D5F66595DA7B), + make_floatx80_init(0xC003, 0xD5A0D84C437F4E58), + make_floatx80_init(0xC003, 0xC90FDAA22168C235), + make_floatx80_init(0xC003, 0xBC7EDCF7FF523611), + make_floatx80_init(0xC003, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0xC003, 0xA35CE1A3BB251DCB), + make_floatx80_init(0xC003, 0x96CBE3F9990E91A8), + make_floatx80_init(0xC003, 0x8A3AE64F76F80584), + make_floatx80_init(0xC002, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0xC002, 0xE231D5F66595DA7B), + make_floatx80_init(0xC002, 0xC90FDAA22168C235), + make_floatx80_init(0xC002, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0xC002, 0x96CBE3F9990E91A8), + make_floatx80_init(0xC001, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0xC001, 0xC90FDAA22168C235), + make_floatx80_init(0xC001, 0x96CBE3F9990E91A8), + make_floatx80_init(0xC000, 0xC90FDAA22168C235), + make_floatx80_init(0xBFFF, 0xC90FDAA22168C235), + make_floatx80_init(0x0000, 0x0000000000000000), + make_floatx80_init(0x3FFF, 0xC90FDAA22168C235), + make_floatx80_init(0x4000, 0xC90FDAA22168C235), + make_floatx80_init(0x4001, 0x96CBE3F9990E91A8), + make_floatx80_init(0x4001, 0xC90FDAA22168C235), + make_floatx80_init(0x4001, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0x4002, 0x96CBE3F9990E91A8), + make_floatx80_init(0x4002, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0x4002, 0xC90FDAA22168C235), + make_floatx80_init(0x4002, 0xE231D5F66595DA7B), + make_floatx80_init(0x4002, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0x4003, 0x8A3AE64F76F80584), + make_floatx80_init(0x4003, 0x96CBE3F9990E91A8), + make_floatx80_init(0x4003, 0xA35CE1A3BB251DCB), + make_floatx80_init(0x4003, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0x4003, 0xBC7EDCF7FF523611), + make_floatx80_init(0x4003, 0xC90FDAA22168C235), + make_floatx80_init(0x4003, 0xD5A0D84C437F4E58), + make_floatx80_init(0x4003, 0xE231D5F66595DA7B), + make_floatx80_init(0x4003, 0xEEC2D3A087AC669F), + make_floatx80_init(0x4003, 0xFB53D14AA9C2F2C2), + make_floatx80_init(0x4004, 0x83F2677A65ECBF73), + make_floatx80_init(0x4004, 0x8A3AE64F76F80584), + make_floatx80_init(0x4004, 0x9083652488034B96), + make_floatx80_init(0x4004, 0x96CBE3F9990E91A8), + make_floatx80_init(0x4004, 0x9D1462CEAA19D7B9), + make_floatx80_init(0x4004, 0xA35CE1A3BB251DCB), + make_floatx80_init(0x4004, 0xA9A56078CC3063DD), + make_floatx80_init(0x4004, 0xAFEDDF4DDD3BA9EE), + make_floatx80_init(0x4004, 0xB6365E22EE46F000), + make_floatx80_init(0x4004, 0xBC7EDCF7FF523611), + make_floatx80_init(0x4004, 0xC2C75BCD105D7C23), + make_floatx80_init(0x4004, 0xC90FDAA22168C235) +}; + +static const float32 pi_tbl2[65] = { + const_float32(0x21800000), + const_float32(0xA0D00000), + const_float32(0xA1E80000), + const_float32(0x21480000), + const_float32(0xA1200000), + const_float32(0x21FC0000), + const_float32(0x21100000), + const_float32(0xA1580000), + const_float32(0x21E00000), + const_float32(0x20B00000), + const_float32(0xA1880000), + const_float32(0x21C40000), + const_float32(0x20000000), + const_float32(0x21380000), + const_float32(0xA1300000), + const_float32(0x9FC00000), + const_float32(0x21000000), + const_float32(0xA1680000), + const_float32(0xA0A00000), + const_float32(0x20900000), + const_float32(0x21600000), + const_float32(0xA1080000), + const_float32(0x1F800000), + const_float32(0xA0B00000), + const_float32(0x20800000), + const_float32(0xA0200000), + const_float32(0x20E00000), + const_float32(0x1F000000), + const_float32(0x20000000), + const_float32(0x20600000), + const_float32(0x1F800000), + const_float32(0x1F000000), + const_float32(0x00000000), + const_float32(0x9F000000), + const_float32(0x9F800000), + const_float32(0xA0600000), + const_float32(0xA0000000), + const_float32(0x9F000000), + const_float32(0xA0E00000), + const_float32(0x20200000), + const_float32(0xA0800000), + const_float32(0x20B00000), + const_float32(0x9F800000), + const_float32(0x21080000), + const_float32(0xA1600000), + const_float32(0xA0900000), + const_float32(0x20A00000), + const_float32(0x21680000), + const_float32(0xA1000000), + const_float32(0x1FC00000), + const_float32(0x21300000), + const_float32(0xA1380000), + const_float32(0xA0000000), + const_float32(0xA1C40000), + const_float32(0x21880000), + const_float32(0xA0B00000), + const_float32(0xA1E00000), + const_float32(0x21580000), + const_float32(0xA1100000), + const_float32(0xA1FC0000), + const_float32(0x21200000), + const_float32(0xA1480000), + const_float32(0x21E80000), + const_float32(0x20D00000), + const_float32(0xA1800000), +}; + +static const floatx80 atan_tbl[128] = { + make_floatx80_init(0x3FFB, 0x83D152C5060B7A51), + make_floatx80_init(0x3FFB, 0x8BC8544565498B8B), + make_floatx80_init(0x3FFB, 0x93BE406017626B0D), + make_floatx80_init(0x3FFB, 0x9BB3078D35AEC202), + make_floatx80_init(0x3FFB, 0xA3A69A525DDCE7DE), + make_floatx80_init(0x3FFB, 0xAB98E94362765619), + make_floatx80_init(0x3FFB, 0xB389E502F9C59862), + make_floatx80_init(0x3FFB, 0xBB797E436B09E6FB), + make_floatx80_init(0x3FFB, 0xC367A5C739E5F446), + make_floatx80_init(0x3FFB, 0xCB544C61CFF7D5C6), + make_floatx80_init(0x3FFB, 0xD33F62F82488533E), + make_floatx80_init(0x3FFB, 0xDB28DA8162404C77), + make_floatx80_init(0x3FFB, 0xE310A4078AD34F18), + make_floatx80_init(0x3FFB, 0xEAF6B0A8188EE1EB), + make_floatx80_init(0x3FFB, 0xF2DAF1949DBE79D5), + make_floatx80_init(0x3FFB, 0xFABD581361D47E3E), + make_floatx80_init(0x3FFC, 0x8346AC210959ECC4), + make_floatx80_init(0x3FFC, 0x8B232A08304282D8), + make_floatx80_init(0x3FFC, 0x92FB70B8D29AE2F9), + make_floatx80_init(0x3FFC, 0x9ACF476F5CCD1CB4), + make_floatx80_init(0x3FFC, 0xA29E76304954F23F), + make_floatx80_init(0x3FFC, 0xAA68C5D08AB85230), + make_floatx80_init(0x3FFC, 0xB22DFFFD9D539F83), + make_floatx80_init(0x3FFC, 0xB9EDEF453E900EA5), + make_floatx80_init(0x3FFC, 0xC1A85F1CC75E3EA5), + make_floatx80_init(0x3FFC, 0xC95D1BE828138DE6), + make_floatx80_init(0x3FFC, 0xD10BF300840D2DE4), + make_floatx80_init(0x3FFC, 0xD8B4B2BA6BC05E7A), + make_floatx80_init(0x3FFC, 0xE0572A6BB42335F6), + make_floatx80_init(0x3FFC, 0xE7F32A70EA9CAA8F), + make_floatx80_init(0x3FFC, 0xEF88843264ECEFAA), + make_floatx80_init(0x3FFC, 0xF7170A28ECC06666), + make_floatx80_init(0x3FFD, 0x812FD288332DAD32), + make_floatx80_init(0x3FFD, 0x88A8D1B1218E4D64), + make_floatx80_init(0x3FFD, 0x9012AB3F23E4AEE8), + make_floatx80_init(0x3FFD, 0x976CC3D411E7F1B9), + make_floatx80_init(0x3FFD, 0x9EB689493889A227), + make_floatx80_init(0x3FFD, 0xA5EF72C34487361B), + make_floatx80_init(0x3FFD, 0xAD1700BAF07A7227), + make_floatx80_init(0x3FFD, 0xB42CBCFAFD37EFB7), + make_floatx80_init(0x3FFD, 0xBB303A940BA80F89), + make_floatx80_init(0x3FFD, 0xC22115C6FCAEBBAF), + make_floatx80_init(0x3FFD, 0xC8FEF3E686331221), + make_floatx80_init(0x3FFD, 0xCFC98330B4000C70), + make_floatx80_init(0x3FFD, 0xD6807AA1102C5BF9), + make_floatx80_init(0x3FFD, 0xDD2399BC31252AA3), + make_floatx80_init(0x3FFD, 0xE3B2A8556B8FC517), + make_floatx80_init(0x3FFD, 0xEA2D764F64315989), + make_floatx80_init(0x3FFD, 0xF3BF5BF8BAD1A21D), + make_floatx80_init(0x3FFE, 0x801CE39E0D205C9A), + make_floatx80_init(0x3FFE, 0x8630A2DADA1ED066), + make_floatx80_init(0x3FFE, 0x8C1AD445F3E09B8C), + make_floatx80_init(0x3FFE, 0x91DB8F1664F350E2), + make_floatx80_init(0x3FFE, 0x97731420365E538C), + make_floatx80_init(0x3FFE, 0x9CE1C8E6A0B8CDBA), + make_floatx80_init(0x3FFE, 0xA22832DBCADAAE09), + make_floatx80_init(0x3FFE, 0xA746F2DDB7602294), + make_floatx80_init(0x3FFE, 0xAC3EC0FB997DD6A2), + make_floatx80_init(0x3FFE, 0xB110688AEBDC6F6A), + make_floatx80_init(0x3FFE, 0xB5BCC49059ECC4B0), + make_floatx80_init(0x3FFE, 0xBA44BC7DD470782F), + make_floatx80_init(0x3FFE, 0xBEA94144FD049AAC), + make_floatx80_init(0x3FFE, 0xC2EB4ABB661628B6), + make_floatx80_init(0x3FFE, 0xC70BD54CE602EE14), + make_floatx80_init(0x3FFE, 0xCD000549ADEC7159), + make_floatx80_init(0x3FFE, 0xD48457D2D8EA4EA3), + make_floatx80_init(0x3FFE, 0xDB948DA712DECE3B), + make_floatx80_init(0x3FFE, 0xE23855F969E8096A), + make_floatx80_init(0x3FFE, 0xE8771129C4353259), + make_floatx80_init(0x3FFE, 0xEE57C16E0D379C0D), + make_floatx80_init(0x3FFE, 0xF3E10211A87C3779), + make_floatx80_init(0x3FFE, 0xF919039D758B8D41), + make_floatx80_init(0x3FFE, 0xFE058B8F64935FB3), + make_floatx80_init(0x3FFF, 0x8155FB497B685D04), + make_floatx80_init(0x3FFF, 0x83889E3549D108E1), + make_floatx80_init(0x3FFF, 0x859CFA76511D724B), + make_floatx80_init(0x3FFF, 0x87952ECFFF8131E7), + make_floatx80_init(0x3FFF, 0x89732FD19557641B), + make_floatx80_init(0x3FFF, 0x8B38CAD101932A35), + make_floatx80_init(0x3FFF, 0x8CE7A8D8301EE6B5), + make_floatx80_init(0x3FFF, 0x8F46A39E2EAE5281), + make_floatx80_init(0x3FFF, 0x922DA7D791888487), + make_floatx80_init(0x3FFF, 0x94D19FCBDEDF5241), + make_floatx80_init(0x3FFF, 0x973AB94419D2A08B), + make_floatx80_init(0x3FFF, 0x996FF00E08E10B96), + make_floatx80_init(0x3FFF, 0x9B773F9512321DA7), + make_floatx80_init(0x3FFF, 0x9D55CC320F935624), + make_floatx80_init(0x3FFF, 0x9F100575006CC571), + make_floatx80_init(0x3FFF, 0xA0A9C290D97CC06C), + make_floatx80_init(0x3FFF, 0xA22659EBEBC0630A), + make_floatx80_init(0x3FFF, 0xA388B4AFF6EF0EC9), + make_floatx80_init(0x3FFF, 0xA4D35F1061D292C4), + make_floatx80_init(0x3FFF, 0xA60895DCFBE3187E), + make_floatx80_init(0x3FFF, 0xA72A51DC7367BEAC), + make_floatx80_init(0x3FFF, 0xA83A51530956168F), + make_floatx80_init(0x3FFF, 0xA93A20077539546E), + make_floatx80_init(0x3FFF, 0xAA9E7245023B2605), + make_floatx80_init(0x3FFF, 0xAC4C84BA6FE4D58F), + make_floatx80_init(0x3FFF, 0xADCE4A4A606B9712), + make_floatx80_init(0x3FFF, 0xAF2A2DCD8D263C9C), + make_floatx80_init(0x3FFF, 0xB0656F81F22265C7), + make_floatx80_init(0x3FFF, 0xB18465150F71496A), + make_floatx80_init(0x3FFF, 0xB28AAA156F9ADA35), + make_floatx80_init(0x3FFF, 0xB37B44FF3766B895), + make_floatx80_init(0x3FFF, 0xB458C3DCE9630433), + make_floatx80_init(0x3FFF, 0xB525529D562246BD), + make_floatx80_init(0x3FFF, 0xB5E2CCA95F9D88CC), + make_floatx80_init(0x3FFF, 0xB692CADA7ACA1ADA), + make_floatx80_init(0x3FFF, 0xB736AEA7A6925838), + make_floatx80_init(0x3FFF, 0xB7CFAB287E9F7B36), + make_floatx80_init(0x3FFF, 0xB85ECC66CB219835), + make_floatx80_init(0x3FFF, 0xB8E4FD5A20A593DA), + make_floatx80_init(0x3FFF, 0xB99F41F64AFF9BB5), + make_floatx80_init(0x3FFF, 0xBA7F1E17842BBE7B), + make_floatx80_init(0x3FFF, 0xBB4712857637E17D), + make_floatx80_init(0x3FFF, 0xBBFABE8A4788DF6F), + make_floatx80_init(0x3FFF, 0xBC9D0FAD2B689D79), + make_floatx80_init(0x3FFF, 0xBD306A39471ECD86), + make_floatx80_init(0x3FFF, 0xBDB6C731856AF18A), + make_floatx80_init(0x3FFF, 0xBE31CAC502E80D70), + make_floatx80_init(0x3FFF, 0xBEA2D55CE33194E2), + make_floatx80_init(0x3FFF, 0xBF0B10B7C03128F0), + make_floatx80_init(0x3FFF, 0xBF6B7A18DACB778D), + make_floatx80_init(0x3FFF, 0xBFC4EA4663FA18F6), + make_floatx80_init(0x3FFF, 0xC0181BDE8B89A454), + make_floatx80_init(0x3FFF, 0xC065B066CFBF6439), + make_floatx80_init(0x3FFF, 0xC0AE345F56340AE6), + make_floatx80_init(0x3FFF, 0xC0F222919CB9E6A7) +}; #endif diff --git a/target/m68k/translate.c b/target/m68k/translate.c index 6d5bde0777..cef6f663ad 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -5042,6 +5042,9 @@ DISAS_INSN(fpu) case 1: /* fint */ gen_helper_firound(cpu_env, cpu_dest, cpu_src); break; + case 2: /* fsinh */ + gen_helper_fsinh(cpu_env, cpu_dest, cpu_src); + break; case 3: /* fintrz */ gen_helper_fitrunc(cpu_env, cpu_dest, cpu_src); break; @@ -5057,6 +5060,24 @@ DISAS_INSN(fpu) case 0x06: /* flognp1 */ gen_helper_flognp1(cpu_env, cpu_dest, cpu_src); break; + case 0x09: /* ftanh */ + gen_helper_ftanh(cpu_env, cpu_dest, cpu_src); + break; + case 0x0a: /* fatan */ + gen_helper_fatan(cpu_env, cpu_dest, cpu_src); + break; + case 0x0c: /* fasin */ + gen_helper_fasin(cpu_env, cpu_dest, cpu_src); + break; + case 0x0d: /* fatanh */ + gen_helper_fatanh(cpu_env, cpu_dest, cpu_src); + break; + case 0x0e: /* fsin */ + gen_helper_fsin(cpu_env, cpu_dest, cpu_src); + break; + case 0x0f: /* ftan */ + gen_helper_ftan(cpu_env, cpu_dest, cpu_src); + break; case 0x10: /* fetox */ gen_helper_fetox(cpu_env, cpu_dest, cpu_src); break; @@ -5084,6 +5105,9 @@ DISAS_INSN(fpu) case 0x5c: /* fdabs */ gen_helper_fdabs(cpu_env, cpu_dest, cpu_src); break; + case 0x19: /* fcosh */ + gen_helper_fcosh(cpu_env, cpu_dest, cpu_src); + break; case 0x1a: /* fneg */ gen_helper_fneg(cpu_env, cpu_dest, cpu_src); break; @@ -5093,6 +5117,12 @@ DISAS_INSN(fpu) case 0x5e: /* fdneg */ gen_helper_fdneg(cpu_env, cpu_dest, cpu_src); break; + case 0x1c: /* facos */ + gen_helper_facos(cpu_env, cpu_dest, cpu_src); + break; + case 0x1d: /* fcos */ + gen_helper_fcos(cpu_env, cpu_dest, cpu_src); + break; case 0x1e: /* fgetexp */ gen_helper_fgetexp(cpu_env, cpu_dest, cpu_src); break; @@ -5150,6 +5180,14 @@ DISAS_INSN(fpu) case 0x6c: /* fdsub */ gen_helper_fdsub(cpu_env, cpu_dest, cpu_src, cpu_dest); break; + case 0x30: case 0x31: case 0x32: + case 0x33: case 0x34: case 0x35: + case 0x36: case 0x37: { + TCGv_ptr cpu_dest2 = gen_fp_ptr(REG(ext, 0)); + gen_helper_fsincos(cpu_env, cpu_dest, cpu_dest2, cpu_src); + tcg_temp_free_ptr(cpu_dest2); + } + break; case 0x38: /* fcmp */ gen_helper_fcmp(cpu_env, cpu_src, cpu_dest); return; |