#include "cpu.h"
#include "exec-all.h"
#include "gdbstub.h"
-#include "helpers.h"
+#include "helper.h"
#include "qemu-common.h"
#include "host-utils.h"
#if !defined(CONFIG_USER_ONLY)
env->cp15.c0_cpuid = id;
switch (id) {
case ARM_CPUID_ARM926:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_VFP);
env->vfp.xregs[ARM_VFP_FPSID] = 0x41011090;
env->cp15.c0_cachetype = 0x1dd20d2;
env->cp15.c1_sys = 0x00090078;
break;
case ARM_CPUID_ARM946:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_MPU);
env->cp15.c0_cachetype = 0x0f004006;
env->cp15.c1_sys = 0x00000078;
break;
case ARM_CPUID_ARM1026:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_VFP);
set_feature(env, ARM_FEATURE_AUXCR);
env->vfp.xregs[ARM_VFP_FPSID] = 0x410110a0;
break;
case ARM_CPUID_ARM1136_R2:
case ARM_CPUID_ARM1136:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_VFP);
set_feature(env, ARM_FEATURE_AUXCR);
env->cp15.c1_sys = 0x00050078;
break;
case ARM_CPUID_ARM11MPCORE:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_V6K);
set_feature(env, ARM_FEATURE_VFP);
env->cp15.c0_cachetype = 0x1dd20d2;
break;
case ARM_CPUID_CORTEXA8:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_V6K);
set_feature(env, ARM_FEATURE_V7);
env->cp15.c1_sys = 0x00c50078;
break;
case ARM_CPUID_CORTEXA9:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_V6K);
set_feature(env, ARM_FEATURE_V7);
env->cp15.c1_sys = 0x00c50078;
break;
case ARM_CPUID_CORTEXM3:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_THUMB2);
set_feature(env, ARM_FEATURE_V7);
set_feature(env, ARM_FEATURE_DIV);
break;
case ARM_CPUID_ANY: /* For userspace emulation. */
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_V6);
set_feature(env, ARM_FEATURE_V6K);
set_feature(env, ARM_FEATURE_V7);
break;
case ARM_CPUID_TI915T:
case ARM_CPUID_TI925T:
+ set_feature(env, ARM_FEATURE_V4T);
set_feature(env, ARM_FEATURE_OMAPCP);
env->cp15.c0_cpuid = ARM_CPUID_TI925T; /* Depends on wiring. */
env->cp15.c0_cachetype = 0x5109149;
case ARM_CPUID_PXA260:
case ARM_CPUID_PXA261:
case ARM_CPUID_PXA262:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_XSCALE);
/* JTAG_ID is ((id << 28) | 0x09265013) */
env->cp15.c0_cachetype = 0xd172172;
case ARM_CPUID_PXA270_B1:
case ARM_CPUID_PXA270_C0:
case ARM_CPUID_PXA270_C5:
+ set_feature(env, ARM_FEATURE_V4T);
+ set_feature(env, ARM_FEATURE_V5);
set_feature(env, ARM_FEATURE_XSCALE);
/* JTAG_ID is ((id << 28) | 0x09265013) */
set_feature(env, ARM_FEATURE_IWMMXT);
env->cp15.c0_cachetype = 0xd172172;
env->cp15.c1_sys = 0x00000078;
break;
+ case ARM_CPUID_SA1100:
+ case ARM_CPUID_SA1110:
+ set_feature(env, ARM_FEATURE_STRONGARM);
+ env->cp15.c1_sys = 0x00000070;
+ break;
default:
cpu_abort(env, "Bad CPU ID: %x\n", id);
break;
set_flush_to_zero(1, &env->vfp.standard_fp_status);
set_flush_inputs_to_zero(1, &env->vfp.standard_fp_status);
set_default_nan_mode(1, &env->vfp.standard_fp_status);
+ set_float_detect_tininess(float_tininess_before_rounding,
+ &env->vfp.fp_status);
+ set_float_detect_tininess(float_tininess_before_rounding,
+ &env->vfp.standard_fp_status);
tlb_flush(env, 1);
}
{ ARM_CPUID_CORTEXA9, "cortex-a9"},
{ ARM_CPUID_TI925T, "ti925t" },
{ ARM_CPUID_PXA250, "pxa250" },
+ { ARM_CPUID_SA1100, "sa1100" },
+ { ARM_CPUID_SA1110, "sa1110" },
{ ARM_CPUID_PXA255, "pxa255" },
{ ARM_CPUID_PXA260, "pxa260" },
{ ARM_CPUID_PXA261, "pxa261" },
/* Switch to the new mode, and to the correct instruction set. */
env->uncached_cpsr = (env->uncached_cpsr & ~CPSR_M) | new_mode;
env->uncached_cpsr |= mask;
- env->thumb = (env->cp15.c1_sys & (1 << 30)) != 0;
+ /* this is a lie, as the was no c1_sys on V4T/V5, but who cares
+ * and we should just guard the thumb mode on V4 */
+ if (arm_feature(env, ARM_FEATURE_V4T)) {
+ env->thumb = (env->cp15.c1_sys & (1 << 30)) != 0;
+ }
env->regs[14] = env->regs[15] + offset;
env->regs[15] = addr;
env->interrupt_request |= CPU_INTERRUPT_EXITTB;
/* This may enable/disable the MMU, so do a TLB flush. */
tlb_flush(env, 1);
break;
- case 1: /* Auxiliary cotrol register. */
+ case 1: /* Auxiliary control register. */
if (arm_feature(env, ARM_FEATURE_XSCALE)) {
env->cp15.c1_xscaleauxcr = val;
break;
case 7: /* Cache control. */
env->cp15.c15_i_max = 0x000;
env->cp15.c15_i_min = 0xff0;
- /* No cache, so nothing to do. */
- /* ??? MPCore has VA to PA translation functions. */
+ if (op1 != 0) {
+ goto bad_reg;
+ }
+ /* No cache, so nothing to do except VA->PA translations. */
+ if (arm_feature(env, ARM_FEATURE_V6K)) {
+ switch (crm) {
+ case 4:
+ if (arm_feature(env, ARM_FEATURE_V7)) {
+ env->cp15.c7_par = val & 0xfffff6ff;
+ } else {
+ env->cp15.c7_par = val & 0xfffff1ff;
+ }
+ break;
+ case 8: {
+ uint32_t phys_addr;
+ target_ulong page_size;
+ int prot;
+ int ret, is_user = op2 & 2;
+ int access_type = op2 & 1;
+
+ if (op2 & 4) {
+ /* Other states are only available with TrustZone */
+ goto bad_reg;
+ }
+ ret = get_phys_addr(env, val, access_type, is_user,
+ &phys_addr, &prot, &page_size);
+ if (ret == 0) {
+ /* We do not set any attribute bits in the PAR */
+ if (page_size == (1 << 24)
+ && arm_feature(env, ARM_FEATURE_V7)) {
+ env->cp15.c7_par = (phys_addr & 0xff000000) | 1 << 1;
+ } else {
+ env->cp15.c7_par = phys_addr & 0xfffff000;
+ }
+ } else {
+ env->cp15.c7_par = ((ret & (10 << 1)) >> 5) |
+ ((ret & (12 << 1)) >> 6) |
+ ((ret & 0xf) << 1) | 1;
+ }
+ break;
+ }
+ }
+ }
break;
case 8: /* MMU TLB control. */
switch (op2) {
case 9:
if (arm_feature(env, ARM_FEATURE_OMAPCP))
break;
+ if (arm_feature(env, ARM_FEATURE_STRONGARM))
+ break; /* Ignore ReadBuffer access */
switch (crm) {
case 0: /* Cache lockdown. */
switch (op1) {
}
}
case 7: /* Cache control. */
+ if (crm == 4 && op1 == 0 && op2 == 0) {
+ return env->cp15.c7_par;
+ }
/* FIXME: Should only clear Z flag if destination is r15. */
env->ZF = 0;
return 0;
/* Signed modulo arithmetic. */
#define SARITH16(a, b, n, op) do { \
int32_t sum; \
- sum = (int16_t)((uint16_t)(a) op (uint16_t)(b)); \
+ sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \
RESULT(sum, n, 16); \
if (sum >= 0) \
ge |= 3 << (n * 2); \
#define SARITH8(a, b, n, op) do { \
int32_t sum; \
- sum = (int8_t)((uint8_t)(a) op (uint8_t)(b)); \
+ sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \
RESULT(sum, n, 8); \
if (sum >= 0) \
ge |= 1 << n; \
target_bits |= 2;
if (host_bits & float_flag_overflow)
target_bits |= 4;
- if (host_bits & float_flag_underflow)
+ if (host_bits & (float_flag_underflow | float_flag_output_denormal))
target_bits |= 8;
if (host_bits & float_flag_inexact)
target_bits |= 0x10;
DO_VFP_cmp(d, float64)
#undef DO_VFP_cmp
-/* Helper routines to perform bitwise copies between float and int. */
-static inline float32 vfp_itos(uint32_t i)
-{
- union {
- uint32_t i;
- float32 s;
- } v;
-
- v.i = i;
- return v.s;
-}
-
-static inline uint32_t vfp_stoi(float32 s)
-{
- union {
- uint32_t i;
- float32 s;
- } v;
-
- v.s = s;
- return v.i;
-}
-
-static inline float64 vfp_itod(uint64_t i)
-{
- union {
- uint64_t i;
- float64 d;
- } v;
-
- v.i = i;
- return v.d;
-}
-
-static inline uint64_t vfp_dtoi(float64 d)
-{
- union {
- uint64_t i;
- float64 d;
- } v;
-
- v.d = d;
- return v.i;
-}
-
-/* Integer to float conversion. */
-float32 VFP_HELPER(uito, s)(float32 x, CPUState *env)
-{
- return uint32_to_float32(vfp_stoi(x), &env->vfp.fp_status);
-}
-
-float64 VFP_HELPER(uito, d)(float32 x, CPUState *env)
-{
- return uint32_to_float64(vfp_stoi(x), &env->vfp.fp_status);
-}
-
-float32 VFP_HELPER(sito, s)(float32 x, CPUState *env)
-{
- return int32_to_float32(vfp_stoi(x), &env->vfp.fp_status);
-}
-
-float64 VFP_HELPER(sito, d)(float32 x, CPUState *env)
-{
- return int32_to_float64(vfp_stoi(x), &env->vfp.fp_status);
-}
-
-/* Float to integer conversion. */
-float32 VFP_HELPER(toui, s)(float32 x, CPUState *env)
-{
- if (float32_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float32_to_uint32(x, &env->vfp.fp_status));
-}
+/* Integer to float and float to integer conversions */
-float32 VFP_HELPER(toui, d)(float64 x, CPUState *env)
-{
- if (float64_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float64_to_uint32(x, &env->vfp.fp_status));
-}
-
-float32 VFP_HELPER(tosi, s)(float32 x, CPUState *env)
-{
- if (float32_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float32_to_int32(x, &env->vfp.fp_status));
+#define CONV_ITOF(name, fsz, sign) \
+ float##fsz HELPER(name)(uint32_t x, void *fpstp) \
+{ \
+ float_status *fpst = fpstp; \
+ return sign##int32_to_##float##fsz(x, fpst); \
}
-float32 VFP_HELPER(tosi, d)(float64 x, CPUState *env)
-{
- if (float64_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float64_to_int32(x, &env->vfp.fp_status));
+#define CONV_FTOI(name, fsz, sign, round) \
+uint32_t HELPER(name)(float##fsz x, void *fpstp) \
+{ \
+ float_status *fpst = fpstp; \
+ if (float##fsz##_is_any_nan(x)) { \
+ float_raise(float_flag_invalid, fpst); \
+ return 0; \
+ } \
+ return float##fsz##_to_##sign##int32##round(x, fpst); \
}
-float32 VFP_HELPER(touiz, s)(float32 x, CPUState *env)
-{
- if (float32_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float32_to_uint32_round_to_zero(x, &env->vfp.fp_status));
-}
+#define FLOAT_CONVS(name, p, fsz, sign) \
+CONV_ITOF(vfp_##name##to##p, fsz, sign) \
+CONV_FTOI(vfp_to##name##p, fsz, sign, ) \
+CONV_FTOI(vfp_to##name##z##p, fsz, sign, _round_to_zero)
-float32 VFP_HELPER(touiz, d)(float64 x, CPUState *env)
-{
- if (float64_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float64_to_uint32_round_to_zero(x, &env->vfp.fp_status));
-}
+FLOAT_CONVS(si, s, 32, )
+FLOAT_CONVS(si, d, 64, )
+FLOAT_CONVS(ui, s, 32, u)
+FLOAT_CONVS(ui, d, 64, u)
-float32 VFP_HELPER(tosiz, s)(float32 x, CPUState *env)
-{
- if (float32_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float32_to_int32_round_to_zero(x, &env->vfp.fp_status));
-}
-
-float32 VFP_HELPER(tosiz, d)(float64 x, CPUState *env)
-{
- if (float64_is_any_nan(x)) {
- return float32_zero;
- }
- return vfp_itos(float64_to_int32_round_to_zero(x, &env->vfp.fp_status));
-}
+#undef CONV_ITOF
+#undef CONV_FTOI
+#undef FLOAT_CONVS
/* floating point conversion */
float64 VFP_HELPER(fcvtd, s)(float32 x, CPUState *env)
}
/* VFP3 fixed point conversion. */
-#define VFP_CONV_FIX(name, p, ftype, itype, sign) \
-ftype VFP_HELPER(name##to, p)(ftype x, uint32_t shift, CPUState *env) \
+#define VFP_CONV_FIX(name, p, fsz, itype, sign) \
+float##fsz HELPER(vfp_##name##to##p)(uint##fsz##_t x, uint32_t shift, \
+ void *fpstp) \
{ \
- ftype tmp; \
- tmp = sign##int32_to_##ftype ((itype##_t)vfp_##p##toi(x), \
- &env->vfp.fp_status); \
- return ftype##_scalbn(tmp, -(int)shift, &env->vfp.fp_status); \
+ float_status *fpst = fpstp; \
+ float##fsz tmp; \
+ tmp = sign##int32_to_##float##fsz((itype##_t)x, fpst); \
+ return float##fsz##_scalbn(tmp, -(int)shift, fpst); \
} \
-ftype VFP_HELPER(to##name, p)(ftype x, uint32_t shift, CPUState *env) \
+uint##fsz##_t HELPER(vfp_to##name##p)(float##fsz x, uint32_t shift, \
+ void *fpstp) \
{ \
- ftype tmp; \
- if (ftype##_is_any_nan(x)) { \
- return ftype##_zero; \
+ float_status *fpst = fpstp; \
+ float##fsz tmp; \
+ if (float##fsz##_is_any_nan(x)) { \
+ float_raise(float_flag_invalid, fpst); \
+ return 0; \
} \
- tmp = ftype##_scalbn(x, shift, &env->vfp.fp_status); \
- return vfp_ito##p(ftype##_to_##itype##_round_to_zero(tmp, \
- &env->vfp.fp_status)); \
-}
-
-VFP_CONV_FIX(sh, d, float64, int16, )
-VFP_CONV_FIX(sl, d, float64, int32, )
-VFP_CONV_FIX(uh, d, float64, uint16, u)
-VFP_CONV_FIX(ul, d, float64, uint32, u)
-VFP_CONV_FIX(sh, s, float32, int16, )
-VFP_CONV_FIX(sl, s, float32, int32, )
-VFP_CONV_FIX(uh, s, float32, uint16, u)
-VFP_CONV_FIX(ul, s, float32, uint32, u)
+ tmp = float##fsz##_scalbn(x, shift, fpst); \
+ return float##fsz##_to_##itype##_round_to_zero(tmp, fpst); \
+}
+
+VFP_CONV_FIX(sh, d, 64, int16, )
+VFP_CONV_FIX(sl, d, 64, int32, )
+VFP_CONV_FIX(uh, d, 64, uint16, u)
+VFP_CONV_FIX(ul, d, 64, uint32, u)
+VFP_CONV_FIX(sh, s, 32, int16, )
+VFP_CONV_FIX(sl, s, 32, int32, )
+VFP_CONV_FIX(uh, s, 32, uint16, u)
+VFP_CONV_FIX(ul, s, 32, uint32, u)
#undef VFP_CONV_FIX
/* Half precision conversions. */
-float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, CPUState *env)
+static float32 do_fcvt_f16_to_f32(uint32_t a, CPUState *env, float_status *s)
{
- float_status *s = &env->vfp.fp_status;
int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0;
float32 r = float16_to_float32(make_float16(a), ieee, s);
if (ieee) {
return r;
}
-uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, CPUState *env)
+static uint32_t do_fcvt_f32_to_f16(float32 a, CPUState *env, float_status *s)
{
- float_status *s = &env->vfp.fp_status;
int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0;
float16 r = float32_to_float16(a, ieee, s);
if (ieee) {
return float16_val(r);
}
+float32 HELPER(neon_fcvt_f16_to_f32)(uint32_t a, CPUState *env)
+{
+ return do_fcvt_f16_to_f32(a, env, &env->vfp.standard_fp_status);
+}
+
+uint32_t HELPER(neon_fcvt_f32_to_f16)(float32 a, CPUState *env)
+{
+ return do_fcvt_f32_to_f16(a, env, &env->vfp.standard_fp_status);
+}
+
+float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, CPUState *env)
+{
+ return do_fcvt_f16_to_f32(a, env, &env->vfp.fp_status);
+}
+
+uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, CPUState *env)
+{
+ return do_fcvt_f32_to_f16(a, env, &env->vfp.fp_status);
+}
+
+#define float32_two make_float32(0x40000000)
+#define float32_three make_float32(0x40400000)
+#define float32_one_point_five make_float32(0x3fc00000)
+
float32 HELPER(recps_f32)(float32 a, float32 b, CPUState *env)
{
- float_status *s = &env->vfp.fp_status;
- float32 two = int32_to_float32(2, s);
- return float32_sub(two, float32_mul(a, b, s), s);
+ float_status *s = &env->vfp.standard_fp_status;
+ if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) ||
+ (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) {
+ if (!(float32_is_zero(a) || float32_is_zero(b))) {
+ float_raise(float_flag_input_denormal, s);
+ }
+ return float32_two;
+ }
+ return float32_sub(float32_two, float32_mul(a, b, s), s);
}
float32 HELPER(rsqrts_f32)(float32 a, float32 b, CPUState *env)
{
float_status *s = &env->vfp.standard_fp_status;
- float32 two = int32_to_float32(2, s);
- float32 three = int32_to_float32(3, s);
float32 product;
if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) ||
(float32_is_infinity(b) && float32_is_zero_or_denormal(a))) {
- product = float32_zero;
- } else {
- product = float32_mul(a, b, s);
+ if (!(float32_is_zero(a) || float32_is_zero(b))) {
+ float_raise(float_flag_input_denormal, s);
+ }
+ return float32_one_point_five;
}
- return float32_div(float32_sub(three, product, s), two, s);
+ product = float32_mul(a, b, s);
+ return float32_div(float32_sub(float32_three, product, s), float32_two, s);
}
/* NEON helpers. */
-/* TODO: The architecture specifies the value that the estimate functions
- should return. We return the exact reciprocal/root instead. */
+/* Constants 256 and 512 are used in some helpers; we avoid relying on
+ * int->float conversions at run-time. */
+#define float64_256 make_float64(0x4070000000000000LL)
+#define float64_512 make_float64(0x4080000000000000LL)
+
+/* The algorithm that must be used to calculate the estimate
+ * is specified by the ARM ARM.
+ */
+static float64 recip_estimate(float64 a, CPUState *env)
+{
+ /* These calculations mustn't set any fp exception flags,
+ * so we use a local copy of the fp_status.
+ */
+ float_status dummy_status = env->vfp.standard_fp_status;
+ float_status *s = &dummy_status;
+ /* q = (int)(a * 512.0) */
+ float64 q = float64_mul(float64_512, a, s);
+ int64_t q_int = float64_to_int64_round_to_zero(q, s);
+
+ /* r = 1.0 / (((double)q + 0.5) / 512.0) */
+ q = int64_to_float64(q_int, s);
+ q = float64_add(q, float64_half, s);
+ q = float64_div(q, float64_512, s);
+ q = float64_div(float64_one, q, s);
+
+ /* s = (int)(256.0 * r + 0.5) */
+ q = float64_mul(q, float64_256, s);
+ q = float64_add(q, float64_half, s);
+ q_int = float64_to_int64_round_to_zero(q, s);
+
+ /* return (double)s / 256.0 */
+ return float64_div(int64_to_float64(q_int, s), float64_256, s);
+}
+
float32 HELPER(recpe_f32)(float32 a, CPUState *env)
{
- float_status *s = &env->vfp.fp_status;
- float32 one = int32_to_float32(1, s);
- return float32_div(one, a, s);
+ float_status *s = &env->vfp.standard_fp_status;
+ float64 f64;
+ uint32_t val32 = float32_val(a);
+
+ int result_exp;
+ int a_exp = (val32 & 0x7f800000) >> 23;
+ int sign = val32 & 0x80000000;
+
+ if (float32_is_any_nan(a)) {
+ if (float32_is_signaling_nan(a)) {
+ float_raise(float_flag_invalid, s);
+ }
+ return float32_default_nan;
+ } else if (float32_is_infinity(a)) {
+ return float32_set_sign(float32_zero, float32_is_neg(a));
+ } else if (float32_is_zero_or_denormal(a)) {
+ if (!float32_is_zero(a)) {
+ float_raise(float_flag_input_denormal, s);
+ }
+ float_raise(float_flag_divbyzero, s);
+ return float32_set_sign(float32_infinity, float32_is_neg(a));
+ } else if (a_exp >= 253) {
+ float_raise(float_flag_underflow, s);
+ return float32_set_sign(float32_zero, float32_is_neg(a));
+ }
+
+ f64 = make_float64((0x3feULL << 52)
+ | ((int64_t)(val32 & 0x7fffff) << 29));
+
+ result_exp = 253 - a_exp;
+
+ f64 = recip_estimate(f64, env);
+
+ val32 = sign
+ | ((result_exp & 0xff) << 23)
+ | ((float64_val(f64) >> 29) & 0x7fffff);
+ return make_float32(val32);
+}
+
+/* The algorithm that must be used to calculate the estimate
+ * is specified by the ARM ARM.
+ */
+static float64 recip_sqrt_estimate(float64 a, CPUState *env)
+{
+ /* These calculations mustn't set any fp exception flags,
+ * so we use a local copy of the fp_status.
+ */
+ float_status dummy_status = env->vfp.standard_fp_status;
+ float_status *s = &dummy_status;
+ float64 q;
+ int64_t q_int;
+
+ if (float64_lt(a, float64_half, s)) {
+ /* range 0.25 <= a < 0.5 */
+
+ /* a in units of 1/512 rounded down */
+ /* q0 = (int)(a * 512.0); */
+ q = float64_mul(float64_512, a, s);
+ q_int = float64_to_int64_round_to_zero(q, s);
+
+ /* reciprocal root r */
+ /* r = 1.0 / sqrt(((double)q0 + 0.5) / 512.0); */
+ q = int64_to_float64(q_int, s);
+ q = float64_add(q, float64_half, s);
+ q = float64_div(q, float64_512, s);
+ q = float64_sqrt(q, s);
+ q = float64_div(float64_one, q, s);
+ } else {
+ /* range 0.5 <= a < 1.0 */
+
+ /* a in units of 1/256 rounded down */
+ /* q1 = (int)(a * 256.0); */
+ q = float64_mul(float64_256, a, s);
+ int64_t q_int = float64_to_int64_round_to_zero(q, s);
+
+ /* reciprocal root r */
+ /* r = 1.0 /sqrt(((double)q1 + 0.5) / 256); */
+ q = int64_to_float64(q_int, s);
+ q = float64_add(q, float64_half, s);
+ q = float64_div(q, float64_256, s);
+ q = float64_sqrt(q, s);
+ q = float64_div(float64_one, q, s);
+ }
+ /* r in units of 1/256 rounded to nearest */
+ /* s = (int)(256.0 * r + 0.5); */
+
+ q = float64_mul(q, float64_256,s );
+ q = float64_add(q, float64_half, s);
+ q_int = float64_to_int64_round_to_zero(q, s);
+
+ /* return (double)s / 256.0;*/
+ return float64_div(int64_to_float64(q_int, s), float64_256, s);
}
float32 HELPER(rsqrte_f32)(float32 a, CPUState *env)
{
- float_status *s = &env->vfp.fp_status;
- float32 one = int32_to_float32(1, s);
- return float32_div(one, float32_sqrt(a, s), s);
+ float_status *s = &env->vfp.standard_fp_status;
+ int result_exp;
+ float64 f64;
+ uint32_t val;
+ uint64_t val64;
+
+ val = float32_val(a);
+
+ if (float32_is_any_nan(a)) {
+ if (float32_is_signaling_nan(a)) {
+ float_raise(float_flag_invalid, s);
+ }
+ return float32_default_nan;
+ } else if (float32_is_zero_or_denormal(a)) {
+ if (!float32_is_zero(a)) {
+ float_raise(float_flag_input_denormal, s);
+ }
+ float_raise(float_flag_divbyzero, s);
+ return float32_set_sign(float32_infinity, float32_is_neg(a));
+ } else if (float32_is_neg(a)) {
+ float_raise(float_flag_invalid, s);
+ return float32_default_nan;
+ } else if (float32_is_infinity(a)) {
+ return float32_zero;
+ }
+
+ /* Normalize to a double-precision value between 0.25 and 1.0,
+ * preserving the parity of the exponent. */
+ if ((val & 0x800000) == 0) {
+ f64 = make_float64(((uint64_t)(val & 0x80000000) << 32)
+ | (0x3feULL << 52)
+ | ((uint64_t)(val & 0x7fffff) << 29));
+ } else {
+ f64 = make_float64(((uint64_t)(val & 0x80000000) << 32)
+ | (0x3fdULL << 52)
+ | ((uint64_t)(val & 0x7fffff) << 29));
+ }
+
+ result_exp = (380 - ((val & 0x7f800000) >> 23)) / 2;
+
+ f64 = recip_sqrt_estimate(f64, env);
+
+ val64 = float64_val(f64);
+
+ val = ((val64 >> 63) & 0x80000000)
+ | ((result_exp & 0xff) << 23)
+ | ((val64 >> 29) & 0x7fffff);
+ return make_float32(val);
}
uint32_t HELPER(recpe_u32)(uint32_t a, CPUState *env)
{
- float_status *s = &env->vfp.fp_status;
- float32 tmp;
- tmp = int32_to_float32(a, s);
- tmp = float32_scalbn(tmp, -32, s);
- tmp = helper_recpe_f32(tmp, env);
- tmp = float32_scalbn(tmp, 31, s);
- return float32_to_int32(tmp, s);
+ float64 f64;
+
+ if ((a & 0x80000000) == 0) {
+ return 0xffffffff;
+ }
+
+ f64 = make_float64((0x3feULL << 52)
+ | ((int64_t)(a & 0x7fffffff) << 21));
+
+ f64 = recip_estimate (f64, env);
+
+ return 0x80000000 | ((float64_val(f64) >> 21) & 0x7fffffff);
}
uint32_t HELPER(rsqrte_u32)(uint32_t a, CPUState *env)
{
- float_status *s = &env->vfp.fp_status;
- float32 tmp;
- tmp = int32_to_float32(a, s);
- tmp = float32_scalbn(tmp, -32, s);
- tmp = helper_rsqrte_f32(tmp, env);
- tmp = float32_scalbn(tmp, 31, s);
- return float32_to_int32(tmp, s);
+ float64 f64;
+
+ if ((a & 0xc0000000) == 0) {
+ return 0xffffffff;
+ }
+
+ if (a & 0x80000000) {
+ f64 = make_float64((0x3feULL << 52)
+ | ((uint64_t)(a & 0x7fffffff) << 21));
+ } else { /* bits 31-30 == '01' */
+ f64 = make_float64((0x3fdULL << 52)
+ | ((uint64_t)(a & 0x3fffffff) << 22));
+ }
+
+ f64 = recip_sqrt_estimate(f64, env);
+
+ return 0x80000000 | ((float64_val(f64) >> 21) & 0x7fffffff);
}
void HELPER(set_teecr)(CPUState *env, uint32_t val)
projects / mirror_qemu.git / blobdiff