diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2018-03-05 13:29:31 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2018-03-05 13:29:31 +0000 |
commit | 4a22592e32868db846898831c27fbee8e73e24e3 (patch) | |
tree | c535db857a8bdc290b1e5ef9e9806a9e2e28665e | |
parent | 7fceeb190ac6fbbbec0bf904f743190708301e31 (diff) | |
parent | 0d379c1709aa6b2d09dd3b493bfdf3a5fe6debcd (diff) |
Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-2.12-pull-request' into staging
# gpg: Signature made Sun 04 Mar 2018 17:32:25 GMT
# gpg: using RSA key F30C38BD3F2FBE3C
# gpg: Good signature from "Laurent Vivier <lvivier@redhat.com>"
# gpg: aka "Laurent Vivier <laurent@vivier.eu>"
# gpg: aka "Laurent Vivier (Red Hat) <lvivier@redhat.com>"
# Primary key fingerprint: CD2F 75DD C8E3 A4DC 2E4F 5173 F30C 38BD 3F2F BE3C
* remotes/vivier/tags/m68k-for-2.12-pull-request:
target/m68k: add fscale, fgetman and fgetexp
softfloat: use floatx80_infinity in softfloat
target/m68k: add fmod/frem
softfloat: export some functions
target/m68k: TCGv returned by gen_load() must be freed
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
-rw-r--r-- | fpu/softfloat-specialize.h | 17 | ||||
-rw-r--r-- | fpu/softfloat.c | 130 | ||||
-rw-r--r-- | include/fpu/softfloat-macros.h (renamed from fpu/softfloat-macros.h) | 10 | ||||
-rw-r--r-- | include/fpu/softfloat.h | 134 | ||||
-rw-r--r-- | target/m68k/Makefile.objs | 3 | ||||
-rw-r--r-- | target/m68k/cpu.h | 1 | ||||
-rw-r--r-- | target/m68k/fpu_helper.c | 50 | ||||
-rw-r--r-- | target/m68k/helper.h | 5 | ||||
-rw-r--r-- | target/m68k/softfloat.c | 249 | ||||
-rw-r--r-- | target/m68k/softfloat.h | 29 | ||||
-rw-r--r-- | target/m68k/translate.c | 26 |
11 files changed, 548 insertions, 106 deletions
diff --git a/fpu/softfloat-specialize.h b/fpu/softfloat-specialize.h index e81ca001e1..9ccb59422c 100644 --- a/fpu/softfloat-specialize.h +++ b/fpu/softfloat-specialize.h @@ -178,6 +178,20 @@ floatx80 floatx80_default_nan(float_status *status) } /*---------------------------------------------------------------------------- +| The pattern for a default generated extended double-precision inf. +*----------------------------------------------------------------------------*/ + +#define floatx80_infinity_high 0x7FFF +#if defined(TARGET_M68K) +#define floatx80_infinity_low LIT64(0x0000000000000000) +#else +#define floatx80_infinity_low LIT64(0x8000000000000000) +#endif + +const floatx80 floatx80_infinity + = make_floatx80_init(floatx80_infinity_high, floatx80_infinity_low); + +/*---------------------------------------------------------------------------- | The pattern for a default generated quadruple-precision NaN. *----------------------------------------------------------------------------*/ float128 float128_default_nan(float_status *status) @@ -1011,8 +1025,7 @@ static floatx80 commonNaNToFloatx80(commonNaNT a, float_status *status) | `b' is a signaling NaN, the invalid exception is raised. *----------------------------------------------------------------------------*/ -static floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, - float_status *status) +floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) { flag aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN; flag aIsLargerSignificand; diff --git a/fpu/softfloat.c b/fpu/softfloat.c index e7fb0d357a..e124df9f7e 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -93,7 +93,7 @@ this code that are retained. | division and square root approximations. (Can be specialized to target if | desired.) *----------------------------------------------------------------------------*/ -#include "softfloat-macros.h" +#include "fpu/softfloat-macros.h" /*---------------------------------------------------------------------------- | Functions and definitions to determine: (1) whether tininess for underflow @@ -2193,25 +2193,6 @@ static void } /*---------------------------------------------------------------------------- -| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a -| single-precision floating-point value, returning the result. After being -| shifted into the proper positions, the three fields are simply added -| together to form the result. This means that any integer portion of `zSig' -| will be added into the exponent. Since a properly normalized significand -| will have an integer portion equal to 1, the `zExp' input should be 1 less -| than the desired result exponent whenever `zSig' is a complete, normalized -| significand. -*----------------------------------------------------------------------------*/ - -static inline float32 packFloat32(flag zSign, int zExp, uint32_t zSig) -{ - - return make_float32( - ( ( (uint32_t) zSign )<<31 ) + ( ( (uint32_t) zExp )<<23 ) + zSig); - -} - -/*---------------------------------------------------------------------------- | Takes an abstract floating-point value having sign `zSign', exponent `zExp', | and significand `zSig', and returns the proper single-precision floating- | point value corresponding to the abstract input. Ordinarily, the abstract @@ -2491,72 +2472,20 @@ static float64 } /*---------------------------------------------------------------------------- -| Returns the fraction bits of the extended double-precision floating-point -| value `a'. -*----------------------------------------------------------------------------*/ - -static inline uint64_t extractFloatx80Frac( floatx80 a ) -{ - - return a.low; - -} - -/*---------------------------------------------------------------------------- -| Returns the exponent bits of the extended double-precision floating-point -| value `a'. -*----------------------------------------------------------------------------*/ - -static inline int32_t extractFloatx80Exp( floatx80 a ) -{ - - return a.high & 0x7FFF; - -} - -/*---------------------------------------------------------------------------- -| Returns the sign bit of the extended double-precision floating-point value -| `a'. -*----------------------------------------------------------------------------*/ - -static inline flag extractFloatx80Sign( floatx80 a ) -{ - - return a.high>>15; - -} - -/*---------------------------------------------------------------------------- | Normalizes the subnormal extended double-precision floating-point value | represented by the denormalized significand `aSig'. The normalized exponent | and significand are stored at the locations pointed to by `zExpPtr' and | `zSigPtr', respectively. *----------------------------------------------------------------------------*/ -static void - normalizeFloatx80Subnormal( uint64_t aSig, int32_t *zExpPtr, uint64_t *zSigPtr ) +void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, + uint64_t *zSigPtr) { int8_t shiftCount; shiftCount = countLeadingZeros64( aSig ); *zSigPtr = aSig<<shiftCount; *zExpPtr = 1 - shiftCount; - -} - -/*---------------------------------------------------------------------------- -| Packs the sign `zSign', exponent `zExp', and significand `zSig' into an -| extended double-precision floating-point value, returning the result. -*----------------------------------------------------------------------------*/ - -static inline floatx80 packFloatx80( flag zSign, int32_t zExp, uint64_t zSig ) -{ - floatx80 z; - - z.low = zSig; - z.high = ( ( (uint16_t) zSign )<<15 ) + zExp; - return z; - } /*---------------------------------------------------------------------------- @@ -2583,9 +2512,9 @@ static inline floatx80 packFloatx80( flag zSign, int32_t zExp, uint64_t zSig ) | Floating-Point Arithmetic. *----------------------------------------------------------------------------*/ -static floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign, - int32_t zExp, uint64_t zSig0, uint64_t zSig1, - float_status *status) +floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign, + int32_t zExp, uint64_t zSig0, uint64_t zSig1, + float_status *status) { int8_t roundingMode; flag roundNearestEven, increment, isTiny; @@ -2707,7 +2636,9 @@ static floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign, ) { return packFloatx80( zSign, 0x7FFE, ~ roundMask ); } - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, + floatx80_infinity_high, + floatx80_infinity_low); } if ( zExp <= 0 ) { isTiny = @@ -2779,10 +2710,10 @@ static floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign, | normalized. *----------------------------------------------------------------------------*/ -static floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, - flag zSign, int32_t zExp, - uint64_t zSig0, uint64_t zSig1, - float_status *status) +floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, + flag zSign, int32_t zExp, + uint64_t zSig0, uint64_t zSig1, + float_status *status) { int8_t shiftCount; @@ -3253,7 +3184,9 @@ floatx80 float32_to_floatx80(float32 a, float_status *status) if (aSig) { return commonNaNToFloatx80(float32ToCommonNaN(a, status), status); } - return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(aSign, + floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) { if ( aSig == 0 ) return packFloatx80( aSign, 0, 0 ); @@ -4108,7 +4041,9 @@ floatx80 float64_to_floatx80(float64 a, float_status *status) if (aSig) { return commonNaNToFloatx80(float64ToCommonNaN(a, status), status); } - return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(aSign, + floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) { if ( aSig == 0 ) return packFloatx80( aSign, 0, 0 ); @@ -4620,10 +4555,7 @@ int64_t floatx80_to_int64(floatx80 a, float_status *status) if ( shiftCount <= 0 ) { if ( shiftCount ) { float_raise(float_flag_invalid, status); - if ( ! aSign - || ( ( aExp == 0x7FFF ) - && ( aSig != LIT64( 0x8000000000000000 ) ) ) - ) { + if (!aSign || floatx80_is_any_nan(a)) { return LIT64( 0x7FFFFFFFFFFFFFFF ); } return (int64_t) LIT64( 0x8000000000000000 ); @@ -4929,7 +4861,9 @@ static floatx80 addFloatx80Sigs(floatx80 a, floatx80 b, flag zSign, if ((uint64_t)(bSig << 1)) { return propagateFloatx80NaN(a, b, status); } - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, + floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) ++expDiff; shift64ExtraRightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); @@ -5004,7 +4938,8 @@ static floatx80 subFloatx80Sigs(floatx80 a, floatx80 b, flag zSign, if ((uint64_t)(bSig << 1)) { return propagateFloatx80NaN(a, b, status); } - return packFloatx80( zSign ^ 1, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign ^ 1, floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) ++expDiff; shift128RightJamming( aSig, 0, - expDiff, &aSig, &zSig1 ); @@ -5109,7 +5044,8 @@ floatx80 floatx80_mul(floatx80 a, floatx80 b, float_status *status) return propagateFloatx80NaN(a, b, status); } if ( ( bExp | bSig ) == 0 ) goto invalid; - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, floatx80_infinity_high, + floatx80_infinity_low); } if ( bExp == 0x7FFF ) { if ((uint64_t)(bSig << 1)) { @@ -5120,7 +5056,8 @@ floatx80 floatx80_mul(floatx80 a, floatx80 b, float_status *status) float_raise(float_flag_invalid, status); return floatx80_default_nan(status); } - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) { if ( aSig == 0 ) return packFloatx80( zSign, 0, 0 ); @@ -5174,7 +5111,8 @@ floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) } goto invalid; } - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, floatx80_infinity_high, + floatx80_infinity_low); } if ( bExp == 0x7FFF ) { if ((uint64_t)(bSig << 1)) { @@ -5190,7 +5128,8 @@ floatx80 floatx80_div(floatx80 a, floatx80 b, float_status *status) return floatx80_default_nan(status); } float_raise(float_flag_divbyzero, status); - return packFloatx80( zSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(zSign, floatx80_infinity_high, + floatx80_infinity_low); } normalizeFloatx80Subnormal( bSig, &bExp, &bSig ); } @@ -6013,7 +5952,8 @@ floatx80 float128_to_floatx80(float128 a, float_status *status) if ( aSig0 | aSig1 ) { return commonNaNToFloatx80(float128ToCommonNaN(a, status), status); } - return packFloatx80( aSign, 0x7FFF, LIT64( 0x8000000000000000 ) ); + return packFloatx80(aSign, floatx80_infinity_high, + floatx80_infinity_low); } if ( aExp == 0 ) { if ( ( aSig0 | aSig1 ) == 0 ) return packFloatx80( aSign, 0, 0 ); diff --git a/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h index c45a23193e..35e1603a5e 100644 --- a/fpu/softfloat-macros.h +++ b/include/fpu/softfloat-macros.h @@ -603,7 +603,7 @@ static inline void | unsigned integer is returned. *----------------------------------------------------------------------------*/ -static uint64_t estimateDiv128To64( uint64_t a0, uint64_t a1, uint64_t b ) +static inline uint64_t estimateDiv128To64(uint64_t a0, uint64_t a1, uint64_t b) { uint64_t b0, b1; uint64_t rem0, rem1, term0, term1; @@ -630,7 +630,7 @@ static uint64_t estimateDiv128To64( uint64_t a0, uint64_t a1, uint64_t b ) * * Licensed under the GPLv2/LGPLv3 */ -static uint64_t div128To64(uint64_t n0, uint64_t n1, uint64_t d) +static inline uint64_t div128To64(uint64_t n0, uint64_t n1, uint64_t d) { uint64_t d0, d1, q0, q1, r1, r0, m; @@ -683,7 +683,7 @@ static uint64_t div128To64(uint64_t n0, uint64_t n1, uint64_t d) | value. *----------------------------------------------------------------------------*/ -static uint32_t estimateSqrt32(int aExp, uint32_t a) +static inline uint32_t estimateSqrt32(int aExp, uint32_t a) { static const uint16_t sqrtOddAdjustments[] = { 0x0004, 0x0022, 0x005D, 0x00B1, 0x011D, 0x019F, 0x0236, 0x02E0, @@ -717,7 +717,7 @@ static uint32_t estimateSqrt32(int aExp, uint32_t a) | `a'. If `a' is zero, 32 is returned. *----------------------------------------------------------------------------*/ -static int8_t countLeadingZeros32( uint32_t a ) +static inline int8_t countLeadingZeros32(uint32_t a) { #if SOFTFLOAT_GNUC_PREREQ(3, 4) if (a) { @@ -765,7 +765,7 @@ static int8_t countLeadingZeros32( uint32_t a ) | `a'. If `a' is zero, 64 is returned. *----------------------------------------------------------------------------*/ -static int8_t countLeadingZeros64( uint64_t a ) +static inline int8_t countLeadingZeros64(uint64_t a) { #if SOFTFLOAT_GNUC_PREREQ(3, 4) if (a) { diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 27876e711c..36626a501b 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -426,6 +426,23 @@ static inline float32 float32_set_sign(float32 a, int sign) #define float32_infinity make_float32(0x7f800000) /*---------------------------------------------------------------------------- +| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a +| single-precision floating-point value, returning the result. After being +| shifted into the proper positions, the three fields are simply added +| together to form the result. This means that any integer portion of `zSig' +| will be added into the exponent. Since a properly normalized significand +| will have an integer portion equal to 1, the `zExp' input should be 1 less +| than the desired result exponent whenever `zSig' is a complete, normalized +| significand. +*----------------------------------------------------------------------------*/ + +static inline float32 packFloat32(flag zSign, int zExp, uint32_t zSig) +{ + return make_float32( + (((uint32_t)zSign) << 31) + (((uint32_t)zExp) << 23) + zSig); +} + +/*---------------------------------------------------------------------------- | The pattern for a default generated single-precision NaN. *----------------------------------------------------------------------------*/ float32 float32_default_nan(float_status *status); @@ -556,6 +573,11 @@ float64 floatx80_to_float64(floatx80, float_status *status); float128 floatx80_to_float128(floatx80, float_status *status); /*---------------------------------------------------------------------------- +| The pattern for an extended double-precision inf. +*----------------------------------------------------------------------------*/ +extern const floatx80 floatx80_infinity; + +/*---------------------------------------------------------------------------- | Software IEC/IEEE extended double-precision operations. *----------------------------------------------------------------------------*/ floatx80 floatx80_round(floatx80 a, float_status *status); @@ -595,7 +617,12 @@ static inline floatx80 floatx80_chs(floatx80 a) static inline int floatx80_is_infinity(floatx80 a) { - return (a.high & 0x7fff) == 0x7fff && a.low == 0x8000000000000000LL; +#if defined(TARGET_M68K) + return (a.high & 0x7fff) == floatx80_infinity.high && !(a.low << 1); +#else + return (a.high & 0x7fff) == floatx80_infinity.high && + a.low == floatx80_infinity.low; +#endif } static inline int floatx80_is_neg(floatx80 a) @@ -638,7 +665,110 @@ static inline bool floatx80_invalid_encoding(floatx80 a) #define floatx80_ln2 make_floatx80(0x3ffe, 0xb17217f7d1cf79acLL) #define floatx80_pi make_floatx80(0x4000, 0xc90fdaa22168c235LL) #define floatx80_half make_floatx80(0x3ffe, 0x8000000000000000LL) -#define floatx80_infinity make_floatx80(0x7fff, 0x8000000000000000LL) + +/*---------------------------------------------------------------------------- +| Returns the fraction bits of the extended double-precision floating-point +| value `a'. +*----------------------------------------------------------------------------*/ + +static inline uint64_t extractFloatx80Frac(floatx80 a) +{ + return a.low; +} + +/*---------------------------------------------------------------------------- +| Returns the exponent bits of the extended double-precision floating-point +| value `a'. +*----------------------------------------------------------------------------*/ + +static inline int32_t extractFloatx80Exp(floatx80 a) +{ + return a.high & 0x7FFF; +} + +/*---------------------------------------------------------------------------- +| Returns the sign bit of the extended double-precision floating-point value +| `a'. +*----------------------------------------------------------------------------*/ + +static inline flag extractFloatx80Sign(floatx80 a) +{ + return a.high >> 15; +} + +/*---------------------------------------------------------------------------- +| Packs the sign `zSign', exponent `zExp', and significand `zSig' into an +| extended double-precision floating-point value, returning the result. +*----------------------------------------------------------------------------*/ + +static inline floatx80 packFloatx80(flag zSign, int32_t zExp, uint64_t zSig) +{ + floatx80 z; + + z.low = zSig; + z.high = (((uint16_t)zSign) << 15) + zExp; + return z; +} + +/*---------------------------------------------------------------------------- +| Normalizes the subnormal extended double-precision floating-point value +| represented by the denormalized significand `aSig'. The normalized exponent +| and significand are stored at the locations pointed to by `zExpPtr' and +| `zSigPtr', respectively. +*----------------------------------------------------------------------------*/ + +void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, + uint64_t *zSigPtr); + +/*---------------------------------------------------------------------------- +| Takes two extended double-precision floating-point values `a' and `b', one +| of which is a NaN, and returns the appropriate NaN result. If either `a' or +| `b' is a signaling NaN, the invalid exception is raised. +*----------------------------------------------------------------------------*/ + +floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status); + +/*---------------------------------------------------------------------------- +| Takes an abstract floating-point value having sign `zSign', exponent `zExp', +| and extended significand formed by the concatenation of `zSig0' and `zSig1', +| and returns the proper extended double-precision floating-point value +| corresponding to the abstract input. Ordinarily, the abstract value is +| rounded and packed into the extended double-precision format, with the +| inexact exception raised if the abstract input cannot be represented +| exactly. However, if the abstract value is too large, the overflow and +| inexact exceptions are raised and an infinity or maximal finite value is +| returned. If the abstract value is too small, the input value is rounded to +| a subnormal number, and the underflow and inexact exceptions are raised if +| the abstract input cannot be represented exactly as a subnormal extended +| double-precision floating-point number. +| If `roundingPrecision' is 32 or 64, the result is rounded to the same +| number of bits as single or double precision, respectively. Otherwise, the +| result is rounded to the full precision of the extended double-precision +| format. +| The input significand must be normalized or smaller. If the input +| significand is not normalized, `zExp' must be 0; in that case, the result +| returned is a subnormal number, and it must not require rounding. The +| handling of underflow and overflow follows the IEC/IEEE Standard for Binary +| Floating-Point Arithmetic. +*----------------------------------------------------------------------------*/ + +floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign, + int32_t zExp, uint64_t zSig0, uint64_t zSig1, + float_status *status); + +/*---------------------------------------------------------------------------- +| Takes an abstract floating-point value having sign `zSign', exponent +| `zExp', and significand formed by the concatenation of `zSig0' and `zSig1', +| and returns the proper extended double-precision floating-point value +| corresponding to the abstract input. This routine is just like +| `roundAndPackFloatx80' except that the input significand does not have to be +| normalized. +*----------------------------------------------------------------------------*/ + +floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision, + flag zSign, int32_t zExp, + uint64_t zSig0, uint64_t zSig1, + float_status *status); /*---------------------------------------------------------------------------- | The pattern for a default generated extended double-precision NaN. diff --git a/target/m68k/Makefile.objs b/target/m68k/Makefile.objs index d143f20270..ac61948676 100644 --- a/target/m68k/Makefile.objs +++ b/target/m68k/Makefile.objs @@ -1,4 +1,5 @@ obj-y += m68k-semi.o -obj-y += translate.o op_helper.o helper.o cpu.o fpu_helper.o +obj-y += translate.o op_helper.o helper.o cpu.o +obj-y += fpu_helper.o softfloat.o obj-y += gdbstub.o obj-$(CONFIG_SOFTMMU) += monitor.o diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h index 65f4fb95cb..2259bf22dc 100644 --- a/target/m68k/cpu.h +++ b/target/m68k/cpu.h @@ -427,6 +427,7 @@ typedef enum { /* Quotient */ #define FPSR_QT_MASK 0x00ff0000 +#define FPSR_QT_SHIFT 16 /* Floating-Point Control Register */ /* Rounding mode */ diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c index 3c5a82aaa0..cdb9b50462 100644 --- a/target/m68k/fpu_helper.c +++ b/target/m68k/fpu_helper.c @@ -23,7 +23,7 @@ #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" -#include "fpu/softfloat.h" +#include "softfloat.h" /* Undefined offsets may be different on various FPU. * On 68040 they return 0.0 (floatx80_zero) @@ -509,3 +509,51 @@ uint32_t HELPER(fmovemd_ld_postinc)(CPUM68KState *env, uint32_t addr, { return fmovem_postinc(env, addr, mask, cpu_ld_float64_ra); } + +static void make_quotient(CPUM68KState *env, floatx80 val) +{ + int32_t quotient; + int sign; + + if (floatx80_is_any_nan(val)) { + return; + } + + quotient = floatx80_to_int32(val, &env->fp_status); + sign = quotient < 0; + if (sign) { + quotient = -quotient; + } + + quotient = (sign << 7) | (quotient & 0x7f); + env->fpsr = (env->fpsr & ~FPSR_QT_MASK) | (quotient << FPSR_QT_SHIFT); +} + +void HELPER(fmod)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) +{ + res->d = floatx80_mod(val1->d, val0->d, &env->fp_status); + + make_quotient(env, res->d); +} + +void HELPER(frem)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) +{ + res->d = floatx80_rem(val1->d, val0->d, &env->fp_status); + + make_quotient(env, res->d); +} + +void HELPER(fgetexp)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_getexp(val->d, &env->fp_status); +} + +void HELPER(fgetman)(CPUM68KState *env, FPReg *res, FPReg *val) +{ + res->d = floatx80_getman(val->d, &env->fp_status); +} + +void HELPER(fscale)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) +{ + res->d = floatx80_scale(val1->d, val0->d, &env->fp_status); +} diff --git a/target/m68k/helper.h b/target/m68k/helper.h index 7f400f0def..c348dced3a 100644 --- a/target/m68k/helper.h +++ b/target/m68k/helper.h @@ -63,6 +63,11 @@ DEF_HELPER_3(fmovemx_ld_postinc, i32, env, i32, i32) DEF_HELPER_3(fmovemd_st_predec, i32, env, i32, i32) DEF_HELPER_3(fmovemd_st_postinc, i32, env, i32, i32) DEF_HELPER_3(fmovemd_ld_postinc, i32, env, i32, i32) +DEF_HELPER_4(fmod, void, env, fp, fp, fp) +DEF_HELPER_4(frem, void, env, fp, fp, fp) +DEF_HELPER_3(fgetexp, void, env, fp, fp) +DEF_HELPER_3(fgetman, void, env, fp, fp) +DEF_HELPER_4(fscale, void, env, fp, 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 new file mode 100644 index 0000000000..9cb141900c --- /dev/null +++ b/target/m68k/softfloat.c @@ -0,0 +1,249 @@ +/* + * Ported from a work by Andreas Grabher for Previous, NeXT Computer Emulator, + * derived from NetBSD M68040 FPSP functions, + * derived from release 2a of the SoftFloat IEC/IEEE Floating-point Arithmetic + * Package. Those parts of the code (and some later contributions) are + * provided under that license, as detailed below. + * It has subsequently been modified by contributors to the QEMU Project, + * so some portions are provided under: + * the SoftFloat-2a license + * the BSD license + * GPL-v2-or-later + * + * Any future contributions to this file will be taken to be licensed under + * the Softfloat-2a license unless specifically indicated otherwise. + */ + +/* Portions of this work are licensed under the terms of the GNU GPL, + * version 2 or later. See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "softfloat.h" +#include "fpu/softfloat-macros.h" + +static floatx80 propagateFloatx80NaNOneArg(floatx80 a, float_status *status) +{ + if (floatx80_is_signaling_nan(a, status)) { + float_raise(float_flag_invalid, status); + } + + if (status->default_nan_mode) { + return floatx80_default_nan(status); + } + + return floatx80_maybe_silence_nan(a, status); +} + +/*---------------------------------------------------------------------------- + | Returns the modulo remainder of the extended double-precision floating-point + | value `a' with respect to the corresponding value `b'. + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status) +{ + flag aSign, zSign; + int32_t aExp, bExp, expDiff; + uint64_t aSig0, aSig1, bSig; + uint64_t qTemp, term0, term1; + + aSig0 = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + bSig = extractFloatx80Frac(b); + bExp = extractFloatx80Exp(b); + + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig0 << 1) + || ((bExp == 0x7FFF) && (uint64_t) (bSig << 1))) { + return propagateFloatx80NaN(a, b, status); + } + goto invalid; + } + if (bExp == 0x7FFF) { + if ((uint64_t) (bSig << 1)) { + return propagateFloatx80NaN(a, b, status); + } + return a; + } + if (bExp == 0) { + if (bSig == 0) { + invalid: + float_raise(float_flag_invalid, status); + return floatx80_default_nan(status); + } + normalizeFloatx80Subnormal(bSig, &bExp, &bSig); + } + if (aExp == 0) { + if ((uint64_t) (aSig0 << 1) == 0) { + return a; + } + normalizeFloatx80Subnormal(aSig0, &aExp, &aSig0); + } + bSig |= LIT64(0x8000000000000000); + zSign = aSign; + expDiff = aExp - bExp; + aSig1 = 0; + if (expDiff < 0) { + return a; + } + qTemp = (bSig <= aSig0); + if (qTemp) { + aSig0 -= bSig; + } + expDiff -= 64; + while (0 < expDiff) { + qTemp = estimateDiv128To64(aSig0, aSig1, bSig); + qTemp = (2 < qTemp) ? qTemp - 2 : 0; + mul64To128(bSig, qTemp, &term0, &term1); + sub128(aSig0, aSig1, term0, term1, &aSig0, &aSig1); + shortShift128Left(aSig0, aSig1, 62, &aSig0, &aSig1); + } + expDiff += 64; + if (0 < expDiff) { + qTemp = estimateDiv128To64(aSig0, aSig1, bSig); + qTemp = (2 < qTemp) ? qTemp - 2 : 0; + qTemp >>= 64 - expDiff; + mul64To128(bSig, qTemp << (64 - expDiff), &term0, &term1); + sub128(aSig0, aSig1, term0, term1, &aSig0, &aSig1); + shortShift128Left(0, bSig, 64 - expDiff, &term0, &term1); + while (le128(term0, term1, aSig0, aSig1)) { + ++qTemp; + sub128(aSig0, aSig1, term0, term1, &aSig0, &aSig1); + } + } + return + normalizeRoundAndPackFloatx80( + 80, zSign, bExp + expDiff, aSig0, aSig1, status); +} + +/*---------------------------------------------------------------------------- + | Returns the mantissa of the extended double-precision floating-point + | value `a'. + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_getman(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + 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) { + if (aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + normalizeFloatx80Subnormal(aSig, &aExp, &aSig); + } + + return roundAndPackFloatx80(status->floatx80_rounding_precision, aSign, + 0x3FFF, aSig, 0, status); +} + +/*---------------------------------------------------------------------------- + | Returns the exponent of the extended double-precision floating-point + | value `a' as an extended double-precision value. + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_getexp(floatx80 a, float_status *status) +{ + flag aSign; + int32_t aExp; + uint64_t aSig; + + 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) { + if (aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + normalizeFloatx80Subnormal(aSig, &aExp, &aSig); + } + + return int32_to_floatx80(aExp - 0x3FFF, status); +} + +/*---------------------------------------------------------------------------- + | Scales extended double-precision floating-point value in operand `a' by + | value `b'. The function truncates the value in the second operand 'b' to + | an integral value and adds that value to the exponent of the operand 'a'. + | The operation performed according to the IEC/IEEE Standard for Binary + | Floating-Point Arithmetic. + *----------------------------------------------------------------------------*/ + +floatx80 floatx80_scale(floatx80 a, floatx80 b, float_status *status) +{ + flag aSign, bSign; + int32_t aExp, bExp, shiftCount; + uint64_t aSig, bSig; + + aSig = extractFloatx80Frac(a); + aExp = extractFloatx80Exp(a); + aSign = extractFloatx80Sign(a); + bSig = extractFloatx80Frac(b); + bExp = extractFloatx80Exp(b); + bSign = extractFloatx80Sign(b); + + if (bExp == 0x7FFF) { + if ((uint64_t) (bSig << 1) || + ((aExp == 0x7FFF) && (uint64_t) (aSig << 1))) { + return propagateFloatx80NaN(a, b, status); + } + float_raise(float_flag_invalid , status); + return floatx80_default_nan(status); + } + if (aExp == 0x7FFF) { + if ((uint64_t) (aSig << 1)) { + return propagateFloatx80NaN(a, b, status); + } + return packFloatx80(aSign, floatx80_infinity.high, + floatx80_infinity.low); + } + if (aExp == 0) { + if (aSig == 0) { + return packFloatx80(aSign, 0, 0); + } + if (bExp < 0x3FFF) { + return a; + } + normalizeFloatx80Subnormal(aSig, &aExp, &aSig); + } + + if (bExp < 0x3FFF) { + return a; + } + + if (0x400F < bExp) { + aExp = bSign ? -0x6001 : 0xE000; + return roundAndPackFloatx80(status->floatx80_rounding_precision, + aSign, aExp, aSig, 0, status); + } + + shiftCount = 0x403E - bExp; + bSig >>= shiftCount; + aExp = bSign ? (aExp - bSig) : (aExp + bSig); + + return roundAndPackFloatx80(status->floatx80_rounding_precision, + aSign, aExp, aSig, 0, status); +} diff --git a/target/m68k/softfloat.h b/target/m68k/softfloat.h new file mode 100644 index 0000000000..78fbc0cd0c --- /dev/null +++ b/target/m68k/softfloat.h @@ -0,0 +1,29 @@ +/* + * Ported from a work by Andreas Grabher for Previous, NeXT Computer Emulator, + * derived from NetBSD M68040 FPSP functions, + * derived from release 2a of the SoftFloat IEC/IEEE Floating-point Arithmetic + * Package. Those parts of the code (and some later contributions) are + * provided under that license, as detailed below. + * It has subsequently been modified by contributors to the QEMU Project, + * so some portions are provided under: + * the SoftFloat-2a license + * the BSD license + * GPL-v2-or-later + * + * Any future contributions to this file will be taken to be licensed under + * the Softfloat-2a license unless specifically indicated otherwise. + */ + +/* Portions of this work are licensed under the terms of the GNU GPL, + * version 2 or later. See the COPYING file in the top-level directory. + */ + +#ifndef TARGET_M68K_SOFTFLOAT_H +#define TARGET_M68K_SOFTFLOAT_H +#include "fpu/softfloat.h" + +floatx80 floatx80_mod(floatx80 a, floatx80 b, float_status *status); +floatx80 floatx80_getman(floatx80 a, float_status *status); +floatx80 floatx80_getexp(floatx80 a, float_status *status); +floatx80 floatx80_scale(floatx80 a, floatx80 b, float_status *status); +#endif diff --git a/target/m68k/translate.c b/target/m68k/translate.c index 93cd38950e..dbb24f8d84 100644 --- a/target/m68k/translate.c +++ b/target/m68k/translate.c @@ -2871,6 +2871,7 @@ DISAS_INSN(unlk) tcg_gen_mov_i32(reg, tmp); tcg_gen_addi_i32(QREG_SP, src, 4); tcg_temp_free(src); + tcg_temp_free(tmp); } #if defined(CONFIG_SOFTMMU) @@ -3148,6 +3149,9 @@ DISAS_INSN(subx_mem) gen_subx(s, src, dest, opsize); gen_store(s, opsize, addr_dest, QREG_CC_N, IS_USER(s)); + + tcg_temp_free(dest); + tcg_temp_free(src); } DISAS_INSN(mov3q) @@ -3354,6 +3358,9 @@ DISAS_INSN(addx_mem) gen_addx(s, src, dest, opsize); gen_store(s, opsize, addr_dest, QREG_CC_N, IS_USER(s)); + + tcg_temp_free(dest); + tcg_temp_free(src); } static inline void shift_im(DisasContext *s, uint16_t insn, int opsize) @@ -4398,6 +4405,8 @@ DISAS_INSN(chk2) gen_flush_flags(s); gen_helper_chk2(cpu_env, reg, bound1, bound2); tcg_temp_free(reg); + tcg_temp_free(bound1); + tcg_temp_free(bound2); } static void m68k_copy_line(TCGv dst, TCGv src, int index) @@ -4547,6 +4556,7 @@ DISAS_INSN(moves) } else { gen_partset_reg(opsize, reg, tmp); } + tcg_temp_free(tmp); } switch (extract32(insn, 3, 3)) { case 3: /* Indirect postincrement. */ @@ -5062,6 +5072,12 @@ DISAS_INSN(fpu) case 0x5e: /* fdneg */ gen_helper_fdneg(cpu_env, cpu_dest, cpu_src); break; + case 0x1e: /* fgetexp */ + gen_helper_fgetexp(cpu_env, cpu_dest, cpu_src); + break; + case 0x1f: /* fgetman */ + gen_helper_fgetman(cpu_env, cpu_dest, cpu_src); + break; case 0x20: /* fdiv */ gen_helper_fdiv(cpu_env, cpu_dest, cpu_src, cpu_dest); break; @@ -5071,6 +5087,9 @@ DISAS_INSN(fpu) case 0x64: /* fddiv */ gen_helper_fddiv(cpu_env, cpu_dest, cpu_src, cpu_dest); break; + case 0x21: /* fmod */ + gen_helper_fmod(cpu_env, cpu_dest, cpu_src, cpu_dest); + break; case 0x22: /* fadd */ gen_helper_fadd(cpu_env, cpu_dest, cpu_src, cpu_dest); break; @@ -5092,6 +5111,12 @@ DISAS_INSN(fpu) case 0x24: /* fsgldiv */ gen_helper_fsgldiv(cpu_env, cpu_dest, cpu_src, cpu_dest); break; + case 0x25: /* frem */ + gen_helper_frem(cpu_env, cpu_dest, cpu_src, cpu_dest); + break; + case 0x26: /* fscale */ + gen_helper_fscale(cpu_env, cpu_dest, cpu_src, cpu_dest); + break; case 0x27: /* fsglmul */ gen_helper_fsglmul(cpu_env, cpu_dest, cpu_src, cpu_dest); break; @@ -5537,6 +5562,7 @@ DISAS_INSN(mac) case 4: /* Pre-decrement. */ tcg_gen_mov_i32(AREG(insn, 0), addr); } + tcg_temp_free(loadval); } } |