diff options
| -rw-r--r-- | fpu/softfloat-specialize.h | 691 | ||||
| -rw-r--r-- | fpu/softfloat.c | 726 | ||||
| -rw-r--r-- | hw/display/Makefile.objs | 2 | ||||
| -rw-r--r-- | hw/usb/ccid-card-passthru.c | 2 | ||||
| -rw-r--r-- | hw/usb/dev-smartcard-reader.c | 14 | ||||
| -rw-r--r-- | include/fpu/softfloat-types.h | 1 | ||||
| -rw-r--r-- | include/fpu/softfloat.h | 18 | ||||
| -rw-r--r-- | target/arm/helper-a64.c | 7 | ||||
| -rw-r--r-- | target/arm/helper.c | 108 | ||||
| -rw-r--r-- | target/arm/helper.h | 10 | ||||
| -rw-r--r-- | target/arm/translate-a64.c | 37 | ||||
| -rw-r--r-- | target/arm/translate.c | 74 | ||||
| -rw-r--r-- | target/arm/translate.h | 12 | ||||
| -rw-r--r-- | target/hppa/cpu.c | 1 | ||||
| -rw-r--r-- | target/hppa/op_helper.c | 2 | ||||
| -rw-r--r-- | target/m68k/softfloat.c | 3 | ||||
| -rw-r--r-- | target/mips/msa_helper.c | 4 | ||||
| -rw-r--r-- | target/mips/op_helper.c | 2 | ||||
| -rw-r--r-- | target/ppc/fpu_helper.c | 1 | ||||
| -rw-r--r-- | target/riscv/fpu_helper.c | 6 | ||||
| -rw-r--r-- | target/s390x/fpu_helper.c | 12 | ||||
| -rw-r--r-- | target/sh4/cpu.c | 1 | ||||
| -rw-r--r-- | target/unicore32/cpu.c | 2 | ||||
| -rw-r--r-- | ui/Makefile.objs | 11 | ||||
| -rw-r--r-- | ui/console.c | 5 | ||||
| -rw-r--r-- | ui/sdl2-2d.c | 6 |
26 files changed, 742 insertions, 1016 deletions
diff --git a/fpu/softfloat-specialize.h b/fpu/softfloat-specialize.h index 27834af..16c0bcb 100644 --- a/fpu/softfloat-specialize.h +++ b/fpu/softfloat-specialize.h @@ -79,82 +79,111 @@ this code that are retained. * version 2 or later. See the COPYING file in the top-level directory. */ -#if defined(TARGET_XTENSA) /* Define for architectures which deviate from IEEE in not supporting * signaling NaNs (so all NaNs are treated as quiet). */ +#if defined(TARGET_XTENSA) #define NO_SIGNALING_NANS 1 #endif -/*---------------------------------------------------------------------------- -| The pattern for a default generated half-precision NaN. -*----------------------------------------------------------------------------*/ -float16 float16_default_nan(float_status *status) +/* Define how the architecture discriminates signaling NaNs. + * This done with the most significant bit of the fraction. + * In IEEE 754-1985 this was implementation defined, but in IEEE 754-2008 + * the msb must be zero. MIPS is (so far) unique in supporting both the + * 2008 revision and backward compatibility with their original choice. + * Thus for MIPS we must make the choice at runtime. + */ +static inline flag snan_bit_is_one(float_status *status) { -#if defined(TARGET_ARM) - return const_float16(0x7E00); -#else - if (status->snan_bit_is_one) { - return const_float16(0x7DFF); - } else { #if defined(TARGET_MIPS) - return const_float16(0x7E00); + return status->snan_bit_is_one; +#elif defined(TARGET_HPPA) || defined(TARGET_UNICORE32) || defined(TARGET_SH4) + return 1; #else - return const_float16(0xFE00); + return 0; #endif - } +} + +/*---------------------------------------------------------------------------- +| For the deconstructed floating-point with fraction FRAC, return true +| if the fraction represents a signalling NaN; otherwise false. +*----------------------------------------------------------------------------*/ + +static bool parts_is_snan_frac(uint64_t frac, float_status *status) +{ +#ifdef NO_SIGNALING_NANS + return false; +#else + flag msb = extract64(frac, DECOMPOSED_BINARY_POINT - 1, 1); + return msb == snan_bit_is_one(status); #endif } /*---------------------------------------------------------------------------- -| The pattern for a default generated single-precision NaN. +| The pattern for a default generated deconstructed floating-point NaN. *----------------------------------------------------------------------------*/ -float32 float32_default_nan(float_status *status) + +static FloatParts parts_default_nan(float_status *status) { + bool sign = 0; + uint64_t frac; + #if defined(TARGET_SPARC) || defined(TARGET_M68K) - return const_float32(0x7FFFFFFF); -#elif defined(TARGET_PPC) || defined(TARGET_ARM) || defined(TARGET_ALPHA) || \ - defined(TARGET_XTENSA) || defined(TARGET_S390X) || \ - defined(TARGET_TRICORE) || defined(TARGET_RISCV) - return const_float32(0x7FC00000); + /* !snan_bit_is_one, set all bits */ + frac = (1ULL << DECOMPOSED_BINARY_POINT) - 1; +#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ + || defined(TARGET_MICROBLAZE) + /* !snan_bit_is_one, set sign and msb */ + frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); + sign = 1; #elif defined(TARGET_HPPA) - return const_float32(0x7FA00000); + /* snan_bit_is_one, set msb-1. */ + frac = 1ULL << (DECOMPOSED_BINARY_POINT - 2); #else - if (status->snan_bit_is_one) { - return const_float32(0x7FBFFFFF); + /* This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, + * S390, SH4, TriCore, and Xtensa. I cannot find documentation + * for Unicore32; the choice from the original commit is unchanged. + * Our other supported targets, CRIS, LM32, Moxie, Nios2, and Tile, + * do not have floating-point. + */ + if (snan_bit_is_one(status)) { + /* set all bits other than msb */ + frac = (1ULL << (DECOMPOSED_BINARY_POINT - 1)) - 1; } else { -#if defined(TARGET_MIPS) - return const_float32(0x7FC00000); -#else - return const_float32(0xFFC00000); -#endif + /* set msb */ + frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); } #endif + + return (FloatParts) { + .cls = float_class_qnan, + .sign = sign, + .exp = INT_MAX, + .frac = frac + }; } /*---------------------------------------------------------------------------- -| The pattern for a default generated double-precision NaN. +| Returns a quiet NaN from a signalling NaN for the deconstructed +| floating-point parts. *----------------------------------------------------------------------------*/ -float64 float64_default_nan(float_status *status) + +static FloatParts parts_silence_nan(FloatParts a, float_status *status) { -#if defined(TARGET_SPARC) || defined(TARGET_M68K) - return const_float64(LIT64(0x7FFFFFFFFFFFFFFF)); -#elif defined(TARGET_PPC) || defined(TARGET_ARM) || defined(TARGET_ALPHA) || \ - defined(TARGET_S390X) || defined(TARGET_RISCV) - return const_float64(LIT64(0x7FF8000000000000)); +#ifdef NO_SIGNALING_NANS + g_assert_not_reached(); #elif defined(TARGET_HPPA) - return const_float64(LIT64(0x7FF4000000000000)); + a.frac &= ~(1ULL << (DECOMPOSED_BINARY_POINT - 1)); + a.frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 2); #else - if (status->snan_bit_is_one) { - return const_float64(LIT64(0x7FF7FFFFFFFFFFFF)); + if (snan_bit_is_one(status)) { + return parts_default_nan(status); } else { -#if defined(TARGET_MIPS) - return const_float64(LIT64(0x7FF8000000000000)); -#else - return const_float64(LIT64(0xFFF8000000000000)); -#endif + a.frac |= 1ULL << (DECOMPOSED_BINARY_POINT - 1); } #endif + a.cls = float_class_qnan; + return a; } /*---------------------------------------------------------------------------- @@ -163,17 +192,16 @@ float64 float64_default_nan(float_status *status) floatx80 floatx80_default_nan(float_status *status) { floatx80 r; + + /* None of the targets that have snan_bit_is_one use floatx80. */ + assert(!snan_bit_is_one(status)); #if defined(TARGET_M68K) r.low = LIT64(0xFFFFFFFFFFFFFFFF); r.high = 0x7FFF; #else - if (status->snan_bit_is_one) { - r.low = LIT64(0xBFFFFFFFFFFFFFFF); - r.high = 0x7FFF; - } else { - r.low = LIT64(0xC000000000000000); - r.high = 0xFFFF; - } + /* X86 */ + r.low = LIT64(0xC000000000000000); + r.high = 0xFFFF; #endif return r; } @@ -193,27 +221,6 @@ 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) -{ - float128 r; - - if (status->snan_bit_is_one) { - r.low = LIT64(0xFFFFFFFFFFFFFFFF); - r.high = LIT64(0x7FFF7FFFFFFFFFFF); - } else { - r.low = LIT64(0x0000000000000000); -#if defined(TARGET_S390X) || defined(TARGET_PPC) || defined(TARGET_RISCV) - r.high = LIT64(0x7FFF800000000000); -#else - r.high = LIT64(0xFFFF800000000000); -#endif - } - return r; -} - -/*---------------------------------------------------------------------------- | Raises the exceptions specified by `flags'. Floating-point traps can be | defined here if desired. It is currently not possible for such a trap | to substitute a result value. If traps are not implemented, this routine @@ -233,17 +240,6 @@ typedef struct { uint64_t high, low; } commonNaNT; -#ifdef NO_SIGNALING_NANS -int float16_is_quiet_nan(float16 a_, float_status *status) -{ - return float16_is_any_nan(a_); -} - -int float16_is_signaling_nan(float16 a_, float_status *status) -{ - return 0; -} -#else /*---------------------------------------------------------------------------- | Returns 1 if the half-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. @@ -251,12 +247,16 @@ int float16_is_signaling_nan(float16 a_, float_status *status) int float16_is_quiet_nan(float16 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return float16_is_any_nan(a_); +#else uint16_t a = float16_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return (((a >> 9) & 0x3F) == 0x3E) && (a & 0x1FF); } else { return ((a & ~0x8000) >= 0x7C80); } +#endif } /*---------------------------------------------------------------------------- @@ -266,97 +266,35 @@ int float16_is_quiet_nan(float16 a_, float_status *status) int float16_is_signaling_nan(float16 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return 0; +#else uint16_t a = float16_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return ((a & ~0x8000) >= 0x7C80); } else { return (((a >> 9) & 0x3F) == 0x3E) && (a & 0x1FF); } -} #endif - -/*---------------------------------------------------------------------------- -| Returns a quiet NaN if the half-precision floating point value `a' is a -| signaling NaN; otherwise returns `a'. -*----------------------------------------------------------------------------*/ -float16 float16_maybe_silence_nan(float16 a_, float_status *status) -{ - if (float16_is_signaling_nan(a_, status)) { - if (status->snan_bit_is_one) { - return float16_default_nan(status); - } else { - uint16_t a = float16_val(a_); - a |= (1 << 9); - return make_float16(a); - } - } - return a_; -} - -/*---------------------------------------------------------------------------- -| Returns the result of converting the half-precision floating-point NaN -| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid -| exception is raised. -*----------------------------------------------------------------------------*/ - -static commonNaNT float16ToCommonNaN(float16 a, float_status *status) -{ - commonNaNT z; - - if (float16_is_signaling_nan(a, status)) { - float_raise(float_flag_invalid, status); - } - z.sign = float16_val(a) >> 15; - z.low = 0; - z.high = ((uint64_t) float16_val(a)) << 54; - return z; } /*---------------------------------------------------------------------------- -| Returns the result of converting the canonical NaN `a' to the half- -| precision floating-point format. -*----------------------------------------------------------------------------*/ - -static float16 commonNaNToFloat16(commonNaNT a, float_status *status) -{ - uint16_t mantissa = a.high >> 54; - - if (status->default_nan_mode) { - return float16_default_nan(status); - } - - if (mantissa) { - return make_float16(((((uint16_t) a.sign) << 15) - | (0x1F << 10) | mantissa)); - } else { - return float16_default_nan(status); - } -} - -#ifdef NO_SIGNALING_NANS -int float32_is_quiet_nan(float32 a_, float_status *status) -{ - return float32_is_any_nan(a_); -} - -int float32_is_signaling_nan(float32 a_, float_status *status) -{ - return 0; -} -#else -/*---------------------------------------------------------------------------- | Returns 1 if the single-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. *----------------------------------------------------------------------------*/ int float32_is_quiet_nan(float32 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return float32_is_any_nan(a_); +#else uint32_t a = float32_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return (((a >> 22) & 0x1FF) == 0x1FE) && (a & 0x003FFFFF); } else { return ((uint32_t)(a << 1) >= 0xFF800000); } +#endif } /*---------------------------------------------------------------------------- @@ -366,39 +304,16 @@ int float32_is_quiet_nan(float32 a_, float_status *status) int float32_is_signaling_nan(float32 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return 0; +#else uint32_t a = float32_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return ((uint32_t)(a << 1) >= 0xFF800000); } else { return (((a >> 22) & 0x1FF) == 0x1FE) && (a & 0x003FFFFF); } -} -#endif - -/*---------------------------------------------------------------------------- -| Returns a quiet NaN if the single-precision floating point value `a' is a -| signaling NaN; otherwise returns `a'. -*----------------------------------------------------------------------------*/ - -float32 float32_maybe_silence_nan(float32 a_, float_status *status) -{ - if (float32_is_signaling_nan(a_, status)) { - if (status->snan_bit_is_one) { -#ifdef TARGET_HPPA - uint32_t a = float32_val(a_); - a &= ~0x00400000; - a |= 0x00200000; - return make_float32(a); -#else - return float32_default_nan(status); #endif - } else { - uint32_t a = float32_val(a_); - a |= (1 << 22); - return make_float32(a); - } - } - return a_; } /*---------------------------------------------------------------------------- @@ -448,7 +363,7 @@ static float32 commonNaNToFloat32(commonNaNT a, float_status *status) | The routine is passed various bits of information about the | two NaNs and should return 0 to select NaN a and 1 for NaN b. | Note that signalling NaNs are always squashed to quiet NaNs -| by the caller, by calling floatXX_maybe_silence_nan() before +| by the caller, by calling floatXX_silence_nan() before | returning them. | | aIsLargerSignificand is only valid if both a and b are NaNs @@ -458,10 +373,10 @@ static float32 commonNaNToFloat32(commonNaNT a, float_status *status) | tie-break rule. *----------------------------------------------------------------------------*/ -#if defined(TARGET_ARM) -static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, +static int pickNaN(FloatClass a_cls, FloatClass b_cls, flag aIsLargerSignificand) { +#if defined(TARGET_ARM) || defined(TARGET_MIPS) || defined(TARGET_HPPA) /* ARM mandated NaN propagation rules (see FPProcessNaNs()), take * the first of: * 1. A if it is signaling @@ -470,23 +385,9 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, * 4. B (quiet) * A signaling NaN is always quietened before returning it. */ - if (aIsSNaN) { - return 0; - } else if (bIsSNaN) { - return 1; - } else if (aIsQNaN) { - return 0; - } else { - return 1; - } -} -#elif defined(TARGET_MIPS) || defined(TARGET_HPPA) -static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag aIsLargerSignificand) -{ /* According to MIPS specifications, if one of the two operands is * a sNaN, a new qNaN has to be generated. This is done in - * floatXX_maybe_silence_nan(). For qNaN inputs the specifications + * floatXX_silence_nan(). For qNaN inputs the specifications * says: "When possible, this QNaN result is one of the operand QNaN * values." In practice it seems that most implementations choose * the first operand if both operands are qNaN. In short this gives @@ -497,35 +398,21 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, * 4. B (quiet) * A signaling NaN is always silenced before returning it. */ - if (aIsSNaN) { + if (is_snan(a_cls)) { return 0; - } else if (bIsSNaN) { + } else if (is_snan(b_cls)) { return 1; - } else if (aIsQNaN) { + } else if (is_qnan(a_cls)) { return 0; } else { return 1; } -} -#elif defined(TARGET_PPC) || defined(TARGET_XTENSA) -static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag aIsLargerSignificand) -{ +#elif defined(TARGET_PPC) || defined(TARGET_XTENSA) || defined(TARGET_M68K) /* PowerPC propagation rules: * 1. A if it sNaN or qNaN * 2. B if it sNaN or qNaN * A signaling NaN is always silenced before returning it. */ - if (aIsSNaN || aIsQNaN) { - return 0; - } else { - return 1; - } -} -#elif defined(TARGET_M68K) -static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag aIsLargerSignificand) -{ /* M68000 FAMILY PROGRAMMER'S REFERENCE MANUAL * 3.4 FLOATING-POINT INSTRUCTION DETAILS * If either operand, but not both operands, of an operation is a @@ -540,16 +427,12 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, * a nonsignaling NaN. The operation then continues as described in the * preceding paragraph for nonsignaling NaNs. */ - if (aIsQNaN || aIsSNaN) { /* a is the destination operand */ - return 0; /* return the destination operand */ + if (is_nan(a_cls)) { + return 0; } else { - return 1; /* return b */ + return 1; } -} #else -static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag aIsLargerSignificand) -{ /* This implements x87 NaN propagation rules: * SNaN + QNaN => return the QNaN * two SNaNs => return the one with the larger significand, silenced @@ -560,13 +443,13 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, * If we get down to comparing significands and they are the same, * return the NaN with the positive sign bit (if any). */ - if (aIsSNaN) { - if (bIsSNaN) { + if (is_snan(a_cls)) { + if (is_snan(b_cls)) { return aIsLargerSignificand ? 0 : 1; } - return bIsQNaN ? 1 : 0; - } else if (aIsQNaN) { - if (bIsSNaN || !bIsQNaN) { + return is_qnan(b_cls) ? 1 : 0; + } else if (is_qnan(a_cls)) { + if (is_snan(b_cls) || !is_qnan(b_cls)) { return 0; } else { return aIsLargerSignificand ? 0 : 1; @@ -574,8 +457,8 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, } else { return 1; } -} #endif +} /*---------------------------------------------------------------------------- | Select which NaN to propagate for a three-input operation. @@ -583,15 +466,14 @@ static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, | information. | Return values : 0 : a; 1 : b; 2 : c; 3 : default-NaN *----------------------------------------------------------------------------*/ -#if defined(TARGET_ARM) -static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag cIsQNaN, flag cIsSNaN, flag infzero, - float_status *status) +static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, + bool infzero, float_status *status) { +#if defined(TARGET_ARM) /* For ARM, the (inf,zero,qnan) case sets InvalidOp and returns * the default NaN */ - if (infzero && cIsQNaN) { + if (infzero && is_qnan(c_cls)) { float_raise(float_flag_invalid, status); return 3; } @@ -599,25 +481,20 @@ static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, /* This looks different from the ARM ARM pseudocode, because the ARM ARM * puts the operands to a fused mac operation (a*b)+c in the order c,a,b. */ - if (cIsSNaN) { + if (is_snan(c_cls)) { return 2; - } else if (aIsSNaN) { + } else if (is_snan(a_cls)) { return 0; - } else if (bIsSNaN) { + } else if (is_snan(b_cls)) { return 1; - } else if (cIsQNaN) { + } else if (is_qnan(c_cls)) { return 2; - } else if (aIsQNaN) { + } else if (is_qnan(a_cls)) { return 0; } else { return 1; } -} #elif defined(TARGET_MIPS) -static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag cIsQNaN, flag cIsSNaN, flag infzero, - float_status *status) -{ /* For MIPS, the (inf,zero,qnan) case sets InvalidOp and returns * the default NaN */ @@ -626,43 +503,38 @@ static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, return 3; } - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { /* Prefer sNaN over qNaN, in the a, b, c order. */ - if (aIsSNaN) { + if (is_snan(a_cls)) { return 0; - } else if (bIsSNaN) { + } else if (is_snan(b_cls)) { return 1; - } else if (cIsSNaN) { + } else if (is_snan(c_cls)) { return 2; - } else if (aIsQNaN) { + } else if (is_qnan(a_cls)) { return 0; - } else if (bIsQNaN) { + } else if (is_qnan(b_cls)) { return 1; } else { return 2; } } else { /* Prefer sNaN over qNaN, in the c, a, b order. */ - if (cIsSNaN) { + if (is_snan(c_cls)) { return 2; - } else if (aIsSNaN) { + } else if (is_snan(a_cls)) { return 0; - } else if (bIsSNaN) { + } else if (is_snan(b_cls)) { return 1; - } else if (cIsQNaN) { + } else if (is_qnan(c_cls)) { return 2; - } else if (aIsQNaN) { + } else if (is_qnan(a_cls)) { return 0; } else { return 1; } } -} #elif defined(TARGET_PPC) -static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag cIsQNaN, flag cIsSNaN, flag infzero, - float_status *status) -{ /* For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer * to return an input NaN if we have one (ie c) rather than generating * a default NaN @@ -675,31 +547,26 @@ static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB */ - if (aIsSNaN || aIsQNaN) { + if (is_nan(a_cls)) { return 0; - } else if (cIsSNaN || cIsQNaN) { + } else if (is_nan(c_cls)) { return 2; } else { return 1; } -} #else -/* A default implementation: prefer a to b to c. - * This is unlikely to actually match any real implementation. - */ -static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, - flag cIsQNaN, flag cIsSNaN, flag infzero, - float_status *status) -{ - if (aIsSNaN || aIsQNaN) { + /* A default implementation: prefer a to b to c. + * This is unlikely to actually match any real implementation. + */ + if (is_nan(a_cls)) { return 0; - } else if (bIsSNaN || bIsQNaN) { + } else if (is_nan(b_cls)) { return 1; } else { return 2; } -} #endif +} /*---------------------------------------------------------------------------- | Takes two single-precision floating-point values `a' and `b', one of which @@ -709,18 +576,26 @@ static int pickNaNMulAdd(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN, static float32 propagateFloat32NaN(float32 a, float32 b, float_status *status) { - flag aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN; flag aIsLargerSignificand; uint32_t av, bv; + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!float32_is_any_nan(a) + ? float_class_normal + : float32_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!float32_is_any_nan(b) + ? float_class_normal + : float32_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); - aIsQuietNaN = float32_is_quiet_nan(a, status); - aIsSignalingNaN = float32_is_signaling_nan(a, status); - bIsQuietNaN = float32_is_quiet_nan(b, status); - bIsSignalingNaN = float32_is_signaling_nan(b, status); av = float32_val(a); bv = float32_val(b); - if (aIsSignalingNaN | bIsSignalingNaN) { + if (is_snan(a_cls) || is_snan(b_cls)) { float_raise(float_flag_invalid, status); } @@ -736,25 +611,19 @@ static float32 propagateFloat32NaN(float32 a, float32 b, float_status *status) aIsLargerSignificand = (av < bv) ? 1 : 0; } - if (pickNaN(aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN, - aIsLargerSignificand)) { - return float32_maybe_silence_nan(b, status); + if (pickNaN(a_cls, b_cls, aIsLargerSignificand)) { + if (is_snan(b_cls)) { + return float32_silence_nan(b, status); + } + return b; } else { - return float32_maybe_silence_nan(a, status); + if (is_snan(a_cls)) { + return float32_silence_nan(a, status); + } + return a; } } -#ifdef NO_SIGNALING_NANS -int float64_is_quiet_nan(float64 a_, float_status *status) -{ - return float64_is_any_nan(a_); -} - -int float64_is_signaling_nan(float64 a_, float_status *status) -{ - return 0; -} -#else /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. @@ -762,13 +631,17 @@ int float64_is_signaling_nan(float64 a_, float_status *status) int float64_is_quiet_nan(float64 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return float64_is_any_nan(a_); +#else uint64_t a = float64_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return (((a >> 51) & 0xFFF) == 0xFFE) && (a & 0x0007FFFFFFFFFFFFULL); } else { return ((a << 1) >= 0xFFF0000000000000ULL); } +#endif } /*---------------------------------------------------------------------------- @@ -778,40 +651,17 @@ int float64_is_quiet_nan(float64 a_, float_status *status) int float64_is_signaling_nan(float64 a_, float_status *status) { +#ifdef NO_SIGNALING_NANS + return 0; +#else uint64_t a = float64_val(a_); - if (status->snan_bit_is_one) { + if (snan_bit_is_one(status)) { return ((a << 1) >= 0xFFF0000000000000ULL); } else { return (((a >> 51) & 0xFFF) == 0xFFE) && (a & LIT64(0x0007FFFFFFFFFFFF)); } -} -#endif - -/*---------------------------------------------------------------------------- -| Returns a quiet NaN if the double-precision floating point value `a' is a -| signaling NaN; otherwise returns `a'. -*----------------------------------------------------------------------------*/ - -float64 float64_maybe_silence_nan(float64 a_, float_status *status) -{ - if (float64_is_signaling_nan(a_, status)) { - if (status->snan_bit_is_one) { -#ifdef TARGET_HPPA - uint64_t a = float64_val(a_); - a &= ~0x0008000000000000ULL; - a |= 0x0004000000000000ULL; - return make_float64(a); -#else - return float64_default_nan(status); #endif - } else { - uint64_t a = float64_val(a_); - a |= LIT64(0x0008000000000000); - return make_float64(a); - } - } - return a_; } /*---------------------------------------------------------------------------- @@ -864,18 +714,26 @@ static float64 commonNaNToFloat64(commonNaNT a, float_status *status) static float64 propagateFloat64NaN(float64 a, float64 b, float_status *status) { - flag aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN; flag aIsLargerSignificand; uint64_t av, bv; + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!float64_is_any_nan(a) + ? float_class_normal + : float64_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!float64_is_any_nan(b) + ? float_class_normal + : float64_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); - aIsQuietNaN = float64_is_quiet_nan(a, status); - aIsSignalingNaN = float64_is_signaling_nan(a, status); - bIsQuietNaN = float64_is_quiet_nan(b, status); - bIsSignalingNaN = float64_is_signaling_nan(b, status); av = float64_val(a); bv = float64_val(b); - if (aIsSignalingNaN | bIsSignalingNaN) { + if (is_snan(a_cls) || is_snan(b_cls)) { float_raise(float_flag_invalid, status); } @@ -891,25 +749,19 @@ static float64 propagateFloat64NaN(float64 a, float64 b, float_status *status) aIsLargerSignificand = (av < bv) ? 1 : 0; } - if (pickNaN(aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN, - aIsLargerSignificand)) { - return float64_maybe_silence_nan(b, status); + if (pickNaN(a_cls, b_cls, aIsLargerSignificand)) { + if (is_snan(b_cls)) { + return float64_silence_nan(b, status); + } + return b; } else { - return float64_maybe_silence_nan(a, status); + if (is_snan(a_cls)) { + return float64_silence_nan(a, status); + } + return a; } } -#ifdef NO_SIGNALING_NANS -int floatx80_is_quiet_nan(floatx80 a_, float_status *status) -{ - return floatx80_is_any_nan(a_); -} - -int floatx80_is_signaling_nan(floatx80 a_, float_status *status) -{ - return 0; -} -#else /*---------------------------------------------------------------------------- | Returns 1 if the extended double-precision floating-point value `a' is a | quiet NaN; otherwise returns 0. This slightly differs from the same @@ -918,7 +770,10 @@ int floatx80_is_signaling_nan(floatx80 a_, float_status *status) int floatx80_is_quiet_nan(floatx80 a, float_status *status) { - if (status->snan_bit_is_one) { +#ifdef NO_SIGNALING_NANS + return floatx80_is_any_nan(a); +#else + if (snan_bit_is_one(status)) { uint64_t aLow; aLow = a.low & ~0x4000000000000000ULL; @@ -929,6 +784,7 @@ int floatx80_is_quiet_nan(floatx80 a, float_status *status) return ((a.high & 0x7FFF) == 0x7FFF) && (LIT64(0x8000000000000000) <= ((uint64_t)(a.low << 1))); } +#endif } /*---------------------------------------------------------------------------- @@ -939,7 +795,10 @@ int floatx80_is_quiet_nan(floatx80 a, float_status *status) int floatx80_is_signaling_nan(floatx80 a, float_status *status) { - if (status->snan_bit_is_one) { +#ifdef NO_SIGNALING_NANS + return 0; +#else + if (snan_bit_is_one(status)) { return ((a.high & 0x7FFF) == 0x7FFF) && ((a.low << 1) >= 0x8000000000000000ULL); } else { @@ -950,24 +809,19 @@ int floatx80_is_signaling_nan(floatx80 a, float_status *status) && (uint64_t)(aLow << 1) && (a.low == aLow); } -} #endif +} /*---------------------------------------------------------------------------- -| Returns a quiet NaN if the extended double-precision floating point value -| `a' is a signaling NaN; otherwise returns `a'. +| Returns a quiet NaN from a signalling NaN for the extended double-precision +| floating point value `a'. *----------------------------------------------------------------------------*/ -floatx80 floatx80_maybe_silence_nan(floatx80 a, float_status *status) +floatx80 floatx80_silence_nan(floatx80 a, float_status *status) { - if (floatx80_is_signaling_nan(a, status)) { - if (status->snan_bit_is_one) { - a = floatx80_default_nan(status); - } else { - a.low |= LIT64(0xC000000000000000); - return a; - } - } + /* None of the targets that have snan_bit_is_one use floatx80. */ + assert(!snan_bit_is_one(status)); + a.low |= LIT64(0xC000000000000000); return a; } @@ -1028,15 +882,22 @@ static floatx80 commonNaNToFloatx80(commonNaNT a, float_status *status) floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) { - flag aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN; flag aIsLargerSignificand; - - aIsQuietNaN = floatx80_is_quiet_nan(a, status); - aIsSignalingNaN = floatx80_is_signaling_nan(a, status); - bIsQuietNaN = floatx80_is_quiet_nan(b, status); - bIsSignalingNaN = floatx80_is_signaling_nan(b, status); - - if (aIsSignalingNaN | bIsSignalingNaN) { + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!floatx80_is_any_nan(a) + ? float_class_normal + : floatx80_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!floatx80_is_any_nan(b) + ? float_class_normal + : floatx80_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); + + if (is_snan(a_cls) || is_snan(b_cls)) { float_raise(float_flag_invalid, status); } @@ -1052,25 +913,19 @@ floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) aIsLargerSignificand = (a.high < b.high) ? 1 : 0; } - if (pickNaN(aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN, - aIsLargerSignificand)) { - return floatx80_maybe_silence_nan(b, status); + if (pickNaN(a_cls, b_cls, aIsLargerSignificand)) { + if (is_snan(b_cls)) { + return floatx80_silence_nan(b, status); + } + return b; } else { - return floatx80_maybe_silence_nan(a, status); + if (is_snan(a_cls)) { + return floatx80_silence_nan(a, status); + } + return a; } } -#ifdef NO_SIGNALING_NANS -int float128_is_quiet_nan(float128 a_, float_status *status) -{ - return float128_is_any_nan(a_); -} - -int float128_is_signaling_nan(float128 a_, float_status *status) -{ - return 0; -} -#else /*---------------------------------------------------------------------------- | Returns 1 if the quadruple-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. @@ -1078,13 +933,17 @@ int float128_is_signaling_nan(float128 a_, float_status *status) int float128_is_quiet_nan(float128 a, float_status *status) { - if (status->snan_bit_is_one) { +#ifdef NO_SIGNALING_NANS + return float128_is_any_nan(a); +#else + if (snan_bit_is_one(status)) { return (((a.high >> 47) & 0xFFFF) == 0xFFFE) && (a.low || (a.high & 0x00007FFFFFFFFFFFULL)); } else { return ((a.high << 1) >= 0xFFFF000000000000ULL) && (a.low || (a.high & 0x0000FFFFFFFFFFFFULL)); } +#endif } /*---------------------------------------------------------------------------- @@ -1094,32 +953,36 @@ int float128_is_quiet_nan(float128 a, float_status *status) int float128_is_signaling_nan(float128 a, float_status *status) { - if (status->snan_bit_is_one) { +#ifdef NO_SIGNALING_NANS + return 0; +#else + if (snan_bit_is_one(status)) { return ((a.high << 1) >= 0xFFFF000000000000ULL) && (a.low || (a.high & 0x0000FFFFFFFFFFFFULL)); } else { return (((a.high >> 47) & 0xFFFF) == 0xFFFE) && (a.low || (a.high & LIT64(0x00007FFFFFFFFFFF))); } -} #endif +} /*---------------------------------------------------------------------------- -| Returns a quiet NaN if the quadruple-precision floating point value `a' is -| a signaling NaN; otherwise returns `a'. +| Returns a quiet NaN from a signalling NaN for the quadruple-precision +| floating point value `a'. *----------------------------------------------------------------------------*/ -float128 float128_maybe_silence_nan(float128 a, float_status *status) +float128 float128_silence_nan(float128 a, float_status *status) { - if (float128_is_signaling_nan(a, status)) { - if (status->snan_bit_is_one) { - a = float128_default_nan(status); - } else { - a.high |= LIT64(0x0000800000000000); - return a; - } +#ifdef NO_SIGNALING_NANS + g_assert_not_reached(); +#else + if (snan_bit_is_one(status)) { + return float128_default_nan(status); + } else { + a.high |= LIT64(0x0000800000000000); + return a; } - return a; +#endif } /*---------------------------------------------------------------------------- @@ -1167,15 +1030,22 @@ static float128 commonNaNToFloat128(commonNaNT a, float_status *status) static float128 propagateFloat128NaN(float128 a, float128 b, float_status *status) { - flag aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN; flag aIsLargerSignificand; - - aIsQuietNaN = float128_is_quiet_nan(a, status); - aIsSignalingNaN = float128_is_signaling_nan(a, status); - bIsQuietNaN = float128_is_quiet_nan(b, status); - bIsSignalingNaN = float128_is_signaling_nan(b, status); - - if (aIsSignalingNaN | bIsSignalingNaN) { + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!float128_is_any_nan(a) + ? float_class_normal + : float128_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!float128_is_any_nan(b) + ? float_class_normal + : float128_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); + + if (is_snan(a_cls) || is_snan(b_cls)) { float_raise(float_flag_invalid, status); } @@ -1191,10 +1061,15 @@ static float128 propagateFloat128NaN(float128 a, float128 b, aIsLargerSignificand = (a.high < b.high) ? 1 : 0; } - if (pickNaN(aIsQuietNaN, aIsSignalingNaN, bIsQuietNaN, bIsSignalingNaN, - aIsLargerSignificand)) { - return float128_maybe_silence_nan(b, status); + if (pickNaN(a_cls, b_cls, aIsLargerSignificand)) { + if (is_snan(b_cls)) { + return float128_silence_nan(b, status); + } + return b; } else { - return float128_maybe_silence_nan(a, status); + if (is_snan(a_cls)) { + return float128_silence_nan(a, status); + } + return a; } } diff --git a/fpu/softfloat.c b/fpu/softfloat.c index bc0f52f..8cd2400 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -96,16 +96,6 @@ this code that are retained. #include "fpu/softfloat-macros.h" /*---------------------------------------------------------------------------- -| Functions and definitions to determine: (1) whether tininess for underflow -| is detected before or after rounding by default, (2) what (if anything) -| happens when exceptions are raised, (3) how signaling NaNs are distinguished -| from quiet NaNs, (4) the default generated quiet NaNs, and (5) how NaNs -| are propagated from function inputs to output. These details are target- -| specific. -*----------------------------------------------------------------------------*/ -#include "softfloat-specialize.h" - -/*---------------------------------------------------------------------------- | Returns the fraction bits of the half-precision floating-point value `a'. *----------------------------------------------------------------------------*/ @@ -124,15 +114,6 @@ static inline int extractFloat16Exp(float16 a) } /*---------------------------------------------------------------------------- -| Returns the sign bit of the single-precision floating-point value `a'. -*----------------------------------------------------------------------------*/ - -static inline flag extractFloat16Sign(float16 a) -{ - return float16_val(a)>>15; -} - -/*---------------------------------------------------------------------------- | Returns the fraction bits of the single-precision floating-point value `a'. *----------------------------------------------------------------------------*/ @@ -198,10 +179,24 @@ typedef enum __attribute__ ((__packed__)) { float_class_inf, float_class_qnan, /* all NaNs from here */ float_class_snan, - float_class_dnan, - float_class_msnan, /* maybe silenced */ } FloatClass; +/* Simple helpers for checking if, or what kind of, NaN we have */ +static inline __attribute__((unused)) bool is_nan(FloatClass c) +{ + return unlikely(c >= float_class_qnan); +} + +static inline __attribute__((unused)) bool is_snan(FloatClass c) +{ + return c == float_class_snan; +} + +static inline __attribute__((unused)) bool is_qnan(FloatClass c) +{ + return c == float_class_qnan; +} + /* * Structure holding all of the decomposed parts of a float. The * exponent is unbiased and the fraction is normalized. All @@ -232,8 +227,10 @@ typedef struct { * frac_shift: shift to normalise the fraction with DECOMPOSED_BINARY_POINT * The following are computed based the size of fraction * frac_lsb: least significant bit of fraction - * fram_lsbm1: the bit bellow the least significant bit (for rounding) + * frac_lsbm1: the bit below the least significant bit (for rounding) * round_mask/roundeven_mask: masks used for rounding + * The following optional modifiers are available: + * arm_althp: handle ARM Alternative Half Precision */ typedef struct { int exp_size; @@ -245,6 +242,7 @@ typedef struct { uint64_t frac_lsbm1; uint64_t round_mask; uint64_t roundeven_mask; + bool arm_althp; } FloatFmt; /* Expand fields based on the size of exponent and fraction */ @@ -263,6 +261,11 @@ static const FloatFmt float16_params = { FLOAT_PARAMS(5, 10) }; +static const FloatFmt float16_params_ahp = { + FLOAT_PARAMS(5, 10), + .arm_althp = true +}; + static const FloatFmt float32_params = { FLOAT_PARAMS(8, 23) }; @@ -322,24 +325,27 @@ static inline float64 float64_pack_raw(FloatParts p) return make_float64(pack_raw(float64_params, p)); } +/*---------------------------------------------------------------------------- +| Functions and definitions to determine: (1) whether tininess for underflow +| is detected before or after rounding by default, (2) what (if anything) +| happens when exceptions are raised, (3) how signaling NaNs are distinguished +| from quiet NaNs, (4) the default generated quiet NaNs, and (5) how NaNs +| are propagated from function inputs to output. These details are target- +| specific. +*----------------------------------------------------------------------------*/ +#include "softfloat-specialize.h" + /* Canonicalize EXP and FRAC, setting CLS. */ static FloatParts canonicalize(FloatParts part, const FloatFmt *parm, float_status *status) { - if (part.exp == parm->exp_max) { + if (part.exp == parm->exp_max && !parm->arm_althp) { if (part.frac == 0) { part.cls = float_class_inf; } else { -#ifdef NO_SIGNALING_NANS - part.cls = float_class_qnan; -#else - int64_t msb = part.frac << (parm->frac_shift + 2); - if ((msb < 0) == status->snan_bit_is_one) { - part.cls = float_class_snan; - } else { - part.cls = float_class_qnan; - } -#endif + part.frac <<= parm->frac_shift; + part.cls = (parts_is_snan_frac(part.frac, status) + ? float_class_snan : float_class_qnan); } } else if (part.exp == 0) { if (likely(part.frac == 0)) { @@ -422,7 +428,15 @@ static FloatParts round_canonical(FloatParts p, float_status *s, } frac >>= frac_shift; - if (unlikely(exp >= exp_max)) { + if (parm->arm_althp) { + /* ARM Alt HP eschews Inf and NaN for a wider exponent. */ + if (unlikely(exp > exp_max)) { + /* Overflow. Return the maximum normal. */ + flags = float_flag_invalid; + exp = exp_max; + frac = -1; + } + } else if (unlikely(exp >= exp_max)) { flags |= float_flag_overflow | float_flag_inexact; if (overflow_norm) { exp = exp_max - 1; @@ -473,13 +487,16 @@ static FloatParts round_canonical(FloatParts p, float_status *s, case float_class_inf: do_inf: + assert(!parm->arm_althp); exp = exp_max; frac = 0; break; case float_class_qnan: case float_class_snan: + assert(!parm->arm_althp); exp = exp_max; + frac >>= parm->frac_shift; break; default: @@ -492,22 +509,27 @@ static FloatParts round_canonical(FloatParts p, float_status *s, return p; } +/* Explicit FloatFmt version */ +static FloatParts float16a_unpack_canonical(float16 f, float_status *s, + const FloatFmt *params) +{ + return canonicalize(float16_unpack_raw(f), params, s); +} + static FloatParts float16_unpack_canonical(float16 f, float_status *s) { - return canonicalize(float16_unpack_raw(f), &float16_params, s); + return float16a_unpack_canonical(f, s, &float16_params); +} + +static float16 float16a_round_pack_canonical(FloatParts p, float_status *s, + const FloatFmt *params) +{ + return float16_pack_raw(round_canonical(p, s, params)); } static float16 float16_round_pack_canonical(FloatParts p, float_status *s) { - switch (p.cls) { - case float_class_dnan: - return float16_default_nan(s); - case float_class_msnan: - return float16_maybe_silence_nan(float16_pack_raw(p), s); - default: - p = round_canonical(p, s, &float16_params); - return float16_pack_raw(p); - } + return float16a_round_pack_canonical(p, s, &float16_params); } static FloatParts float32_unpack_canonical(float32 f, float_status *s) @@ -517,15 +539,7 @@ static FloatParts float32_unpack_canonical(float32 f, float_status *s) static float32 float32_round_pack_canonical(FloatParts p, float_status *s) { - switch (p.cls) { - case float_class_dnan: - return float32_default_nan(s); - case float_class_msnan: - return float32_maybe_silence_nan(float32_pack_raw(p), s); - default: - p = round_canonical(p, s, &float32_params); - return float32_pack_raw(p); - } + return float32_pack_raw(round_canonical(p, s, &float32_params)); } static FloatParts float64_unpack_canonical(float64 f, float_status *s) @@ -535,29 +549,7 @@ static FloatParts float64_unpack_canonical(float64 f, float_status *s) static float64 float64_round_pack_canonical(FloatParts p, float_status *s) { - switch (p.cls) { - case float_class_dnan: - return float64_default_nan(s); - case float_class_msnan: - return float64_maybe_silence_nan(float64_pack_raw(p), s); - default: - p = round_canonical(p, s, &float64_params); - return float64_pack_raw(p); - } -} - -/* Simple helpers for checking if what NaN we have */ -static bool is_nan(FloatClass c) -{ - return unlikely(c >= float_class_qnan); -} -static bool is_snan(FloatClass c) -{ - return c == float_class_snan; -} -static bool is_qnan(FloatClass c) -{ - return c == float_class_qnan; + return float64_pack_raw(round_canonical(p, s, &float64_params)); } static FloatParts return_nan(FloatParts a, float_status *s) @@ -565,11 +557,11 @@ static FloatParts return_nan(FloatParts a, float_status *s) switch (a.cls) { case float_class_snan: s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_msnan; + a = parts_silence_nan(a, s); /* fall through */ case float_class_qnan: if (s->default_nan_mode) { - a.cls = float_class_dnan; + return parts_default_nan(s); } break; @@ -586,15 +578,16 @@ static FloatParts pick_nan(FloatParts a, FloatParts b, float_status *s) } if (s->default_nan_mode) { - a.cls = float_class_dnan; + return parts_default_nan(s); } else { - if (pickNaN(is_qnan(a.cls), is_snan(a.cls), - is_qnan(b.cls), is_snan(b.cls), + if (pickNaN(a.cls, b.cls, a.frac > b.frac || (a.frac == b.frac && a.sign < b.sign))) { a = b; } - a.cls = float_class_msnan; + if (is_snan(a.cls)) { + return parts_silence_nan(a, s); + } } return a; } @@ -608,17 +601,13 @@ static FloatParts pick_nan_muladd(FloatParts a, FloatParts b, FloatParts c, s->float_exception_flags |= float_flag_invalid; } - which = pickNaNMulAdd(is_qnan(a.cls), is_snan(a.cls), - is_qnan(b.cls), is_snan(b.cls), - is_qnan(c.cls), is_snan(c.cls), - inf_zero, s); + which = pickNaNMulAdd(a.cls, b.cls, c.cls, inf_zero, s); if (s->default_nan_mode) { /* Note that this check is after pickNaNMulAdd so that function * has an opportunity to set the Invalid flag. */ - a.cls = float_class_dnan; - return a; + which = 3; } switch (which) { @@ -631,13 +620,14 @@ static FloatParts pick_nan_muladd(FloatParts a, FloatParts b, FloatParts c, a = c; break; case 3: - a.cls = float_class_dnan; - return a; + return parts_default_nan(s); default: g_assert_not_reached(); } - a.cls = float_class_msnan; + if (is_snan(a.cls)) { + return parts_silence_nan(a, s); + } return a; } @@ -685,7 +675,7 @@ static FloatParts addsub_floats(FloatParts a, FloatParts b, bool subtract, if (a.cls == float_class_inf) { if (b.cls == float_class_inf) { float_raise(float_flag_invalid, s); - a.cls = float_class_dnan; + return parts_default_nan(s); } return a; } @@ -831,9 +821,7 @@ static FloatParts mul_floats(FloatParts a, FloatParts b, float_status *s) if ((a.cls == float_class_inf && b.cls == float_class_zero) || (a.cls == float_class_zero && b.cls == float_class_inf)) { s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_dnan; - a.sign = sign; - return a; + return parts_default_nan(s); } /* Multiply by 0 or Inf */ if (a.cls == float_class_inf || a.cls == float_class_zero) { @@ -911,8 +899,7 @@ static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, if (inf_zero) { s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_dnan; - return a; + return parts_default_nan(s); } if (flags & float_muladd_negate_c) { @@ -936,12 +923,12 @@ static FloatParts muladd_floats(FloatParts a, FloatParts b, FloatParts c, if (c.cls == float_class_inf) { if (p_class == float_class_inf && p_sign != c.sign) { s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_dnan; + return parts_default_nan(s); } else { a.cls = float_class_inf; a.sign = c.sign ^ sign_flip; + return a; } - return a; } if (p_class == float_class_inf) { @@ -1151,8 +1138,7 @@ static FloatParts div_floats(FloatParts a, FloatParts b, float_status *s) && (a.cls == float_class_inf || a.cls == float_class_zero)) { s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_dnan; - return a; + return parts_default_nan(s); } /* Inf / x or 0 / x */ if (a.cls == float_class_inf || a.cls == float_class_zero) { @@ -1203,6 +1189,104 @@ float64 float64_div(float64 a, float64 b, float_status *status) } /* + * Float to Float conversions + * + * Returns the result of converting one float format to another. The + * conversion is performed according to the IEC/IEEE Standard for + * Binary Floating-Point Arithmetic. + * + * The float_to_float helper only needs to take care of raising + * invalid exceptions and handling the conversion on NaNs. + */ + +static FloatParts float_to_float(FloatParts a, const FloatFmt *dstf, + float_status *s) +{ + if (dstf->arm_althp) { + switch (a.cls) { + case float_class_qnan: + case float_class_snan: + /* There is no NaN in the destination format. Raise Invalid + * and return a zero with the sign of the input NaN. + */ + s->float_exception_flags |= float_flag_invalid; + a.cls = float_class_zero; + a.frac = 0; + a.exp = 0; + break; + + case float_class_inf: + /* There is no Inf in the destination format. Raise Invalid + * and return the maximum normal with the correct sign. + */ + s->float_exception_flags |= float_flag_invalid; + a.cls = float_class_normal; + a.exp = dstf->exp_max; + a.frac = ((1ull << dstf->frac_size) - 1) << dstf->frac_shift; + break; + + default: + break; + } + } else if (is_nan(a.cls)) { + if (is_snan(a.cls)) { + s->float_exception_flags |= float_flag_invalid; + a = parts_silence_nan(a, s); + } + if (s->default_nan_mode) { + return parts_default_nan(s); + } + } + return a; +} + +float32 float16_to_float32(float16 a, bool ieee, float_status *s) +{ + const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; + FloatParts p = float16a_unpack_canonical(a, s, fmt16); + FloatParts pr = float_to_float(p, &float32_params, s); + return float32_round_pack_canonical(pr, s); +} + +float64 float16_to_float64(float16 a, bool ieee, float_status *s) +{ + const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; + FloatParts p = float16a_unpack_canonical(a, s, fmt16); + FloatParts pr = float_to_float(p, &float64_params, s); + return float64_round_pack_canonical(pr, s); +} + +float16 float32_to_float16(float32 a, bool ieee, float_status *s) +{ + const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; + FloatParts p = float32_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, fmt16, s); + return float16a_round_pack_canonical(pr, s, fmt16); +} + +float64 float32_to_float64(float32 a, float_status *s) +{ + FloatParts p = float32_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &float64_params, s); + return float64_round_pack_canonical(pr, s); +} + +float16 float64_to_float16(float64 a, bool ieee, float_status *s) +{ + const FloatFmt *fmt16 = ieee ? &float16_params : &float16_params_ahp; + FloatParts p = float64_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, fmt16, s); + return float16a_round_pack_canonical(pr, s, fmt16); +} + +float32 float64_to_float32(float64 a, float_status *s) +{ + FloatParts p = float64_unpack_canonical(a, s); + FloatParts pr = float_to_float(p, &float32_params, s); + return float32_round_pack_canonical(pr, s); +} + +/* * Rounds the floating-point value `a' to an integer, and returns the * result as a floating-point value. The operation is performed * according to the IEC/IEEE Standard for Binary Floating-Point @@ -1350,8 +1434,6 @@ static int64_t round_to_int_and_pack(FloatParts in, int rmode, switch (p.cls) { case float_class_snan: case float_class_qnan: - case float_class_dnan: - case float_class_msnan: s->float_exception_flags = orig_flags | float_flag_invalid; return max; case float_class_inf: @@ -1442,8 +1524,6 @@ static uint64_t round_to_uint_and_pack(FloatParts in, int rmode, uint64_t max, switch (p.cls) { case float_class_snan: case float_class_qnan: - case float_class_dnan: - case float_class_msnan: s->float_exception_flags = orig_flags | float_flag_invalid; return max; case float_class_inf: @@ -1943,8 +2023,7 @@ static FloatParts sqrt_float(FloatParts a, float_status *s, const FloatFmt *p) } if (a.sign) { s->float_exception_flags |= float_flag_invalid; - a.cls = float_class_dnan; - return a; + return parts_default_nan(s); } if (a.cls == float_class_inf) { return a; /* sqrt(+inf) = +inf */ @@ -2013,6 +2092,78 @@ float64 __attribute__((flatten)) float64_sqrt(float64 a, float_status *status) return float64_round_pack_canonical(pr, status); } +/*---------------------------------------------------------------------------- +| The pattern for a default generated NaN. +*----------------------------------------------------------------------------*/ + +float16 float16_default_nan(float_status *status) +{ + FloatParts p = parts_default_nan(status); + p.frac >>= float16_params.frac_shift; + return float16_pack_raw(p); +} + +float32 float32_default_nan(float_status *status) +{ + FloatParts p = parts_default_nan(status); + p.frac >>= float32_params.frac_shift; + return float32_pack_raw(p); +} + +float64 float64_default_nan(float_status *status) +{ + FloatParts p = parts_default_nan(status); + p.frac >>= float64_params.frac_shift; + return float64_pack_raw(p); +} + +float128 float128_default_nan(float_status *status) +{ + FloatParts p = parts_default_nan(status); + float128 r; + + /* Extrapolate from the choices made by parts_default_nan to fill + * in the quad-floating format. If the low bit is set, assume we + * want to set all non-snan bits. + */ + r.low = -(p.frac & 1); + r.high = p.frac >> (DECOMPOSED_BINARY_POINT - 48); + r.high |= LIT64(0x7FFF000000000000); + r.high |= (uint64_t)p.sign << 63; + + return r; +} + +/*---------------------------------------------------------------------------- +| Returns a quiet NaN from a signalling NaN for the floating point value `a'. +*----------------------------------------------------------------------------*/ + +float16 float16_silence_nan(float16 a, float_status *status) +{ + FloatParts p = float16_unpack_raw(a); + p.frac <<= float16_params.frac_shift; + p = parts_silence_nan(p, status); + p.frac >>= float16_params.frac_shift; + return float16_pack_raw(p); +} + +float32 float32_silence_nan(float32 a, float_status *status) +{ + FloatParts p = float32_unpack_raw(a); + p.frac <<= float32_params.frac_shift; + p = parts_silence_nan(p, status); + p.frac >>= float32_params.frac_shift; + return float32_pack_raw(p); +} + +float64 float64_silence_nan(float64 a, float_status *status) +{ + FloatParts p = float64_unpack_raw(a); + p.frac <<= float64_params.frac_shift; + p = parts_silence_nan(p, status); + p.frac >>= float64_params.frac_shift; + return float64_pack_raw(p); +} /*---------------------------------------------------------------------------- | Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 @@ -3147,42 +3298,7 @@ float128 uint64_to_float128(uint64_t a, float_status *status) if (a == 0) { return float128_zero; } - return normalizeRoundAndPackFloat128(0, 0x406E, a, 0, status); -} - - - - -/*---------------------------------------------------------------------------- -| Returns the result of converting the single-precision floating-point value -| `a' to the double-precision floating-point format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 float32_to_float64(float32 a, float_status *status) -{ - flag aSign; - int aExp; - uint32_t aSig; - a = float32_squash_input_denormal(a, status); - - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - if ( aExp == 0xFF ) { - if (aSig) { - return commonNaNToFloat64(float32ToCommonNaN(a, status), status); - } - return packFloat64( aSign, 0x7FF, 0 ); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return packFloat64( aSign, 0, 0 ); - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - --aExp; - } - return packFloat64( aSign, aExp + 0x380, ( (uint64_t) aSig )<<29 ); - + return normalizeRoundAndPackFloat128(0, 0x406E, 0, a, status); } /*---------------------------------------------------------------------------- @@ -3703,173 +3819,6 @@ int float32_unordered_quiet(float32 a, float32 b, float_status *status) return 0; } - -/*---------------------------------------------------------------------------- -| Returns the result of converting the double-precision floating-point value -| `a' to the single-precision floating-point format. The conversion is -| performed according to the IEC/IEEE Standard for Binary Floating-Point -| Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 float64_to_float32(float64 a, float_status *status) -{ - flag aSign; - int aExp; - uint64_t aSig; - uint32_t zSig; - a = float64_squash_input_denormal(a, status); - - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - if ( aExp == 0x7FF ) { - if (aSig) { - return commonNaNToFloat32(float64ToCommonNaN(a, status), status); - } - return packFloat32( aSign, 0xFF, 0 ); - } - shift64RightJamming( aSig, 22, &aSig ); - zSig = aSig; - if ( aExp || zSig ) { - zSig |= 0x40000000; - aExp -= 0x381; - } - return roundAndPackFloat32(aSign, aExp, zSig, status); - -} - - -/*---------------------------------------------------------------------------- -| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a -| half-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 float16 packFloat16(flag zSign, int zExp, uint16_t zSig) -{ - return make_float16( - (((uint32_t)zSign) << 15) + (((uint32_t)zExp) << 10) + zSig); -} - -/*---------------------------------------------------------------------------- -| Takes an abstract floating-point value having sign `zSign', exponent `zExp', -| and significand `zSig', and returns the proper half-precision floating- -| point value corresponding to the abstract input. Ordinarily, the abstract -| value is simply rounded and packed into the half-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 half- -| precision floating-point number. -| The `ieee' flag indicates whether to use IEEE standard half precision, or -| ARM-style "alternative representation", which omits the NaN and Inf -| encodings in order to raise the maximum representable exponent by one. -| The input significand `zSig' has its binary point between bits 22 -| and 23, which is 13 bits to the left of the usual location. This shifted -| significand must be normalized or smaller. If `zSig' is not normalized, -| `zExp' must be 0; in that case, the result returned is a subnormal number, -| and it must not require rounding. In the usual case that `zSig' is -| normalized, `zExp' must be 1 less than the ``true'' floating-point exponent. -| Note the slightly odd position of the binary point in zSig compared with the -| other roundAndPackFloat functions. This should probably be fixed if we -| need to implement more float16 routines than just conversion. -| The handling of underflow and overflow follows the IEC/IEEE Standard for -| Binary Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -static float16 roundAndPackFloat16(flag zSign, int zExp, - uint32_t zSig, flag ieee, - float_status *status) -{ - int maxexp = ieee ? 29 : 30; - uint32_t mask; - uint32_t increment; - bool rounding_bumps_exp; - bool is_tiny = false; - - /* Calculate the mask of bits of the mantissa which are not - * representable in half-precision and will be lost. - */ - if (zExp < 1) { - /* Will be denormal in halfprec */ - mask = 0x00ffffff; - if (zExp >= -11) { - mask >>= 11 + zExp; - } - } else { - /* Normal number in halfprec */ - mask = 0x00001fff; - } - - switch (status->float_rounding_mode) { - case float_round_nearest_even: - increment = (mask + 1) >> 1; - if ((zSig & mask) == increment) { - increment = zSig & (increment << 1); - } - break; - case float_round_ties_away: - increment = (mask + 1) >> 1; - break; - case float_round_up: - increment = zSign ? 0 : mask; - break; - case float_round_down: - increment = zSign ? mask : 0; - break; - default: /* round_to_zero */ - increment = 0; - break; - } - - rounding_bumps_exp = (zSig + increment >= 0x01000000); - - if (zExp > maxexp || (zExp == maxexp && rounding_bumps_exp)) { - if (ieee) { - float_raise(float_flag_overflow | float_flag_inexact, status); - return packFloat16(zSign, 0x1f, 0); - } else { - float_raise(float_flag_invalid, status); - return packFloat16(zSign, 0x1f, 0x3ff); - } - } - - if (zExp < 0) { - /* Note that flush-to-zero does not affect half-precision results */ - is_tiny = - (status->float_detect_tininess == float_tininess_before_rounding) - || (zExp < -1) - || (!rounding_bumps_exp); - } - if (zSig & mask) { - float_raise(float_flag_inexact, status); - if (is_tiny) { - float_raise(float_flag_underflow, status); - } - } - - zSig += increment; - if (rounding_bumps_exp) { - zSig >>= 1; - zExp++; - } - - if (zExp < -10) { - return packFloat16(zSign, 0, 0); - } - if (zExp < 0) { - zSig >>= -zExp; - zExp = 0; - } - return packFloat16(zSign, zExp, zSig >> 13); -} - /*---------------------------------------------------------------------------- | If `a' is denormal and we are in flush-to-zero mode then set the | input-denormal exception and return zero. Otherwise just return the value. @@ -3885,163 +3834,6 @@ float16 float16_squash_input_denormal(float16 a, float_status *status) return a; } -static void normalizeFloat16Subnormal(uint32_t aSig, int *zExpPtr, - uint32_t *zSigPtr) -{ - int8_t shiftCount = countLeadingZeros32(aSig) - 21; - *zSigPtr = aSig << shiftCount; - *zExpPtr = 1 - shiftCount; -} - -/* Half precision floats come in two formats: standard IEEE and "ARM" format. - The latter gains extra exponent range by omitting the NaN/Inf encodings. */ - -float32 float16_to_float32(float16 a, flag ieee, float_status *status) -{ - flag aSign; - int aExp; - uint32_t aSig; - - aSign = extractFloat16Sign(a); - aExp = extractFloat16Exp(a); - aSig = extractFloat16Frac(a); - - if (aExp == 0x1f && ieee) { - if (aSig) { - return commonNaNToFloat32(float16ToCommonNaN(a, status), status); - } - return packFloat32(aSign, 0xff, 0); - } - if (aExp == 0) { - if (aSig == 0) { - return packFloat32(aSign, 0, 0); - } - - normalizeFloat16Subnormal(aSig, &aExp, &aSig); - aExp--; - } - return packFloat32( aSign, aExp + 0x70, aSig << 13); -} - -float16 float32_to_float16(float32 a, flag ieee, float_status *status) -{ - flag aSign; - int aExp; - uint32_t aSig; - - a = float32_squash_input_denormal(a, status); - - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - if ( aExp == 0xFF ) { - if (aSig) { - /* Input is a NaN */ - if (!ieee) { - float_raise(float_flag_invalid, status); - return packFloat16(aSign, 0, 0); - } - return commonNaNToFloat16( - float32ToCommonNaN(a, status), status); - } - /* Infinity */ - if (!ieee) { - float_raise(float_flag_invalid, status); - return packFloat16(aSign, 0x1f, 0x3ff); - } - return packFloat16(aSign, 0x1f, 0); - } - if (aExp == 0 && aSig == 0) { - return packFloat16(aSign, 0, 0); - } - /* Decimal point between bits 22 and 23. Note that we add the 1 bit - * even if the input is denormal; however this is harmless because - * the largest possible single-precision denormal is still smaller - * than the smallest representable half-precision denormal, and so we - * will end up ignoring aSig and returning via the "always return zero" - * codepath. - */ - aSig |= 0x00800000; - aExp -= 0x71; - - return roundAndPackFloat16(aSign, aExp, aSig, ieee, status); -} - -float64 float16_to_float64(float16 a, flag ieee, float_status *status) -{ - flag aSign; - int aExp; - uint32_t aSig; - - aSign = extractFloat16Sign(a); - aExp = extractFloat16Exp(a); - aSig = extractFloat16Frac(a); - - if (aExp == 0x1f && ieee) { - if (aSig) { - return commonNaNToFloat64( - float16ToCommonNaN(a, status), status); - } - return packFloat64(aSign, 0x7ff, 0); - } - if (aExp == 0) { - if (aSig == 0) { - return packFloat64(aSign, 0, 0); - } - - normalizeFloat16Subnormal(aSig, &aExp, &aSig); - aExp--; - } - return packFloat64(aSign, aExp + 0x3f0, ((uint64_t)aSig) << 42); -} - -float16 float64_to_float16(float64 a, flag ieee, float_status *status) -{ - flag aSign; - int aExp; - uint64_t aSig; - uint32_t zSig; - - a = float64_squash_input_denormal(a, status); - - aSig = extractFloat64Frac(a); - aExp = extractFloat64Exp(a); - aSign = extractFloat64Sign(a); - if (aExp == 0x7FF) { - if (aSig) { - /* Input is a NaN */ - if (!ieee) { - float_raise(float_flag_invalid, status); - return packFloat16(aSign, 0, 0); - } - return commonNaNToFloat16( - float64ToCommonNaN(a, status), status); - } - /* Infinity */ - if (!ieee) { - float_raise(float_flag_invalid, status); - return packFloat16(aSign, 0x1f, 0x3ff); - } - return packFloat16(aSign, 0x1f, 0); - } - shift64RightJamming(aSig, 29, &aSig); - zSig = aSig; - if (aExp == 0 && zSig == 0) { - return packFloat16(aSign, 0, 0); - } - /* Decimal point between bits 22 and 23. Note that we add the 1 bit - * even if the input is denormal; however this is harmless because - * the largest possible single-precision denormal is still smaller - * than the smallest representable half-precision denormal, and so we - * will end up ignoring aSig and returning via the "always return zero" - * codepath. - */ - zSig |= 0x00800000; - aExp -= 0x3F1; - - return roundAndPackFloat16(aSign, aExp, zSig, ieee, status); -} - /*---------------------------------------------------------------------------- | Returns the result of converting the double-precision floating-point value | `a' to the extended double-precision floating-point format. The conversion diff --git a/hw/display/Makefile.objs b/hw/display/Makefile.objs index 3c7c75b..11321e4 100644 --- a/hw/display/Makefile.objs +++ b/hw/display/Makefile.objs @@ -20,6 +20,8 @@ common-obj-$(CONFIG_MILKYMIST) += milkymist-vgafb.o common-obj-$(CONFIG_ZAURUS) += tc6393xb.o common-obj-$(CONFIG_MILKYMIST_TMU2) += milkymist-tmu2.o +milkymist-tmu2.o-cflags := $(X11_CFLAGS) +milkymist-tmu2.o-libs := $(X11_LIBS) obj-$(CONFIG_OMAP) += omap_dss.o obj-$(CONFIG_OMAP) += omap_lcdc.o diff --git a/hw/usb/ccid-card-passthru.c b/hw/usb/ccid-card-passthru.c index 7684db0..25fb19b 100644 --- a/hw/usb/ccid-card-passthru.c +++ b/hw/usb/ccid-card-passthru.c @@ -345,7 +345,7 @@ static void passthru_realize(CCIDCardState *base, Error **errp) card->vscard_in_pos = 0; card->vscard_in_hdr = 0; if (qemu_chr_fe_backend_connected(&card->cs)) { - error_setg(errp, "ccid-card-passthru: initing chardev"); + DPRINTF(card, D_INFO, "ccid-card-passthru: initing chardev"); qemu_chr_fe_set_handlers(&card->cs, ccid_card_vscard_can_read, ccid_card_vscard_read, diff --git a/hw/usb/dev-smartcard-reader.c b/hw/usb/dev-smartcard-reader.c index cabb564..f745192 100644 --- a/hw/usb/dev-smartcard-reader.c +++ b/hw/usb/dev-smartcard-reader.c @@ -1064,7 +1064,8 @@ err: return; } -static void ccid_bulk_in_copy_to_guest(USBCCIDState *s, USBPacket *p) +static void ccid_bulk_in_copy_to_guest(USBCCIDState *s, USBPacket *p, + unsigned int max_packet_size) { int len = 0; @@ -1072,10 +1073,13 @@ static void ccid_bulk_in_copy_to_guest(USBCCIDState *s, USBPacket *p) if (s->current_bulk_in != NULL) { len = MIN(s->current_bulk_in->len - s->current_bulk_in->pos, p->iov.size); - usb_packet_copy(p, s->current_bulk_in->data + - s->current_bulk_in->pos, len); + if (len) { + usb_packet_copy(p, s->current_bulk_in->data + + s->current_bulk_in->pos, len); + } s->current_bulk_in->pos += len; - if (s->current_bulk_in->pos == s->current_bulk_in->len) { + if (s->current_bulk_in->pos == s->current_bulk_in->len + && len != max_packet_size) { ccid_bulk_in_release(s); } } else { @@ -1107,7 +1111,7 @@ static void ccid_handle_data(USBDevice *dev, USBPacket *p) case USB_TOKEN_IN: switch (p->ep->nr) { case CCID_BULK_IN_EP: - ccid_bulk_in_copy_to_guest(s, p); + ccid_bulk_in_copy_to_guest(s, p, dev->ep_ctl.max_packet_size); break; case CCID_INT_IN_EP: if (s->notify_slot_change) { diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index 4e378cb..2aae6a8 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -173,6 +173,7 @@ typedef struct float_status { /* should denormalised inputs go to zero and set the input_denormal flag? */ flag flush_inputs_to_zero; flag default_nan_mode; + /* not always used -- see snan_bit_is_one() in softfloat-specialize.h */ flag snan_bit_is_one; } float_status; diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index 36626a5..69f4dbc 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -211,10 +211,10 @@ float128 uint64_to_float128(uint64_t, float_status *status); /*---------------------------------------------------------------------------- | Software half-precision conversion routines. *----------------------------------------------------------------------------*/ -float16 float32_to_float16(float32, flag, float_status *status); -float32 float16_to_float32(float16, flag, float_status *status); -float16 float64_to_float16(float64 a, flag ieee, float_status *status); -float64 float16_to_float64(float16 a, flag ieee, float_status *status); +float16 float32_to_float16(float32, bool ieee, float_status *status); +float32 float16_to_float32(float16, bool ieee, float_status *status); +float16 float64_to_float16(float64 a, bool ieee, float_status *status); +float64 float16_to_float64(float16 a, bool ieee, float_status *status); int16_t float16_to_int16(float16, float_status *status); uint16_t float16_to_uint16(float16 a, float_status *status); int16_t float16_to_int16_round_to_zero(float16, float_status *status); @@ -257,7 +257,7 @@ int float16_compare_quiet(float16, float16, float_status *status); int float16_is_quiet_nan(float16, float_status *status); int float16_is_signaling_nan(float16, float_status *status); -float16 float16_maybe_silence_nan(float16, float_status *status); +float16 float16_silence_nan(float16, float_status *status); static inline int float16_is_any_nan(float16 a) { @@ -368,7 +368,7 @@ float32 float32_minnummag(float32, float32, float_status *status); float32 float32_maxnummag(float32, float32, float_status *status); int float32_is_quiet_nan(float32, float_status *status); int float32_is_signaling_nan(float32, float_status *status); -float32 float32_maybe_silence_nan(float32, float_status *status); +float32 float32_silence_nan(float32, float_status *status); float32 float32_scalbn(float32, int, float_status *status); static inline float32 float32_abs(float32 a) @@ -497,7 +497,7 @@ float64 float64_minnummag(float64, float64, float_status *status); float64 float64_maxnummag(float64, float64, float_status *status); int float64_is_quiet_nan(float64 a, float_status *status); int float64_is_signaling_nan(float64, float_status *status); -float64 float64_maybe_silence_nan(float64, float_status *status); +float64 float64_silence_nan(float64, float_status *status); float64 float64_scalbn(float64, int, float_status *status); static inline float64 float64_abs(float64 a) @@ -600,7 +600,7 @@ int floatx80_compare(floatx80, floatx80, float_status *status); int floatx80_compare_quiet(floatx80, floatx80, float_status *status); int floatx80_is_quiet_nan(floatx80, float_status *status); int floatx80_is_signaling_nan(floatx80, float_status *status); -floatx80 floatx80_maybe_silence_nan(floatx80, float_status *status); +floatx80 floatx80_silence_nan(floatx80, float_status *status); floatx80 floatx80_scalbn(floatx80, int, float_status *status); static inline floatx80 floatx80_abs(floatx80 a) @@ -811,7 +811,7 @@ int float128_compare(float128, float128, float_status *status); int float128_compare_quiet(float128, float128, float_status *status); int float128_is_quiet_nan(float128, float_status *status); int float128_is_signaling_nan(float128, float_status *status); -float128 float128_maybe_silence_nan(float128, float_status *status); +float128 float128_silence_nan(float128, float_status *status); float128 float128_scalbn(float128, int, float_status *status); static inline float128 float128_abs(float128 a) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index 4f8034c..f92bdea 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -376,7 +376,7 @@ float16 HELPER(frecpx_f16)(float16 a, void *fpstp) float16 nan = a; if (float16_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_maybe_silence_nan(a, fpst); + nan = float16_silence_nan(a, fpst); } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -405,7 +405,7 @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) float32 nan = a; if (float32_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_maybe_silence_nan(a, fpst); + nan = float32_silence_nan(a, fpst); } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -434,7 +434,7 @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) float64 nan = a; if (float64_is_signaling_nan(a, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_maybe_silence_nan(a, fpst); + nan = float64_silence_nan(a, fpst); } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); @@ -466,7 +466,6 @@ float32 HELPER(fcvtx_f64_to_f32)(float64 a, CPUARMState *env) set_float_rounding_mode(float_round_to_zero, &tstat); set_float_exception_flags(0, &tstat); r = float64_to_float32(a, &tstat); - r = float32_maybe_silence_nan(r, &tstat); exflags = get_float_exception_flags(&tstat); if (exflags & float_flag_inexact) { r = make_float32(float32_val(r) | 1); diff --git a/target/arm/helper.c b/target/arm/helper.c index c6fd7f9..db8bbe5 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -11348,20 +11348,12 @@ FLOAT_CONVS(ui, d, 64, u) /* floating point conversion */ float64 VFP_HELPER(fcvtd, s)(float32 x, CPUARMState *env) { - float64 r = float32_to_float64(x, &env->vfp.fp_status); - /* ARM requires that S<->D conversion of any kind of NaN generates - * a quiet NaN by forcing the most significant frac bit to 1. - */ - return float64_maybe_silence_nan(r, &env->vfp.fp_status); + return float32_to_float64(x, &env->vfp.fp_status); } float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) { - float32 r = float64_to_float32(x, &env->vfp.fp_status); - /* ARM requires that S<->D conversion of any kind of NaN generates - * a quiet NaN by forcing the most significant frac bit to 1. - */ - return float32_maybe_silence_nan(r, &env->vfp.fp_status); + return float64_to_float32(x, &env->vfp.fp_status); } /* VFP3 fixed point conversion. */ @@ -11540,64 +11532,56 @@ uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) } /* Half precision conversions. */ -static float32 do_fcvt_f16_to_f32(uint32_t a, CPUARMState *env, float_status *s) +float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float32 r = float16_to_float32(make_float16(a), ieee, s); - if (ieee) { - return float32_maybe_silence_nan(r, s); - } + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing input denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_inputs_to_zero(fpst); + set_flush_inputs_to_zero(false, fpst); + float32 r = float16_to_float32(a, !ahp_mode, fpst); + set_flush_inputs_to_zero(save, fpst); return r; } -static uint32_t do_fcvt_f32_to_f16(float32 a, CPUARMState *env, float_status *s) -{ - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float16 r = float32_to_float16(a, ieee, s); - if (ieee) { - r = float16_maybe_silence_nan(r, s); - } - return float16_val(r); -} - -float32 HELPER(neon_fcvt_f16_to_f32)(uint32_t a, CPUARMState *env) -{ - return do_fcvt_f16_to_f32(a, env, &env->vfp.standard_fp_status); -} - -uint32_t HELPER(neon_fcvt_f32_to_f16)(float32 a, CPUARMState *env) -{ - return do_fcvt_f32_to_f16(a, env, &env->vfp.standard_fp_status); -} - -float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, CPUARMState *env) -{ - return do_fcvt_f16_to_f32(a, env, &env->vfp.fp_status); -} - -uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, CPUARMState *env) +float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) { - return do_fcvt_f32_to_f16(a, env, &env->vfp.fp_status); + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing output denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_to_zero(fpst); + set_flush_to_zero(false, fpst); + float16 r = float32_to_float16(a, !ahp_mode, fpst); + set_flush_to_zero(save, fpst); + return r; } -float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, CPUARMState *env) +float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float64 r = float16_to_float64(make_float16(a), ieee, &env->vfp.fp_status); - if (ieee) { - return float64_maybe_silence_nan(r, &env->vfp.fp_status); - } + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing input denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_inputs_to_zero(fpst); + set_flush_inputs_to_zero(false, fpst); + float64 r = float16_to_float64(a, !ahp_mode, fpst); + set_flush_inputs_to_zero(save, fpst); return r; } -uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, CPUARMState *env) +float16 HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) { - int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0; - float16 r = float64_to_float16(a, ieee, &env->vfp.fp_status); - if (ieee) { - r = float16_maybe_silence_nan(r, &env->vfp.fp_status); - } - return float16_val(r); + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing output denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_to_zero(fpst); + set_flush_to_zero(false, fpst); + float16 r = float64_to_float16(a, !ahp_mode, fpst); + set_flush_to_zero(save, fpst); + return r; } #define float32_two make_float32(0x40000000) @@ -11739,7 +11723,7 @@ float16 HELPER(recpe_f16)(float16 input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float16_maybe_silence_nan(f16, fpst); + nan = float16_silence_nan(f16, fpst); } if (fpst->default_nan_mode) { nan = float16_default_nan(fpst); @@ -11787,7 +11771,7 @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float32_maybe_silence_nan(f32, fpst); + nan = float32_silence_nan(f32, fpst); } if (fpst->default_nan_mode) { nan = float32_default_nan(fpst); @@ -11835,7 +11819,7 @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, fpst)) { float_raise(float_flag_invalid, fpst); - nan = float64_maybe_silence_nan(f64, fpst); + nan = float64_silence_nan(f64, fpst); } if (fpst->default_nan_mode) { nan = float64_default_nan(fpst); @@ -11934,7 +11918,7 @@ float16 HELPER(rsqrte_f16)(float16 input, void *fpstp) float16 nan = f16; if (float16_is_signaling_nan(f16, s)) { float_raise(float_flag_invalid, s); - nan = float16_maybe_silence_nan(f16, s); + nan = float16_silence_nan(f16, s); } if (s->default_nan_mode) { nan = float16_default_nan(s); @@ -11978,7 +11962,7 @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) float32 nan = f32; if (float32_is_signaling_nan(f32, s)) { float_raise(float_flag_invalid, s); - nan = float32_maybe_silence_nan(f32, s); + nan = float32_silence_nan(f32, s); } if (s->default_nan_mode) { nan = float32_default_nan(s); @@ -12021,7 +12005,7 @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) float64 nan = f64; if (float64_is_signaling_nan(f64, s)) { float_raise(float_flag_invalid, s); - nan = float64_maybe_silence_nan(f64, s); + nan = float64_silence_nan(f64, s); } if (s->default_nan_mode) { nan = float64_default_nan(s); diff --git a/target/arm/helper.h b/target/arm/helper.h index ce89968..047f3bc 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -187,12 +187,10 @@ DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) -DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env) -DEF_HELPER_2(vfp_fcvt_f32_to_f16, i32, f32, env) -DEF_HELPER_2(neon_fcvt_f16_to_f32, f32, i32, env) -DEF_HELPER_2(neon_fcvt_f32_to_f16, i32, f32, env) -DEF_HELPER_FLAGS_2(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, i32, env) -DEF_HELPER_FLAGS_2(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, i32, f64, env) +DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, f16, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32) DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index a0b0c43..d8284678 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -5147,10 +5147,15 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, } else { /* Single to half */ TCGv_i32 tcg_rd = tcg_temp_new_i32(); - gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, cpu_env); + TCGv_i32 ahp = get_ahp_flag(); + TCGv_ptr fpst = get_fpstatus_ptr(false); + + gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, fpst, ahp); /* write_fp_sreg is OK here because top half of tcg_rd is zero */ write_fp_sreg(s, rd, tcg_rd); tcg_temp_free_i32(tcg_rd); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); } tcg_temp_free_i32(tcg_rn); break; @@ -5163,9 +5168,13 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, /* Double to single */ gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, cpu_env); } else { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); /* Double to half */ - gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, fpst, ahp); /* write_fp_sreg is OK here because top half of tcg_rd is zero */ + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } write_fp_sreg(s, rd, tcg_rd); tcg_temp_free_i32(tcg_rd); @@ -5175,17 +5184,21 @@ static void handle_fp_fcvt(DisasContext *s, int opcode, case 0x3: { TCGv_i32 tcg_rn = read_fp_sreg(s, rn); + TCGv_ptr tcg_fpst = get_fpstatus_ptr(false); + TCGv_i32 tcg_ahp = get_ahp_flag(); tcg_gen_ext16u_i32(tcg_rn, tcg_rn); if (dtype == 0) { /* Half to single */ TCGv_i32 tcg_rd = tcg_temp_new_i32(); - gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); write_fp_sreg(s, rd, tcg_rd); + tcg_temp_free_ptr(tcg_fpst); + tcg_temp_free_i32(tcg_ahp); tcg_temp_free_i32(tcg_rd); } else { /* Half to double */ TCGv_i64 tcg_rd = tcg_temp_new_i64(); - gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, cpu_env); + gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); write_fp_dreg(s, rd, tcg_rd); tcg_temp_free_i64(tcg_rd); } @@ -9053,12 +9066,17 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, } else { TCGv_i32 tcg_lo = tcg_temp_new_i32(); TCGv_i32 tcg_hi = tcg_temp_new_i32(); + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); + tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, tcg_op); - gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, cpu_env); - gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp); + gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp); tcg_gen_deposit_i32(tcg_res[pass], tcg_lo, tcg_hi, 16, 16); tcg_temp_free_i32(tcg_lo); tcg_temp_free_i32(tcg_hi); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } break; case 0x56: /* FCVTXN, FCVTXN2 */ @@ -11532,18 +11550,23 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, /* 16 -> 32 bit fp conversion */ int srcelt = is_q ? 4 : 0; TCGv_i32 tcg_res[4]; + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); for (pass = 0; pass < 4; pass++) { tcg_res[pass] = tcg_temp_new_i32(); read_vec_element_i32(s, tcg_res[pass], rn, srcelt + pass, MO_16); gen_helper_vfp_fcvt_f16_to_f32(tcg_res[pass], tcg_res[pass], - cpu_env); + fpst, ahp); } for (pass = 0; pass < 4; pass++) { write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32); tcg_temp_free_i32(tcg_res[pass]); } + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(ahp); } } diff --git a/target/arm/translate.c b/target/arm/translate.c index 731cf32..46a9725 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -3824,38 +3824,56 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) gen_vfp_sqrt(dp); break; case 4: /* vcvtb.f32.f16, vcvtb.f64.f16 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp_mode = get_ahp_flag(); tmp = gen_vfp_mrs(); tcg_gen_ext16u_i32(tmp, tmp); if (dp) { gen_helper_vfp_fcvt_f16_to_f64(cpu_F0d, tmp, - cpu_env); + fpst, ahp_mode); } else { gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp, - cpu_env); + fpst, ahp_mode); } + tcg_temp_free_i32(ahp_mode); + tcg_temp_free_ptr(fpst); tcg_temp_free_i32(tmp); break; + } case 5: /* vcvtt.f32.f16, vcvtt.f64.f16 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); tmp = gen_vfp_mrs(); tcg_gen_shri_i32(tmp, tmp, 16); if (dp) { gen_helper_vfp_fcvt_f16_to_f64(cpu_F0d, tmp, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp, - cpu_env); + fpst, ahp); } tcg_temp_free_i32(tmp); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); break; + } case 6: /* vcvtb.f16.f32, vcvtb.f16.f64 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); tmp = tcg_temp_new_i32(); + if (dp) { gen_helper_vfp_fcvt_f64_to_f16(tmp, cpu_F0d, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, - cpu_env); + fpst, ahp); } + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); gen_mov_F0_vreg(0, rd); tmp2 = gen_vfp_mrs(); tcg_gen_andi_i32(tmp2, tmp2, 0xffff0000); @@ -3863,15 +3881,21 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp2); gen_vfp_msr(tmp); break; + } case 7: /* vcvtt.f16.f32, vcvtt.f16.f64 */ + { + TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_i32 ahp = get_ahp_flag(); tmp = tcg_temp_new_i32(); if (dp) { gen_helper_vfp_fcvt_f64_to_f16(tmp, cpu_F0d, - cpu_env); + fpst, ahp); } else { gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, - cpu_env); + fpst, ahp); } + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); tcg_gen_shli_i32(tmp, tmp, 16); gen_mov_F0_vreg(0, rd); tmp2 = gen_vfp_mrs(); @@ -3880,6 +3904,7 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp2); gen_vfp_msr(tmp); break; + } case 8: /* cmp */ gen_vfp_cmp(dp); break; @@ -7222,53 +7247,70 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; case NEON_2RM_VCVT_F16_F32: + { + TCGv_ptr fpst; + TCGv_i32 ahp; + if (!arm_dc_feature(s, ARM_FEATURE_VFP_FP16) || q || (rm & 1)) { return 1; } tmp = tcg_temp_new_i32(); tmp2 = tcg_temp_new_i32(); + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 0)); - gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 1)); - gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 2)); - gen_helper_neon_fcvt_f32_to_f16(tmp, cpu_F0s, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 3)); neon_store_reg(rd, 0, tmp2); tmp2 = tcg_temp_new_i32(); - gen_helper_neon_fcvt_f32_to_f16(tmp2, cpu_F0s, cpu_env); + gen_helper_vfp_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); tcg_gen_shli_i32(tmp2, tmp2, 16); tcg_gen_or_i32(tmp2, tmp2, tmp); neon_store_reg(rd, 1, tmp2); tcg_temp_free_i32(tmp); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); break; + } case NEON_2RM_VCVT_F32_F16: + { + TCGv_ptr fpst; + TCGv_i32 ahp; if (!arm_dc_feature(s, ARM_FEATURE_VFP_FP16) || q || (rd & 1)) { return 1; } + fpst = get_fpstatus_ptr(true); + ahp = get_ahp_flag(); tmp3 = tcg_temp_new_i32(); tmp = neon_load_reg(rm, 0); tmp2 = neon_load_reg(rm, 1); tcg_gen_ext16u_i32(tmp3, tmp); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 0)); tcg_gen_shri_i32(tmp3, tmp, 16); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 1)); tcg_temp_free_i32(tmp); tcg_gen_ext16u_i32(tmp3, tmp2); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 2)); tcg_gen_shri_i32(tmp3, tmp2, 16); - gen_helper_neon_fcvt_f16_to_f32(cpu_F0s, tmp3, cpu_env); + gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 3)); tcg_temp_free_i32(tmp2); tcg_temp_free_i32(tmp3); + tcg_temp_free_i32(ahp); + tcg_temp_free_ptr(fpst); break; + } case NEON_2RM_AESE: case NEON_2RM_AESMC: if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) || ((rm | rd) & 1)) { diff --git a/target/arm/translate.h b/target/arm/translate.h index 37a1bba..45f0424 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -177,4 +177,16 @@ void arm_free_cc(DisasCompare *cmp); void arm_jump_cc(DisasCompare *cmp, TCGLabel *label); void arm_gen_test_cc(int cc, TCGLabel *label); +/* Return state of Alternate Half-precision flag, caller frees result */ +static inline TCGv_i32 get_ahp_flag(void) +{ + TCGv_i32 ret = tcg_temp_new_i32(); + + tcg_gen_ld_i32(ret, cpu_env, + offsetof(CPUARMState, vfp.xregs[ARM_VFP_FPSCR])); + tcg_gen_extract_i32(ret, ret, 26, 1); + + return ret; +} + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/hppa/cpu.c b/target/hppa/cpu.c index c261b6b..00bf444 100644 --- a/target/hppa/cpu.c +++ b/target/hppa/cpu.c @@ -141,7 +141,6 @@ static void hppa_cpu_initfn(Object *obj) cs->env_ptr = env; cs->exception_index = -1; cpu_hppa_loaded_fr0(env); - set_snan_bit_is_one(true, &env->fp_status); cpu_hppa_put_psw(env, PSW_W); } diff --git a/target/hppa/op_helper.c b/target/hppa/op_helper.c index a3af62d..912e8d5 100644 --- a/target/hppa/op_helper.c +++ b/target/hppa/op_helper.c @@ -341,7 +341,6 @@ float64 HELPER(fdiv_d)(CPUHPPAState *env, float64 a, float64 b) float64 HELPER(fcnv_s_d)(CPUHPPAState *env, float32 arg) { float64 ret = float32_to_float64(arg, &env->fp_status); - ret = float64_maybe_silence_nan(ret, &env->fp_status); update_fr0_op(env, GETPC()); return ret; } @@ -349,7 +348,6 @@ float64 HELPER(fcnv_s_d)(CPUHPPAState *env, float32 arg) float32 HELPER(fcnv_d_s)(CPUHPPAState *env, float64 arg) { float32 ret = float64_to_float32(arg, &env->fp_status); - ret = float32_maybe_silence_nan(ret, &env->fp_status); update_fr0_op(env, GETPC()); return ret; } diff --git a/target/m68k/softfloat.c b/target/m68k/softfloat.c index d093997..b45a5e8 100644 --- a/target/m68k/softfloat.c +++ b/target/m68k/softfloat.c @@ -31,13 +31,14 @@ static floatx80 propagateFloatx80NaNOneArg(floatx80 a, float_status *status) { if (floatx80_is_signaling_nan(a, status)) { float_raise(float_flag_invalid, status); + a = floatx80_silence_nan(a, status); } if (status->default_nan_mode) { return floatx80_default_nan(status); } - return floatx80_maybe_silence_nan(a, status); + return a; } /*---------------------------------------------------------------------------- diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c index 8fb7a36..c74e3cd 100644 --- a/target/mips/msa_helper.c +++ b/target/mips/msa_helper.c @@ -1615,7 +1615,6 @@ static inline float16 float16_from_float32(int32_t a, flag ieee, float16 f_val; f_val = float32_to_float16((float32)a, ieee, status); - f_val = float16_maybe_silence_nan(f_val, status); return a < 0 ? (f_val | (1 << 15)) : f_val; } @@ -1625,7 +1624,6 @@ static inline float32 float32_from_float64(int64_t a, float_status *status) float32 f_val; f_val = float64_to_float32((float64)a, status); - f_val = float32_maybe_silence_nan(f_val, status); return a < 0 ? (f_val | (1 << 31)) : f_val; } @@ -1636,7 +1634,6 @@ static inline float32 float32_from_float16(int16_t a, flag ieee, float32 f_val; f_val = float16_to_float32((float16)a, ieee, status); - f_val = float32_maybe_silence_nan(f_val, status); return a < 0 ? (f_val | (1 << 31)) : f_val; } @@ -1646,7 +1643,6 @@ static inline float64 float64_from_float32(int32_t a, float_status *status) float64 f_val; f_val = float32_to_float64((float64)a, status); - f_val = float64_maybe_silence_nan(f_val, status); return a < 0 ? (f_val | (1ULL << 63)) : f_val; } diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c index 798cdad..9025f42 100644 --- a/target/mips/op_helper.c +++ b/target/mips/op_helper.c @@ -2700,7 +2700,6 @@ uint64_t helper_float_cvtd_s(CPUMIPSState *env, uint32_t fst0) uint64_t fdt2; fdt2 = float32_to_float64(fst0, &env->active_fpu.fp_status); - fdt2 = float64_maybe_silence_nan(fdt2, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); return fdt2; } @@ -2790,7 +2789,6 @@ uint32_t helper_float_cvts_d(CPUMIPSState *env, uint64_t fdt0) uint32_t fst2; fst2 = float64_to_float32(fdt0, &env->active_fpu.fp_status); - fst2 = float32_maybe_silence_nan(fst2, &env->active_fpu.fp_status); update_fcr31(env, GETPC()); return fst2; } diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index 9ae418a..d31a933 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -3382,7 +3382,6 @@ void helper_xssqrtqp(CPUPPCState *env, uint32_t opcode) xt.f128 = xb.f128; } else if (float128_is_neg(xb.f128) && !float128_is_zero(xb.f128)) { float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSQRT, 1); - set_snan_bit_is_one(0, &env->fp_status); xt.f128 = float128_default_nan(&env->fp_status); } } diff --git a/target/riscv/fpu_helper.c b/target/riscv/fpu_helper.c index abbadea..fdb87d8 100644 --- a/target/riscv/fpu_helper.c +++ b/target/riscv/fpu_helper.c @@ -279,14 +279,12 @@ uint64_t helper_fmax_d(CPURISCVState *env, uint64_t frs1, uint64_t frs2) uint64_t helper_fcvt_s_d(CPURISCVState *env, uint64_t rs1) { - rs1 = float64_to_float32(rs1, &env->fp_status); - return float32_maybe_silence_nan(rs1, &env->fp_status); + return float64_to_float32(rs1, &env->fp_status); } uint64_t helper_fcvt_d_s(CPURISCVState *env, uint64_t rs1) { - rs1 = float32_to_float64(rs1, &env->fp_status); - return float64_maybe_silence_nan(rs1, &env->fp_status); + return float32_to_float64(rs1, &env->fp_status); } uint64_t helper_fsqrt_d(CPURISCVState *env, uint64_t frs1) diff --git a/target/s390x/fpu_helper.c b/target/s390x/fpu_helper.c index 43f8bf1..5c5b451 100644 --- a/target/s390x/fpu_helper.c +++ b/target/s390x/fpu_helper.c @@ -269,7 +269,7 @@ uint64_t HELPER(ldeb)(CPUS390XState *env, uint64_t f2) { float64 ret = float32_to_float64(f2, &env->fpu_status); handle_exceptions(env, GETPC()); - return float64_maybe_silence_nan(ret, &env->fpu_status); + return ret; } /* convert 128-bit float to 64-bit float */ @@ -277,7 +277,7 @@ uint64_t HELPER(ldxb)(CPUS390XState *env, uint64_t ah, uint64_t al) { float64 ret = float128_to_float64(make_float128(ah, al), &env->fpu_status); handle_exceptions(env, GETPC()); - return float64_maybe_silence_nan(ret, &env->fpu_status); + return ret; } /* convert 64-bit float to 128-bit float */ @@ -285,7 +285,7 @@ uint64_t HELPER(lxdb)(CPUS390XState *env, uint64_t f2) { float128 ret = float64_to_float128(f2, &env->fpu_status); handle_exceptions(env, GETPC()); - return RET128(float128_maybe_silence_nan(ret, &env->fpu_status)); + return RET128(ret); } /* convert 32-bit float to 128-bit float */ @@ -293,7 +293,7 @@ uint64_t HELPER(lxeb)(CPUS390XState *env, uint64_t f2) { float128 ret = float32_to_float128(f2, &env->fpu_status); handle_exceptions(env, GETPC()); - return RET128(float128_maybe_silence_nan(ret, &env->fpu_status)); + return RET128(ret); } /* convert 64-bit float to 32-bit float */ @@ -301,7 +301,7 @@ uint64_t HELPER(ledb)(CPUS390XState *env, uint64_t f2) { float32 ret = float64_to_float32(f2, &env->fpu_status); handle_exceptions(env, GETPC()); - return float32_maybe_silence_nan(ret, &env->fpu_status); + return ret; } /* convert 128-bit float to 32-bit float */ @@ -309,7 +309,7 @@ uint64_t HELPER(lexb)(CPUS390XState *env, uint64_t ah, uint64_t al) { float32 ret = float128_to_float32(make_float128(ah, al), &env->fpu_status); handle_exceptions(env, GETPC()); - return float32_maybe_silence_nan(ret, &env->fpu_status); + return ret; } /* 32-bit FP compare */ diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index 541ffc2..b9f393b 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -71,7 +71,6 @@ static void superh_cpu_reset(CPUState *s) set_flush_to_zero(1, &env->fp_status); #endif set_default_nan_mode(1, &env->fp_status); - set_snan_bit_is_one(1, &env->fp_status); } static void superh_cpu_disas_set_info(CPUState *cpu, disassemble_info *info) diff --git a/target/unicore32/cpu.c b/target/unicore32/cpu.c index 29d160a..68f978d 100644 --- a/target/unicore32/cpu.c +++ b/target/unicore32/cpu.c @@ -70,7 +70,6 @@ static void unicore_ii_cpu_initfn(Object *obj) set_feature(env, UC32_HWCAP_CMOV); set_feature(env, UC32_HWCAP_UCF64); - set_snan_bit_is_one(1, &env->ucf64.fp_status); } static void uc32_any_cpu_initfn(Object *obj) @@ -83,7 +82,6 @@ static void uc32_any_cpu_initfn(Object *obj) set_feature(env, UC32_HWCAP_CMOV); set_feature(env, UC32_HWCAP_UCF64); - set_snan_bit_is_one(1, &env->ucf64.fp_status); } static void uc32_cpu_realizefn(DeviceState *dev, Error **errp) diff --git a/ui/Makefile.objs b/ui/Makefile.objs index cc78434..00f6976 100644 --- a/ui/Makefile.objs +++ b/ui/Makefile.objs @@ -15,10 +15,6 @@ common-obj-$(CONFIG_COCOA) += cocoa.o common-obj-$(CONFIG_VNC) += $(vnc-obj-y) common-obj-$(call lnot,$(CONFIG_VNC)) += vnc-stubs.o -common-obj-$(CONFIG_X11) += x_keymap.o -x_keymap.o-cflags := $(X11_CFLAGS) -x_keymap.o-libs := $(X11_LIBS) - # ui-sdl module common-obj-$(CONFIG_SDL) += sdl.mo ifeq ($(CONFIG_SDLABI),1.2) @@ -46,6 +42,13 @@ gtk.mo-objs += gtk-gl-area.o endif endif +ifeq ($(CONFIG_X11),y) +sdl.mo-objs += x_keymap.o +gtk.mo-objs += x_keymap.o +x_keymap.o-cflags := $(X11_CFLAGS) +x_keymap.o-libs := $(X11_LIBS) +endif + common-obj-$(CONFIG_CURSES) += curses.mo curses.mo-objs := curses.o curses.mo-cflags := $(CURSES_CFLAGS) diff --git a/ui/console.c b/ui/console.c index 945f05d..ef1247f 100644 --- a/ui/console.c +++ b/ui/console.c @@ -372,6 +372,11 @@ void qmp_screendump(const char *filename, bool has_device, const char *device, graphic_hw_update(con); surface = qemu_console_surface(con); + if (!surface) { + error_setg(errp, "no surface"); + return; + } + ppm_save(filename, surface, errp); } diff --git a/ui/sdl2-2d.c b/ui/sdl2-2d.c index 1f34817..8548440 100644 --- a/ui/sdl2-2d.c +++ b/ui/sdl2-2d.c @@ -36,9 +36,7 @@ void sdl2_2d_update(DisplayChangeListener *dcl, struct sdl2_console *scon = container_of(dcl, struct sdl2_console, dcl); DisplaySurface *surf = qemu_console_surface(dcl->con); SDL_Rect rect; - size_t surface_data_offset = surface_bytes_per_pixel(surf) * x + - surface_stride(surf) * y; - + size_t surface_data_offset; assert(!scon->opengl); if (!surf) { @@ -48,6 +46,8 @@ void sdl2_2d_update(DisplayChangeListener *dcl, return; } + surface_data_offset = surface_bytes_per_pixel(surf) * x + + surface_stride(surf) * y; rect.x = x; rect.y = y; rect.w = w; |