123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333 |
- /*
- * linux/arch/arm/vfp/vfpsingle.c
- *
- * This code is derived in part from John R. Housers softfloat library, which
- * carries the following notice:
- *
- * ===========================================================================
- * This C source file is part of the SoftFloat IEC/IEEE Floating-point
- * Arithmetic Package, Release 2.
- *
- * Written by John R. Hauser. This work was made possible in part by the
- * International Computer Science Institute, located at Suite 600, 1947 Center
- * Street, Berkeley, California 94704. Funding was partially provided by the
- * National Science Foundation under grant MIP-9311980. The original version
- * of this code was written as part of a project to build a fixed-point vector
- * processor in collaboration with the University of California at Berkeley,
- * overseen by Profs. Nelson Morgan and John Wawrzynek. More information
- * is available through the web page `http://HTTP.CS.Berkeley.EDU/~jhauser/
- * arithmetic/softfloat.html'.
- *
- * THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE. Although reasonable effort
- * has been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT
- * TIMES RESULT IN INCORRECT BEHAVIOR. USE OF THIS SOFTWARE IS RESTRICTED TO
- * PERSONS AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ANY
- * AND ALL LOSSES, COSTS, OR OTHER PROBLEMS ARISING FROM ITS USE.
- *
- * Derivative works are acceptable, even for commercial purposes, so long as
- * (1) they include prominent notice that the work is derivative, and (2) they
- * include prominent notice akin to these three paragraphs for those parts of
- * this code that are retained.
- * ===========================================================================
- */
- #include <linux/kernel.h>
- #include <linux/bitops.h>
- #include <asm/div64.h>
- #include <asm/vfp.h>
- #include "vfpinstr.h"
- #include "vfp.h"
- static struct vfp_single vfp_single_default_qnan = {
- .exponent = 255,
- .sign = 0,
- .significand = VFP_SINGLE_SIGNIFICAND_QNAN,
- };
- static void vfp_single_dump(const char *str, struct vfp_single *s)
- {
- pr_debug("VFP: %s: sign=%d exponent=%d significand=%08x\n",
- str, s->sign != 0, s->exponent, s->significand);
- }
- static void vfp_single_normalise_denormal(struct vfp_single *vs)
- {
- int bits = 31 - fls(vs->significand);
- vfp_single_dump("normalise_denormal: in", vs);
- if (bits) {
- vs->exponent -= bits - 1;
- vs->significand <<= bits;
- }
- vfp_single_dump("normalise_denormal: out", vs);
- }
- #ifndef DEBUG
- #define vfp_single_normaliseround(sd,vsd,fpscr,except,func) __vfp_single_normaliseround(sd,vsd,fpscr,except)
- u32 __vfp_single_normaliseround(int sd, struct vfp_single *vs, u32 fpscr, u32 exceptions)
- #else
- u32 vfp_single_normaliseround(int sd, struct vfp_single *vs, u32 fpscr, u32 exceptions, const char *func)
- #endif
- {
- u32 significand, incr, rmode;
- int exponent, shift, underflow;
- vfp_single_dump("pack: in", vs);
- /*
- * Infinities and NaNs are a special case.
- */
- if (vs->exponent == 255 && (vs->significand == 0 || exceptions))
- goto pack;
- /*
- * Special-case zero.
- */
- if (vs->significand == 0) {
- vs->exponent = 0;
- goto pack;
- }
- exponent = vs->exponent;
- significand = vs->significand;
- /*
- * Normalise first. Note that we shift the significand up to
- * bit 31, so we have VFP_SINGLE_LOW_BITS + 1 below the least
- * significant bit.
- */
- shift = 32 - fls(significand);
- if (shift < 32 && shift) {
- exponent -= shift;
- significand <<= shift;
- }
- #ifdef DEBUG
- vs->exponent = exponent;
- vs->significand = significand;
- vfp_single_dump("pack: normalised", vs);
- #endif
- /*
- * Tiny number?
- */
- underflow = exponent < 0;
- if (underflow) {
- significand = vfp_shiftright32jamming(significand, -exponent);
- exponent = 0;
- #ifdef DEBUG
- vs->exponent = exponent;
- vs->significand = significand;
- vfp_single_dump("pack: tiny number", vs);
- #endif
- if (!(significand & ((1 << (VFP_SINGLE_LOW_BITS + 1)) - 1)))
- underflow = 0;
- }
- /*
- * Select rounding increment.
- */
- incr = 0;
- rmode = fpscr & FPSCR_RMODE_MASK;
- if (rmode == FPSCR_ROUND_NEAREST) {
- incr = 1 << VFP_SINGLE_LOW_BITS;
- if ((significand & (1 << (VFP_SINGLE_LOW_BITS + 1))) == 0)
- incr -= 1;
- } else if (rmode == FPSCR_ROUND_TOZERO) {
- incr = 0;
- } else if ((rmode == FPSCR_ROUND_PLUSINF) ^ (vs->sign != 0))
- incr = (1 << (VFP_SINGLE_LOW_BITS + 1)) - 1;
- pr_debug("VFP: rounding increment = 0x%08x\n", incr);
- /*
- * Is our rounding going to overflow?
- */
- if ((significand + incr) < significand) {
- exponent += 1;
- significand = (significand >> 1) | (significand & 1);
- incr >>= 1;
- #ifdef DEBUG
- vs->exponent = exponent;
- vs->significand = significand;
- vfp_single_dump("pack: overflow", vs);
- #endif
- }
- /*
- * If any of the low bits (which will be shifted out of the
- * number) are non-zero, the result is inexact.
- */
- if (significand & ((1 << (VFP_SINGLE_LOW_BITS + 1)) - 1))
- exceptions |= FPSCR_IXC;
- /*
- * Do our rounding.
- */
- significand += incr;
- /*
- * Infinity?
- */
- if (exponent >= 254) {
- exceptions |= FPSCR_OFC | FPSCR_IXC;
- if (incr == 0) {
- vs->exponent = 253;
- vs->significand = 0x7fffffff;
- } else {
- vs->exponent = 255; /* infinity */
- vs->significand = 0;
- }
- } else {
- if (significand >> (VFP_SINGLE_LOW_BITS + 1) == 0)
- exponent = 0;
- if (exponent || significand > 0x80000000)
- underflow = 0;
- if (underflow)
- exceptions |= FPSCR_UFC;
- vs->exponent = exponent;
- vs->significand = significand >> 1;
- }
- pack:
- vfp_single_dump("pack: final", vs);
- {
- s32 d = vfp_single_pack(vs);
- #ifdef DEBUG
- pr_debug("VFP: %s: d(s%d)=%08x exceptions=%08x\n", func,
- sd, d, exceptions);
- #endif
- vfp_put_float(d, sd);
- }
- return exceptions;
- }
- /*
- * Propagate the NaN, setting exceptions if it is signalling.
- * 'n' is always a NaN. 'm' may be a number, NaN or infinity.
- */
- static u32
- vfp_propagate_nan(struct vfp_single *vsd, struct vfp_single *vsn,
- struct vfp_single *vsm, u32 fpscr)
- {
- struct vfp_single *nan;
- int tn, tm = 0;
- tn = vfp_single_type(vsn);
- if (vsm)
- tm = vfp_single_type(vsm);
- if (fpscr & FPSCR_DEFAULT_NAN)
- /*
- * Default NaN mode - always returns a quiet NaN
- */
- nan = &vfp_single_default_qnan;
- else {
- /*
- * Contemporary mode - select the first signalling
- * NAN, or if neither are signalling, the first
- * quiet NAN.
- */
- if (tn == VFP_SNAN || (tm != VFP_SNAN && tn == VFP_QNAN))
- nan = vsn;
- else
- nan = vsm;
- /*
- * Make the NaN quiet.
- */
- nan->significand |= VFP_SINGLE_SIGNIFICAND_QNAN;
- }
- *vsd = *nan;
- /*
- * If one was a signalling NAN, raise invalid operation.
- */
- return tn == VFP_SNAN || tm == VFP_SNAN ? FPSCR_IOC : VFP_NAN_FLAG;
- }
- /*
- * Extended operations
- */
- static u32 vfp_single_fabs(int sd, int unused, s32 m, u32 fpscr)
- {
- vfp_put_float(vfp_single_packed_abs(m), sd);
- return 0;
- }
- static u32 vfp_single_fcpy(int sd, int unused, s32 m, u32 fpscr)
- {
- vfp_put_float(m, sd);
- return 0;
- }
- static u32 vfp_single_fneg(int sd, int unused, s32 m, u32 fpscr)
- {
- vfp_put_float(vfp_single_packed_negate(m), sd);
- return 0;
- }
- static const u16 sqrt_oddadjust[] = {
- 0x0004, 0x0022, 0x005d, 0x00b1, 0x011d, 0x019f, 0x0236, 0x02e0,
- 0x039c, 0x0468, 0x0545, 0x0631, 0x072b, 0x0832, 0x0946, 0x0a67
- };
- static const u16 sqrt_evenadjust[] = {
- 0x0a2d, 0x08af, 0x075a, 0x0629, 0x051a, 0x0429, 0x0356, 0x029e,
- 0x0200, 0x0179, 0x0109, 0x00af, 0x0068, 0x0034, 0x0012, 0x0002
- };
- u32 vfp_estimate_sqrt_significand(u32 exponent, u32 significand)
- {
- int index;
- u32 z, a;
- if ((significand & 0xc0000000) != 0x40000000) {
- printk(KERN_WARNING "VFP: estimate_sqrt: invalid significand\n");
- }
- a = significand << 1;
- index = (a >> 27) & 15;
- if (exponent & 1) {
- z = 0x4000 + (a >> 17) - sqrt_oddadjust[index];
- z = ((a / z) << 14) + (z << 15);
- a >>= 1;
- } else {
- z = 0x8000 + (a >> 17) - sqrt_evenadjust[index];
- z = a / z + z;
- z = (z >= 0x20000) ? 0xffff8000 : (z << 15);
- if (z <= a)
- return (s32)a >> 1;
- }
- {
- u64 v = (u64)a << 31;
- do_div(v, z);
- return v + (z >> 1);
- }
- }
- static u32 vfp_single_fsqrt(int sd, int unused, s32 m, u32 fpscr)
- {
- struct vfp_single vsm, vsd;
- int ret, tm;
- vfp_single_unpack(&vsm, m);
- tm = vfp_single_type(&vsm);
- if (tm & (VFP_NAN|VFP_INFINITY)) {
- struct vfp_single *vsp = &vsd;
- if (tm & VFP_NAN)
- ret = vfp_propagate_nan(vsp, &vsm, NULL, fpscr);
- else if (vsm.sign == 0) {
- sqrt_copy:
- vsp = &vsm;
- ret = 0;
- } else {
- sqrt_invalid:
|