~ [ source navigation ] ~ [ diff markup ] ~ [ identifier search ] ~

TOMOYO Linux Cross Reference
Linux/Documentation/arch/arm/nwfpe/todo.rst

Version: ~ [ linux-6.12-rc7 ] ~ [ linux-6.11.7 ] ~ [ linux-6.10.14 ] ~ [ linux-6.9.12 ] ~ [ linux-6.8.12 ] ~ [ linux-6.7.12 ] ~ [ linux-6.6.60 ] ~ [ linux-6.5.13 ] ~ [ linux-6.4.16 ] ~ [ linux-6.3.13 ] ~ [ linux-6.2.16 ] ~ [ linux-6.1.116 ] ~ [ linux-6.0.19 ] ~ [ linux-5.19.17 ] ~ [ linux-5.18.19 ] ~ [ linux-5.17.15 ] ~ [ linux-5.16.20 ] ~ [ linux-5.15.171 ] ~ [ linux-5.14.21 ] ~ [ linux-5.13.19 ] ~ [ linux-5.12.19 ] ~ [ linux-5.11.22 ] ~ [ linux-5.10.229 ] ~ [ linux-5.9.16 ] ~ [ linux-5.8.18 ] ~ [ linux-5.7.19 ] ~ [ linux-5.6.19 ] ~ [ linux-5.5.19 ] ~ [ linux-5.4.285 ] ~ [ linux-5.3.18 ] ~ [ linux-5.2.21 ] ~ [ linux-5.1.21 ] ~ [ linux-5.0.21 ] ~ [ linux-4.20.17 ] ~ [ linux-4.19.323 ] ~ [ linux-4.18.20 ] ~ [ linux-4.17.19 ] ~ [ linux-4.16.18 ] ~ [ linux-4.15.18 ] ~ [ linux-4.14.336 ] ~ [ linux-4.13.16 ] ~ [ linux-4.12.14 ] ~ [ linux-4.11.12 ] ~ [ linux-4.10.17 ] ~ [ linux-4.9.337 ] ~ [ linux-4.4.302 ] ~ [ linux-3.10.108 ] ~ [ linux-2.6.32.71 ] ~ [ linux-2.6.0 ] ~ [ linux-2.4.37.11 ] ~ [ unix-v6-master ] ~ [ ccs-tools-1.8.12 ] ~ [ policy-sample ] ~
Architecture: ~ [ i386 ] ~ [ alpha ] ~ [ m68k ] ~ [ mips ] ~ [ ppc ] ~ [ sparc ] ~ [ sparc64 ] ~

Diff markup

Differences between /Documentation/arch/arm/nwfpe/todo.rst (Version linux-6.12-rc7) and /Documentation/arch/i386/nwfpe/todo.rst (Version linux-6.1.116)


  1 TODO LIST                                         
  2 =========                                         
  3                                                   
  4 ::                                                
  5                                                   
  6   POW{cond}<S|D|E>{P,M,Z} Fd, Fn, <Fm,#value>     
  7   RPW{cond}<S|D|E>{P,M,Z} Fd, Fn, <Fm,#value>     
  8   POL{cond}<S|D|E>{P,M,Z} Fd, Fn, <Fm,#value>     
  9                                                   
 10   LOG{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - lo    
 11   LGN{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - lo    
 12   EXP{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - ex    
 13   SIN{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - si    
 14   COS{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - co    
 15   TAN{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - ta    
 16   ASN{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - ar    
 17   ACS{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - ar    
 18   ATN{cond}<S|D|E>{P,M,Z} Fd, <Fm,#value> - ar    
 19                                                   
 20 These are not implemented.  They are not curre    
 21 and are handled by routines in libc.  These ar    
 22 hardware, but are handled by the floating poin    
 23 be implemented in future versions.                
 24                                                   
 25 There are a couple of ways to approach the imp    
 26 method would be to use accurate table methods     
 27 a couple of papers by S. Gal from IBM's resear    
 28 seem to promise extreme accuracy (in the order    
 29 These methods are used in GLIBC for some of th    
 30                                                   
 31 Another approach, which I know little about is    
 32 Coordinate Rotation Digital Computer, and is a    
 33 transcendental functions using mostly shifts a    
 34 multiplications and divisions.  The ARM excels    
 35 so such a method could be promising, but requi    
 36 determine if it is feasible.                      
 37                                                   
 38 Rounding Methods                                  
 39 ----------------                                  
 40                                                   
 41 The IEEE standard defines 4 rounding modes.  R    
 42 default, but rounding to + or - infinity or ro    
 43 Many architectures allow the rounding mode to     
 44 in a control register.  Not so with the ARM FP    
 45 the rounding mode one must specify it with eac    
 46                                                   
 47 This has made porting some benchmarks difficul    
 48 introduce such a capability into the emulator.    
 49 bits describing the rounding mode.  The emulat    
 50 examine a flag, which if set forced it to igno    
 51 the instruction, and use the mode specified in    
 52                                                   
 53 This would require a method of getting/setting    
 54 in the FPCR.  This requires a kernel call in A    
 55 supervisor only instructions.  If anyone has a    
 56 would like to hear them.                          
 57                                                   
 58 NOTE:                                             
 59  pulled out from some docs on ARM floating poi    
 60  for the Acorn FPE, but not limited to it:        
 61                                                   
 62  The floating point control register (FPCR) ma    
 63  implementations: it is there to control the h    
 64  specific manner, for example to disable the f    
 65  mode of the ARM is not permitted to use this     
 66  reserved to alter it between implementations)    
 67  instructions will trap if tried in user mode.    
 68                                                   
 69  Hence, the answer is yes, you could do this,     
 70  risk of becoming isolated if and when hardwar    
 71                                                   
 72                 -- Russell.                       
                                                      

~ [ source navigation ] ~ [ diff markup ] ~ [ identifier search ] ~

kernel.org | git.kernel.org | LWN.net | Project Home | SVN repository | Mail admin

Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.

sflogo.php