| .. |
|
aasmcpu.pas
|
7949bebb8d
* synchronised with r28168 of trunk
|
11 years ago |
|
agx86att.pas
|
045f161012
Separate out nasm assembler for i8086, i386 and x86_64 cpus, also separte based on target object format
|
11 years ago |
|
agx86int.pas
|
7949bebb8d
* synchronised with r28168 of trunk
|
11 years ago |
|
agx86nsm.pas
|
7949bebb8d
* synchronised with r28168 of trunk
|
11 years ago |
|
cga.pas
|
d88d644925
+ support for FMA intrinsic: if there is no hardware support, the compiler throws an error.
|
11 years ago |
|
cgx86.pas
|
ae627a4ba8
* tcgx86.a_op_const_reg_reg: optimize trivial cases before considering more complex ones.
|
11 years ago |
|
cpubase.pas
|
07e90aaa24
+ Implemented IEEE 754-compliant checking for unordered results of floating-point compares on x86 targets. Mantis #9362.
|
11 years ago |
|
hlcgx86.pas
|
71deda6f50
+ added interface to ncgutil.gen_load_loc_cgpara() to hlcgobj + generic
|
14 years ago |
|
itcpugas.pas
|
926dd1b41e
* command line compilation of i8086 fixed
|
12 years ago |
|
itx86int.pas
|
0e41df598e
* merge i8086 branch by Nikolay Nikolov
|
12 years ago |
|
ni86mem.pas
|
4a79481c51
* isolated segment-related functionality of tabsolutevarsym into i386/i8086-
|
11 years ago |
|
nx86add.pas
|
499dd078e3
+ automatically insert fma inlines into floating point code if possible and fastmath is activated
|
11 years ago |
|
nx86cal.pas
|
81427523ab
* pass a list of (pointers to) the paralocs to hlcgobj.a_call/g_call*, as
|
11 years ago |
|
nx86cnv.pas
|
d613ab8578
* x86: improve x87 qword to float conversion, using single-precision constants saves space and removes need in separate load on FPU stack. No precision loss occurs because 2**64 is representable exactly even in single precision.
|
11 years ago |
|
nx86con.pas
|
45f60bc4b5
* small changes (copyright, typo, readability)
|
12 years ago |
|
nx86inl.pas
|
8207e0ef22
+ make use of vfnmsub*/vfmsub*/vfnmadd* instructions if possible
|
11 years ago |
|
nx86mat.pas
|
05ecd3cec1
* One more fix of operand size, likely harmless because shift amount is taken modulo bit-width anyway.
|
11 years ago |
|
nx86mem.pas
|
bacd303208
* synchronized with trunk up to r27758
|
11 years ago |
|
nx86set.pas
|
5e8f8f4755
* Use GOT-relative constants for i386 PIC jump tables, they don't need runtime relocations. Now almost ABI-compliant on Linux/BSD (Darwin targets unchanged). Also clean up i8086-specific stuff: using tai_const.create_type_sym(aitconst_ptr,...) generates near pointers on i8086, which is the desired goal.
|
11 years ago |
|
rax86.pas
|
aa107b914c
* merged avx2 branch, developed by Torsten Grundke
|
11 years ago |
|
rax86att.pas
|
d6180b1e70
* properly propagate PIC-related suffixes from the x86 assembler reader in
|
12 years ago |
|
rax86int.pas
|
9b560ffd64
* x86 intel syntax inline asm: allow a segment override (segcs,segds,seges,etc.)
|
11 years ago |
|
rgx86.pas
|
7949bebb8d
* synchronised with r28168 of trunk
|
11 years ago |
|
symi86.pas
|
fc71081b74
* i8086 and i386-specific code from tabstractprocdef.is_pushleftright moved to
|
11 years ago |
|
symx86.pas
|
94bcb9878a
* reimplemented r28329 in a different way, as suggested by Jonas
|
11 years ago |
|
x86ins.dat
|
842e027a9f
+ prove of concept how FMA4 could be supported in inline assembler
|
11 years ago |
|
x86reg.dat
|
5af873ee5b
* x86 targets: Profiling shows that quite a bit of time is spent in findreg_by_number(), despite it uses binary search. Worse, it is repeated for every piece of register information. Trying to get rid of some of these calls: rearranged registers so that their "opcode" matches 3 LSBs of superregister number (with a few exceptions described at the beginning of x86reg.dat). This allows to lookup opcodes in regval() with O(1) complexity, and removes need in rXXXop.inc files.
|
12 years ago |
Jonas Maebe
5c75b6dd6b
* synchronised with trunk up till r28402