Michael VAN CANNEYT
|
7fad431910
* string -> shortstring
|
il y a 2 ans |
Michael VAN CANNEYT
|
733cfe505b
* Char -> AnsiChar
|
il y a 2 ans |
Rika Ichinose
|
7553fee9c5
Handle Index* / Compare* tail by directly reading last VECSIZE bytes, if there was at least one full vector.
|
il y a 2 ans |
Rika Ichinose
|
f343e39f25
IndexWord and IndexDWord for i386 without REP SCAS.
|
il y a 2 ans |
Rika Ichinose
|
0c2a6e0c36
SSE2 Index* and Compare* for i386, chosen at runtime.
|
il y a 2 ans |
florian
|
c948282e3c
* patch by Rika, trivial adjustments to !373, resolves #40172
|
il y a 2 ans |
Rika Ichinose
|
d782771cfe
Improved CompareWord for i386 and x86_64.
|
il y a 2 ans |
Rika Ichinose
|
6b216d83e7
Improved CompareDWord for i386 and x86_64.
|
il y a 2 ans |
Rika Ichinose
|
88d3d4d2fa
Improved CompareByte for i386 and x86_64.
|
il y a 2 ans |
Jonas Maebe
|
0758aa1143
FPU exception mask: generlised system unit interface
|
il y a 3 ans |
florian
|
0d03cad279
* i386: make use of *fence instructions
|
il y a 3 ans |
florian
|
39836e2d37
- removed superfluous comment
|
il y a 3 ans |
svenbarth
|
48cc5250f9
* fpc_geteipasebx and fpc_geteipasecx are used as procedures, not functions, so declare them as such
|
il y a 5 ans |
florian
|
3e6e72118b
* keep stack aligned to 16 byte boundaries in assembler subroutines calling other subroutines
|
il y a 6 ans |
florian
|
62f890efa3
* improved floating point signal handling on x86/linux
|
il y a 6 ans |
pierre
|
239b623027
Fix typo in last commit
|
il y a 8 ans |
pierre
|
df7946a9cc
* Do not use fastmove.inc if OLD_ASSEMBLER is defined,
|
il y a 8 ans |
pierre
|
82aa8c4d2f
Use REPE prefix instead of REP before CMPS{B,W,L} instruction (wasm generates an error for REP)
|
il y a 8 ans |
florian
|
9b1e6e1976
- removed i386 specific fpc_pchar_length implementation as it is much slower than the generic one which takes advantage of IndexByte
|
il y a 9 ans |
sergei
|
b16c6f8ced
* i386 and x86_64 changes for Delphi compatibility:
|
il y a 11 ans |
sergei
|
d1348d3f9b
- i386 and x86_64: Once softfloat stuff has been cleaned up, SysResetFPU and SysInitFPU end up doing exactly the same. Removed one of them.
|
il y a 11 ans |
sergei
|
8ad5e6fb26
- RTL: cleaned out FPC_FREEMEM_X. We now have a dedicated compilerproc 'fpc_freemem' for this purpose.
|
il y a 11 ans |
sergei
|
4952754184
- i386 and x86_64 no longer use any softfloat stuff.
|
il y a 11 ans |
sergei
|
6baba5065c
* i386: Perform all CPU-related initialization in fpc_cpucodeinit, instead of having it scattered between fpc_cpuinit,fpc_cpucodeinit and check_sse_support. Simplifies things quite a bit.
|
il y a 11 ans |
sergei
|
a9b0a92873
* cpuid_support: translated to ATT syntax and optimized a bit.
|
il y a 11 ans |
nickysn
|
4b3bf874df
* Added CLDs in the RTL i386 inline asm routines, wrapped in {$ifdef
|
il y a 12 ans |
florian
|
bb397e2b2f
+ has_sse2_support for i386
|
il y a 12 ans |
sergei
|
30a6432a17
+ Assembler implementation of SarInt64 for i386.
|
il y a 12 ans |
florian
|
8818b58e5d
* Bsf/Bsr on x86 handle now correctly 0 as argument, resolves #22783
|
il y a 13 ans |
florian
|
9be3ca04ad
* split FPC_HAS_INTERNAL_BSX_* defines into FPC_HAS_INTERNAL_BSF_* and FPC_HAS_INTERNAL_BSR_*
|
il y a 13 ans |