| .. |
|
aoptcpu.pas
|
53ea4fb7d4
* unify x86 peephole optimizer helpers
|
10 年 前 |
|
aoptcpub.pas
|
2f5ce095ce
* RefsHaveIndexReg -> cpurefshaveindexreg
|
13 年 前 |
|
aoptcpud.pas
|
790a4fe2d3
* log and id tags removed
|
20 年 前 |
|
cgcpu.pas
|
1b965e6766
* x86: Don't save/restore integer registers that are volatile per calling convention of current procedure. It implies that nothing will be saved for procedures with OLDFPCCALL, FAR16 and PASCAL and calling conventions. OLDFPCCALL restores behavior that was in effect before r25224.
|
9 年 前 |
|
cpubase.inc
|
bfbb0c5b9d
* optimize mov/lea
|
12 年 前 |
|
cpuelf.pas
|
7ca62febcd
AROS/x86_64: initial AROS/x86_64 support and implement syscalls for AROS/x86_64
|
10 年 前 |
|
cpuinfo.pas
|
3cb9be73bc
Moved tcontrollerdatatype out into cpuinfo.
|
10 年 前 |
|
cpunode.pas
|
bacd303208
* synchronized with trunk up to r27758
|
11 年 前 |
|
cpupara.pas
|
a27927e658
* disable parameter struct padding for llvm, as llvm does that it by itself
|
9 年 前 |
|
cpupi.pas
|
70dda94474
* x86_64-win64: don't allocate outgoing parameter area in nostackframe procedures, it fails compilation if range/overflow/etc checking is enabled (which always sets pi_do_call) due to check introduced in r22677.
|
12 年 前 |
|
cputarg.pas
|
7ca62febcd
AROS/x86_64: initial AROS/x86_64 support and implement syscalls for AROS/x86_64
|
10 年 前 |
|
hlcgcpu.pas
|
67b8aceaee
* synchronized with privatetrunk till r30095
|
10 年 前 |
|
nx64add.pas
|
2459518bdd
* use IMUL even for unsigned multiplication on x86_64, when overflow checking is
|
11 年 前 |
|
nx64cal.pas
|
f0ccbc87f2
AROS/x86_64: enable syscalls code in the parser, fix EAX->RAX reference base while calculating syscall offset
|
10 年 前 |
|
nx64cnv.pas
|
687bb15299
* renamed getdatalabel() to getglobaldatalabel
|
10 年 前 |
|
nx64flw.pas
|
529677cc79
ncal.pas:
|
10 年 前 |
|
nx64inl.pas
|
1bcc276dcf
* remove implicit typecast to extended automatically inserted for trunc/round
|
10 年 前 |
|
nx64mat.pas
|
b594eee70b
* Moved x86_64 mod/div code to x86, with minimal changes to ensure it compiles on i386/i8086. Merging optimized division-by-const code from i386 is pending...
|
11 年 前 |
|
nx64set.pas
|
859676d7d3
* fixed r26519 for darwin/x86-64, see comments (mantis #25644)
|
11 年 前 |
|
r8664ari.inc
|
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 年 前 |
|
r8664att.inc
|
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 年 前 |
|
r8664con.inc
|
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 年 前 |
|
r8664dwrf.inc
|
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 年 前 |
|
r8664int.inc
|
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 年 前 |
|
r8664iri.inc
|
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 年 前 |
|
r8664nasm.inc
|
2ec5a649d7
* set Ch_* for more operations
|
11 年 前 |
|
r8664nor.inc
|
283ff05127
* merged avx support in inline assembler developed by Torsten Grundke
|
13 年 前 |
|
r8664num.inc
|
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 年 前 |
|
r8664ot.inc
|
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 年 前 |
|
r8664rni.inc
|
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 年 前 |
|
r8664sri.inc
|
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 年 前 |
|
r8664stab.inc
|
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 年 前 |
|
r8664std.inc
|
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 年 前 |
|
rax64att.pas
|
8f05f8c839
- Forgot to commit with r29081
|
10 年 前 |
|
rax64int.pas
|
f726e1691b
* Fixed warnings and notes.
|
16 年 前 |
|
rgcpu.pas
|
a3f58e84be
* rbp can be used for normal purpose under certain conditions so it shouldn't interfere with all other registers
|
11 年 前 |
|
symcpu.pas
|
4f7b4a2735
* changed {$ifdef x86} code in defcmp into virtual methods
|
9 年 前 |
|
win64unw.pas
|
6a3fe72de9
+ Support .rva directive in AT&T reader. Put it into base class because it generally applies to all targets with COFF output, but enabled for Windows targets only (others need additional testing).
|
14 年 前 |
|
x8664ats.inc
|
a78250a78b
* x87 FBSTP and FBLD instructions cannot have size suffix in ATT syntax. Mantis #29095.
|
9 年 前 |
|
x8664att.inc
|
d6e4af8279
+ applied remaining patches of Torsten Grundke: adds gather instructions of avx2
|
10 年 前 |
|
x8664int.inc
|
d6e4af8279
+ applied remaining patches of Torsten Grundke: adds gather instructions of avx2
|
10 年 前 |
|
x8664nop.inc
|
d6e4af8279
+ applied remaining patches of Torsten Grundke: adds gather instructions of avx2
|
10 年 前 |
|
x8664op.inc
|
d6e4af8279
+ applied remaining patches of Torsten Grundke: adds gather instructions of avx2
|
10 年 前 |
|
x8664pro.inc
|
99635658ec
* corrects change flags for VSQRTSD
|
10 年 前 |
|
x8664tab.inc
|
d6e4af8279
+ applied remaining patches of Torsten Grundke: adds gather instructions of avx2
|
10 年 前 |
Jonas Maebe
a27927e658
* disable parameter struct padding for llvm, as llvm does that it by itself