| .. |
|
aoptcpu.pas
|
2fa066b003
* optimize vmovaps/vmovapd after avx instructions
|
hace 11 años |
|
aoptcpub.pas
|
2f5ce095ce
* RefsHaveIndexReg -> cpurefshaveindexreg
|
hace 13 años |
|
aoptcpud.pas
|
790a4fe2d3
* log and id tags removed
|
hace 20 años |
|
cgcpu.pas
|
d8c898742a
* handle the fact that records containing a single extended value are
|
hace 11 años |
|
cpubase.inc
|
bfbb0c5b9d
* optimize mov/lea
|
hace 12 años |
|
cpuelf.pas
|
f733e0021a
--- Merging r29574 into '.':
|
hace 10 años |
|
cpuinfo.pas
|
5c67fcc43f
+ change always floating point divisions into multiplications if they are a power of two,
|
hace 11 años |
|
cpunode.pas
|
b57c95043f
+ support overriding tdef/tsym methods with target-specific functionality:
|
hace 11 años |
|
cpupara.pas
|
ad937e79fa
--- Merging r30239 into '.':
|
hace 10 años |
|
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.
|
hace 12 años |
|
cputarg.pas
|
3327d508ee
Enable nasm assembler for x86_64 cpu
|
hace 11 años |
|
hlcgcpu.pas
|
71deda6f50
+ added interface to ncgutil.gen_load_loc_cgpara() to hlcgobj + generic
|
hace 14 años |
|
nx64add.pas
|
2459518bdd
* use IMUL even for unsigned multiplication on x86_64, when overflow checking is
|
hace 11 años |
|
nx64cal.pas
|
b837694207
* factored out releasing an unused return value into
|
hace 14 años |
|
nx64cnv.pas
|
edd42aa42a
* moved subsetref/reg and bit_set/test support from cgobj to hlcgobj for
|
hace 13 años |
|
nx64flw.pas
|
de3a3d11e2
--- Merging r31475 into '.':
|
hace 10 años |
|
nx64inl.pas
|
790a4fe2d3
* log and id tags removed
|
hace 20 años |
|
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...
|
hace 11 años |
|
nx64set.pas
|
859676d7d3
* fixed r26519 for darwin/x86-64, see comments (mantis #25644)
|
hace 11 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
r8664nasm.inc
|
2ec5a649d7
* set Ch_* for more operations
|
hace 11 años |
|
r8664nor.inc
|
283ff05127
* merged avx support in inline assembler developed by Torsten Grundke
|
hace 13 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
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.
|
hace 12 años |
|
rax64att.pas
|
8f05f8c839
- Forgot to commit with r29081
|
hace 11 años |
|
rax64int.pas
|
f726e1691b
* Fixed warnings and notes.
|
hace 16 años |
|
rgcpu.pas
|
a3f58e84be
* rbp can be used for normal purpose under certain conditions so it shouldn't interfere with all other registers
|
hace 11 años |
|
symcpu.pas
|
5f8057775b
--- Merging r30757 into '.':
|
hace 9 años |
|
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).
|
hace 14 años |
|
x8664ats.inc
|
6040c041e4
--- Merging r32541 into '.':
|
hace 9 años |
|
x8664att.inc
|
dc628b8969
* x86: Completely skip instructions that do not exist for target CPU bit width. The existing behavior of writing mnemonics and properties but no encoding allows an invalid instruction to be recognized by assembler reader or even generated by compiler, but it but won't assemble anyway.
|
hace 11 años |
|
x8664int.inc
|
dc628b8969
* x86: Completely skip instructions that do not exist for target CPU bit width. The existing behavior of writing mnemonics and properties but no encoding allows an invalid instruction to be recognized by assembler reader or even generated by compiler, but it but won't assemble anyway.
|
hace 11 años |
|
x8664nop.inc
|
842e027a9f
+ prove of concept how FMA4 could be supported in inline assembler
|
hace 11 años |
|
x8664op.inc
|
dc628b8969
* x86: Completely skip instructions that do not exist for target CPU bit width. The existing behavior of writing mnemonics and properties but no encoding allows an invalid instruction to be recognized by assembler reader or even generated by compiler, but it but won't assemble anyway.
|
hace 11 años |
|
x8664pro.inc
|
6040c041e4
--- Merging r32541 into '.':
|
hace 9 años |
|
x8664tab.inc
|
842e027a9f
+ prove of concept how FMA4 could be supported in inline assembler
|
hace 11 años |
marco
6040c041e4
--- Merging r32541 into '.':