 florian
|
9e4c130bc4
* do not allocate unnecessarily an extra pair of registers when multiplying int64s on arm
|
11 years ago |
 sergei
|
a3efd9e1df
+ Added method taddnode.use_generic_mul64bit, allowing it to inline full 64-bit multiplications, and fixed ARM to comply (it was not checking for possible 32x32 to 64 optimization after detecting a 64-bit operand, so recently added code for 32x32 to 64 bit optimization was inactive).
|
11 years ago |
|
florian
|
1fc6316cbc
* use generic 32*32 -> 64 bit multiplication on arm thumb
|
11 years ago |
 masta
|
bcec29f1b4
Disable generation of UMULL when generating thumb1 code
|
11 years ago |
|
masta
|
e5b3d89a5d
Add CPUARM_HAS_UMULL flag
|
11 years ago |
|
masta
|
d32abdf047
Little cleanup in tarmaddnode.second_add64bit
|
11 years ago |
|
masta
|
cec633e86e
Optimized support for 32x32 => 64bit multiplications on ARM
|
11 years ago |
 Károly Balogh
|
25619d4991
removed the const-in-the-left internalerror
|
12 years ago |
|
florian
|
d4968e054b
+ arm: tsettings.instructionset
|
12 years ago |
|
Károly Balogh
|
6591a24bd3
removed some code which must never be called, added an internalerror() instead
|
12 years ago |
|
florian
|
bb73a2891b
* prevent generation of mul/mla statements with illegal registers
|
12 years ago |
|
Károly Balogh
|
614afca755
ARM: try to inline 64bit multiplication for the most common cases instead of calling FPC_MUL_ helpers (results in 5-10x speedup)
|
12 years ago |
|
florian
|
3a393f839e
* do not reuse register locations on arm fpa/vfp
|
12 years ago |
 Jonas Maebe
|
5051453806
+ support for LOC_(C)MMREGISTER in hlcg
|
12 years ago |
|
florian
|
ed2825fbb0
* arm thumb: handle constants in second_cmpsmallset correctly
|
12 years ago |
|
florian
|
1eeeb309c7
* intial armv6m support, it is not working yet, constant pool insertation and conditional branch fixup is not working yet
|
12 years ago |
|
florian
|
47d43750e4
* remove unused units from uses statements
|
12 years ago |
 Jeppe Johansen
|
a8f9b0dac4
Added initial support for the Cortex-M4F FPv4_S16 FPU
|
13 years ago |
|
masta
|
0f40429389
Improve handling of set operations with constant values on ARM
|
13 years ago |
|
florian
|
3b980cae63
* floating point compares use flags as well so allocate flags
|
13 years ago |
|
florian
|
45383fd32d
+ a lot missing flag allocs/deallocs added
|
13 years ago |
|
florian
|
d8161c185c
+ track usage of flags by using a new register RS_/NR_DEFAULTFLAGS
|
13 years ago |
|
masta
|
8a684c1f10
Don't generate IT instruction in second_cmp64bit for Thumb-2
|
13 years ago |
|
florian
|
d5aa89449e
* generate less register wasting code for 64 bit comparions
|
13 years ago |
|
Jonas Maebe
|
6ba8dc7146
+ support for the ARM hard float EABI on Linux (patch by Peter Green):
|
13 years ago |
|
Jonas Maebe
|
d1538ab023
o added ARM VPFv2/VFPv3 support:
|
15 years ago |
|
florian
|
515774b864
* merged armthum branch
|
16 years ago |
|
florian
|
7ef191021f
+ check for location.loc<>expectloc in extdebug mode
|
17 years ago |
|
Jonas Maebe
|
1d96dcc50d
* renamed nf_swaped to nf_swapped
|
18 years ago |
|
florian
|
85d63d9fa9
* settings refactored
|
19 years ago |
