 Con Kolivas
|
4d73057772
Build binaries with unique filenames from the kernel generated and save them.
|
14 years ago |
|
Con Kolivas
|
973b2199e1
Tidy.
|
14 years ago |
|
Con Kolivas
|
2b6e841673
Use a buffer of up to 512 * 4 integers when retrieving work from the GPU.
|
14 years ago |
|
ckolivas
|
1dfbe60353
Put sanity limit on work size since some nvidia fail :(
|
14 years ago |
|
Con Kolivas
|
6374e0fafe
Import the phatk kernel. Enable it only for hardware with amd media ops for now since it crashes nvidia et. al.
|
14 years ago |
|
Con Kolivas
|
2dbb39444d
Base was being set wrongly meaning we were repeating searches and the rate was actually lower than displayed :(
|
14 years ago |
|
Con Kolivas
|
c566605195
Tab dainbramage.
|
14 years ago |
|
Con Kolivas
|
11c8818558
32 bit only builds one elf, not an elf in an elf, so account for it to be able to bfi int patch properly.
|
14 years ago |
|
Con Kolivas
|
623b9b9fd8
Patch bitalign separately from bfi_int.
|
14 years ago |
|
Con Kolivas
|
06f3950658
Fix typo which prevented BFI INT patch working on multi-GPUs.
|
14 years ago |
|
Con Kolivas
|
30e38e2ef8
Typo i - gpu
|
14 years ago |
|
Con Kolivas
|
fdb46f2d9b
32bit fixes.
|
14 years ago |
|
Con Kolivas
|
656b485d80
Make the worksize and vector width configurable.
|
14 years ago |
|
Con Kolivas
|
401586f92a
Only try to patch GPU referenced.
|
14 years ago |
|
Con Kolivas
|
ac4ab6afdc
Fix mutli-gpu initialisation when BFI_INT patching.
|
14 years ago |
|
ckolivas
|
64f268c8c7
Display correct worksize.
|
14 years ago |
|
Con Kolivas
|
808d5b07f9
Make output debug.
|
14 years ago |
|
ckolivas
|
feb8cfc8fa
applog fixes.
|
14 years ago |
|
ckolivas
|
26546ad5b9
Make the optimisations per-gpu card and update code to work properly with multiple cards.
|
14 years ago |
|
Con Kolivas
|
afc83cb25b
Need gnu_source for memmem to work properly.
|
14 years ago |
|
Con Kolivas
|
4cd5f47efa
Revert "Multiple compiler warning fixes."
|
14 years ago |
|
Con Kolivas
|
88761e6cf2
Multiple compiler warning fixes.
|
14 years ago |
|
ckolivas
|
d28f526b1e
Need memmem in advance() to work properly for patching.
|
14 years ago |
|
ckolivas
|
19eea9067f
Implement code detecting max work size and optimal vector width.
|
14 years ago |
|
ckolivas
|
33352213eb
Report preferred vector width.
|
14 years ago |
|
Con Kolivas
|
407df0f4b1
Use correct boolean testing and long enough string for cl_amd_media ops testing and kernel changing.
|
14 years ago |
|
ckolivas
|
c2e4165590
Detect platforms that support cl_amd_media_ops and decide whether to BFI_INT patch or not.
|
14 years ago |
|
ckolivas
|
b4d2733cfc
Convert to poclbm kernel.
|
14 years ago |
|
ckolivas
|
79fec01a46
Remove the input buffer and just pass args to the kernel as per plugin design.
|
14 years ago |
|
Con Kolivas
|
f05270b8c8
Optimise loop and make debug debug only.
|
14 years ago |
