| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
| |
If CUDA 9.X is used and the miner is compiled for `sm_70` and used with Volta GPUs than the miner
deadlocks if `threads` is not a multiple of `32`.
- use `__activemask()` to get all active lanes
|
| |
|
|
|
|
|
|
| |
solve #1494
- add algorithm `cryptonight_v7_stellite` (internal named: `cryptonight_stellite`)
|
|
|
|
|
| |
- add algorithm `cryptonight_lite_v7_xor`
- update documentation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- allow the dev pool to fork on a different block version than the user descriped coin
All algorithm are centered around the user coin description.
It is allowed to have two two different coin algorithms in the user coin description.
It is only allowed to use algorithms for the dev pool coin description those are used in the user coin description.
There are two ways to define a non forking coin.
- set both user coin algorithm descriptions to the same algorithm and set version to zero
- set the first algorithm in the user coin description to something you like to use in the dev pool
and set the second algorithm to the correct representation of the coin. Set the version to 255.
This will allow that the dev pool can mine on a different coin algorithm than the not forking user coin.
Do not use an algorithm with different scratchpad size for the dev pool.
|
|
|
|
| |
Use the maximum scratchpad size from before and after the fork.
|
| |
|
|
|
|
|
|
|
|
| |
sumokoin is broken if `bfactor >= 5` is used (default for windows)
sumokoin for `sm_20` is broken due to the missing extern shared memory
- call phase3 kernel two times if sumokoin is enabled
- create extern shared memory for phase3 kernel
|
|
|
|
|
|
| |
fix #1297
If sm_20 is mixed with other architectures the detection for the minimal supported architecture is broken.
|
|
|
|
|
| |
- add `fork_height` to currency
- refactor algorithm selection
|
|
|
|
|
| |
- add new pow for AEON
- fix missing cryptonight-heavy selection for multi hashes
|
|
|
|
| |
revert #1198, the block size is limited to 84byte
|
| |
|
| |
|
|
|
|
|
|
|
| |
Co-authored-by: psychocrypt <psychocryptHPC@gmail.com>
Co-authored-by: fireice-uk <fireice-uk@users.noreply.github.com>
Co-authored-by: Lee Clagett <code@leeclagett.com>
Co-authored-by: curie-kief <curie-kief@users.noreply.github.com>
|
|
|
|
|
|
|
| |
- enable L1 cache for Nvidia Volta GPUs and newer
- remove explicit cache controll for Volta GPU and newer
This pull request increases the hash rate for Volta GPUs by ~5%
|
|
|
|
| |
reduce memory usage to 1GiB for NVIDIA devices with <=6 SMX
|
|\
| |
| | |
handle cuda error codes
|
| |
| |
| |
| | |
handle all error codes from the cuda api calls.
|
|/
|
|
|
| |
- fix cuda9.1 compile (remove includ eof device_functions.hpp/ removed with cuda9.1)
- remove NVIDIA Volta gpus for MAC OSX
|
|
|
|
| |
Makes casting more explicit.
|
|
|
|
|
| |
When compiled with VS2017, the negative applied to the uint wait
time is ignored. Fixed by casting first.
|
|
|
|
| |
- fix indention
|
|
|
|
|
|
|
|
| |
Be more conservative with the auto suggestion.
- increase bfactor if `smx <= 6`
- limit memory for pascal < GTX1070 to 2GiB
- limt memory for pascal <= GTX1080 to 4GiB
|
|\
| |
| | |
add message to `CUDA_CHECK...` macros
|
| |
| |
| |
| |
| | |
- add macro `CUDA_CHECK_MSG_KERNEL` and `CUDA_CHECK_MSG`
- add suggestion of typicle errors can be solved
|
|/
|
|
|
| |
- add option `sync_mode`
- update auto suggestion and jconf
|
|\
| |
| | |
fix CUDA launch bounds usage
|
| |
| |
| |
| |
| |
| | |
fix #191
lauch bounds must be placed before the return type but after the template paramater
|
|/
|
|
| |
Increase bfactor for all devices with lesser than 6 multi processors.
|
|\
| |
| | |
fix wrong cuda binary arch detection
|
| |
| |
| |
| | |
fix wrong arch comparsion
|
|/
|
|
|
| |
The lmem is still incalculably and crash the miner very often.
Increase the potential lmem usage to 16kiB to respect lmem alignments, ...
|
| |
|
|
|
|
|
|
| |
- check if the gpu architecture is supported by the compiled miner binary
- remove not supported gpus from the auto suggestion
- disallow the selection of a not supported gpu by hand tuning the config
|
|
|
|
|
|
|
|
|
| |
Free and total memory is only evaluated on the first device.
To detect the gpu memory the gpu must be selected.
- create context on the gpu before the memory is checked
- add smx to the auto detection
- change the result code of `cuda_get_deviceinfo()`
|
|
|
|
|
| |
- avoid creation of a config with zero threads or blocks
- WINDOWS: reduce the used memory for the auto suggestion by the amount of already used memory
|
|
|
|
|
| |
- fix windows linker error during compile
- fix wrong parameter to call aeon (nvidia-backend)
|
|
|
|
|
| |
- increase safty memory from 64 to 128 MiB
- NVIDIA: increase lmem reserve per thread to 1kiB
|
|
|
|
|
|
| |
- rename all `xmr` to `monero`
- be insensitive while check for set currency
- add function to compate two strings insensitive
|
|
|
|
|
| |
- add template parameter to kernel to support aeon and xmr
- update auto suggestion
|
|\
| |
| | |
fix illegal memory access
|
| |
| |
| |
| | |
remove restricted pointer
|
|/
|
|
| |
use `__shffl_snyc` if CUDA 9+ is avalable
|
| |
|
|
- move source code to `src`
- categorize files and move to group folder
- change upper case class files to lower case
- change C++ header to `*.hpp`
|