sgminer/findnonce.h

#ifndef __FINDNONCE_H__
#define __FINDNONCE_H__
#include "miner.h"
#include "config.h"

#define MAXTHREADS (0xFFFFFFFEULL)
#define MAXBUFFERS (0x10)
#define BUFFERSIZE (sizeof(uint32_t) * MAXBUFFERS)
#define FOUND (0x0F)

#ifdef HAVE_OPENCL
extern void precalc_hash(dev_blk_ctx *blk, uint32_t *state, uint32_t *data);
extern void postcalc_hash_async(struct thr_info *thr, struct work *work, uint32_t *res);
#endif /* HAVE_OPENCL */
#endif /*__FINDNONCE_H__*/
Make postcalc_hash asynchronous as well. 2011-06-27 11:31:05 +10:00			`#ifndef __FINDNONCE_H__`
			`#define __FINDNONCE_H__`
Merge gpumining from oclmine. Unstable. 2011-06-14 10:32:54 +10:00			`#include "miner.h"`
Make it possible to build without opencl for cpu mining only. 2011-07-05 19:47:03 +10:00			`#include "config.h"`
Merge gpumining from oclmine. Unstable. 2011-06-14 10:32:54 +10:00
Ensure that we don't overflow due to 32 bit limitations. 2011-06-29 11:19:43 +10:00			`#define MAXTHREADS (0xFFFFFFFEULL)`
Use atomic ops to never miss a nonce on opencl kernels, including nonce==0, also allowing us to make the output buffer smaller. 2012-08-23 10:48:15 +10:00			`#define MAXBUFFERS (0x10)`
Move to 256 sized buffers and don't risk overwrite by using only 127 mask. 2011-08-17 16:07:15 +10:00			`#define BUFFERSIZE (sizeof(uint32_t) * MAXBUFFERS)`
Use atomic ops to never miss a nonce on opencl kernels, including nonce==0, also allowing us to make the output buffer smaller. 2012-08-23 10:48:15 +10:00			`#define FOUND (0x0F)`
Fixes. 2011-06-17 14:00:41 +10:00
Make it possible to build without opencl for cpu mining only. 2011-07-05 19:47:03 +10:00			`#ifdef HAVE_OPENCL`
Merge gpumining from oclmine. Unstable. 2011-06-14 10:32:54 +10:00			`extern void precalc_hash(dev_blk_ctx blk, uint32_t state, uint32_t *data);`
Use a buffer of up to 512 * 4 integers when retrieving work from the GPU. This allows each local thread id to have one slot to put any positive results into, thus making overlapping results far less likely. Thus races will be much rarer, allowing more threads. It should also pick up blocks close to each other more reliably and hopefully decrease the number of rejects and opencl errors. Do the search over the buffer entirely in a separate thread to allow the GPU to stay as busy as possible. Detach threads from themselves to prevent unlucky even where dereferencing occurs by freeing the data that stores the thread info. 2011-06-29 23:38:16 +10:00			`extern void postcalc_hash_async(struct thr_info thr, struct work work, uint32_t *res);`
Make it possible to build without opencl for cpu mining only. 2011-07-05 19:47:03 +10:00			`#endif /* HAVE_OPENCL */`
Make postcalc_hash asynchronous as well. 2011-06-27 11:31:05 +10:00			`#endif /__FINDNONCE_H__/`