sgminer

Commit Graph

Author	SHA1	Message	Date
Con Kolivas	f90e73af51	Queue and pop precisely the same amount of work in flush_request to ensure all work is cleared and there isn't an uneven add/remove possible.	14 years ago
Con Kolivas	af6e7937ca	Signal handling in dns lookup code is responsible for libcurl crashes when multithreading. Disable signal handling and use many curl handles instead, thus making work more asynchronous. Theoretically a curl can wait forever on a dns lookup with this but it's extremely unlikely.	14 years ago
Con Kolivas	91f9c527ba	Rename code and application binary to cgminer version 1.0.9 preempting version 1.1.0, moving main code to main.c.	14 years ago
Con Kolivas	8f098e4ab4	Put locking around the queued count to ensure we're never left without work.	14 years ago
Con Kolivas	122f0cf260	With pre-emptive queueing of work there is no need to have extra work in the queue by default. Make it a list of extra queue items instead of a total and default to 0.	14 years ago
Con Kolivas	5cbc33e756	Change default retry to 5 seconds.	14 years ago
Con Kolivas	de3d07d13b	Make the next work item queue 2/3 of the way through the work on the current work item. Load the first queued extra work in the main function to avoid having a once-off variable in get_work(). Load an extra set of work for each function in advance once a longpoll is detected since every thread will need to get new work. Discard requests with a separate function to ensure the right number is always queued.	14 years ago
Con Kolivas	ad787e1c2a	Move the flushing of old work into restart threads so it's done before any worker threads grab more work.	14 years ago
Con Kolivas	5007805d1f	Update CPU reentrant scan code to work properly for extended periods up to scantime and adjust rate properly. Simplify locking in hashmeter since it's called relatively infrequently anyway. Set gpuminer hashmeter interval update to log interval / 5 as well.	14 years ago
Con Kolivas	e4f9ea68a9	CPU mining is spending too much time in the work thread and not receiving restart messages. Update the code to return at log interval / 5 and only get work at the right time.	14 years ago
Con Kolivas	8999bea110	People expect miners to run indefinitely instead of giving up by default so change to never giving up if json call fails.	14 years ago
Con Kolivas	9f726400d4	Logic error in the queueing of work ended up generating more stale blocks. There is a small chance that a longpoll is signalled right at the start which would lead to a deadlock so check for first work before restart.	14 years ago
Con Kolivas	594b38b8cb	Fix redefinition of gnu source.	14 years ago
Ycros	9fe2106467	Fixed up using config.h instead of cpuminer-config.h.	14 years ago
Con Kolivas	edd0591e19	Make the number of queued work items configurable and default to 2.	14 years ago
Con Kolivas	131f60a5ee	Move queueing of one request to separate function in preparation for variable length queues.	14 years ago
Con Kolivas	ffdffe77d3	Make sure the work gets attributed to the correct gpu. Add an fflush to stderr to minimise garbled output when multiple threads write at once.	14 years ago
Con Kolivas	86e40ed9c8	Stale block control makes it possible to make 2 threads per gpu the default again.	14 years ago
Con Kolivas	48caf248a7	Check for stale block after failed submission as well.	14 years ago
Con Kolivas	09104ce3e8	Flag the work back to just thread 0 used by all the threads to avoid lots of queued older work for each thread.	14 years ago
Con Kolivas	bed692152f	Get rid of the requirement for a static struct that needs locking to cache work. Make it possible to use the thread id for getting work again. Flag the getwork() function when we have a new block to explicitly discard any cached work when a new block is detected. Store the header of each new work and compare it to blocks we're about to submit to decide if they're stale due to a new block and don't try to submit them. This should significantly decrease the number of rejected blocks.	14 years ago
Con Kolivas	e2fb3e84cb	Queueing all kernel parameters dramatically reduces stale block rates.	14 years ago
ckolivas	7ae9afc40f	Profile points and warning clean ups.	14 years ago
ckolivas	b54a342529	Change default number of threads back to 1. The 2nd just increases the time taken to complete a work item thus increasing stale blocks, despite increasing the rate slightly.	14 years ago
Con Kolivas	88d9d631e3	Use two separate curl instances for submit and get and use separate threads for each to prevent one blocking the other.	14 years ago
Con Kolivas	72baac0889	Clearly delineate the cpus from the gpus for their local data.	14 years ago
Con Kolivas	142576a961	We already have gpu/cpu from id, so use that. Likely the current convoluted code is wrong and leading to segfaults!	14 years ago
Con Kolivas	18f8b0f9a5	Submit work async is still unreliable and only used for cpu mining, so back it out for now.	14 years ago
Con Kolivas	d5d4d1da16	Don't want to free the work data out of the transient structs.	14 years ago
Con Kolivas	d100281df3	Make sure correct thread id is in work struct and correct cpu is set for per-cpu data.	14 years ago
Con Kolivas	998d8d45f4	Postcalc hash is already its own thread so work can be submitted synchronously from that.	14 years ago
Con Kolivas	2b6e841673	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.	14 years ago
ckolivas	6af84770d0	Add spaces to make output clearer.	14 years ago
ckolivas	e1dd27c5c2	Ensure that we don't overflow due to 32 bit limitations.	14 years ago
ckolivas	b38a02bd24	Make the log time hash rate a rolling exponential average so it doesn't fluctuate so dramatically.	14 years ago
ckolivas	08a7821072	Make the log show what the thread is: cpu or gpu and what number.	14 years ago
ckolivas	f490143a9a	Add local thread count to info, store hw error count, and make share submission debug only.	14 years ago
Con Kolivas	e016d0c8f3	Increase maximum intensity configurable to 14.	14 years ago
Con Kolivas	dfc52fd543	Make sure we can have gpu and cpu threads running.	14 years ago
Con Kolivas	24a28e29e9	Make it possible to run as a pure cpu miner by setting gpu threads to 0.	14 years ago
ckolivas	e1d01d0635	Minor fixes.	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. Fallback to the poclbm kernel for the rest. Try harder to avoid stale blocks around longpoll detecting new blocks.	14 years ago
Con Kolivas	948b514cf2	The buffer needs to be flushed before enqueueing the kernel again. Further optimise the mining loop by removing the need_work bool.	14 years ago
Con Kolivas	a45c54aaf8	Make postcalc_hash asynchronous as well.	14 years ago
Con Kolivas	378d18f8eb	Submit all work asynchronously via a submit_work thread.	14 years ago
Con Kolivas	612c3a456f	Curl doesn't like multiple instances so go back to one instance.	14 years ago
Con Kolivas	f0dcd127b4	Show which cpu mining thread when giving affinity message.	14 years ago
Con Kolivas	58f6bf42e2	Prevent 32bit overflow of local_mhashes as well.	14 years ago
Con Kolivas	00de822534	Upper limit should be -hashes.	14 years ago
Con Kolivas	c29a4322dd	Only update the hashmeter once per second from gpu mining threads.	14 years ago

3 Commits (bbac2b938beeb3d97abd54bd9b0ad2081da25cd5)