sgminer

Commit Graph

Author	SHA1	Message	Date
Noel Maersk	5f326d64f5	kernel: allow choosing Alexey Karimov's kernels. Am I the only one who gets a segfault?..	11 years ago
Noel Maersk	81337e0064	kernel: vanilla Alexey Karimov kernels (alexkarnew and alexkarold). alexkarnew: (for driver 13.4 and newer, and cgminer 3.3.1) alexkarold: (for older drivers than 13.4, and cgminer 3.3.1) https://litecointalk.org/index.php?topic=4082.0 > I was able to optimize the code of cgminer's scrypt.cl. > It gives 0-3% increase, depending on the drivers and hardware. > 1. Without optimization, when "CO" is used, every time > z+xzSIZE+yxSIZEzSIZE is calculated. > I have created "CO" variable, and made so that xSIZE is calculated only > once. Now, when "CO" is used, every time z+yxSIZEzSIZE is calculated. > In one case, variable y is incremented by 1 after 8 "CO" calculations. > I have created "CO_tmp" variable, where contains result of xSIZEzSIZE. > And after 8 "CO" calculations I add "CO_tmp" to "CO". > Now, when "CO" is used, every time only z is calculated. It is faster as > z+xzSIZE+yxSIZEzSIZE :) > In other case when "CO" is used, every time z+yxSIZEzSIZE is > calculated, but it faster than z+xzSIZE+yxSIZE*zSIZE too. > 2. I have replaced multiplication by 2 with bit rotation - it is faster. > For 7xxx cards you can try to set --thread-concurrency equal to (2^n + 1). > It may give a little more mining speed. > For example: 16385 (it is 2^14 + 1), 8193 (2^13 + 1), or 4097 (2^12 + 1). > I have almost no information, how it works on other series. > LMqRcHdwnZtTMH6c2kWoxSoKM5KySfaP5C	11 years ago
Gabriel A. Devenyi	a6ccc05e5f	Replace multiply by 2 (i*2) with left shift. This should be slightly faster. Can't use OpenCL rotate becase of bit carry overs	11 years ago
Noel Maersk	f796aa51ca	kernel/misc: change ckolivas.cl encoding to UTF-8.	11 years ago
Noel Maersk	9d1db95a28	misc: move scrypt130511.cl kernel file to kernel/ckolivas.cl Prepare for more kernels. :) Get rid of the kernel date, since this fudges up commit history. Named after Con Kolivas, the most recent committer.	11 years ago
Noel Maersk	95586f72f0	Squash-merge branch dead-end with unnecessary check removals.	11 years ago
Con Kolivas	b196d4fa0c	Support more shares to be returned for scrypt mining.	12 years ago
Con Kolivas	580607cf1c	Update kernel file names signifying changes.	12 years ago
Con Kolivas	7f595ca04b	Use global constant arrays for all other constants used in scrypt kernel.	12 years ago
Con Kolivas	9b6a518acf	Use global __constants for sha functions in scrypt kernel.	12 years ago
Con Kolivas	6bb942ffe5	Use constants for endian swap macros.	12 years ago
Con Kolivas	f08c3f766d	Revise scrypt kernel copyright notice.	12 years ago
Con Kolivas	3d032ce615	Separate out additions in scrypt kernel.	12 years ago
ckolivas	53c3cce6ac	Bump opencl kernel version numbers.	12 years ago
ckolivas	775a27281a	Remove atomic ops from opencl kernels given rarity of more than once nonce on the same wavefront and the potential increased ramspeed requirements to use the atomics.	12 years ago
Con Kolivas	9bec1e158e	Simplify macros in output kernels avoiding apparent loops and local variables.	12 years ago
Con Kolivas	4fbe5bed15	OpenCL 1.0 does not have native atomic_add and extremely slow support with atom_add so detect opencl1.0 and use a non-atomic workaround.	12 years ago
Con Kolivas	f7f55e777d	Increase kernel versions signifying changed APIs.	12 years ago
Con Kolivas	86d5377e72	Use atomic ops to never miss a nonce on opencl kernels, including nonce==0, also allowing us to make the output buffer smaller.	12 years ago
Con Kolivas	bff58c3bed	Add back in new cl files.	12 years ago

2 Commits (abeeff3d454572377c04c5f19a3dad0e18881854)