Tanguy Pruvot
aaa24a6262
stats: submit real freqs and plimit to yiimp benchmarks
2017-02-05 13:20:38 +01:00
Tanguy Pruvot
ef44e88ef9
ccminer: link --max-log-rate to the command line
2017-01-30 12:36:50 +00:00
Tanguy Pruvot
b9da6c67f5
improve jh512 with vectors (nist5,quark,sib,x11+,zr5)
...
the main improvement is to reduce asm calls to read global mem
but, a few more regs are used (68 mini vs 64 on SM 5.2)
so reduce the forced launch bounds to allow 80 or 128 regs per thread
Note: cuda 6.5 seems not able to store with v4.u32... (7.5 is fine)
st.global.v4.u32 [%rd2], {%r3783, %r3824, %r3823, %r3822};
st.global.v2.u32 [%rd2+16], {%r3821, %r3820};
st.global.u32 [%rd2+24], %r3819;
st.global.u32 [%rd2+28], %r3818;
st.global.u32 [%rd2+44], %r3814;
st.global.u32 [%rd2+40], %r3815;
...
todo, check alexis variant.. but wanted to keep this code before in git...
2017-01-30 07:27:01 +01:00
Tanguy Pruvot
6440a9bf41
windows: some default intensity adjustments
2017-01-30 02:31:44 +01:00
Tanguy Pruvot
2152fd102d
lbry cleanup, and proper error on cuda 6.5
...
both merged and unmerged implementations are broken with CUDA 6.5
No perf changes...
2017-01-30 02:31:28 +01:00
Tanguy Pruvot
aaef92cab2
nvml: workaround for beta drivers 378.49 clocks
...
even nvidia-smi doesnt report the right pascal clocks
2017-01-29 22:23:05 +01:00
Tanguy Pruvot
b47d9acaf5
readme + small warnings detected by vstudio
2017-01-29 22:23:05 +01:00
Tanguy Pruvot
c8ff854456
sia was migrated too...
2017-01-29 06:10:08 +01:00
Tanguy Pruvot
0ff75791e5
migrate 2nd nonce storage of most algos
...
This allow to keep pdata[19] as cursor between scans, and later, to sort them..
remains... heavy, scrypt, sia...
2017-01-29 05:46:45 +01:00
Tanguy Pruvot
5a77d36635
groestl: explain code and improve perf on SM 2.x
...
Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com>
2017-01-29 00:51:42 +01:00
Tanguy Pruvot
feb99d020f
skein: merge the double implementations in one
...
based on alexis skein kernels, tested ok on SM 2.1 and 3.0
code is a bit hard to read but... well... users dont care :p
2017-01-29 00:01:06 +01:00
Tanguy Pruvot
16ac9b688f
x13+: improve and clean a bit fugue512
...
reduce constant mem and load global data in bulk (vectors)
2017-01-29 00:00:43 +01:00
Tanguy Pruvot
013cda1cd2
ccminer: show first block diff even with -q
2017-01-29 00:00:28 +01:00
Tanguy Pruvot
496052e47d
xmr: vstudio warning fix about mpcount linkage
...
and move ptr type cast defines to common cuda helper
2017-01-25 21:16:31 +00:00
Tanguy Pruvot
dc816b4673
xmr: nicehash nonce prefix/hack support (v2)
2017-01-22 23:19:22 +01:00
Tanguy Pruvot
def9888bd5
xmr: prefer 32bit uint4 and smaller offsets in core
...
also prefer ulong2 shared load to be closer to the ptx
2017-01-16 06:36:24 +01:00
Tanguy Pruvot
214f392778
xmr: default settings with card attributes
2017-01-15 01:42:25 +01:00
Tanguy Pruvot
94aa6b8e91
ccminer: allow 192 car. for the username
2017-01-14 18:55:36 +01:00
Tanguy Pruvot
588c7ba361
xmr: dont use shared mem hack, windows dont like
2017-01-14 15:13:31 +01:00
Tanguy Pruvot
bd030db5d1
xmr: vectors rewrite, now the phase2 is using only 40 regs
...
no more constant memory used for aes.
tested only on linux cuda 8 for now... wip
2017-01-14 04:34:23 +01:00
Tanguy Pruvot
23be7f308d
xmr: link the --bfactor setting (0-11)
2017-01-12 23:02:00 +01:00
Tanguy Pruvot
e231343060
xmr: make it more smooth on windows with defaults
...
also improve a bit the 750 ti on linux...
2017-01-12 06:00:59 +01:00
Tanguy Pruvot
12ae185594
hwmonitor: efficiency unit and clean dead code
2017-01-10 14:20:33 +01:00
Tanguy Pruvot
0dd022779b
power monitoring thread + some api changes
...
based on alexis monitoring thread idea, but which only use one thread
note: other api changes will come soon, related to that
2017-01-10 02:26:28 +00:00
Tanguy Pruvot
242aa4144b
scanlog: remember sharediff for multiple nonces
...
rpc2: handle properly secondary nonce(s) + api ping time fix
be sure to fully recompile, structures are changed
2017-01-09 18:40:00 +01:00
Tanguy Pruvot
93adb56c8e
handle cryptonight light variant
...
Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com>
2017-01-09 18:30:59 +01:00
Tanguy Pruvot
39aad5a003
xmr: allow to set intensity on command line
2017-01-08 22:36:03 +00:00
Tanguy Pruvot
804b5b5f53
xmr: be safe with diff divide
2017-01-08 21:28:54 +00:00
Tanguy Pruvot
2479ffaaa2
xmr: fix decimal diff + aes cleanup
...
change default launch config to -l 32x16 to handle the 750 Ti better
not definitive, doing tests..
2017-01-08 21:16:45 +00:00
Tanguy Pruvot
c1f1ad9280
xmr: stabilize the final kernel
2017-01-08 14:39:13 +01:00
Tanguy Pruvot
066a569357
import xmr, to finish
...
todo: fix jh cuda and wrong decimal diff (0xffff problem ?)
2017-01-07 01:40:59 +01:00
Tanguy Pruvot
2bbccc5ff4
wildkeccak, basic stratum port of rpc 2.0
...
scratchpad delete fix and redownload, reduce rejects
(work in progress)
2017-01-06 08:55:15 +01:00
Tanguy Pruvot
099389f64f
ccminer: be more quiet with -q, skip header noise
2016-12-30 15:18:35 +01:00
Tanguy Pruvot
50534789bc
Release 1.8.4
2016-12-21 20:35:09 +01:00
Tanguy Pruvot
c11901260a
limit per gpu hashrate logs to 3 sec intervals
...
may be required for very fast algos, like blake2s
2016-12-21 20:16:47 +01:00
Tanguy Pruvot
44bd244fc4
blake2s improved
...
based on alexis work, with the new work->nonces
2016-12-21 19:44:20 +01:00
Tanguy Pruvot
ce6a8da188
cuda: prevent ptxas crash with -n
2016-12-18 03:35:19 +01:00
Tanguy Pruvot
397472818d
prepare 1.8.4 release
2016-11-03 18:55:42 +01:00
Tanguy Pruvot
36aedbb48e
veltor update, 10x faster :p
...
From Alexis work, sib hash rate 200% also..
2016-11-03 18:54:29 +01:00
Tanguy Pruvot
3eba451d4c
nvml: add Elsa vendor and workaround for Colorful pid
...
Colorful (and Inno3D) only set their vid, with an empty product id
2016-10-25 03:40:07 +02:00
Tanguy Pruvot
c27f3139aa
update startup credits
2016-10-06 13:08:41 +02:00
Tanguy Pruvot
056098dd86
update readme
2016-09-29 03:37:36 +02:00
Tanguy Pruvot
7b82915032
cuda 8
2016-09-29 00:40:06 +02:00
Tanguy Pruvot
225f25a6b9
uint2: remove the slower asm in operators funcs
2016-09-28 07:12:05 +02:00
Tanguy Pruvot
665de3a1f2
sia: use the new work share diff
2016-09-28 01:28:04 +02:00
Tanguy Pruvot
1a31d4d2d6
sia: move specific code in a new rpc unit
...
part 1: longpoll stuff (nanopool)
2016-09-28 01:27:57 +02:00
Tanguy Pruvot
f84c83afe5
nvml: force 64bits types for mem sizes
...
size_t can be a bit... imprevisible on x86
2016-09-28 00:31:13 +02:00
Tanguy Pruvot
5a0b779434
api: use the new throughput2intensity func
2016-09-27 23:20:28 +02:00
Tanguy Pruvot
a43205a84f
decred: multiple nonces code cleanup
...
The double loop is not useful, and prefer the __thread attribute
to enhance the code readability (remove the 2D host arrays).
squashed: return to host 2D array to allow the free
2016-09-27 22:50:52 +02:00
Tanguy Pruvot
6f6cf966f8
lbry: new share diff and duplicate fix
...
when 2 nonces were found, the next scan was not at the right value
Doesn't really affect mining performance...
2016-09-27 22:50:51 +02:00
