Arch Linux User Repository

+pkgbase = mfaktc

+ pkgdesc = A CUDA program for Mersenne prefactoring.

+ pkgver = 0.21

+ pkgrel = 1

+ url = https://mersenneforum.org/showthread.php?t=12827

+ arch = x86_64

+ license = GPL3

+ makedepends = cuda

+ depends = nvidia

+ source = https://download.mersenne.ca/mfaktc/mfaktc-0.21/mfaktc-0.21.tar.gz

+ source = mfaktc.ini

+ source = makeandparams.patch

+ md5sums = 292d9a3bee013e9992ab199dfdfeece9

+ md5sums = edf7197ee8d1e5d99ce8a9acf9287ea7

+ md5sums = 2acc9b787a77a2e6ba07cbd0904c776b

+ sha256sums = 1973b5fae564035a33aa89bcb1a7e6dae571307a874e2eeb845e5b93939c2079

+ sha256sums = SKIP

+ sha256sums = SKIP

+

+pkgname = mfaktc

+

+#Maintainer: Dylan Delgado <dylan1496 at live dot com>

+

+pkgname=mfaktc

+pkgver=0.21

+pkgrel=1

+pkgdesc="A CUDA program for Mersenne prefactoring."

+arch=('x86_64')

+url="https://mersenneforum.org/showthread.php?t=12827"

+license=('GPL3')

+depends=('nvidia')

+makedepends=('cuda')

+source=("https://download.mersenne.ca/${pkgname}/${pkgname}-${pkgver}/${pkgname}-${pkgver}.tar.gz"

+"mfaktc.ini"

+"makeandparams.patch")

+md5sums=('292d9a3bee013e9992ab199dfdfeece9'

+'edf7197ee8d1e5d99ce8a9acf9287ea7'

+'2acc9b787a77a2e6ba07cbd0904c776b')

+sha256sums=('1973b5fae564035a33aa89bcb1a7e6dae571307a874e2eeb845e5b93939c2079'

+'SKIP'

+'SKIP')

+

+prepare() {

+cd ${srcdir}/${pkgname}-${pkgver}/src

+patch -p2 < "../../../makeandparams.patch"

+}

+

+build () {

+cd ${srcdir}/${pkgname}-${pkgver}/src

+make -f Makefile all

+}

+

+package () {

+cd ${srcdir}/${pkgname}-${pkgver}

+install -Dm755 mfaktc.exe ${pkgdir}/usr/bin/mfaktc

+cd ..

+install -Dm755 mfaktc.ini ${pkgdir}/etc/mfaktc/mfaktc.ini

+echo "A default mfaktc.ini file will be installed"

+echo "in /etc/mfaktc/mfaktc.ini. Copy this to the"

+echo "directory where you want to run mfaktc."

+} \ No newline at end of file

+diff --unified --recursive --text mfaktc-0.21/src/Makefile mfaktc-0.21-new/src/Makefile

+--- mfaktc-0.21/src/Makefile 2015-02-17 15:12:49.305144447 -0500

++++ mfaktc-0.21-new/src/Makefile 2020-12-06 16:39:26.876217215 -0500

+@@ -1,5 +1,5 @@

+ # where is the CUDA Toolkit installed?

+-CUDA_DIR = /usr/local/cuda

++CUDA_DIR = /opt/cuda

+ CUDA_INCLUDE = -I$(CUDA_DIR)/include/

+ CUDA_LIB = -L$(CUDA_DIR)/lib64/

+

+@@ -13,11 +13,15 @@

+ NVCCFLAGS = $(CUDA_INCLUDE) --ptxas-options=-v

+

+ # generate code for various compute capabilities

+-NVCCFLAGS += --generate-code arch=compute_11,code=sm_11 # CC 1.1, 1.2 and 1.3 GPUs will use this code (1.0 is not possible for mfaktc)

+-NVCCFLAGS += --generate-code arch=compute_20,code=sm_20 # CC 2.x GPUs will use this code, one code fits all!

+-NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code

+-NVCCFLAGS += --generate-code arch=compute_35,code=sm_35 # but CC 3.5 (3.2?) _CAN_ use funnel shift which is useful for mfaktc

+-NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code

++# note, CUDA 11.1 supports CC 3.5+ (some Kepler, Maxwell, Pascal, Volta, Turing and Ampere)

++NVCCFLAGS += --generate-code arch=compute_35,code=sm_35 # CC 3.5 and 3.7 cards will use this code (some Kepler cards)

++NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code (Maxwell)

++NVCCFLAGS += --generate-code arch=compute_60,code=sm_60

++NVCCFLAGS += --generate-code arch=compute_61,code=sm_61 # CC 6.x GPUs will use this code (Pascal)

++NVCCFLAGS += --generate-code arch=compute_70,code=sm_70 # Titan V and Tesla V100 will use this code

++NVCCFLAGS += --generate-code arch=compute_75,code=sm_75 # CC 7.5 GPU's will use this code (Volta)

++NVCCFLAGS += --generate-code arch=compute_80,code=sm_80 # CC 8.0 GPU's will use this code (Tesla A100)

++NVCCFLAGS += --generate-code arch=compute_86,code=sm_86 # CC 8.6 GPU's will use this code (Ampere)

+

+ # pass some options to the C host compiler (e.g. gcc on Linux)

+ NVCCFLAGS += --compiler-options=-Wall

+diff --unified --recursive --text mfaktc-0.21/src/params.h mfaktc-0.21-new/src/params.h

+--- mfaktc-0.21/src/params.h 2015-02-17 15:12:49.322145383 -0500

++++ mfaktc-0.21-new/src/params.h 2020-12-06 16:51:24.334385208 -0500

+@@ -175,7 +175,7 @@

+

+ #define GPU_SIEVE_SIZE_MIN 4 /* A 4M bit sieve seems like a reasonable minimum */

+ #define GPU_SIEVE_SIZE_DEFAULT 64 /* Default is a 16M bit sieve */

+-#define GPU_SIEVE_SIZE_MAX 128 /* We've only tested up to 128M bits. The GPU sieve code may be able to go higher. */

++#define GPU_SIEVE_SIZE_MAX 2047 /* We've only tested up to 128M bits. The GPU sieve code may be able to go higher. */

+

+ #define GPU_SIEVE_PROCESS_SIZE_MIN 8 /* Processing 8K bits in each block is minimum (256 threads * 1 word of 32 bits) */

+ #define GPU_SIEVE_PROCESS_SIZE_DEFAULT 16 /* Default is processing 8K bits */

+# SievePrimes defines how far the factor candidates (FCs) are presieved on

+# the CPU. The first <SievePrimes> odd primes are used to sieve the FCs.

+#

+# Minimum: SievePrimes=2000 (check SievePrimesMin)

+# Maximum: SievePrimes=200000

+#

+# Default: SievePrimes=25000

+

+SievePrimes=25000

+

+

+# Set this to 1 to enable automatically adjustments of SievePrimes during

+# runtime based on the "average wait times".

+#

+# Default: SievePrimesAdjust=1

+

+SievePrimesAdjust=1

+

+

+# Set the minimum and maximum limit for SievePrimes, this is needed if

+# SievePrimesAdjust is enabled. These are soft limits, there are hard limits

+# in the code which should never ever be changed.

+#

+# Current limits are:

+# 2000 <= SievePrimesMin <= SievePrimes <= SievePrimesMax <= 200000

+#

+# Default: SievePrimesMin=5000

+# SievePrimesMax=100000

+

+SievePrimesMin=5000

+SievePrimesMax=100000

+

+

+# Set the number of CUDA streams / data sets used by mfaktc.

+# NumStreams must be >= 1. In this case mfaktc can process one stream /

+# data set on the GPU while the GPU can preprocess the other one. When

+# NumStreams is >= 2 than the time needed to upload (CPU->GPU transfer)

+# the data sets can be hidden (if the hardware supports it (most GPUs are

+# supporting this)).

+# On Linux systems 2 or 3 seems a good numbers. There are comments that

+# Windows systems need a greater number of streams.

+# A greater number increases the memory consumed by mfaktc (host and GPU

+# memory). The current limit for the number of streams is 10!

+# Don't be too greedy with this value, high values are usualy just a waste

+# of memory.

+#

+# Minimum: NumStreams=1

+# Maximum: NumStreams=10

+#

+# Default: NumStreams=3

+

+NumStreams=3

+

+

+# Set the number of data sets which can be preprocessed on CPU. This allows

+# to tolerate more jitter on runtime of preprocessing and GPU stream

+# runtime.

+# Don't be too greedy with this value, high values are usualy just a waste

+# of memory.

+#

+# Minimum: CPUStreams=1

+# Maximum: CPUStreams=5

+#

+# Default: CPUStreams=3

+

+CPUStreams=3

+

+

+# The GridSize affects the number of threads per grid.

+# Depending on the number of multiprocessors of your GPU, too, the

+# automatic parameter threads per grid is set to:

+# GridSize = 0: 65536 < threads per grid <= 131072

+# GridSize = 1: 131072 < threads per grid <= 262144

+# GridSize = 2: 262144 < threads per grid <= 524288

+# GridSize = 3: 524288 < threads per grid <= 1048576 (default)

+# A smaller GridSize has more overhead than a bigger GridSize for long

+# running jobs. For really small jobs there can be a small benefit on

+# computation time if the GridSize is small. A smaller GridSize directly

+# reduces the runtime per kernel launch and might result in a better

+# interactivity one older GPUs.

+#

+# Default: GridSize=3

+

+GridSize=3

+

+

+# Checkpoints = 0: disable checkpoints

+# Checkpoints = 1: enable checkpoints

+# Checkpoints are needed for resume capability, after a class is finished a

+# checkpoint file is written. When mfaktc is interrupted during the run and

+# restarted later it will begin at the last processed class.

+#

+# Default: Checkpoints=1

+

+Checkpoints=1

+

+

+# CheckpointDelay is the time in seconds between two checkpoint writes.

+# Allowed values are 0 <= CheckpointDelay <= 900.

+#

+# Minimum: CheckpointDelay=0

+# Maximum: CheckpointDelay=900

+#

+# Default: CheckpointDelay=30

+

+CheckpointDelay=30

+

+

+# WorkFileAddDelay defines, how often mfaktc should check for worktodo.add.

+# When a worktodo.add is deteced it will wait WorkFileAddDelay seconds until

+# processing it.

+#

+# Minimum: WorkFileAddDelay=30 (WorkFileAddDelay=0 disables this feature)

+# Maximum: WorkFileAddDelay=3600

+#

+# Default: WorkFileAddDelay=600

+

+WorkFileAddDelay=600

+

+

+# Allow to split an assignment into multiple bit ranges.

+# 0 = disabled

+# 1 = enabled

+# Enabled Stages make only sense when StopAfterFactor is 1 or 2.

+# Do not change this in the middle of a run which spans over multiple

+# bitlevels, in this case mfaktc will ignore the checkpoint file and

+# restarts from the beginning.

+#

+# Default: Stages=1

+

+Stages=1

+

+

+# possible values for StopAfterFactor:

+# 0: Do not stop the current assignment after a factor was found.

+# 1: When a factor was found for the current assignment stop after the

+# current bitlevel. This makes only sense when Stages is enabled.

+# 2: When a factor was found for the current assignment stop after the

+# current class.

+#

+# Default: StopAfterFactor=1

+

+StopAfterFactor=1

+

+

+# possible values for PrintMode:

+# 0: print a new line for each finished class

+# 1: overwrite the current line (more compact output)

+#

+# Default: PrintMode=0

+

+PrintMode=0

+

+

+# allow the CPU to sleep if nothing can be preprocessed?

+# 0: Do not sleep if the CPU must wait for the GPU

+# 1: The CPU can sleep for a short time if it has to wait for the GPU

+#

+# Default: AllowSleep=0

+

+AllowSleep=0

+

+

+# if V5UserID and ComputerID are specified, then the result lines in the

+# results file will have the prefix "UID: user/host, " - the same way as

+# prime95 does it.

+#

+# Default: none (unset)

+#

+#V5UserID=TheJudger

+#ComputerID=Ananke

+

+

+# TimeStampInResults allows to configure if each output line in the results

+# file should be preceeded with a date-and-time stamp (similar to prime95)

+#

+# Default: TimeStampInResults=0

+

+TimeStampInResults=0

+

+

+# PrintFormat allows to customize the progress output of mfaktc. You can use

+# any combination of the following format specifications, which will be

+# replaced correspondingly in the progress line:

+#

+# %C - class ID (n/420) or (n/4620) "%4d"

+# %c - class number (n/96) or (n/960) "%3d"

+# %p - percent complete (%) "%5.1f"

+# %g - GHz-days/day (GHz) "%7.2f"

+# %t - time per class (s) "%6.0f" / "%6.1f" / "%6.2f" / "%6.3f"

+# %e - eta (d/h/m/s) "%2dm%02ds" / "%2dh%02dm" / "%2dd%02dh"

+# %n - number of candidates (M/G) "%6.2fM"/"%6.2fG"

+# %r - rate (M/s) "%6.2f" / "%6.1f"

+# %s - SievePrimes "%7d"

+# %w - CPU wait time for GPU (us) n.a. (mfakto only!)

+# %W - CPU wait % (%) "6.2f"

+# %d - date (Mon nn) "%b %d" (strftime format)

+# %T - time (HH:MM) "%H:%M" (strftime format)

+# %U - username (as configured) "%s" no fixed width

+# %H - hostname (as configured) "%s" no fixed width

+# %M - the exponent being worked on "%-10u"

+# %l - the lower bit-limit "%2d"

+# %u - the upper bit-limit "%2d"

+#

+# Using the ProgressHeader you can specify a fix string that is displayed as

+# a header to the progress without any modification.

+# Keep in mind that "number of candidates (M/G)" and "rate (M/s)" are NOT

+# compareable between CPU- and GPU-sieving. When sieving is done on GPU

+# those number count all factor candidates prior to sieving while CPU

+# sieving counts the numbers after the sieving process.

+#

+

+# mfaktc 0.20+ (default)

+ProgressHeader=Date Time | class Pct | time ETA | GHz-d/day Sieve Wait

+ProgressFormat=%d %T | %C %p%% | %t %e | %g %s %W%%

+

+# old mfaktc 0.18/0.19 style

+#

+#ProgressHeader= class | candidates | time | ETA | avg. rate | SievePrimes | CPU wait

+#ProgressFormat=%C/4620 | %n | %ts | %e | %rM/s | %s | %W%%

+

+# print everything

+#ProgressHeader=[date time] exponent [TF bits]: percent class #, seq | GHZ | time | ETA | #FCs | rate | SieveP. | CPU wait | V5UserID@ComputerID

+#ProgressFormat=[%d %T] M%M [%l-%u]: %p%% %C/4620,%c/960 | %g | %ts | %e | %n | %rM/s | %s | %W%% | %U@%H

+

+

+# enable or disable GPU sieving

+# SieveOnGPU=0: use the CPU for sieving factor candidates (high CPU usage)

+# SieveOnGPU=1: use the GPU for sieving factor candidates (very low CPU usage)

+# GPU sieving is supported on GPUs with compute capability 2.0 or higher.

+# (e.g. Geforce 400 series or newer)

+#

+# Default: SieveOnGPU=1

+

+SieveOnGPU=1

+

+

+# GPUSievePrimes defines how far we sieve the factor candidates on the GPU.

+# The first <GPUSievePrimes> primes are sieved.

+#

+# Minimum: GPUSievePrimes=0

+# Maximum: GPUSievePrimes=1075000

+#

+# Default: GPUSievePrimes=82486

+

+GPUSievePrimes=82486

+

+

+# GPUSieveSize defines how big of a GPU sieve we use (in M bits).

+#

+# Minimum: GPUSieveSize=4

+# Maximum: GPUSieveSize=2047

+#

+# Default: GPUSieveSize=64

+

+GPUSieveSize=2047

+

+

+# GPUSieveProcessSize defines how far many bits of the sieve each TF block

+# processes (in K bits). Larger values may lead to less wasted cycles by

+# reducing the number of times all threads in a warp are not TFing a

+# candidate. However, more shared memory is used which may reduce occupancy.

+# Smaller values should lead to a more responsive system (each kernel takes

+# less time to execute). GPUSieveProcessSize must be a multiple of 8.

+#

+# Minimum: GPUSieveProcessSize=8

+# Maximum: GPUSieveProcessSize=32

+#

+# Default: GPUSieveProcessSize=16

+

+GPUSieveProcessSize=32