/barrelfish-master/lib/phoenix/ |
H A D | map_reduce.h | 91 * reduce function, except that this function returns the reduced value 108 /* Partition function takes in the number of reduce tasks, a pointer to 109 * a key, and the lendth of the key in bytes. It assigns a key to a reduce task. 110 * The value returned is the # of the reduce task where the key will be processed. 132 reduce_t reduce; /* If NULL, identity reduce function is used, member in struct:__anon1383 148 /* Creates one emit queue for each reduce task, 149 * instead of per reduce thread. This improves 157 int num_reduce_threads; /* # of threads to run reduce tasks on. 182 * It is responsible for creating and scheduling all map and reduce task [all...] |
H A D | map_reduce.c | 128 /* Internal map reduce state. */ 133 int num_reduce_tasks; /* # of reduce tasks. */ 137 int num_reduce_threads; /* # of threads for reduce tasks. */ 143 bool oneOutputQueuePerReduceTask; /* One output queue per reduce task? */ 149 reduce_t reduce; /* Reduce function. */ member in struct:__anon279 161 /* Array to send to reduce task. */ 223 static void reduce(mr_env_t* mr); 303 dprintf("In scheduler, all map tasks are done, now scheduling reduce tasks\n"); 305 /* Run reduce tasks and get final values. */ 307 reduce (en 1840 static void reduce (mr_env_t* env) function [all...] |
/barrelfish-master/tools/harness/ |
H A D | builds.py | 149 e = reduce(split_reduce_env, e, (False, ['']))[1]
|
/barrelfish-master/usr/eclipseclp/documents/tutorial/ |
H A D | modelling.tex | 65 algorithms that reduce the need for search. 231 constraints. Even though high-level models reduce the need for finding
|
H A D | solversintro.tex | 116 resource level. They reduce the finite domains of the task start times
|
H A D | real.tex | 333 Other times, propagation will reduce the domains of the variables to
|
H A D | hybrid.tex | 714 \Note{The definition of the reduce cost here is the one used by the eplex 964 To test its performance, reduce the domains thus:
|
H A D | eprolog.tex | 79 To reduce the need for auxiliary recursive predicates, \eclipse{} allows
|
H A D | search.tex | 485 placing queens in the middle of the board to reduce the number of
|
/barrelfish-master/usr/tests/phoenix_tests/ |
H A D | kmeans.c | 397 // Setup map reduce args 401 map_reduce_args.reduce = kmeans_reduce;
|
/barrelfish-master/usr/eclipseclp/Kernel/lib/ |
H A D | kernel_bips.pl | 362 % sorting the list first is not necessary, but likely to reduce
|
/barrelfish-master/usr/eclipseclp/documents/userman/ |
H A D | umsmemory.tex | 199 The only way to reduce Control Stack usage is to avoid unnecessary 246 Ways to reduce Trail Stack consumption are
|
H A D | umscompiler.tex | 214 will disable certain compiler optimizations and usually reduce performance. 803 improve indexing and to reduce code size.
|
H A D | extmeta.tex | 188 this optimization (some systems can reduce these chains
|
H A D | umsarrays.tex | 48 state) and reduce the risk of memory leaks.
|
/barrelfish-master/lib/tommath/ |
H A D | bn.tex | 1319 This will reduce $a$ in place modulo $b$ with the precomputed $\mu$ value in $c$. $a$ must be in the range 1346 /* now reduce `c' modulo b */ 1360 /* now reduce `c' modulo b */ 1453 /* now reduce `c' back down to c = a^2R^2 * R^-1 == a^2R */ 1467 /* now reduce `c' back down to c = a^3R^2 * R^-1 == a^3R */ 1474 /* now reduce (again) `c' back down to c = a^3R * R^-1 == a^3 */ 1544 This will reduce $a$ in place modulo $n$ with the pre--computed value $d$. From my experience this routine is
|
H A D | tommath.tex | 1441 is zero. Next we set the digit and reduce it modulo $\beta$ (line 22). After this step we have to 1445 We can quickly reduce modulo $\beta$ since it is of the form $2^k$ and a quick binary AND operation with 2445 Recalling that reducing modulo $2^k$ and a binary ``and'' with $2^k - 1$ are numerically equivalent we can quickly reduce 2446 the number. First we zero any digits above the last digit in $2^b$ (line 42). Next we reduce the 2647 after the nested loop to reduce the amount of work requiored. Succintly the first step of the algorithm is to compute 2780 reduce the memory bandwidth to two \textbf{mp\_digit} reads per iteration. 3034 chosen such that $\zeta$ is easy to compute and the resulting system of equations easy to reduce. Here, the points $\zeta_{0}$, 3679 reduce the number. 3688 See~\ref{sec:division} for further details.} might as well be used in its place. The key to optimizing the reduction is to reduce the precision of 3741 After the quotient has been calculated it is used to reduce th [all...] |
/barrelfish-master/usr/eclipseclp/documents/libman/ |
H A D | introduction.tex | 96 resource level. They reduce the finite domains of the task start times
|
H A D | gfd.tex | 232 This could reduce the cost of performing the propagation.
1023 The binary-choice methods create two search alternatives, which reduce the variable domain
1408 state; instead, the previous state is recomputed. To reduce the amount
|
H A D | eplex.tex | 526 setup of the problem to reduce overheads.
|
/barrelfish-master/usr/eclipseclp/icparc_solvers/ |
H A D | ic_probe_search.pl | 267 the given task so as to reduce the number of overlapping tasks.
|
H A D | probe_search.pl | 268 the given task so as to reduce the number of overlapping tasks.
|
/barrelfish-master/doc/014-bulk-transfer/ |
H A D | bulk-transfer.tex | 270 \item Should reduce the data copy as much as possible. 697 consumer decides to quit or if producer decides to reduce the number 974 we reduce the capacity of NIC hardware as typically RX-queue 1118 consumers). This solution also reduce the number of messages
|
/barrelfish-master/doc/003-hake/ |
H A D | Hake.tex | 564 To reduce the number of types and leave the library OS selection mechanism 779 reduce in size over time. Here are a few:
|
/barrelfish-master/usr/eclipseclp/documents/intro_paper/ |
H A D | eclipse.tex | 203 choices is to reduce the number of constraint violations until all 842 tough challenge to reduce this time from hours to minutes! 1749 it repeatedly attempts to reduce the domains of its variables further 1751 any other constraints reduce any of these domains.
|