Lines Matching full:loops
508 -falign-labels=N -falign-loops=N
540 -fsched2-use-traces -fsee -freschedule-modulo-scheduled-loops
544 -funroll-all-loops -funroll-loops -fpeel-loops
545 -fsplit-ivs-in-unroller -funswitch-loops
765 -malign-loops -mno-align-loops
1450 calls to `memcpy' may become inline copy loops. The resulting
3518 places because they were moved out of loops.
4187 Dump each function after applying vectorization of loops.
4206 loops that got vectorized. If N=2 the vectorizer also reports
4207 non-vectorized loops that passed the first analysis phase
4209 single-entry/exit loops. This is the same verbosity level that
4212 amount of information reported for more loops: If N=3, alignment
4216 vectorizer reports also non-vectorized inner-most loops that did
4219 reports also non-vectorized nested loops. For N=7, all the
4439 -falign-loops -falign-labels
4453 `-funswitch-loops' and `-fgcse-after-reload' options.
4464 -falign-functions -falign-jumps -falign-loops
4641 scheduling pass. This pass looks at innermost loops and reorders
4760 to move stores out of loops. When used in conjunction with
4761 `-fgcse-lm', loops containing a load/store sequence can be changed
4780 overflow, and that the loops with nontrivial exit condition are not
4924 `-freschedule-modulo-scheduled-loops'
5018 With `-funswitch-loops' it also moves operands of conditions that
5087 `-funroll-loops'
5088 Unroll loops whose number of iterations can be determined at
5089 compile time or upon entry to the loop. `-funroll-loops' implies
5093 `-funroll-all-loops'
5094 Unroll all loops, even if their number of iterations is uncertain
5096 slowly. `-funroll-all-loops' implies the same options as
5097 `-funroll-loops',
5120 prefetch memory to improve the performance of loops that access
5124 dependent on the structure of loops within the source code.
5280 If `-falign-loops' or `-falign-jumps' are applicable and are
5288 `-falign-loops'
5289 `-falign-loops=N'
5290 Align loops to a power-of-two boundary, skipping up to N bytes
5295 `-fno-align-loops' and `-falign-loops=1' are equivalent and mean
5296 that loops will not be aligned.
5310 that loops will not be aligned.
5364 Enabled by default with `-funroll-loops'.
5400 `-fvpt', `-funroll-loops', `-fpeel-loops', `-ftracer'
5597 Enabled by default with `-funroll-loops'.
5606 `-funroll-loops'
5607 Unroll loops whose number of iterations can be determined at
5608 compile time or upon entry to the loop. `-funroll-loops' implies
5611 loops with small constant number of iterations). This option
5616 `-funroll-all-loops'
5617 Unroll all loops, even if their number of iterations is uncertain
5619 slowly. `-funroll-all-loops' implies the same options as
5620 `-funroll-loops'.
5622 `-fpeel-loops'
5623 Peels the loops for that there is enough information that they do
5625 loop peeling (i.e. complete removal of loops with small constant
5634 `-funswitch-loops'
5662 exposed only during reload, thus hoisting loads out of loops and
5958 The induction variable optimizations give up on loops that
10062 `-malign-loops'
10063 Align all loops to a 32-byte boundary.
10065 `-mno-align-loops'
10066 Do not enforce a 32-byte alignment for loops. This is the default.
12379 loops more than 2^23 times on the C3x?). Note that GCC will try
12417 only used for innermost loops that do not call functions or jump
12419 RPTB loops due to the overhead required to save and restore the
14284 in GNU C. This allows you to use loops, switches, and local variables
14413 contains nested loops, a `goto' can be useful for breaking out of them.
16096 Interesting non-pure functions are functions with infinite loops
17923 if the output operands aren't used, or move them out of loops, or
26045 to loops or to other control structures, the statistics are less
27569 * Deleting "empty" loops.
27571 Historically, GCC has not deleted "empty" loops under the
27580 GCC will remove operations from loops whenever it can determine
29105 mountains of C++ work, load/store hoisting out of loops, alias
29940 * falign-loops: Optimize Options. (line 938)
30210 * fpeel-loops: Optimize Options. (line 1271)
30250 * fscheduling-in-modulo-scheduled-loops: Optimize Options. (line 573)
30288 * funroll-all-loops: Optimize Options. (line 742)
30289 * funroll-loops: Optimize Options. (line 736)
30299 * funswitch-loops: Optimize Options. (line 1283)
30487 * malign-loops: M32R/D Options. (line 73)
30871 * mno-align-loops: M32R/D Options. (line 76)
