llvm-svn: 37081

llvm-svn: 37057

llvm-svn: 37034

llvm-svn: 37020

llvm-svn: 36996

llvm-svn: 36994

with unknown trip counts. This is left off by default, and a
command-line option enables it. It also begins to separate loop
unrolling into a utility routine; eventually it might be made usable
from other passes.

It currently works by inserting conditional branches between each
unrolled iteration, unless it proves that the trip count is a
multiple of a constant integer > 1, which it currently only does in
the rare case that the trip count expression is a Mul operator with
a ConstantInt operand. Eventually this information might be provided
by other sources, for example by a pass that peels/splits the loop
for this purpose.

llvm-svn: 36990

Transforms/InstCombine/2006-12-08-ICmp-Combining.ll

llvm-svn: 36989

llvm-svn: 36984

Testcases :
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20070507/049451.html
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20070507/049452.html

llvm-svn: 36955

llvm-svn: 36936

llvm-svn: 36935

llvm-svn: 36917

llvm-svn: 36894

llvm-svn: 36873

llvm-svn: 36857

llvm-svn: 36809

llvm-svn: 36807

If we have a LCSSA, only modify the input value if the inval was defined
by an instruction in the loop.  If defined by something before the loop,
it is still valid.

llvm-svn: 36784

llvm-svn: 36782

llvm-svn: 36775

slightly nicer than using CallInst with an extra check; thanks Chris.

llvm-svn: 36743

address operand in a prefetch intrinsic.

llvm-svn: 36713

llvm-svn: 36662

Due to darwin gcc bug, one version of darwin linker coalesces
static const int, which defauts PassID based pass identification.

llvm-svn: 36652

llvm-svn: 36648

llvm-svn: 36632

llvm-svn: 36564

bitcasts of them.

llvm-svn: 36537

llvm-svn: 36527

previous clients.  This fixes MallocBench/gs

llvm-svn: 36525

llvm-svn: 36523

llvm-svn: 36521

for unrelated casts.

llvm-svn: 36511

llvm-svn: 36475

llvm-svn: 36444

llvm-svn: 36441

will follow.

llvm-svn: 36435

copies from a constant global, then we can change the reads to read from the
global instead of from the alloca.  This eliminates the alloca and the memcpy,
and promotes secondary optimizations (because the loads are now loads from
a constant global).

This is important for a common C idiom:

void foo() {
   int A[] = {1,2,3,4,5,6,7,8,9...};
   ... only reads of A ...
}

For some reason, people forget to mark the array static or const.

This triggers on these multisource benchmarks:
JM/ldecode: block_pos, [3 x [4 x [4 x i32]]]
FreeBench/mason: m, [18 x i32], inlined 4 times
MiBench/office-stringsearch: search_strings, [1332 x i8*]
MiBench/office-stringsearch: find_strings, [1333 x i8*]
Prolangs-C++/city: dirs, [9 x i8*], inlined 4 places

and these spec benchmarks:
177.mesa: message, [8 x [32 x i8]]
186.crafty: bias_rl45, [64 x i32]
186.crafty: diag_sq, [64 x i32]
186.crafty: empty, [9 x i8]
186.crafty: xlate, [15 x i8]
186.crafty: status, [13 x i8]
186.crafty: bdinfo, [25 x i8]
445.gobmk: routines, [16 x i8*]
458.sjeng: piece_rep, [14 x i8*]
458.sjeng: t, [13 x i32], inlined 4 places.
464.h264ref: block8x8_idx, [3 x [4 x [4 x i32]]]
464.h264ref: block_pos, [3 x [4 x [4 x i32]]]
464.h264ref: j_off_tab, [12 x i32]

This implements Transforms/ScalarRepl/memcpy-from-global.ll

llvm-svn: 36429

llvm-svn: 36426