llvm-svn: 36433

llvm-svn: 36432

llvm-svn: 36431

llvm-svn: 36430

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: 36428

llvm-svn: 36427

llvm-svn: 36426

llvm-svn: 36425

llvm-svn: 36424

llvm-svn: 36423

llvm-svn: 36422

this approach is no longer appropriate.

llvm-svn: 36421

llvm-svn: 36420

llvm-svn: 36419

llvm-svn: 36418

http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20070423/048376.html

llvm-svn: 36417

llvm-svn: 36416

llvm-svn: 36415

llvm-svn: 36414

This fixes CodeGen/X86/2007-04-24-VectorCrash.ll

llvm-svn: 36413

llvm-svn: 36412

llvm-svn: 36411

llvm-svn: 36410

llvm-svn: 36409

llvm-svn: 36408

llvm-svn: 36407

llvm-svn: 36406

llvm-svn: 36405

llvm-svn: 36404

        vector_shuffle v1, v2, <2, 6, 3, 7>

I.e.

         vector_shuffle v, undef, <2, 2, 3, 3>

MMX only has a shuffle for v4i16 vectors. It needs to use the unpackh for
this type of operation.

llvm-svn: 36403

real vector type in this case.

llvm-svn: 36402

llvm-svn: 36401

llvm-svn: 36400

llvm-svn: 36399

easy breakpointing).

Fix bugs reading constantexpr geps.  We now can disassemble kc++ global
initializers.

llvm-svn: 36398

llvm-svn: 36397

llvm-svn: 36396

llvm-svn: 36395

llvm-svn: 36394