Sanjay Patel b89304eb7c Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802). ... The SLP vectorizer should propagate IR-level optimization hints/flags (nsw, nuw, exact, fast-math) when converting scalar instructions into vectors. But this isn't a simple copy - we need to take the intersection (the logical 'and') of the sets of flags on the scalars. The solution is further complicated because we can have non-uniform (non-SIMD) vector ops after: http://reviews.llvm.org/D4015 http://llvm.org/viewvc/llvm-project?view=revision&revision=211339 The vast majority of changed files are existing tests that were not propagating IR flags, but I've also added a new test file for focused testing of IR flag possibilities. Differential Revision: http://reviews.llvm.org/D5172 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217051 91177308-0d34-0410-b5e6-96231b3b80d8		2014-09-03 17:40:30 +00:00
..
addsub.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
align.ll	SLPVectorizer: Use the type of the value loaded/stored to get the ABI alignment	2014-08-07 22:47:27 +00:00
barriercall.ll
call.ll	Vectorize intrinsic math function calls in SLPVectorizer.	2014-05-03 09:59:54 +00:00
cast.ll
cmp_sel.ll
compare-reduce.ll
consecutive-access.ll	Implement sext(C1 + C2*X) --> sext(C1) + sext(C2*X) and	2014-05-24 08:09:57 +00:00
continue_vectorizing.ll	Continue slp vectorization even the BB already has vectorized store radar://16641956	2014-04-29 19:37:20 +00:00
crash_7zip.ll
crash_binaryop.ll	Fix: SLPVectorizer tried to move an instruction which was replaced by a vector instruction.	2014-08-28 07:04:02 +00:00
crash_bullet3.ll
crash_bullet.ll
crash_dequeue.ll
crash_flop7.ll
crash_gep.ll	Revert r210342 and r210343, add test case for the crasher.	2014-08-26 19:06:41 +00:00
crash_lencod.ll
crash_mandeltext.ll
crash_netbsd_decompress.ll
crash_scheduling.ll	fix bug 20513 - Crash in SLP Vectorizer	2014-08-02 19:39:42 +00:00
crash_sim4b1.ll
crash_smallpt.ll
crash_vectorizeTree.ll	SLPVectorizer: improved scheduling algorithm.	2014-08-01 09:20:42 +00:00
cross_block_slp.ll
cse.ll	SLPVectorizer: When sorting by domination for CSE don't assert on unreachable code.	2014-05-09 23:28:49 +00:00
cycle_dup.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
debug_info.ll	Debug Info: update testing cases to specify the debug info version number.	2013-11-22 21:49:45 +00:00
diamond.ll
external_user.ll	SLPVectorizer: An in-tree vectorized entry cannot also be a scalar external use	2013-12-05 15:14:40 +00:00
extract_in_tree_user.ll	Generate extract for in-tree uses if the use is scalar operand in vectorized instruction. radar://18144665	2014-09-02 21:00:39 +00:00
extract.ll
extractcost.ll	SLP Vectorizer: Extract cost will only be added once even if the scalar has multiple external uses.	2013-11-22 01:57:02 +00:00
flag.ll
gep.ll	[SLP] Re-enable vectorization of GEP expressions (re-apply r210342 with a fix).	2014-08-27 15:01:18 +00:00
hoist.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
horizontal.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
implicitfloat.ll
in-tree-user.ll	SLPVectorizer: improved scheduling algorithm.	2014-08-01 09:20:42 +00:00
insert-element-build-vector.ll	Fix broken FileCheck prefixes	2014-05-23 19:06:24 +00:00
intrinsic.ll	Allow vectorization of intrinsics such as powi,cttz and ctlz in Loop and SLP Vectorizer.	2014-05-30 04:31:24 +00:00
lit.local.cfg	Reduce verbiage of lit.local.cfg files	2014-06-09 22:42:55 +00:00
long_chains.ll
loopinvariant.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
metadata.ll	Trivial test commit.	2014-03-05 02:09:51 +00:00
multi_block.ll
multi_user.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
non-vectorizable-intrinsic.ll	SLPVectorizer: Only vectorize intrinsics whose operands are widened equally	2014-04-09 14:20:47 +00:00
odd_store.ll
operandorder.ll
opt.ll	opt: Mirror vectorization presets of clang	2013-12-03 16:33:06 +00:00
ordering.ll
phi3.ll
phi_landingpad.ll
phi_overalignedtype.ll
phi.ll	Fix broken CHECK lines.	2014-01-11 21:06:00 +00:00
powof2div.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
pr16571.ll
pr16628.ll
pr16899.ll
pr18060.ll	PR1860 - We can't save a list of ExtractElement instructions to CSE because some of these instructions	2013-11-26 22:24:25 +00:00
pr19657.ll	Fix PR19657 (scalar loads not combined into vector load)	2014-06-06 06:20:08 +00:00
propagate_ir_flags.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
reduction2.ll
reduction.ll
rgb_phi.ll
saxpy.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
scheduling.ll	Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).	2014-09-03 17:40:30 +00:00
simple-loop.ll
simplebb.ll	SLPVectorizer: Don't vectorize volatile memory operations	2013-10-16 17:52:40 +00:00
tiny-tree.ll	SLPVectorizer: Try vectorizing 'splat' stores	2014-02-24 19:52:29 +00:00
unreachable.ll	fix: SLPVectorizer crashes for unreachable blocks containing not schedulable instructions.	2014-08-22 01:18:39 +00:00
value-bug.ll	SLPVectorizer: Bring back the insertelement patch (r205965) with fixes	2014-05-04 17:10:15 +00:00
vector.ll