Commit Graph

17 Commits

Author SHA1 Message Date
Andrew Trick
07269265b0 misched: tag a few XFAILs that I plan to fix
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153222 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-21 22:31:31 +00:00
Eric Christopher
7c2cdb1c05 Turn on list-ilp scheduling by default on x86 and x86-64, fix up
testcases accordingly. Some are currently xfailed and will be filed
as bugs to be fixed or understood.

Performance results:

roughly neutral on SPEC
some micro benchmarks in the llvm suite are up between 100 and 150%, only
a pair of regressions that are due to be investigated

john-the-ripper saw:
10% improvement in traditional DES
8% improvement in BSDI DES
59% improvement in FreeBSD MD5
67% improvement in OpenBSD Blowfish
14% improvement in LM DES

Small compile time impact.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127208 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-08 02:42:25 +00:00
Jakob Stoklund Olesen
7eb589d3f9 Try again to disable critical edge splitting in CodeGenPrepare.
The bug that broke i386 linux has been fixed in r115191.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115204 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-30 20:51:52 +00:00
Jakob Stoklund Olesen
08342f2d11 Revert "Disable codegen prepare critical edge splitting. Machine instruction passes now"
This reverts revision 114633. It was breaking llvm-gcc-i386-linux-selfhost.

It seems there is a downstream bug that is exposed by
-cgp-critical-edge-splitting=0. When that bug is fixed, this patch can go back
in.

Note that the changes to tailcallfp2.ll are not reverted. They were good are
required.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114859 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-27 18:43:48 +00:00
Evan Cheng
dd3a41a6b3 Disable codegen prepare critical edge splitting. Machine instruction passes now
break critical edges on demand.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114633 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-23 06:55:34 +00:00
Evan Cheng
6edb0eac87 Teach machine sink to
1) Do forward copy propagation. This makes it easier to estimate the cost of the
   instruction being sunk.
2) Break critical edges on demand, including cases where the value is used by
   PHI nodes.
Critical edge splitting is not yet enabled by default.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114227 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-17 22:28:18 +00:00
Dan Gohman
191bd64a39 Revert 112442 and 112440 until the compile time problems introduced
by 112440 are resolved.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112692 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-01 01:45:53 +00:00
Dan Gohman
eaa40ff74e Make IVUsers iterative instead of recursive.
This has the side effect of reversing the order of most of
IVUser's results.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112442 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-29 16:40:03 +00:00
Evan Cheng
97b9b97853 PHI elimination should not break back edge. It can cause some significant code placement issues. rdar://8263994
good:
LBB0_2:
  mov     r2, r0
  . . .
  mov     r1, r2
  bne     LBB0_2

bad:
LBB0_2:
  mov     r2, r0
  . . .
@ BB#3:
  mov     r1, r2
  b       LBB0_2


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111221 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-17 01:20:36 +00:00
Dan Gohman
584fedf188 Teach two-address lowering how to unfold a load to open up commuting
opportunities. For example, this lets it emit this:

   movq (%rax), %rcx
   addq %rdx, %rcx

instead of this:

   movq %rdx, %rcx
   addq (%rax), %rcx

in the case where %rdx has subsequent uses. It's the same number
of instructions, and usually the same encoding size on x86, but
it appears faster, and in general, it may allow better scheduling
for the load.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@106493 91177308-0d34-0410-b5e6-96231b3b80d8
2010-06-21 22:17:20 +00:00
Dan Gohman
1e3121c80a Include the use kind along with the expression in the key of the
use sharing map. The reconcileNewOffset logic already forces a
separate use if the kinds differ, so incorporating the kind in the
key means we can track more sharing opportunities.

More sharing means fewer total uses to track, which means smaller
problem sizes, which means the conservative throttles don't kick
in as often.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@106396 91177308-0d34-0410-b5e6-96231b3b80d8
2010-06-19 21:29:59 +00:00
Dan Gohman
9f23dee08c Start function numbering at 0.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101638 91177308-0d34-0410-b5e6-96231b3b80d8
2010-04-17 16:29:15 +00:00
Evan Cheng
bdc652bab8 Turning off post-ra scheduling for x86. It isn't a consistent win.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@98810 91177308-0d34-0410-b5e6-96231b3b80d8
2010-03-18 06:55:42 +00:00
Dan Gohman
1b7bf18def When determining the set of interesting reuse factors, consider
strides in foreign loops. This helps locate reuse opportunities
with existing induction variables in foreign loops and reduces
the need for inserting new ones. This fixes rdar://7657764.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96629 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-19 00:05:23 +00:00
Dan Gohman
572645cf84 Reapply the new LoopStrengthReduction code, with compile time and
bug fixes, and with improved heuristics for analyzing foreign-loop
addrecs.

This change also flattens IVUsers, eliminating the stride-oriented
groupings, which makes it easier to work with.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95975 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-12 10:34:29 +00:00
Dan Gohman
7979b72feb Revert LoopStrengthReduce.cpp to pre-r94061 for now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@94123 91177308-0d34-0410-b5e6-96231b3b80d8
2010-01-22 00:46:49 +00:00
Dan Gohman
a10756ee65 Re-implement the main strength-reduction portion of LoopStrengthReduction.
This new version is much more aggressive about doing "full" reduction in
cases where it reduces register pressure, and also more aggressive about
rewriting induction variables to count down (or up) to zero when doing so
reduces register pressure.

It currently uses fairly simplistic algorithms for finding reuse
opportunities, but it introduces a new framework allows it to combine
multiple strategies at once to form hybrid solutions, instead of doing
all full-reduction or all base+index.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@94061 91177308-0d34-0410-b5e6-96231b3b80d8
2010-01-21 02:09:26 +00:00