Commit Graph

282 Commits

Author SHA1 Message Date
Benjamin Kramer
51bfb0fe50 Fabs folding is implemented.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162186 91177308-0d34-0410-b5e6-96231b3b80d8
2012-08-19 09:51:44 +00:00
Micah Villmow
9a7963947c Test revert of test changes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160632 91177308-0d34-0410-b5e6-96231b3b80d8
2012-07-23 16:42:45 +00:00
Micah Villmow
f79c031bdc Test commit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160631 91177308-0d34-0410-b5e6-96231b3b80d8
2012-07-23 16:37:24 +00:00
Benjamin Kramer
d52998a815 Add a microoptimization note.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@159082 91177308-0d34-0410-b5e6-96231b3b80d8
2012-06-23 15:19:31 +00:00
Benjamin Kramer
503a86b731 Remove README entry obsoleted by register masks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154588 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-12 12:47:29 +00:00
Benjamin Kramer
9b58464330 Add another note about a missed compare with nsw arithmetic instcombine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153574 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-28 10:50:18 +00:00
Benjamin Kramer
f2fd23b062 Add a note about a cute little fabs optimization.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153543 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-27 22:42:42 +00:00
Benjamin Kramer
c8591a451a Add two missed instcombines related to compares with nsw arithmetic.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153542 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-27 22:03:19 +00:00
Benjamin Kramer
3e328ecbd8 Add two notes for correlated-expression optimizations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139263 91177308-0d34-0410-b5e6-96231b3b80d8
2011-09-07 22:49:26 +00:00
Benjamin Kramer
3ff25514ce Don't emit a bit test if there is only one case the test can yield false. A simple SETNE is sufficient.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135126 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-14 01:38:42 +00:00
Benjamin Kramer
e7fdcad2f2 InstCombine: Fold A-b == C --> b == A-C if A and C are constants.
The backend already knew this trick.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132915 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-13 15:24:24 +00:00
Chris Lattner
32232fc2b5 clarify this, apparently it is confusing :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131916 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-23 20:17:44 +00:00
Chris Lattner
87943e3698 add a note.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131863 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-22 18:28:46 +00:00
Chris Lattner
b6fcf4cfbc move PR9408 here.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131841 91177308-0d34-0410-b5e6-96231b3b80d8
2011-05-22 05:45:06 +00:00
Chris Lattner
325eeb1cd7 Transform: "icmp eq (trunc (lshr(X, cst1)), cst" to "icmp (and X, mask), cst"
when X has multiple uses.  This is useful for exposing secondary optimizations,
but the X86 backend isn't ready for this when X has a single use.  For example,
this can disable load folding.

This is inching towards resolving PR6627.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130238 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-26 20:18:20 +00:00
Chris Lattner
ed0318eab8 add a missed bitfield instcombine.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130137 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-25 18:44:26 +00:00
Benjamin Kramer
e7cf062537 DAGCombine: fold "(zext x) == C" into "x == (trunc C)" if the trunc is lossless.
On x86 this allows to fold a load into the cmp, greatly reducing register pressure.
  movzbl	(%rdi), %eax
  cmpl	$47, %eax
->
  cmpb	$47, (%rdi)

This shaves 8k off gcc.o on i386. I'll leave applying the patch in README.txt to Chris :)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130005 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-22 18:47:44 +00:00
Chris Lattner
df2ef9015f add a minor missed dag combine that is blocking mid-level optimization
improvements, that will lead to fixing PR6627.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@129504 91177308-0d34-0410-b5e6-96231b3b80d8
2011-04-14 04:21:42 +00:00
Benjamin Kramer
ef7b8d9e5a Add a note.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128286 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-25 17:32:40 +00:00
Eli Friedman
97ab5803df A bit more analysis of a memset-related README entry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128107 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-22 20:49:53 +00:00
Eli Friedman
ddfa02ba24 This README entry was fixed recently.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@127982 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-21 01:33:03 +00:00
Chris Lattner
d3e768ecab add a note
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126719 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-01 00:24:51 +00:00
Benjamin Kramer
7466678003 Add some DAGCombines for (adde 0, 0, glue), which are useful to optimize legalized code for large integer arithmetic.
1. Inform users of ADDEs with two 0 operands that it never sets carry
2. Fold other ADDs or ADDCs into the ADDE if possible

It would be neat if we could do the same thing for SETCC+ADD eventually, but we can't do that in target independent code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126557 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-26 22:48:07 +00:00
Chris Lattner
19310fc199 add a missed loop deletion case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126103 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-21 02:13:39 +00:00
Chris Lattner
477a98824a add an idiom that loop idiom could theoretically catch.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126101 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-21 01:33:38 +00:00
Duncan Sands
fe167c5a14 This has been implemented.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125738 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-17 08:16:56 +00:00
Chris Lattner
cb40195641 add some notes on compares + binops. Remove redundant entries.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125702 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-17 01:43:46 +00:00
Chris Lattner
5653f1f904 Add a few missed xforms from GCC PR14753
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125681 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-16 19:16:34 +00:00
Eli Friedman
eb1dc98aa7 Remove outdated README entry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125660 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-16 07:41:19 +00:00
Eli Friedman
fd51e95171 Remove outdated README entry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125659 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-16 07:18:18 +00:00
Eli Friedman
c5cb996e9c Update README entry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125658 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-16 07:17:44 +00:00
Anders Carlsson
9c93d48b6b Remove a virtual inheritance case that clang can devirtualize fully now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124989 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-06 20:16:49 +00:00
Benjamin Kramer
56442dfdcf SimplifyCFG: Turn switches into sub+icmp+branch if possible.
This makes the job of the later optzn passes easier, allowing the vast amount of
icmp transforms to chew on it.

We transform 840 switches in gcc.c, leading to a 16k byte shrink of the resulting
binary on i386-linux.

The testcase from README.txt now compiles into
  decl  %edi
  cmpl  $3, %edi
  sbbl  %eax, %eax
  andl  $1, %eax
  ret

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124724 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-02 15:56:22 +00:00
Chris Lattner
fd2ad8783c add a note, progress unblocked by PR8575 being fixed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124599 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-31 20:23:28 +00:00
Benjamin Kramer
9b108a338d Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off.
This happens all the time when a smul is promoted to a larger type.

On x86-64 we now compile "int test(int x) { return x/10; }" into
  movslq  %edi, %rax
  imulq $1717986919, %rax, %rax
  movq  %rax, %rcx
  shrq  $63, %rcx
  sarq  $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax"
  addl  %ecx, %eax

This fires 96 times in gcc.c on x86-64.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124559 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-30 16:38:43 +00:00
Chris Lattner
96c0771c01 this isn't a memset, we do convert dest[i] to one though :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124097 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-24 02:32:00 +00:00
Chris Lattner
7ea7d32de6 with recent work, we now optimize this into:
define i32 @foo(i32 %x) nounwind readnone ssp {
entry:
  %tobool = icmp eq i32 %x, 0
  %tmp5 = select i1 %tobool, i32 2, i32 1
  ret i32 %tmp5
}



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124091 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-24 01:12:18 +00:00
Anders Carlsson
f330b3227a Add a memset loop that LoopIdiomRecognize doesn't recognize.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124082 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-23 20:31:00 +00:00
Chris Lattner
908d8e82b5 add a note
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123752 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-18 07:47:48 +00:00
Anders Carlsson
5822b86e4d Update README.txt to remove the DAE enhancement.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123597 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-16 21:26:15 +00:00
Chris Lattner
b0daffc609 add some commentary
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123572 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-16 06:39:44 +00:00
Chandler Carruth
cad33c624e Simplify a README.txt entry significantly to expose the core issue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123556 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-16 01:40:23 +00:00
Chris Lattner
4c5456a56f typo
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123406 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-13 22:11:56 +00:00
Chris Lattner
4cd18f98f7 memcpy + metadata = bliss :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123405 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-13 22:08:15 +00:00
Chandler Carruth
15ed90c859 Teach constant folding to perform conversions from constant floating
point values to their integer representation through the SSE intrinsic
calls. This is the last part of a README.txt entry for which I have real
world examples.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123206 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-11 01:07:24 +00:00
Owen Anderson
da1c122da5 Fix a random missed optimization by making InstCombine more aggressive when determining which bits are demanded by
a comparison against a constant.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123203 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-11 00:36:45 +00:00
Chris Lattner
4a6fb94c40 +0.0 vs -0.0 differences can be handled by looking at the user of the
operation in some cases.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123190 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-10 21:01:17 +00:00
Chris Lattner
00a35d0f14 expand on a note
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123145 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-10 00:33:01 +00:00
Chris Lattner
66d7a5793c typo
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123142 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-09 23:48:41 +00:00
Chris Lattner
7cc4e304a6 xref a PR #
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123141 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-09 23:42:22 +00:00