| c81fe9cab545a93a61c059b1c2813f622aef43ae |
|
30-Aug-2012 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: Fix comment to reflect the code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162911 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 639570c3117aaabb0c97b34a9bf05d09f8903ef4 |
|
30-Aug-2012 |
Nadav Rotem <nrotem@apple.com> |
It is illegal to transform (sdiv (ashr X c1) c2) -> (sdiv x (2^c1 * c2)),
because C always rounds towards zero.
Thanks Dirk and Ben.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162899 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 37dca6331d6bfadfb80b3c68a1cabd6bdf1a13be |
|
28-Aug-2012 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: Defensively avoid undefined shifts by limiting the amount to the bit width.
No test case, undefined shifts get folded early, but can occur when other
transforms generate a constant. Thanks to Duncan for bringing this up.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162755 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| aac7c650a6cac09d42c5fda8d3761bc9c871ff03 |
|
28-Aug-2012 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: Guard the transform introduced in r162743 against large ints and non-const shifts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162751 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| a694e2a6910a33596ca706e2c6fc713f02b64c50 |
|
28-Aug-2012 |
Nadav Rotem <nrotem@apple.com> |
Make sure that we don't call getZExtValue on values > 64 bits.
Thanks Benjamin for noticing this.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162749 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 9753f0b9b4ab33919c5010acb6a7b2dc1e875aff |
|
28-Aug-2012 |
Nadav Rotem <nrotem@apple.com> |
Teach InstCombine to canonicalize [SU]div+[AL]shl patterns.
For example:
%1 = lshr i32 %x, 2
%2 = udiv i32 %1, 100
rdar://12182093
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@162743 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 2a5422b1a6955977d05af48222c86c77c7549484 |
|
22-Jun-2012 |
Evan Cheng <evan.cheng@apple.com> |
Look pass zext to strength reduce an udiv. Patch by David Majnemer. rdar://11721329
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158946 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 7302d80490feabfc8a01bee0fa698aab55169544 |
|
06-Feb-2012 |
Chris Lattner <sabre@nondot.org> |
Remove some dead code and tidy things up now that vectors use ConstantDataVector
instead of always using ConstantVector.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149912 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| a78fa8cc2dd6d2ffe5e4fe605f38aae7b3d2fb7a |
|
27-Jan-2012 |
Chris Lattner <sabre@nondot.org> |
continue making the world safe for ConstantDataVector. At this point,
we should (theoretically optimize and codegen ConstantDataVector as well
as ConstantVector.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149116 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 4ca829e89567f002fc74eb0e3e532a7c7662e031 |
|
25-Jan-2012 |
Chris Lattner <sabre@nondot.org> |
use ConstantVector::getSplat in a few places.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148929 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| a29fc806fe02cea76f7896b7e344bb919dd7ac25 |
|
08-Nov-2011 |
Pete Cooper <peter_cooper@apple.com> |
InstCombine now optimizes vector udiv by power of 2 to shifts
Fixes r8429
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@144036 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| a9390a4d5f5d568059a80970d22194b165d097a7 |
|
27-Sep-2011 |
Benjamin Kramer <benny.kra@googlemail.com> |
Stop emitting instructions with the name "tmp" they eat up memory and have to be uniqued, without any benefit.
If someone prefers %tmp42 to %42, run instnamer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140634 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| db125cfaf57cc83e7dd7453de2d509bc8efd0e5e |
|
18-Jul-2011 |
Chris Lattner <sabre@nondot.org> |
land David Blaikie's patch to de-constify Type, with a few tweaks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135375 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| c73b24db5f6226ed44ebc44ce1c25bb357206623 |
|
15-Jul-2011 |
Chris Lattner <sabre@nondot.org> |
start using the new helper methods a bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135251 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| f1002828fdaffa4e005a81f269c77fe72951f39f |
|
01-Jun-2011 |
Stuart Hastings <stuart@apple.com> |
Reapply 132348 with fixes. rdar://problem/6501862
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132402 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 3200c4b53ca742bd0103454250ca89fec2776211 |
|
31-May-2011 |
Stuart Hastings <stuart@apple.com> |
Revert to pacify a buildbot. rdar://problem/6501862
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132351 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| df48e84b5bf0967c1fc397912c109f29475c791b |
|
31-May-2011 |
Stuart Hastings <stuart@apple.com> |
Followup to 132316; accept arbitrary constants, add with a constant,
sub with a non-constant. Fix comments, enlarge test case.
rdar://problem/6501862
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132348 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| acbf107d9b9ffeddbcc3d015107c6faff439ee9b |
|
30-May-2011 |
Stuart Hastings <stuart@apple.com> |
(1 - X) * (-2) -> (x - 1) * 2, for all positive nonzero powers of 2
rdar://problem/6501862
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@132316 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 613f1a3994ef6f009c93264f6708830249130896 |
|
23-May-2011 |
Chris Lattner <sabre@nondot.org> |
rearrange two transforms, since one subsumes the other. Make the shift-exactness
xform recurse.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131888 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 05cd88656135255b545d24adb51c2ba1b5c8b99e |
|
23-May-2011 |
Chris Lattner <sabre@nondot.org> |
Transform any logical shift of a power of two into an exact/NUW shift when
in a known-non-zero context.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131887 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 6083bb935373020af240bdf8fbec1cdcf360303f |
|
23-May-2011 |
Chris Lattner <sabre@nondot.org> |
use the valuetracking isPowerOfTwo function, which is more powerful than checking
for a constant directly. Thanks to Duncan for pointing this out.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131885 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 6c9b8d3d411b0ee65263dc41d2b953fe118cf31e |
|
22-May-2011 |
Chris Lattner <sabre@nondot.org> |
add some random notes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131862 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 1add46ddfa38f23669cb02de342fdb59a8709245 |
|
22-May-2011 |
Chris Lattner <sabre@nondot.org> |
Carve out a place in instcombine to put transformations which work knowing that their
result is non-zero. Implement an example optimization (PR9814), which allows us to
transform:
A / ((1 << B) >>u 2)
into:
A >>u (B-2)
which we compile into:
_divu3: ## @divu3
leal -2(%rsi), %ecx
shrl %cl, %edi
movl %edi, %eax
ret
instead of:
_divu3: ## @divu3
movb %sil, %cl
movl $1, %esi
shll %cl, %esi
shrl $2, %esi
movl %edi, %eax
xorl %edx, %edx
divl %esi, %eax
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131860 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 00676a6df1116f47a015de589f911d2b5b7f4117 |
|
02-May-2011 |
Duncan Sands <baldrick@free.fr> |
Remove unused variable.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130705 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| f24ed77d2416b66178d8ff1d807858dfab37ca18 |
|
02-May-2011 |
Duncan Sands <baldrick@free.fr> |
Move some rem transforms out of instcombine and into instsimplify.
This automagically provides a transform noticed by my super-optimizer
as occurring quite often: "rem x, (select cond, x, 1)" -> 0.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130694 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 7d6eb5a018ef4352730d63dc202cfaf013f489fe |
|
30-Apr-2011 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: Turn (zext A) udiv (zext B) into (zext (A udiv B)). Same for urem or constant B.
This obviously helps a lot if the division would be turned into a libcall
(think i64 udiv on i386), but div is also one of the few remaining instructions
on modern CPUs that become more expensive when the bitwidth gets bigger.
This also helps register pressure on i386 when dividing chars, divb needs
two 8-bit parts of a 16 bit register as input where divl uses two registers.
int foo(unsigned char a) { return a/10; }
int bar(unsigned char a, unsigned char b) { return a/b; }
compiles into (x86_64)
_foo:
imull $205, %edi, %eax
shrl $11, %eax
ret
_bar:
movzbl %dil, %eax
divb %sil, %al
movzbl %al, %eax
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130615 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 23b02cd0315625d9d586118abcc972053298d50b |
|
30-Apr-2011 |
Benjamin Kramer <benny.kra@googlemail.com> |
Use SimplifyDemandedBits on div instructions.
This folds away silly stuff like (a&255)/1000 -> 0.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@130614 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 546739656ec9469499d3866d87dca6fdbcf2eee0 |
|
30-Mar-2011 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: If the divisor of an fdiv has an exact inverse, turn it into an fmul.
Fixes PR9587.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128546 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 7a6aa1a3919af8ece92702c36dc552d81be9151a |
|
10-Feb-2011 |
Chris Lattner <sabre@nondot.org> |
Enhance a bunch of transformations in instcombine to start generating
exact/nsw/nuw shifts and have instcombine infer them when it can prove
that the relevant properties are true for a given shift without them.
Also, a variety of refactoring to use the new patternmatch logic thrown
in for good luck. I believe that this takes care of a bunch of related
code quality issues attached to PR8862.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125267 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 35bda8914c0d1c02a6f90f42e7810c83150737e1 |
|
06-Feb-2011 |
Chris Lattner <sabre@nondot.org> |
enhance vmcore to know that udiv's can be exact, and add a trivial
instcombine xform to exercise this.
Nothing forms exact udivs yet though. This is progress on PR8862
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124992 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 31726c154dafa9fef08b1bcac9822c2a4618ec19 |
|
29-Jan-2011 |
Frits van Bommel <fvbommel@gmail.com> |
Call SimplifyFDivInst() in InstCombiner::visitFDiv().
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124535 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 1fca2c32cc99197215d3fd32a4ad05214c74edd1 |
|
29-Jan-2011 |
Frits van Bommel <fvbommel@gmail.com> |
Move InstCombine's knowledge of fdiv to SimplifyInstruction().
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124534 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 593faa53fa6d89841e601cc4571d143a6a05f0b4 |
|
28-Jan-2011 |
Duncan Sands <baldrick@free.fr> |
My auto-simplifier noticed that ((X/Y)*Y)/Y occurs several times in SPEC
benchmarks, and that it can be simplified to X/Y. (In general you can only
simplify (Z*Y)/Y to Z if the multiplication did not overflow; if Z has the
form "X/Y" then this is the case). This patch implements that transform and
moves some Div logic out of instcombine and into InstructionSimplify.
Unfortunately instcombine gets in the way somewhat, since it likes to change
(X/Y)*Y into X-(X rem Y), so I had to teach instcombine about this too.
Finally, thanks to the NSW/NUW flags, sometimes we know directly that "Z*Y"
does not overflow, because the flag says so, so I added that logic too. This
eliminates a bunch of divisions and subtractions in 447.dealII, and has good
effects on some other benchmarks too. It seems to have quite an effect on
tramp3d-v4 but it's hard to say if it's good or bad because inlining decisions
changed, resulting in massive changes all over.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124487 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 37bf92b5238434b00fde79347ba5336e7554e562 |
|
22-Dec-2010 |
Duncan Sands <baldrick@free.fr> |
Add a generic expansion transform: A op (B op' C) -> (A op B) op' (A op C)
if both A op B and A op C simplify. This fires fairly often but doesn't
make that much difference. On gcc-as-one-file it removes two "and"s and
turns one branch into a select.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122399 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 82fdab335881cd90f8f7ab3ad1f1ca0bb3ee886a |
|
21-Dec-2010 |
Duncan Sands <baldrick@free.fr> |
Pull a few more simplifications out of instcombine (there are still
plenty left though!), in particular for multiplication.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122330 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 40f8f6264d5af2c38e797e0dc59827cd231e8ff7 |
|
07-Dec-2010 |
Jay Foad <jay.foad@gmail.com> |
PR5207: Change APInt methods trunc(), sext(), zext(), sextOrTrunc() and
zextOrTrunc(), and APSInt methods extend(), extOrTrunc() and new method
trunc(), to be const and to return a new value instead of modifying the
object in place.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@121120 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 1951a5b721187ab85db0b2db55ae39eec3733c20 |
|
17-Nov-2010 |
Benjamin Kramer <benny.kra@googlemail.com> |
InstCombine: Add a missing irem identity (X % X -> 0).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119538 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 096aa79276b8527a3cbbb3691e40e729dea09523 |
|
13-Nov-2010 |
Duncan Sands <baldrick@free.fr> |
Generalize the reassociation transform in SimplifyCommutative (now renamed to
SimplifyAssociativeOrCommutative) "(A op C1) op C2" -> "A op (C1 op C2)",
which previously was only done if C1 and C2 were constants, to occur whenever
"C1 op C2" simplifies (a la InstructionSimplify). Since the simplifying operand
combination can no longer be assumed to be the right-hand terms, consider all of
the possible permutations. When compiling "gcc as one big file", transform 2
(i.e. using right-hand operands) fires about 4000 times but it has to be said
that most of the time the simplifying operands are both constants. Transforms
3, 4 and 5 each fired once. Transform 6, which is an existing transform that
I didn't change, never fired. With this change, the testcase is now optimized
perfectly with one run of instcombine (previously it required instcombine +
reassociate + instcombine, and it may just have been luck that this worked).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@119002 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| a9445e11c553855a6caacbbbf77a9b993ecc651e |
|
02-Mar-2010 |
Dan Gohman <gohman@apple.com> |
Floating-point add, sub, and mul are now spelled fadd, fsub, and fmul,
respectively.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@97531 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 1df9859c40492511b8aa4321eb76496005d3b75b |
|
16-Feb-2010 |
Duncan Sands <baldrick@free.fr> |
There are two ways of checking for a given type, for example isa<PointerType>(T)
and T->isPointerTy(). Convert most instances of the first form to the second form.
Requested by Chris.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96344 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| b0bc6c361da9009e8414efde317d9bbff755f6c0 |
|
15-Feb-2010 |
Duncan Sands <baldrick@free.fr> |
Uniformize the names of type predicates: rather than having isFloatTy and
isInteger, we now have isFloatTy and isIntegerTy. Requested by Chris!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96223 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 5b39620e2da1451c5db50559085ae4b86a152936 |
|
17-Jan-2010 |
Owen Anderson <resistor@mac.com> |
Fix comment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@93679 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| 11acaa374cdcebb161bf0de5f244265d78a749c1 |
|
05-Jan-2010 |
Benjamin Kramer <benny.kra@googlemail.com> |
Convert a ton of simple integer type equality tests to the new predicate.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@92760 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|
| d12c27ce0079ba14e73e0c422a30dac68c631a23 |
|
05-Jan-2010 |
Chris Lattner <sabre@nondot.org> |
split mul/div/rem instructions out to their own file.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@92689 91177308-0d34-0410-b5e6-96231b3b80d8
/external/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
|