| Age | Commit message (Collapse) | Author |
|---|
|
One performs: (X == 13 | X == 14) -> X-13 <u 2
The other: (A == C1 || A == C2) -> (A & ~(C1 ^ C2)) == C1
The problem is that there are certain values of C1 and C2 that
trigger both transforms but the first one blocks out the second,
this generates suboptimal code.
Reordering the transforms should be better in every case and
allows us to do interesting stuff like turn:
%shr = lshr i32 %X, 4
%and = and i32 %shr, 15
%add = add i32 %and, -14
%tobool = icmp ne i32 %add, 0
into:
%and = and i32 %X, 240
%tobool = icmp ne i32 %and, 224
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179493 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179492 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
and add the cost of extracting values from the roots of the tree.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179475 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179470 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
There is a Constant with non-constant operands: blockaddress.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179460 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This is basically the same fix in three different places. We use a set to avoid
walking the whole tree of a big ConstantExprs multiple times.
For example: (select cmp, (add big_expr 1), (add big_expr 2))
We don't want to visit big_expr twice here, it may consist of thousands of
nodes.
The testcase exercises this by creating an insanely large ConstantExprs out of
a loop. It's questionable if the optimizer should ever create those, but this
can be triggered with real C code. Fixes PR15714.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179458 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Fixes PR15737.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179417 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
perform a preliminary traversal of the graph to collect values with multiple users and check where the users came from.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179414 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
from 1 to two. Fixed a few tests that changes because now the cost of one insert + a vector operation on two doubles is lower than two scalar operations on doubles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179413 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Previously it was just instruction attachments.
Depends on a driver change to actually work:
https://codereview.chromium.org/14072004/
BUG= http://code.google.com/p/nativeclient/issues/detail?id=3348
Review URL: https://codereview.chromium.org/14022009
|
|
extend the ABI checker to verify.
Also promote weak symbols to internal ones, which was required because the scons barebones tests define weak versions of memcpy/memset
BUG= https://code.google.com/p/nativeclient/issues/detail?id=3339
TEST= llvm-regression (globalcleanup.ll), scons barebones tests
Review URL: https://codereview.chromium.org/13989005
|
|
The transform will execute like so:
(A & ~B) == 0 --> (A & B) != 0
(A & ~B) != 0 --> (A & B) == 0
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179386 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Don't classify idiv/udiv as a reduction operation. Integer division is lossy.
For example : (1 / 2) * 4 != 4/2.
Example:
int a[] = { 2, 5, 2, 2}
int x = 80;
for()
x /= a[i];
Scalar:
x /= 2 // = 40
x /= 5 // = 8
x /= 2 // = 4
x /= 2 // = 2
Vectorized:
<80, 1> / <2,5> //= <40,0>
<40, 0> / <2,2> //= <20,0>
20*0 = 0
radar://13640654
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179381 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Allows LLVM to optimize sequences like the following:
%add = add nsw i32 %x, 1
%cmp = icmp sgt i32 %add, %y
into:
%cmp = icmp sge i32 %x, %y
as well as:
%add1 = add nsw i32 %x, 20
%add2 = add nsw i32 %y, 57
%cmp = icmp sge i32 %add1, %add2
into:
%add = add nsw i32 %y, 37
%cmp = icmp sle i32 %cmp, %x
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179316 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
When trying to collapse sequences of insertelement/extractelement
instructions into single shuffle instructions, there is one specific
case where the Instruction Combiner wrongly updates the resulting
Mask of shuffle indexes.
The problem is in function CollectShuffleElments.
If we have a sequence of insert/extract element instructions
like the one below:
%tmp1 = extractelement <4 x float> %LHS, i32 0
%tmp2 = insertelement <4 x float> %RHS, float %tmp1, i32 1
%tmp3 = extractelement <4 x float> %RHS, i32 2
%tmp4 = insertelement <4 x float> %tmp2, float %tmp3, i32 3
Where:
. %RHS will have a mask of [4,5,6,7]
. %LHS will have a mask of [0,1,2,3]
The Mask of shuffle indexes is wrongly computed to [4,1,6,7]
instead of [4,0,6,7].
When analyzing %tmp2 in order to compute the Mask for the
resulting shuffle instruction, the algorithm forgets to update
the mask index at position 1 with the index associated to the
element extracted from %LHS by instruction %tmp1.
Patch by Andrea DiBiagio!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179291 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179277 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179276 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
function calls when we check if it is safe to sink instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179207 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations.
The infrastructure has three potential users:
1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]).
2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute.
3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization.
This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code:
void SAXPY(int *x, int *y, int a, int i) {
x[i] = a * x[i] + y[i];
x[i+1] = a * x[i+1] + y[i+1];
x[i+2] = a * x[i+2] + y[i+2];
x[i+3] = a * x[i+3] + y[i+3];
}
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179111 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179087 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
new/new[] operators.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179084 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
uninitialized memory.
Users may overide new-operators and implement any function that they like.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179071 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
The fix for PR14972 in r177055 introduced a real think-o in the *store*
side, likely because I was much more focused on the load side. While we
can arbitrarily widen (or narrow) a loaded value, we can't arbitrarily
widen a value to be stored, as that changes the width of memory access!
Lock down the code path in the store rewriting which would do this to
only handle the intended circumstance.
All of the existing tests continue to pass, and I've added a test from
the PR.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178974 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This is the counterpart to commit r160637, except it performs the action
in the bottomup portion of the data flow analysis.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178922 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
The normal dataflow sequence in the ARC optimizer consists of the following
states:
Retain -> CanRelease -> Use -> Release
The optimizer before this patch stored the uses that determine the lifetime of
the retainable object pointer when it bottom up hits a retain or when top down
it hits a release. This is correct for an imprecise lifetime scenario since what
we are trying to do is remove retains/releases while making sure that no
``CanRelease'' (which is usually a call) deallocates the given pointer before we
get to the ``Use'' (since that would cause a segfault).
If we are considering the precise lifetime scenario though, this is not
correct. In such a situation, we *DO* care about the previous sequence, but
additionally, we wish to track the uses resulting from the following incomplete
sequences:
Retain -> CanRelease -> Release (TopDown)
Retain <- Use <- Release (BottomUp)
*NOTE* This patch looks large but the most of it consists of updating
test cases. Additionally this fix exposed an additional bug. I removed
the test case that expressed said bug and will recommit it with the fix
in a little bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178921 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
index.
This optimization is unstable at this moment; it
1) block us on a very important application
2) PR15200
3) test6 and test7 in test/Transforms/ScalarRepl/dynamic-vector-gep.ll
(the CHECK command compare the output against wrong result)
I personally believe this optimization should not have any impact on the
autovectorized code, as auto-vectorizer is supposed to put gather/scatter
in a "right" way. Although in theory downstream optimizaters might reveal
some gather/scatter optimization opportunities, the chance is quite slim.
For the hand-crafted vectorizing code, in term of redundancy elimination,
load-CSE, copy-propagation and DSE can collectively achieve the same result,
but in much simpler way. On the other hand, these optimizers are able to
improve the code in a incremental way; in contrast, SROA is sort of all-or-none
approach. However, SROA might slighly win in stack size, as it tries to figure
out a stretch of memory tightenly cover the area accessed by the dynamic index.
rdar://13174884
PR15200
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178912 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Pass down the fact that an operand is going to be a vector of constants.
This should bring the performance of MultiSource/Benchmarks/PAQ8p/paq8p on x86
back. It had degraded to scalar performance due to my pervious shift cost change
that made all shifts expensive on x86.
radar://13576547
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178809 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
I've encountered two uses of va_arg on an empty argument list: NaCl's
open() wrapper (now fixed), and 176.gcc in Spec2k. Although this is
invalid use of va_arg (giving undefined behaviour), it's too awkward
to fix 176.gcc.
Work around this invalid usage by ensuring that the argument list
pointer points to a location on the stack rather than being
uninitialised. va_arg will return undefined values as it does in the
usual native ABIs, rather than crashing.
We could add options for non-strict and strict modes (possibly with a
bounds check), but that's too much complication for now.
BUG=https://code.google.com/p/nativeclient/issues/detail?id=3338
TEST=test/Transforms/NaCl/*.ll + ran 176.gcc from Spec2k
Review URL: https://codereview.chromium.org/13510004
|
|
objc_autoreleaseReturnValue.
The semantics of ARC implies that a pointer passed into an objc_autorelease
must live until some point (potentially down the stack) where an
autorelease pool is popped. On the other hand, an
objc_autoreleaseReturnValue just signifies that the object must live
until the end of the given function at least.
Thus objc_autorelease is stronger than objc_autoreleaseReturnValue in
terms of the semantics of ARC* implying that performing the given
strength reduction without any knowledge of how this relates to
the autorelease pool pop that is further up the stack violates the
semantics of ARC.
*Even though objc_autoreleaseReturnValue if you know that no RV
optimization will occur is more computationally expensive.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178612 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
The iterator could be invalidated when it's recursively deleting a whole bunch
of constant expressions in a constant initializer.
Note: This was only reproducible if `opt' was run on a `.bc' file. If `opt' was
run on a `.ll' file, it wouldn't crash. This is why the test first pushes the
`.ll' file through `llvm-as' before feeding it to `opt'.
PR15440
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178531 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178484 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
instruction counts.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178459 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
rule 1: (x | c1) ^ c2 => (x & ~c1) ^ (c1^c2),
only useful when c1=c2
rule 2: (x & c1) ^ (x & c2) = (x & (c1^c2))
rule 3: (x | c1) ^ (x | c2) = (x & c3) ^ c3 where c3 = c1 ^ c2
rule 4: (x | c1) ^ (x & c2) => (x & c3) ^ c1, where c3 = ~c1 ^ c2
It reduces an application's size (in terms of # of instructions) by 8.9%.
Reviwed by Pete Cooper. Thanks a lot!
rdar://13212115
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178409 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
ExpandTls's use of replaceUsesOfWith() didn't work for PHI nodes
containing the same Constant twice (which needs to work for same or
differing incoming BasicBlocks). The same applies to
ExpandTlsConstantExpr.
I noticed this while implementing ExpandConstantExpr.
Fix this and factor out some common code that all three passes can
use.
BUG=https://code.google.com/p/nativeclient/issues/detail?id=2837
TEST=test/Transforms/NaCl/*.ll
Review URL: https://codereview.chromium.org/13128002
|
|
objc-arc-expand runs before objc-arc/objc-arc-contract.
Specifically, objc-arc-expand will make sure that the
objc_retainAutoreleasedReturnValue, objc_autoreleaseReturnValue, and ret
will all have %call as an argument.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178382 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
present in a module.
clang.arc.used is an interesting call for ARC since ObjCARCContract
needs to run to remove said intrinsic to avoid a linker error (since the
call does not exist).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178369 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This only works on instruction attachments for now. Since it is a
ModulePass we can add something to strip NamedMetadata
based on a whitelist, if we want to retain some of that.
It does not touch debug metadata, and leaves -strip-debug to handle that.
BUG= https://code.google.com/p/nativeclient/issues/detail?id=3348
Review URL: https://codereview.chromium.org/12844027
|
|
Since we handle optimizable objc_retainBlocks through strength reduction
in OptimizableIndividualCalls, we know that all code after that point
will only see non-optimizable objc_retainBlock calls. IsForwarding is
only called by functions after that point, so it is ok to just classify
objc_retainBlock as non-forwarding.
<rdar://problem/13249661>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178285 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
objc_retainBlock is optimizable.
If an objc_retainBlock has the copy_on_escape metadata attached to it
AND if the block pointer argument only escapes down the stack, we are
allowed to strength reduce the objc_retainBlock to to an objc_retain and
thus optimize it.
Current there is logic in the ARC data flow analysis to handle
this case which is complicated and involved making distinctions in
between objc_retainBlock and objc_retain in certain places and
considering them the same in others.
This patch simplifies said code by:
1. Performing the strength reduction in the initial ARC peephole
analysis (ObjCARCOpts::OptimizeIndividualCalls).
2. Changes the ARC dataflow analysis (which runs after the peephole
analysis) to consider all objc_retainBlock calls to not be optimizable
(since if the call was optimizable, we would have strength reduced it
already).
This patch leaves in the infrastructure in the ARC dataflow analysis to
handle this case, which due to 2 will just be dead code. I am doing this
on purpose to separate the removal of the old code from the testing of
the new code.
<rdar://problem/13249661>.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178284 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178278 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This reverts commit 342d92c7a0adeabc9ab00f3f0d88d739fe7da4c7.
Turns out we're going with a different schema design to represent
DW_TAG_imported_modules so we won't need this extra field.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178215 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178208 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
* Ensure that the "byval" attribute is preserved for the fixed
arguments. Before, it was stripped off from function calls but
left in for function definitions, which broke passing struct
arguments (which PNaCl Clang generates as "byval").
* Ensure that function and return attributes are preserved too.
* Handle "byval" variable arguments in calls too by dereferencing the
pointer. These are not yet usable with PNaCl Clang, which does not
allow va_arg on structs (see
https://code.google.com/p/nativeclient/issues/detail?id=2381), but
we might as well make this pass ready to handle this.
BUG=https://code.google.com/p/nativeclient/issues/detail?id=3338
TEST=test/Transforms/NaCl/expand-varargs*.ll
Review URL: https://codereview.chromium.org/13100002
|
|
The test was removed since I had not turned off the test during release
builds. This fails since ARC annotations support is conditionally
compiled out during release builds. I added the proper requires header
to assuage this issue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178101 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This is just the basic groundwork for supporting DW_TAG_imported_module but I
wanted to commit this before pushing support further into Clang or LLVM so that
this rather churny change is isolated from the rest of the work. The major
churn here is obviously adding another field (within the common DIScope prefix)
to all DIScopes (files, classes, namespaces, lexical scopes, etc). This should
be the last big churny change needed for DW_TAG_imported_module/using directive
support/PR14606.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178099 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This is similar to the GEP handling in visitGetElementPtr() in
lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp.
Once this pass is enabled, it will simplify the language to reduce the
set of constructs that a PNaCl translator needs to handle as part of a
stable wire format for PNaCl.
BUG=https://code.google.com/p/nativeclient/issues/detail?id=3343
TEST=test/Transforms/NaCl/expand-getelementptr.ll
Review URL: https://codereview.chromium.org/12849009
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178038 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177956 91177308-0d34-0410-b5e6-96231b3b80d8
|
