Use the fact that if we visit a for node first in pre and next in post order
we know we did not visit any children, thus we found an innermost loop.
+ Test case for an innermost loop with a conditional inside
llvm-svn: 213870
+ Renamed context into build when it's the isl_ast_build
+ Use the IslAstInfo functions to extract the schedule of a node
+ Use the IslAstInfo functions to extract the build/context of a node
+ Move the payload struct into the IslAstInfo class
+ Use a constructor and destructor (also new and delete) to
allocate/initialize the payload struct
llvm-svn: 213792
Offer the static functions to extract information out of an IslAst for node
as members of IslAstInfo not as top level entities.
+ Refactor common code
+ Add isParallel and isReductionParallel
+ Rename IslAstUser to IslAstUserPayload to make it clear this is just a (or
the) payload struct.
llvm-svn: 213272
+ Introduced dependency type TYPE_TC_RED to represent the transitive closure
(& the reverse) of reduction dependences. These are used when we check for
reduction parallel loops.
+ Test cases including loop reversals and modulo schedules which compute
reductions in a alternated order.
llvm-svn: 213019
As our delinearization works optimistically, we need in some cases run-time
checks that verify our optimistic assumptions. A simple example is the
following code:
void foo(long n, long m, long o, double A[n][m][o]) {
for (long i = 0; i < 100; i++)
for (long j = 0; j < 150; j++)
for (long k = 0; k < 200; k++)
A[i][j][k] = 1.0;
}
After clang linearized the access to A and we delinearized it again to
A[i][j][k] we need to ensure that we do not access the delinearized array
out of bounds (this information is not available in LLVM-IR). Hence, we
need to verify the following constraints at run-time:
CHECK: Assumed Context:
CHECK: [o, m] -> { : m >= 150 and o >= 200 }
llvm-svn: 212198
To translate the old induction variables as they exist before Polly to new
new induction variables introduced during AST code generation we need to
generate code that computes the new values from the old ones. We can do this
by just looking at the arguments isl generates in each scheduled statement.
Example:
// Old
for i
S(i)
// New
for c0
for c1
S(c0 + c1)
To get the value of i, we need to compute 'c0 + c1'. This expression is readily
available in the user statements generated by isl and just needs to be
translated to LLVM-IR.
This replaces an old confusing construct that constructed during ast generation
an isl multi affine expression that described this relation and which was then
again ast generated for each statement and argument when translating the isl ast
to LLVM-IR. This approach was difficult to understand and the additional ast
generation calls where entirely redundant as isl provides the relevant
expressions as arguments of the generated user statements.
llvm-svn: 212186
We use llvm.codegen intrinsic to generate code for embedded LLVM-IR
strings. The reason we introduce such a intrinsic is that previous
clang/opt tools was NOT linked with various LLVM targets and their
AsmParsers and AsmPrinters. Since clang/opt been linked with all the
needed libraries, we no longer need the llvm.codegen intrinsic.
llvm-svn: 211573
+ Collect reduction dependences
+ Introduced TYPE_RED in Dependences.h which can be used to obtain the
reduction dependences
+ Used TYPE_RED to prevent parallelization while we do not have a privatizing
code generation
+ Relax the dependences for non-parallel code generation
+ Add privatization dependences to ensure correctness
+ 12 Test cases to check for reduction and privatization dependences
llvm-svn: 211369
definition below all of the header #include lines, Polly edition.
If you want to know more details about this, you can see the recent
commits to Debug.h in LLVM. This is just the Polly segment of a cleanup
I'm doing globally for this macro.
llvm-svn: 206852
Commit r206510 falsely advertised to fix the load cases, even though it only
fixed the store case. This commit adds the same fix for the load case including
the missing test coverage.
llvm-svn: 206577
Even tough we may want to generate a vector load, the address from which to load
still is a scalar. Make sure even if previous address computations may have been
vectorized, that the addresses are also available as scalars.
This fixes http://llvm.org/PR19469
Reported-by: Jeremy Huddleston Sequoia <jeremyhu@apple.com>
llvm-svn: 206510
For complex examples it may happen that we do not compute dependences. In this
case we do not want to crash, but just not detect parallel loops.
llvm-svn: 204470
This patch enables vectorization of loops containing backward array
traversal (array stride is -1).
Contributed-by: Chris Jenneisch <chrisj@codeaurora.org>
llvm-svn: 204257
For now we only mark innermost loops for the loop vectorizer. We could later
also mark not-innermost loops to enable the introduction of openmp parallelism.
llvm-svn: 202854
PollyIRBuilder is currently just a typedef to IRBuilder<>. Consequently, this
change should not affect behavior. In subsequent patches we will extend its
functionality to emit loop.parallel metadata.
llvm-svn: 202853
The module LLVMPolly.so links to that. There is really no reason to build a
large number of mini-libraries here, especially as we do have dependences
between the libraries that are not properly handled and that make linking fail
on darwin.
Submitted-by: David Fang <fang@csl.cornell.edu>
llvm-svn: 202743
clang-formats behaviour has changed for a couple of C++11 formattings. We adapt
Polly to ensure our formatting checks are clean again.
llvm-svn: 202650
Sven suggested to use this simpler code generation strategy as the convex_hull
computation is apparently rather inefficient. We do not have a test case that
shows a difference, but, in case we find a test case where this makes a
difference, we can reconsider our decission.
llvm-svn: 201997
We now skip the debug intrinsics which is a lot better than crashing due to
uncopied metadata references. We should step by step investigate which debug
intrinsics we can copy without trouble.
We still keep the debug location metadata.
llvm-svn: 201860
This includes the following very useful isl commit:
commit d962967ab42323ea5ca0398956fbff6a98c782fa
Author: Sven Verdoolaege <skimo@kotnet.org>
Date: Wed Dec 18 12:05:32 2013 +0100
allow the user to impose a bound on the number of low-level operations
This should allow the user to deterministically limit the effort spent on a
computation.
llvm-svn: 200155
This removes the last isl_int dependency in the default build. There are
still some in OpenScop and Scoplib. For those isl-0.12.2 still needs to be used.
llvm-svn: 199585
For for-nodes that are translated to a set of vector lanes, we already know the
overall number of iterations. Calculating the upper bound is consequently not
necessary. This change removes the code for upper bound calculation, which was
probably copy/pasted from the code generation for the normal for-loop.
This issue was found by Sylvestre's scan-build server.
llvm-svn: 193925
When constructing a scop sometimes the exact representation of a statement or
condition would be very complex, but there is a common case which is a lot
simpler, but which is only valid under certain assumptions. The assumed context
records the assumptions taken during the construction of this scop and that need
to be code generated as a run-time test.
At the moment, we do not yet model any assumptions, but only added the
AssumedContext as well as the isl-ast generation support. As a next step,
this needs to be hooked up with the isl code generation.
if (1) /* run-time condition */
{ /* optimized code */ }
else
{ /* original code */ }
llvm-svn: 193652
We now use __isl_take to annotate the uses of the isl_set where we got the
memory management wrong.
Thanks to Rafael! His pipefail work hardened our test environment and exposed
this bug nicely.
llvm-svn: 187338
Split the old getNewValue into two parts:
1. The function "lookupAvailableValue" that return the new version of
the instruction which is already available.
2. The function calls "lookupAvailableValue", and tries to generate
the new version if it is not available yet.
llvm-svn: 187114
Orignally, we first test if a ValueMap contains a Value, and than use the
index operator to get the corresponding new value. This requires the ValueMap
to lookup the key (i.e. the old value) twice.
Now, we directly use the "lookup" function provided by DenseMap to implement
the same functionality.
llvm-svn: 185260
1. Do not allow creating new memory access record in the InstructionToAccess map
on the fly in function getAccessFor.
2. Do not allow user to modify the memory accesses returned by getAccessFor
during the code generation process.
llvm-svn: 185253
isl recently introduced isl_val as an abstract interface to represent arbitrary
precision numbers. This interface superseeds the old isl_int interface. In
contrast to the old interface which implemented arbitrary precision arithmetic
using macros that forward to the gmp library, the new library hides the math
library implementation in isl. This allows us to switch the math library used by
isl without affecting users such as Polly.
llvm-svn: 184529
In GDB when "step" through generateScalarLoad and "finish" the call, the
returned value is non NULL, however when printing the value contained in
BBMap[Load] after this stmt:
BBMap[Load] = generateScalarLoad(...);
the value in BBMap[Load] is NULL, and the BBMap.count(Load) is 1.
The only intuitive idea that I have to explain this behavior is that we are
playing with the undefined behavior of eval order of the params for the function
standing for "BBMap[Load] = generateScalarLoad()". "BBMap[Load] = " may be
executed before generateScalarLoad is called.
Here are some other possible explanations from Will Dietz <w@wdtz.org>:
The error is likely due to BBMap[Load] being evaluated first (creating
a {Load -> uninitialized } entry in the DenseMap), then
generateScalarLoad eventually accesses the same element and finds it
to be NULL (DenseMap[Old]).. Offhand I'm not sure if this is
guaranteed to be NULL or if it's uninitialized and happens to be NULL.
The same issue can also go wrong in an even worse way: the second
DenseMap access can trigger a rehash and *invalidate* the an earlier
evaluated expression (for example LHS of the assignment), leading to a
crash when performing the assignment store.
llvm-svn: 182655
When the Polly code generation was written we did not correctly update the
LoopInfo data, but still claimed that the loop information is correct. This
does not only lead to missed optimizations, but it can also cause
miscompilations in case passes such as LoopSimplify are run after Polly.
Reported-by: Sergei Larin <slarin@codeaurora.org>
llvm-svn: 181987
BeforeBB
|
v
GuardBB
/ \
__ PreHeaderBB \
/ \ / |
latch HeaderBB |
\ / \ /
< \ /
\ /
ExitBB
This does not only remove the need for an explicit loop rotate pass, but it also
gives us the possibility to skip the construction of the guard condition in case
the loop is known to be executed at least once. We do not yet exploit this, but
by implementing this analysis in the isl code generator we should be able to
remove more guards than the generic loop rotate pass can. Another point is that
loop rotation can introduce additional PHI nodes, which may hide that a loop can
be executed in parallel. This change avoids this complication and will make it
easier to move the openmp code generation into a separate pass.
llvm-svn: 181986
Use the new cl::OptionCategory support to move the Polly options into a separate
option category. The aim is to hide most options and show by default only the
options a user needs to influence '-O3 -polly'. The available options probably
need some care, but here is the current status:
Polly Options:
Configure the polly loop optimizer
-enable-polly-openmp - Generate OpenMP parallel code
-polly - Enable the polly optimizer (only at -O3)
-polly-no-tiling - Disable tiling in the scheduler
-polly-only-func=<function-name> - Only run on a single function
-polly-report - Print information about the activities
of Polly
-polly-vectorizer - Select the vectorization strategy
=none - No Vectorization
=polly - Polly internal vectorizer
=unroll-only - Only grouped unroll the vectorize
candidate loops
=bb - The Basic Block vectorizer driven by
Polly
llvm-svn: 181295
In the classical (non -polly-codegen-scev) mode, we assume that we can always
recreate PHI nodes during code generation. This is not true. We can only
reconstruct them from the polyhedral information, in case the entire loop of the
PHI node is part of the SCoP and consequently the PHI node was translated in
the polyhedral description.
llvm-svn: 179674
Regions that have multiple entry edges are very common. A simple if condition
yields e.g. such a region:
if
/ \
then else
\ /
for_region
This for_region contains two entry edges 'then' -> 'for_region' and 'else' -> 'for_region'.
Previously we scheduled the RegionSimplify pass to translate such regions into
simple regions. With this patch, we now support them natively when the region is
in -loop-simplify form, which means the entry block should not be a loop header.
Contributed by: Star Tan <tanmx_star@yeah.net>
llvm-svn: 179586
Regions that have multiple exit edges are very common. A simple if condition
yields e.g. such a region:
if
/ \
then else
\ /
after
Region: if -> after
This regions contains the bbs 'if', 'then', 'else', but not 'after'. It has
two exit edges 'then' -> 'after' and 'else' -> 'after'.
Previously we scheduled the RegionSimplify pass to translate such regions into
simple regions. With this patch, we now support them natively.
Contributed-by: Star Tan <tanmx_star@yeah.net>
llvm-svn: 179159
During code generation we split the original entry and exit basic blocks
of the scop to make room for the newly generated code. To keep the region tree
up to date, we need to update the region tree. This patch ensures that not only
the region of the scop is updated, but also all child regions that share the
same entry or exit block.
We have now test case here, as the bug is only exposed by the subsequent commit.
The test cases of that commit also cover this bug.
Contributed-by: Star Tan <tanmx_star@yeah.net>
llvm-svn: 179158
After this commit, polly is clang-format clean. This can be tested with
'ninja polly-check-format'. Updates to clang-format may change this, but the
differences will hopefully be both small and general improvements to the
formatting.
We currently have some not very nice formatting for a couple of items, DEBUG()
stmts for example. I believe the benefit of being clang-format clean outweights
the not perfect layout of this code.
llvm-svn: 177796
Given the following code
for (i = 0; i < 10; i++) {
;
}
S: A[i] = 0
When code generating S using scev based code generation, we need to retrieve
the scev of 'i' at the location of 'S'. If we do not do this the scev that
we obtain will be expressed as {0,+,1}_for and will reference loop iterators
that do not surround 'S' and that we consequently do not know how to code
generate. What we really want is the scev to be instantiated to the value of 'i'
after the loop. This value is {10} and it can be code generated without
troubles.
llvm-svn: 177777
When using the scev based code generation, we now do not rely on the presence
of a canonical induction variable any more. This commit prepares the path to
(conditionally) disable the induction variable canonicalization pass.
llvm-svn: 177548
When doing SCEV based code generation, we ignore instructions calculating values
that are fully defined by a SCEV expression. The values that are calculated by
this instructions are recalculated on demand.
This commit improves the check to verify if certain instructions can be ignored
and recalculated on demand.
llvm-svn: 177313
We fix the following formatting problems found by clang-format:
- 80 cols violations
- Obvious problems with missing or too many spaces
- multiple new lines in a row
clang-format suggests many more changes, most of them falling in the following
two categories:
1) clang-format does not at all format a piece of code nicely
2) The style that clang-format suggests does not match the style used in
Polly/LLVM
I consider differences caused by reason 1) bugs, which should be fixed by
improving clang-format. Differences due to 2) need to be investigated closer
to understand the cause of the difference and the solution that should be taken.
llvm-svn: 171241
Recent changes in isl:
- Allow analysis of loops during code generation
This simplifies the detection of parallel loops.
- Simplify the way costumized ast printers are defined
This enables us to highlight parallel / vector loops in our debug output.
- Compile time improvements for codegen contexts that include parameters
- Various bug fixes
This update also gets us in sync for the isl 0.11 release.
llvm-svn: 169100
generation.
We don't use the exact same way to build loop body for GPGPU codegen as openmp
codegen and other transformations do currently, in which cases 'createLoop'
function is called recursively. GPGPU codegen may fail due to improper restore
of ValueMap and ClastVars .
Contributed by: Yabin Hu <yabin.hwu@gmail.com>
llvm-svn: 168966
The detection of values that need to be copied in to the generated OpenMP
subfunction also detects the array base addresses needed in the SCoP. Hence, it
is not necessary to unconditionally copy all the base addresses to the generated
function.
Test cases are modified to reflect this change. Arrays which are global
variables do not occur in the struct passed to the subfunction anymore. A test
case for base address copy-in is added in copy_in_array.{c,ll}.
Committed with slight modifications
Contributed by: Armin Groesslinger <armin.groesslinger@uni-passau.de>
llvm-svn: 167215
In addition to the arrays and clast variables a SCoP statement may also refer to
values defined before the SCoP or to function arguments. Detect these values and
add them to the set of values passed to the function generated for OpenMP
parallel execution of a clast.
Committed with additional test cases and some refactoring.
Contributed by: Armin Groesslinger <armin.groesslinger@uni-passau.de>
llvm-svn: 167214
When generating OpenMP or GPGPU code the original ValueMap and ClastVars must be
kept. We already recovered the original ClastVars by reverting the changes, but
we did not keep the content of the ValueMap. This patch keeps now an explicit
copy of both maps and restores them after generating OpenMP or GPGPU code.
This is an adapted version of a patch contributed by:
Armin Groesslinger <armin.groesslinger@uni-passau.de>
llvm-svn: 167213
This change ensures that isl is only detected if it includes code generation
support. This allows us to remove a lot of conditional compilation and also
avoids missing test cases in case the feature is not available.
llvm-svn: 166403
Previously isl always generated '<=' or '>='. However, in many cases '<' or '>'
leads to simpler code. This commit updates isl and adds the relevant code
generation support to Polly.
llvm-svn: 166020
This pass implements a new code generator that uses the code generation
algorithm included in isl.
For the moment the new code generation is limited to sequential code.
llvm-svn: 165037
Translate the selected parallel loop body into a ptx string and run it with the
cuda driver API. We limit this preliminary implementation to target the
following special test cases:
- Support only 2-dimensional parallel loops with or without only one innermost
non-parallel loop.
- Support write memory access to only one array in a SCoP.
The patch was committed with smaller changes to the build system:
There is now a flag to enable gpu code generation explictly. This was required
as we need the llvm.codegen() patch applied on the llvm sources, to compile this
feature correctly. Also, enabling gpu code generation does not require cuda.
This requirement was removed to allow 'make polly-test' runs, even without an
installed cuda runtime.
Contributed by: Yabin Hu <yabin.hwu@gmail.com>
llvm-svn: 161239
I did not take into account, that this patch fails to compile without the
llvm.codegen patch applied. This breaks buildbots.
I revert this until we found a solution to commit this without buildbots
complaining.
This reverts commit cb43ab80e94434e780a66be3b9a6ad466822fe33.
llvm-svn: 160165
Translate the selected parallel loop body into a ptx string and run it
with cuda driver API. We limit this preliminary implementation to
target the following special test cases:
- Support only 2-dimensional parallel loops with or without only one
innermost non-parallel loop.
- Support write memory access to only one array in a SCoP.
Contributed by: Yabin Hu <yabin.hwu@gmail.com>
llvm-svn: 160164
CLooG and the CLooG based code generation does not yet correctly derive the
types of the expressions, but just uses i64 for everything. This is incorrect,
but works normally pretty well. However, the recent change of adding parameter
bounds to the context made CLooG generate expressions that contain a lot of very
large integers that possibly don't fit into an i64. This broke the code
generation for several benchmarks.
To get the CLooG based code generation working again, we just don't take into
account any constraints in the context. This brings us back to the theoretical
incorrect, but in practice generally correct code.
The next step will be the isl based code generation. Here we will derive
automatically correct types.
llvm-svn: 158015
This is an incomplete implementation of the SCEV based code generation.
When finished it will remove the need for -indvars -enable-iv-rewrite.
For the moment it is still disabled. Even though it passes 'make polly-test',
there are still loose ends especially in respect of OpenMP code generation.
llvm-svn: 155717
This fixes two crashes that appeared in case of:
- A load of a non vectorizable type (e.g. float**)
- An instruction that is not vectorizable (e.g. call)
llvm-svn: 154586
Grouped unrolling means that we unroll a loop such that the different instances
of a certain statement are scheduled right after each other, but we do
not generate any vector code. The idea here is that we can schedule the
bb vectorizer right afterwards and use it heuristics to decide when
vectorization should be performed.
llvm-svn: 154251
To avoid overflows we still use a larger type (i64) while calculating the value
of the old ivs. However, we truncate the result to the type of the old iv when
providing it to the new code.
A corresponding test case is added to the polly test suite. Also, a failing test
case is fixed.
This fixes PR12311.
Contributed by: Tsingray Liu <tsingrayliu@gmail.com>
llvm-svn: 153952
When deriving new values for the statements of a SCoP, we assumed that parameter
values are constant within the SCoP and consquently do not need to be rewritten.
For OpenMP code generation this assumption is wrong, as such values are not
available in the OpenMP subfunction and consequently also may need to be
rewritten.
Committed with some changes.
Contributed-By: Johannes Doerfert <s9jodoer@stud.uni-saarland.de>
llvm-svn: 153838
Johannes Doerfert