If the GEP instructions give us enough insights, model scalar accesses as
multi-dimensional (and generate the relevant run-time checks to ensure
correctness). This will allow us to simplify the dependence computation in
a subsequent commit.
llvm-svn: 247906
This will allow to generate non-wrap assumptions for integer expressions
that are part of the SCoP. We compare the common isl representation of
the expression with one computed with modulo semantic. For all parameter
combinations they are not equal we can have integer overflows.
The nsw flags are respected when the modulo representation is computed,
nuw and nw flags are ignored for now.
In order to not increase compile time to much, the non-wrap assumptions
are collected in a separate boundary context instead of the assumed
context. This helps compile time as the boundary context can become
complex and it is therefor not advised to use it in other operations
except runtime check generation. However, the assumed context is e.g.,
used to tighten dependences. While the boundary context might help to
tighten the assumed context it is doubtful that it will help in practice
(it does not effect lnt much) as the boundary (or no-wrap assumptions)
only restrict the very end of the possible value range of parameters.
PET uses a different approach to compute the no-wrap context, though lnt runs
have shown that this version performs slightly better for us.
llvm-svn: 247732
As we do not rely on ScalarEvolution any more we do not need to get
the backedge taken count. Additionally, our domain generation handles
everything that is affine and has one latch and our ScopDetection will
over-approximate everything else.
This change will therefor allow loops with:
- one latch
- exiting conditions that are affine
Additionally, it will not check for structured control flow anymore.
Hence, loops and conditionals are not necessarily single entry single
exit regions any more.
Differential Version: http://reviews.llvm.org/D12758
llvm-svn: 247289
If a region does not have more than one loop, we do not identify it as
a Scop in ScopDetection. The main optimizations Polly is currently performing
(tiling, preparation for outer-loop vectorization and loop fusion) are unlikely
to have a positive impact on individual loops. In some cases, Polly's run-time
alias checks or conditional hoisting may still have a positive impact, but those
are mostly enabling transformations which LLVM already performs for individual
loops. As we do not focus on individual loops, we leave them untouched to not
introduce compile time regressions and execution time noise. This results in
good compile time reduction (oourafft: -73.99%, smg2000: -56.25%).
Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in>
Reviewers: grosser
Differential Revision: http://reviews.llvm.org/D12268
llvm-svn: 246161
Instead of generating code for an empty assumed context we bail out
early. As the number of assumptions we generate increases this becomes
more and more important. Additionally, this change will allow us to
hide internal contexts that are only used in runtime checks e.g., a
boundary context with constraints not suited for simplifications.
llvm-svn: 245540
As specified in PR23888, run-time alias check generation is expensive
in terms of compile-time. This reduces the compile time by computing
minimal/maximal access only once for each base pointer
Contributed-by: Pratik Bhatu <cs12b1010@iith.ac.in>
llvm-svn: 243024
Instead of flat schedules, we now use so-called schedule trees to represent the
execution order of the statements in a SCoP. Schedule trees make it a lot easier
to analyze, understand and modify properties of a schedule, as specific nodes
in the tree can be choosen and possibly replaced.
This patch does not yet fully move our DependenceInfo pass to schedule trees,
as some additional performance analysis is needed here. (In general schedule
trees should be faster in compile-time, as the more structured representation
is generally easier to analyze and work with). We also can not yet perform the
reduction analysis on schedule trees.
For more information regarding schedule trees, please see Section 6 of
https://lirias.kuleuven.be/handle/123456789/497238
llvm-svn: 242130
I just learned that target triples prevent test cases to be run on other
architectures. Polly test cases are until now sufficiently target independent
to not require any target triples. Hence, we drop them.
llvm-svn: 235384
This allows us to delinerize code such as:
A[][n]
for (i
for (j
A[i][n-j-1] = ...
which would previously have been delinearize to an access A[i+1][-j-1].
To recover the correct access we apply the piecewise expression:
{ A[i][j] -> A[i-1][i+N]: i < 0; A[i][j] -> A[i][i]: i >= 0}
This approach generalizes to higher dimensions.
llvm-svn: 233566
isl recently introduced a new interface to create run-time checks from
constraint sets. Use this interface to simplify our run-time check generation.
llvm-svn: 230640
Scops that only read seem generally uninteresting and scops that only write are
most likely initializations where there is also little to optimize. To not
waste compile time we bail early.
Differential Revision: http://reviews.llvm.org/D7735
llvm-svn: 229820
This commit imports the latest isl version into lib/External/isl. The changes
relavant for Polly are:
1) Schedule trees [1] have been introduced as a more structured way to
describe schedules. Polly does not yet use them, but we may switch to them
in the near future.
2) Another set of coalescing changes [2] simplifies some data dependences and
removes a couple of code generation artifacts.
We now understand that the following sets can be merged:
{ Stmt_S1[i0, i1] -> Stmt_S2[i0 + i1] :
i0 >= 0 and i1 <= 1023 - i0 and i1 >= 1
Stmt_S1[i0, 0] -> Stmt_S2[i0] : i0 <= 1023 and i0 >= 1}
into:
{ Stmt_S1[i0, i1] -> Stmt_S2[i0 + i1] : i1 <= 1023 - i0 and i1 >= 0 and
i1 >= 1 - i0 and i0 >= 0 }
Changes of this kind reduce unnecessary specialization during code
generation.
- for (int c3 = 0; c3 <= 1023; c3 += 1) {
- if (c3 % 2 == 0) {
- Stmt_for_body3(c1, c3);
- } else
- Stmt_for_body3(c1, c3);
- }
+ for (int c3 = 0; c3 <= 1023; c3 += 1)
+ Stmt_for_body3(c1, c3);
[1] http://impact.gforge.inria.fr/impact2014/papers/impact2014-verdoolaege.pdf
[2] http://impact.gforge.inria.fr/impact2015/papers/impact2015-verdoolaege.pdf
llvm-svn: 229423
This allows us to skip ast and code generation if we did not optimize
a SCoP and will not generate parallel or alias annotations. The
initial heuristic to exit is simple but allows improvements later on.
All failing test cases have been modified to disable early exit, thus
to keep their coverage.
Differential Revision: http://reviews.llvm.org/D7254
llvm-svn: 228851
Schedule dimensions that have the same constant value accross all statements do
not carry any information, but due to the increased dimensionality of the
schedule cost compile time. To not pay this cost, we remove constant dimensions
if possible.
llvm-svn: 225067
Isl now specifically marks modulo operations that are compared against zero.
They can be implemented with the C/LLVM remainder operation.
We also update a couple of test cases where the output of isl has slightly
changed.
llvm-svn: 223607
In case a GEP instruction references into a fixed size array e.g., an access
A[i][j] into an array A[100x100], LLVM-IR does not guarantee that the subscripts
always compute values that are within array bounds. We now derive the set of
parameter values for which all accesses are within bounds and add the assumption
that the scop is only every executed with this set of parameter values.
Example:
void foo(float A[][20], long n, long m {
for (long i = 0; i < n; i++)
for (long j = 0; j < m; j++)
A[i][j] = ...
This loop yields out-of-bound accesses if m is at least 20 and at the same time
at least one iteration of the outer loop is executed. Hence, we assume:
n <= 0 or m <= 20.
Doing so simplifies the dependence analysis problem, allows us to perform
more optimizations and generate better code.
TODO: The location where the GEP instruction is executed is not necessarily the
location where the memory is actually accessed. As a result scanning for GEP[s]
is imprecise. Even though this is not a correctness problem, this imprecision
may result in missed optimizations or non-optimal run-time checks.
In polybench where this mismatch between parametric loop bounds and fixed size
arrays is common, we see with this patch significant reductions in compile time
(up to 50%) and execution time (up to 70%). We see two significant compile time
regressions (fdtd-2d, jacobi-2d-imper), and one execution time regression
(trmm). Both regressions arise due to additional optimizations that have been
enabled by this patch. They can be addressed in subsequent commits.
http://reviews.llvm.org/D6369
llvm-svn: 222754
Instead of parallelizing every parallel outermost loop, we now use a very
minimalistic cost model. Specifically, we assume innermost loops are not
worth parallelising and all non-innermost loops are.
When parallelizing all loops in LNT we got several slowdowns/timeouts due to
us parallelizing innermost loops that are executed only a couple of times
(number of iterations not known statically). With this basic heuristic enabled
LNT does not show any more timeouts, while several interesting loops are still
parallelized.
There are many ways to obtain an improved heuristic. Constructing such an
improvide heuristic from a position of minimal slow-down and zero code size
increase seems to be the best, as it allows us to track progress on LNT.
llvm-svn: 222096
We introduces a new flag -polly-parallel and use it to annotate the for-nodes in
the isl ast that we want to execute thread parallel (e.g., using OpenMP). We
previously already emmitted openmp annotations, but we did this for various
kinds of parallel loops, including some which we can not run in parallel.
With this patch we now have three annotations:
1) #pragma known-parallel [reduction]
2) #pragma omp for
3) #pragma simd
meaning:
1) loop has no loop carried dependences
2) loop will be executed thread-parallel
3) loop can possibly be vectorized
This patch introduces 1) and reduces the use of 2) to only the cases where we
will actually generate thread parallel code.
It is in preparation of openmp code generation in our isl backend.
Legacy:
- We also have a command line option -enable-polly-openmp. This option controls
the OpenMP code generation in CLooG. It will become an alias of
-polly-parallel after the CLooG code generation has been dropped.
http://reviews.llvm.org/D6142
llvm-svn: 221479
If there are multiple read only base addresses in an alias group
we can split it into multiple alias groups each with only one
read only access. This way we might reduce the number of
comparisons significantly as it grows linear in the number of
alias groups but exponential in their size.
Differential Revision: http://reviews.llvm.org/D5435
llvm-svn: 218757
During the IslAst parallelism check also compute the minimal dependency
distance and store it in the IstAst for node.
Reviewer: sebpop
Differential Revision: http://reviews.llvm.org/D4987
llvm-svn: 217729
There was a bug in the IslAst which caused that no more outermost
parallel loops were detected/checked after a parallel outermost loop
of depth 1.
+ Test case attached
llvm-svn: 217452
There is no needed for neither 1-dimensional nor higher dimensional arrays to
require positive offsets in the outermost array dimension.
We originally introduced this assumption with the support for delinearizing
multi-dimensional arrays.
llvm-svn: 214665
+ 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
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
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
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
Tobias Grosser