replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[BasicAA] Replace -basicaa with -basic-aa in polly 

Follow up to https://reviews.llvm.org/D82607.
This commit is contained in:
Arthur Eubanks 2020-06-30 15:40:24 -07:00
parent 4c2c6c7cc1
commit b210c9899b
92 changed files with 165 additions and 165 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
polly/docs/HowToManuallyUseTheIndividualPiecesOfPolly.rst
View File

@ -45,7 +45,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-ast -analyze matmul.preopt.ll -polly-process-unprofitable -polly-use-llvm-names
$ opt -basic-aa -polly-ast -analyze matmul.preopt.ll -polly-process-unprofitable -polly-use-llvm-names
.. code-block:: guess
@ -84,8 +84,8 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -polly-use-llvm-names -basicaa -view-scops -disable-output matmul.preopt.ll
$ opt -polly-use-llvm-names -basicaa -view-scops-only -disable-output matmul.preopt.ll
$ opt -polly-use-llvm-names -basic-aa -view-scops -disable-output matmul.preopt.ll
$ opt -polly-use-llvm-names -basic-aa -view-scops-only -disable-output matmul.preopt.ll
The output for the different functions:
@ -104,7 +104,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -polly-use-llvm-names -basicaa -polly-scops -analyze matmul.preopt.ll -polly-process-unprofitable
$ opt -polly-use-llvm-names -basic-aa -polly-scops -analyze matmul.preopt.ll -polly-process-unprofitable
.. code-block:: guess
@ -194,7 +194,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names -polly-dependences -analyze matmul.preopt.ll -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names -polly-dependences -analyze matmul.preopt.ll -polly-process-unprofitable
.. code-block:: guess
@ -226,7 +226,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names -polly-export-jscop matmul.preopt.ll -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names -polly-export-jscop matmul.preopt.ll -polly-process-unprofitable
.. code-block:: guess
@ -254,7 +254,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-ast -analyze -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-ast -analyze -polly-process-unprofitable
.. code-block:: c
@ -282,7 +282,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged -polly-ast -analyze -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged -polly-ast -analyze -polly-process-unprofitable
.. code-block:: c
@ -311,7 +311,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-ast -analyze -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-ast -analyze -polly-process-unprofitable
.. code-block:: c
@ -346,7 +346,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -basicaa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-ast -analyze -polly-process-unprofitable
$ opt -basic-aa -polly-use-llvm-names matmul.preopt.ll -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-ast -analyze -polly-process-unprofitable
.. code-block:: c
@ -387,7 +387,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -S matmul.preopt.ll -basicaa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged -polly-codegen -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged.ll
$ opt -S matmul.preopt.ll -basic-aa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged -polly-codegen -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged.ll
.. code-block:: guess
@ -397,7 +397,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -S matmul.preopt.ll -basicaa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-codegen -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled.ll
$ opt -S matmul.preopt.ll -basic-aa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled -polly-codegen -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled.ll
.. code-block:: guess
@ -407,7 +407,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -S matmul.preopt.ll -basicaa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen -polly-vectorizer=polly -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled+vector.ll
$ opt -S matmul.preopt.ll -basic-aa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen -polly-vectorizer=polly -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled+vector.ll
.. code-block:: guess
@ -417,7 +417,7 @@ performance improvement can be expected by an optimal automatic optimizer.
.. code-block:: console
$ opt -S matmul.preopt.ll -basicaa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen -polly-vectorizer=polly -polly-parallel -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled+openmp.ll
$ opt -S matmul.preopt.ll -basic-aa -polly-use-llvm-names -polly-import-jscop -polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen -polly-vectorizer=polly -polly-parallel -polly-process-unprofitable | opt -S -O3 -o matmul.polly.interchanged+tiled+openmp.ll
.. code-block:: guess

32
polly/docs/experiments/matmul/runall.sh
View File

@ -7,61 +7,61 @@ echo "--> 2. Prepare the LLVM-IR for Polly"
opt -S -polly-canonicalize matmul.ll -o matmul.preopt.ll
echo "--> 3. Show the SCoPs detected by Polly"
opt -basicaa -polly-ast -analyze matmul.preopt.ll \
opt -basic-aa -polly-ast -analyze matmul.preopt.ll \
-polly-process-unprofitable -polly-use-llvm-names
echo "--> 4.1 Highlight the detected SCoPs in the CFGs of the program"
# We only create .dot files, as directly -view-scops directly calls graphviz
# which would require user interaction to continue the script.
# opt -basicaa -view-scops -disable-output matmul.preopt.ll
opt -basicaa -dot-scops -disable-output matmul.preopt.ll -polly-use-llvm-names
# opt -basic-aa -view-scops -disable-output matmul.preopt.ll
opt -basic-aa -dot-scops -disable-output matmul.preopt.ll -polly-use-llvm-names
echo "--> 4.2 Highlight the detected SCoPs in the CFGs of the program (print \
no instructions)"
# We only create .dot files, as directly -view-scops-only directly calls
# graphviz which would require user interaction to continue the script.
# opt -basicaa -view-scops-only -disable-output matmul.preopt.ll
opt -basicaa -dot-scops-only -disable-output matmul.preopt.ll -polly-use-llvm-names
# opt -basic-aa -view-scops-only -disable-output matmul.preopt.ll
opt -basic-aa -dot-scops-only -disable-output matmul.preopt.ll -polly-use-llvm-names
echo "--> 4.3 Create .png files from the .dot files"
for i in `ls *.dot`; do dot -Tpng $i > $i.png; done
echo "--> 5. View the polyhedral representation of the SCoPs"
opt -basicaa -polly-scops -analyze matmul.preopt.ll \
opt -basic-aa -polly-scops -analyze matmul.preopt.ll \
-polly-process-unprofitable -polly-use-llvm-names
echo "--> 6. Show the dependences for the SCoPs"
opt -basicaa -polly-dependences -analyze matmul.preopt.ll \
opt -basic-aa -polly-dependences -analyze matmul.preopt.ll \
-polly-process-unprofitable -polly-use-llvm-names
echo "--> 7. Export jscop files"
opt -basicaa -polly-export-jscop matmul.preopt.ll \
opt -basic-aa -polly-export-jscop matmul.preopt.ll \
-polly-process-unprofitable -disable-output -polly-use-llvm-names
echo "--> 8. Import the updated jscop files and print the new SCoPs. (optional)"
opt -basicaa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
opt -basic-aa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
-polly-process-unprofitable -polly-use-llvm-names
opt -basicaa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
opt -basic-aa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
-polly-import-jscop-postfix=interchanged -polly-process-unprofitable -polly-use-llvm-names
opt -basicaa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
opt -basic-aa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
-polly-import-jscop-postfix=interchanged+tiled -polly-process-unprofitable -polly-use-llvm-names
opt -basicaa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
opt -basic-aa -polly-import-jscop -polly-ast -analyze matmul.preopt.ll \
-polly-import-jscop-postfix=interchanged+tiled+vector \
-polly-process-unprofitable -polly-use-llvm-names
echo "--> 9. Codegenerate the SCoPs"
opt -S -basicaa -polly-import-jscop -polly-import-jscop-postfix=interchanged \
opt -S -basic-aa -polly-import-jscop -polly-import-jscop-postfix=interchanged \
-polly-codegen -polly-process-unprofitable -polly-use-llvm-names \
matmul.preopt.ll | opt -O3 -S -o matmul.polly.interchanged.ll
opt -S -basicaa -polly-import-jscop \
opt -S -basic-aa -polly-import-jscop \
-polly-import-jscop-postfix=interchanged+tiled -polly-codegen \
matmul.preopt.ll -polly-process-unprofitable -polly-use-llvm-names \
| opt -O3 -S -o matmul.polly.interchanged+tiled.ll
opt -S -basicaa -polly-import-jscop -polly-process-unprofitable\
opt -S -basic-aa -polly-import-jscop -polly-process-unprofitable\
-polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen \
matmul.preopt.ll -polly-vectorizer=polly -polly-use-llvm-names \
| opt -O3 -S -o matmul.polly.interchanged+tiled+vector.ll
opt -S -basicaa -polly-import-jscop -polly-process-unprofitable\
opt -S -basic-aa -polly-import-jscop -polly-process-unprofitable\
-polly-import-jscop-postfix=interchanged+tiled+vector -polly-codegen \
matmul.preopt.ll -polly-vectorizer=polly -polly-parallel -polly-use-llvm-names \
| opt -O3 -S -o matmul.polly.interchanged+tiled+vector+openmp.ll

4
polly/test/DeadCodeElimination/chained_iterations.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
;
; for(i = 0; i < 200; i++ )

4
polly/test/DeadCodeElimination/chained_iterations_2.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
;
; for(i = 0; i < 200; i++ )

4
polly/test/DeadCodeElimination/computeout.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -S %loadPolly -basicaa -polly-dce -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-dce -polly-ast -analyze -polly-dependences-computeout=1 < %s | FileCheck %s -check-prefix=TIMEOUT
; RUN: opt -S %loadPolly -basic-aa -polly-dce -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basic-aa -polly-dce -polly-ast -analyze -polly-dependences-computeout=1 < %s | FileCheck %s -check-prefix=TIMEOUT
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
; for(i = 0; i < 100; i++ )

2
polly/test/DeadCodeElimination/dead_iteration_elimination.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-dce -polly-dce-precise-steps=2 -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-dce -polly-dce-precise-steps=2 -polly-ast -analyze < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
;
; for(i = 0; i < 200; i++ )

2
polly/test/DeadCodeElimination/null_schedule.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -S %loadPolly -basicaa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
; RUN: opt -S %loadPolly -basic-aa -polly-dependences-analysis-type=value-based -polly-dce -polly-ast -analyze < %s | FileCheck %s -check-prefix=CHECK-DCE
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
; A[0] = 1;
;

8
polly/test/DependenceInfo/do_pluto_matmult.ll
View File

@ -1,7 +1,7 @@
; RUN: opt %loadPolly -basicaa -polly-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=VALUE
; RUN: opt %loadPolly -basicaa -polly-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=MEMORY
; RUN: opt %loadPolly -basicaa -polly-function-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=FUNC-VALUE
; RUN: opt %loadPolly -basicaa -polly-function-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=FUNC-MEMORY
; RUN: opt %loadPolly -basic-aa -polly-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=VALUE
; RUN: opt %loadPolly -basic-aa -polly-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=MEMORY
; RUN: opt %loadPolly -basic-aa -polly-function-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=FUNC-VALUE
; RUN: opt %loadPolly -basic-aa -polly-function-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=FUNC-MEMORY
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/DependenceInfo/reduction_dependences_equal_non_reduction_dependences.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-dependences -analyze < %s | FileCheck %s
;
; This loopnest contains a reduction which imposes the same dependences as the
; accesses to the array A. We need to ensure we keep the dependences of A.

6
polly/test/DependenceInfo/reduction_multiple_loops_array_sum.ll
View File

@ -1,6 +1,6 @@
; RUN: opt -basicaa %loadPolly -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt -basicaa %loadPolly -polly-dependences -polly-dependences-analysis-level=reference-wise -analyze < %s | FileCheck %s
; RUN: opt -basicaa %loadPolly -polly-dependences -polly-dependences-analysis-level=access-wise -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-dependences -polly-dependences-analysis-level=reference-wise -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-dependences -polly-dependences-analysis-level=access-wise -analyze < %s | FileCheck %s
;
; Verify that only the inner reduction like accesses cause reduction dependences
;

2
polly/test/DependenceInfo/reduction_multiple_loops_array_sum_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-dependences -analyze -basicaa < %s | FileCheck %s
; RUN: opt %loadPolly -polly-dependences -analyze -basic-aa < %s | FileCheck %s
;
; CHECK: RAW dependences:
; CHECK-NEXT: { }

2
polly/test/DependenceInfo/reduction_multiple_loops_array_sum_3.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-dependences -analyze -basicaa < %s | FileCheck %s
; RUN: opt %loadPolly -polly-dependences -analyze -basic-aa < %s | FileCheck %s
;
; CHECK: Reduction dependences:
; CHECK-NEXT: { Stmt_for_inc[i0, i1] -> Stmt_for_inc[i0, 1 + i1] : 0 <= i0 <= 99 and 0 <= i1 <= 98 }

2
polly/test/DependenceInfo/reduction_multiple_reductions.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-dependences -analyze < %s | FileCheck %s
;
; Verify we do not have dependences between the if and the else clause
;

2
polly/test/DependenceInfo/reduction_multiple_reductions_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-dependences -analyze < %s | FileCheck %s
;
;
; These are the important RAW dependences, as they need to originate/end in only one iteration:

2
polly/test/DependenceInfo/reduction_partially_escaping_intermediate_in_other_stmt.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-dependences -analyze -basicaa < %s | FileCheck %s
; RUN: opt %loadPolly -polly-dependences -analyze -basic-aa < %s | FileCheck %s
;
; CHECK: Reduction dependences:
; CHECK-NEXT: [N] -> { Stmt_for_body3[i0, i1] -> Stmt_for_body3[i0, 1 + i1] : 0 <= i0 <= 1023 and i1 >= 0 and 1024 - N + i0 <= i1 <= 1022 }

2
polly/test/DependenceInfo/reduction_two_reductions_different_rloops.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-dependences -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-dependences -analyze < %s | FileCheck %s
;
; CHECK: RAW dependences:
; CHECK-NEXT: { }

6
polly/test/DependenceInfo/sequential_loops.ll
View File

@ -1,6 +1,6 @@
; RUN: opt -S %loadPolly -basicaa -polly-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=VALUE
; RUN: opt -S %loadPolly -basicaa -polly-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=MEMORY
; RUN: opt -S %loadPolly -basicaa -polly-dependences -analyze -polly-dependences-analysis-type=value-based -polly-dependences-analysis-level=access-wise < %s | FileCheck %s -check-prefix=VALUE_ACCESS
; RUN: opt -S %loadPolly -basic-aa -polly-dependences -analyze -polly-dependences-analysis-type=value-based < %s | FileCheck %s -check-prefix=VALUE
; RUN: opt -S %loadPolly -basic-aa -polly-dependences -analyze -polly-dependences-analysis-type=memory-based < %s | FileCheck %s -check-prefix=MEMORY
; RUN: opt -S %loadPolly -basic-aa -polly-dependences -analyze -polly-dependences-analysis-type=value-based -polly-dependences-analysis-level=access-wise < %s | FileCheck %s -check-prefix=VALUE_ACCESS
; VALUE-LABEL: Printing analysis 'Polly - Calculate dependences' for region: 'S1 => exit.3' in function 'sequential_writes':
; VALUE-NEXT: RAW dependences:

2
polly/test/Isl/Ast/dependence_distance_multiple_constant.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-stmt-granularity=bb -polyhedral-info -polly-check-parallel -analyze < %s | FileCheck %s -check-prefix=PINFO
;
; void f(int *restrict A, int *restrict B, int N) {

2
polly/test/Isl/Ast/dependence_distance_varying_multiple.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-stmt-granularity=bb -polyhedral-info -polly-check-parallel -analyze < %s | FileCheck %s -check-prefix=PINFO
;
; void f(int *restrict A, int *restrict B, int *restrict C, int *restrict D,

2
polly/test/Isl/Ast/reduction_dependences_equal_non_reduction_dependences.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
;
; This loopnest contains a reduction which imposes the same dependences as the
; accesses to the array A. We need to ensure we do __not__ parallelize anything

2
polly/test/Isl/Ast/reduction_different_reduction_clauses.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
;
; CHECK: #pragma simd reduction (+ : MemRef_sum{{[1,2]}}, MemRef_sum{{[1,2]}}) reduction (* : MemRef_prod) reduction (| : MemRef_or) reduction (& : MemRef_and)
; CHECK: #pragma known-parallel reduction (+ : MemRef_sum{{[1,2]}}, MemRef_sum{{[1,2]}}) reduction (* : MemRef_prod) reduction (| : MemRef_or) reduction (& : MemRef_and)

2
polly/test/Isl/Ast/run-time-condition.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze < %s | FileCheck %s
; for (i = 0; i < 1024; i++)
; A[i] = B[i];

4
polly/test/Isl/Ast/single_loop_strip_mine.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-import-jscop \
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-import-jscop \
; RUN: -polly-ast-print-accesses \
; RUN: -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s \
; RUN: -check-prefix=CHECK-VECTOR

2
polly/test/Isl/CodeGen/MemAccess/default_aligned_new_access_function.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-import-jscop -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-import-jscop -analyze < %s | FileCheck %s
;
; Check that we allow the new access functions even though they access
; different locations than the original ones (but the alignment is the

2
polly/test/Isl/CodeGen/MemAccess/simple_stride_test.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-import-jscop -polly-codegen -polly-vectorizer=polly -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-import-jscop -polly-codegen -polly-vectorizer=polly -S < %s | FileCheck %s
;
; Check that we use the correct __new__ strides:
; stride zero for B

4
polly/test/Isl/CodeGen/OpenMP/loop-body-references-outer-values-3.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-codegen -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -basic-aa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -basic-aa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-codegen -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; The interesting part of this test case is the instruction:
; %tmp = bitcast i8* %call to i64**

2
polly/test/Isl/CodeGen/create-conditional-scop.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -verify-loop-info < %s -S | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -verify-loop-info < %s -S | FileCheck %s
target datalayout = "e-p:32:32:32-i64:64:64-i32:32:32-i16:16:16-i1:32:32-f64:64:64-f32:32:32-a0:0-n32"

2
polly/test/Isl/CodeGen/intrinsics_lifetime.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -S < %s | FileCheck %s
;
; Verify that we remove the lifetime markers from everywhere.
;

2
polly/test/Isl/CodeGen/intrinsics_misc.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -S < %s | FileCheck %s
;
; Verify that we remove the misc intrinsics from the optimized SCoP.
;

2
polly/test/Isl/CodeGen/invariant_load_hoist_alignment.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -S \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -S \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-unknown-linux-gnu"

2
polly/test/Isl/CodeGen/loop_with_condition.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze < %s | FileCheck %s
;#include <string.h>
;#define N 1024

2
polly/test/Isl/CodeGen/loop_with_condition_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -polly-ast-detect-parallel -analyze < %s | FileCheck %s
; Verify that we actually detect this loop as the innermost loop even though
; there is a conditional inside.

2
polly/test/Isl/CodeGen/loop_with_condition_ineq.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze < %s | FileCheck %s
;#include <string.h>
;#define N 1024

4
polly/test/Isl/CodeGen/loop_with_condition_nested.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen -loops -analyze < %s | FileCheck %s -check-prefix=LOOPS
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -loops -analyze < %s | FileCheck %s -check-prefix=LOOPS
;#include <string.h>

2
polly/test/Isl/CodeGen/partial_write_mapped_vector.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-import-jscop -polly-import-jscop-postfix=transformed -polly-vectorizer=polly -polly-opt-isl -polly-ast -polly-codegen -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-import-jscop -polly-import-jscop-postfix=transformed -polly-vectorizer=polly -polly-opt-isl -polly-ast -polly-codegen -S < %s | FileCheck %s
;
; Polly's vectorizer does not support partial accesses.
;

2
polly/test/Isl/CodeGen/reduction_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-ast -analyze \
; RUN: opt %loadPolly -basic-aa -polly-ast -analyze \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
;#include <string.h>

2
polly/test/Isl/CodeGen/run-time-condition.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"

4
polly/test/Isl/CodeGen/simple_vec_assign_scalar.ll
View File

@ -1,7 +1,7 @@
; RUN: opt %loadPolly -basicaa -polly-codegen \
; RUN: opt %loadPolly -basic-aa -polly-codegen \
; RUN: -polly-vectorizer=polly -dce -S < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=stripmine -dce -S < %s | FileCheck %s --check-prefix=STRIPMINE
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=stripmine -dce -S < %s | FileCheck %s --check-prefix=STRIPMINE
;#define N 1024
;float A[N];

2
polly/test/Isl/CodeGen/simple_vec_assign_scalar_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
;#define N 1024
;float A[N];

2
polly/test/Isl/CodeGen/simple_vec_call.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -S \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -S \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/Isl/CodeGen/simple_vec_call_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -dce \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -dce \
; RUN: -polly-invariant-load-hoisting=true -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/Isl/CodeGen/simple_vec_cast.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly \
; RUN: -polly-invariant-load-hoisting=true -dce -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/Isl/CodeGen/simple_vec_const.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -S \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -S \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
;#define N 1024

2
polly/test/Isl/CodeGen/simple_vec_large_width.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
@A = common global [1024 x float] zeroinitializer, align 16

2
polly/test/Isl/CodeGen/simple_vec_ptr_ptr_ty.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -S \
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -S \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/Isl/CodeGen/simple_vec_stride_x.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
;#define N 1024
;float A[N];

2
polly/test/Isl/CodeGen/simple_vec_two_stmts.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-codegen -polly-vectorizer=polly -dce -S < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
@A = common global [1024 x float] zeroinitializer, align 16

2
polly/test/ScheduleOptimizer/2012-04-16-Trivially-vectorizable-loops.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-opt-isl -polly-vectorizer=polly < %s
; RUN: opt %loadPolly -basic-aa -polly-opt-isl -polly-vectorizer=polly < %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }

4
polly/test/ScheduleOptimizer/computeout.ll
View File

@ -1,5 +1,5 @@
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze -polly-dependences-computeout=1 < %s | FileCheck %s -check-prefix=TIMEOUT
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl -polly-opt-fusion=max -polly-ast -analyze -polly-dependences-computeout=1 < %s | FileCheck %s -check-prefix=TIMEOUT
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
; for(i = 0; i < 100; i++ )

2
polly/test/ScheduleOptimizer/prevectorization-without-tiling.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl -polly-tiling=false \
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl -polly-tiling=false \
; RUN: -polly-pattern-matching-based-opts=false -polly-vectorizer=polly \
; RUN: -polly-ast -analyze < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

6
polly/test/ScheduleOptimizer/prevectorization.ll
View File

@ -1,11 +1,11 @@
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl \
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl \
; RUN: -polly-pattern-matching-based-opts=false -polly-vectorizer=polly \
; RUN: -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl \
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl \
; RUN: -polly-pattern-matching-based-opts=false -polly-vectorizer=stripmine \
; RUN: -polly-ast -analyze < %s | FileCheck %s
; RUN: opt -S %loadPolly -basicaa -polly-opt-isl \
; RUN: opt -S %loadPolly -basic-aa -polly-opt-isl \
; RUN: -polly-vectorizer=polly -polly-pattern-matching-based-opts=false \
; RUN: -polly-ast -analyze -polly-prevect-width=16 < %s | \
; RUN: FileCheck %s -check-prefix=VEC16

2
polly/test/ScopDetect/intrinsics_1.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze < %s | FileCheck %s
;
; CHECK: Valid Region for Scop: for.cond => for.end
;

2
polly/test/ScopDetect/intrinsics_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze < %s | FileCheck %s
;
; Verify that we allow the lifetime markers for the tmp array.
;

2
polly/test/ScopDetect/intrinsics_3.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze < %s | FileCheck %s
;
; Verify that we allow the misc intrinsics.
;

2
polly/test/ScopDetect/keep_going_expansion.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect-track-failures -polly-detect-keep-going -polly-detect -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-detect-track-failures -polly-detect-keep-going -polly-detect -analyze < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

4
polly/test/ScopDetect/mod_ref_read_pointer.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze \
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze \
; RUN: -polly-allow-modref-calls < %s | FileCheck %s -check-prefix=MODREF
; RUN: opt %loadPolly -basicaa -polly-detect -analyze \
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze \
; RUN: < %s | FileCheck %s
;
; CHECK-NOT: Valid Region for Scop: for.body => for.end

8
polly/test/ScopDetect/non-affine-loop-condition-dependent-access.ll
View File

@ -1,7 +1,7 @@
; RUN: opt %loadPolly -basicaa -polly-detect -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=false -analyze < %s | FileCheck %s --check-prefix=REJECTNONAFFINELOOPS
; RUN: opt %loadPolly -basicaa -polly-detect -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true -analyze < %s | FileCheck %s --check-prefix=ALLOWNONAFFINELOOPS
; RUN: opt %loadPolly -basicaa -polly-detect -polly-allow-nonaffine -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true -analyze < %s | FileCheck %s --check-prefix=ALLOWNONAFFINELOOPSANDACCESSES
; RUN: opt %loadPolly -basicaa -polly-detect -polly-process-unprofitable=false \
; RUN: opt %loadPolly -basic-aa -polly-detect -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=false -analyze < %s | FileCheck %s --check-prefix=REJECTNONAFFINELOOPS
; RUN: opt %loadPolly -basic-aa -polly-detect -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true -analyze < %s | FileCheck %s --check-prefix=ALLOWNONAFFINELOOPS
; RUN: opt %loadPolly -basic-aa -polly-detect -polly-allow-nonaffine -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true -analyze < %s | FileCheck %s --check-prefix=ALLOWNONAFFINELOOPSANDACCESSES
; RUN: opt %loadPolly -basic-aa -polly-detect -polly-process-unprofitable=false \
; RUN: -polly-allow-nonaffine -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=true -analyze < %s \
; RUN: | FileCheck %s --check-prefix=PROFIT

2
polly/test/ScopDetect/simple_loop_with_param.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze < %s | FileCheck %s -check-prefix=PHI
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze < %s | FileCheck %s -check-prefix=PHI
; void f(long A[], long N, long *init_ptr) {
; long i, j;

2
polly/test/ScopDetect/simple_loop_with_param_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-detect -analyze < %s | FileCheck %s
; void f(long A[], int N, int *init_ptr) {
; long i, j;

12
polly/test/ScopDetectionDiagnostics/ReportMultipleNonAffineAccesses.ll
View File

@ -1,9 +1,9 @@
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -analyze < %s 2>&1| FileCheck %s
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-delinearize=false -polly-detect-keep-going -analyze < %s 2>&1| FileCheck %s -check-prefix=ALL
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -analyze < %s 2>&1| FileCheck %s -check-prefix=DELIN
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-detect-keep-going -analyze < %s 2>&1| FileCheck %s -check-prefix=DELIN-ALL
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-allow-nonaffine -analyze < %s 2>&1| FileCheck %s -check-prefix=NONAFFINE
; RUN: opt %loadPolly -basicaa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-allow-nonaffine -analyze < %s 2>&1| FileCheck %s -check-prefix=NONAFFINE
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -analyze < %s 2>&1| FileCheck %s
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-delinearize=false -polly-detect-keep-going -analyze < %s 2>&1| FileCheck %s -check-prefix=ALL
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -analyze < %s 2>&1| FileCheck %s -check-prefix=DELIN
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-detect-keep-going -analyze < %s 2>&1| FileCheck %s -check-prefix=DELIN-ALL
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-allow-nonaffine -analyze < %s 2>&1| FileCheck %s -check-prefix=NONAFFINE
; RUN: opt %loadPolly -basic-aa -pass-remarks-missed="polly-detect" -polly-detect-track-failures -polly-detect -polly-allow-nonaffine -analyze < %s 2>&1| FileCheck %s -check-prefix=NONAFFINE
; 1 void manyaccesses(float A[restrict], long n, float B[restrict][n])
; 2 {

4
polly/test/ScopInfo/NonAffine/non-affine-loop-condition-dependent-access_1.ll
View File

@ -1,8 +1,8 @@
; RUN: opt %loadPolly -basicaa -polly-scops \
; RUN: opt %loadPolly -basic-aa -polly-scops \
; RUN: -polly-allow-nonaffine -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=true -analyze < %s | FileCheck %s \
; RUN: -check-prefix=SCALAR
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine \
; RUN: -polly-process-unprofitable=false \
; RUN: -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s -check-prefix=PROFIT

6
polly/test/ScopInfo/NonAffine/non-affine-loop-condition-dependent-access_2.ll
View File

@ -1,10 +1,10 @@
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine-branches \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=false \
; RUN: -analyze < %s | FileCheck %s --check-prefix=INNERMOST
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine-branches \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s --check-prefix=INNERMOST
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine \
; RUN: -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s \
; RUN: --check-prefix=ALL

6
polly/test/ScopInfo/NonAffine/non-affine-loop-condition-dependent-access_3.ll
View File

@ -1,10 +1,10 @@
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine-branches \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=false \
; RUN: -analyze < %s | FileCheck %s --check-prefix=INNERMOST
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine-branches \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine-branches \
; RUN: -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s --check-prefix=INNERMOST
; RUN: opt %loadPolly -basicaa -polly-scops -polly-allow-nonaffine \
; RUN: opt %loadPolly -basic-aa -polly-scops -polly-allow-nonaffine \
; RUN: -polly-allow-nonaffine-branches -polly-allow-nonaffine-loops=true \
; RUN: -analyze < %s | FileCheck %s --check-prefix=ALL
;

2
polly/test/ScopInfo/NonAffine/non_affine_parametric_loop.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze -polly-allow-nonaffine < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze -polly-allow-nonaffine < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
; void foo(long n, double A[], int INDEX[]) {

2
polly/test/ScopInfo/assume_gep_bounds_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze < %s \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze < %s \
; RUN: -polly-precise-inbounds | FileCheck %s
;
; void foo(float A[restrict][20], float B[restrict][20], long n, long m,

2
polly/test/ScopInfo/inter_bb_scalar_dep.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops \
; RUN: opt %loadPolly -basic-aa -polly-scops \
; RUN: -polly-invariant-load-hoisting=true -analyze < %s | FileCheck %s
; void f(long A[], int N, int *init_ptr) {

2
polly/test/ScopInfo/intra_and_inter_bb_scalar_dep.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
; void f(long A[], int N, int *init_ptr) {

2
polly/test/ScopInfo/intra_bb_scalar_dep.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
; void f(long A[], int N, int *init_ptr) {

2
polly/test/ScopInfo/isl_aff_out_of_bounds.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-detect < %s
; RUN: opt %loadPolly -basic-aa -polly-detect < %s
; Used to fail with:
; ../../isl/isl_aff.c:591: position out of bounds

4
polly/test/ScopInfo/licm_load.ll
View File

@ -1,7 +1,7 @@
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -polly-prepare \
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -polly-prepare \
; RUN: -polly-invariant-load-hoisting=true -polly-scops -analyze < %s \
; RUN: | FileCheck %s
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -licm -polly-prepare \
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -licm -polly-prepare \
; RUN: -polly-invariant-load-hoisting=true -polly-scops -analyze < %s \
; RUN: | FileCheck %s
;

4
polly/test/ScopInfo/licm_potential_store.ll
View File

@ -1,10 +1,10 @@
; RUN: opt %loadPolly -basicaa -sroa -instcombine -simplifycfg -tailcallopt \
; RUN: opt %loadPolly -basic-aa -sroa -instcombine -simplifycfg -tailcallopt \
; RUN: -simplifycfg -reassociate -loop-rotate -instcombine -indvars \
; RUN: -polly-prepare -polly-scops -analyze < %s \
; RUN: \
; RUN: | FileCheck %s --check-prefix=NOLICM
; RUN: opt %loadPolly -basicaa -sroa -instcombine -simplifycfg -tailcallopt \
; RUN: opt %loadPolly -basic-aa -sroa -instcombine -simplifycfg -tailcallopt \
; RUN: -simplifycfg -reassociate -loop-rotate -instcombine -indvars -licm \
; RUN: -polly-prepare -polly-scops -analyze < %s \
; RUN: \

4
polly/test/ScopInfo/licm_reduction.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
;
; XFAIL: *
;

4
polly/test/ScopInfo/licm_reduction_nested.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
;
; XFAIL: *
;

4
polly/test/ScopInfo/licm_store.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -polly-prepare -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -loop-rotate -indvars -licm -polly-prepare -polly-scops -analyze < %s | FileCheck %s
;
; XFAIL: *
;

2
polly/test/ScopInfo/loop_carry.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/ScopInfo/memcpy-raw-source.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -scoped-noalias -tbaa -polly-scops -analyze < %s
; RUN: opt %loadPolly -basic-aa -scoped-noalias -tbaa -polly-scops -analyze < %s
;
; Ensure that ScopInfo's alias analysis llvm.memcpy for,
; like the AliasSetTracker, preserves bitcasts.

4
polly/test/ScopInfo/memcpy.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-allow-differing-element-types -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -S -basicaa -polly-allow-differing-element-types -polly-codegen < %s | FileCheck --check-prefix=IR %s
; RUN: opt %loadPolly -basic-aa -polly-allow-differing-element-types -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -S -basic-aa -polly-allow-differing-element-types -polly-codegen < %s | FileCheck --check-prefix=IR %s
;
; CHECK: Arrays {
; CHECK-NEXT: i8 MemRef_A[*]; // Element size 1

4
polly/test/ScopInfo/memmove.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-allow-differing-element-types -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -S -basicaa -polly-allow-differing-element-types -polly-codegen < %s | FileCheck --check-prefix=IR %s
; RUN: opt %loadPolly -basic-aa -polly-allow-differing-element-types -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -S -basic-aa -polly-allow-differing-element-types -polly-codegen < %s | FileCheck --check-prefix=IR %s
;
; CHECK: Arrays {
; CHECK-NEXT: i8 MemRef_A[*]; // Element size 1

4
polly/test/ScopInfo/mod_ref_access_pointee_arguments.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-scops -analyze -polly-allow-modref-calls \
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-scops -analyze -polly-allow-modref-calls \
; RUN: < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-codegen -polly-allow-modref-calls \
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-codegen -polly-allow-modref-calls \
; RUN: -disable-output < %s
;
; Verify that we model the may-write access of the prefetch intrinsic

4
polly/test/ScopInfo/mod_ref_read_pointee_arguments.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-scops -analyze -polly-allow-modref-calls \
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-scops -analyze -polly-allow-modref-calls \
; RUN: < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen -disable-output \
; RUN: opt %loadPolly -basic-aa -polly-codegen -disable-output \
; RUN: -polly-allow-modref-calls < %s
;
; Verify that we model the read access of the gcread intrinsic

4
polly/test/ScopInfo/mod_ref_read_pointer.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze -polly-allow-modref-calls \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze -polly-allow-modref-calls \
; RUN: < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen -disable-output \
; RUN: opt %loadPolly -basic-aa -polly-codegen -disable-output \
; RUN: -polly-allow-modref-calls < %s
;
; Check that we assume the call to func has a read on the whole A array.

4
polly/test/ScopInfo/mod_ref_read_pointers.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze -polly-allow-modref-calls \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze -polly-allow-modref-calls \
; RUN: < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-codegen -disable-output \
; RUN: opt %loadPolly -basic-aa -polly-codegen -disable-output \
; RUN: -polly-allow-modref-calls < %s
;
; Check that the call to func will "read" not only the A array but also the

2
polly/test/ScopInfo/reduction_disabled_multiplicative.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -basicaa %loadPolly -polly-stmt-granularity=bb -polly-scops -analyze -polly-disable-multiplicative-reductions < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-stmt-granularity=bb -polly-scops -analyze -polly-disable-multiplicative-reductions < %s | FileCheck %s
;
; CHECK: ReadAccess := [Reduction Type: +
; CHECK: { Stmt_for_body[i0] -> MemRef_sum[0] };

2
polly/test/ScopInfo/reduction_escaping_intermediate.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze < %s | FileCheck %s
;
; void f(int N, int * restrict sums, int * restrict escape) {
; int i, j;

2
polly/test/ScopInfo/reduction_escaping_intermediate_2.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
;
; void f(int N, int * restrict sums, int * restrict escape) {
; int i, j;

2
polly/test/ScopInfo/reduction_invalid_different_operators.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze < %s | FileCheck %s
;
; int f() {
; int i, sum = 0, sth = 0;

2
polly/test/ScopInfo/reduction_multiple_loops_array_sum.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -basicaa %loadPolly -polly-scops -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-scops -analyze < %s | FileCheck %s
;
; CHECK: Stmt_for_body
; CHECK: Reduction Type: *

2
polly/test/ScopInfo/reduction_multiple_loops_array_sum_1.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -basicaa %loadPolly -polly-scops -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-scops -analyze < %s | FileCheck %s
;
; CHECK: Stmt_for_body
; CHECK: Reduction Type: NONE

2
polly/test/ScopInfo/reduction_multiple_simple_binary.ll
View File

@ -1,4 +1,4 @@
; RUN: opt -basicaa %loadPolly -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
; RUN: opt -basic-aa %loadPolly -polly-stmt-granularity=bb -polly-scops -analyze < %s | FileCheck %s
;
; CHECK: ReadAccess := [Reduction Type: NONE
; CHECK: { Stmt_for_body[i0] -> MemRef_A[1 + i0] };

4
polly/test/ScopInfo/scalar_to_array.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basicaa -polly-function-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -basic-aa -polly-function-scops -analyze < %s | FileCheck %s
; ModuleID = 'scalar_to_array.ll'
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"

2
polly/test/ScopInfo/tempscop-printing.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -basicaa -polly-scops -analyze \
; RUN: opt %loadPolly -basic-aa -polly-scops -analyze \
; RUN: -polly-invariant-load-hoisting=true < %s | FileCheck %s
; void f(long A[], int N, int *init_ptr) {

6
polly/www/documentation/gpgpucodegen.html
View File

@ -121,7 +121,7 @@ The jscop file describing the tiling transformation is:
</pre>
We can test the schedule with the following command line.
<pre>
opt -load /path/to/polly/build/LLVMPolly.so -basicaa -polly-import-jscop
opt -load /path/to/polly/build/LLVMPolly.so -basic-aa -polly-import-jscop
-polly-ast -analyze -q ./test.ll
-polly-import-jscop-postfix=transformed+gpu
</pre>
@ -157,7 +157,7 @@ git am /path/to/polly/source/utils/0001-Add-llvm.codegen-intrinsic.patch</pre>
<pre>/path/to/polly/source/test/create_ll.sh test.c</pre>
<p>3. Get and edit the jscop file (take function "gpu_codegen" as an example).
</p>
<pre>opt -load /path/to/polly/build/lib/LLVMPolly.so -basicaa
<pre>opt -load /path/to/polly/build/lib/LLVMPolly.so -basic-aa
-polly-export-jscop ./test.ll
cp gpu_codegen___%for.cond---%for.end8.jscop
gpu_codegen___%for.cond---%for.end8.jscop.transformed+gpu
@ -165,7 +165,7 @@ vi gpu_codegen___%for.cond---%for.end8.jscop.transformed+gpu</pre>
<p><em>(Please refer to section "The Work Flow" on how to edit the "schedule"
part of a statement)</em></p>
<p>4. Optimize the code with GPGPU code generation.</p>
<pre>opt -load /path/to/polly/build/lib/LLVMPolly.so -basicaa
<pre>opt -load /path/to/polly/build/lib/LLVMPolly.so -basic-aa
-polly-import-jscop-postfix=transformed+gpu -enable-polly-gpgpu
-polly-gpgpu-triple=nvptx64-unknown-unknown -polly-codegen ./test.ll -S
-o test.gpued.ll</pre>