maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Introduce minimalistic cost model for auto parallelization 

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
This commit is contained in:
Tobias Grosser 2014-11-16 14:24:53 +00:00
parent 670bdb5a64
commit bf34f1d2b2
14 changed files with 51 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
polly/lib/CodeGen/IslAst.cpp
View File

@ -47,6 +47,11 @@ static cl::opt<bool>
cl::desc("Generate thread parallel code (isl codegen only)"),
cl::init(false), cl::ZeroOrMore, cl::cat(PollyCategory));
static cl::opt<bool> PollyParallelForce(
"polly-parallel-force",
cl::desc("Force generation of thread parallel code ignoring any cost model"),
cl::init(false), cl::ZeroOrMore, cl::cat(PollyCategory));
static cl::opt<bool> UseContext("polly-ast-use-context",
cl::desc("Use context"), cl::Hidden,
cl::init(false), cl::ZeroOrMore,
@ -454,8 +459,23 @@ bool IslAstInfo::isReductionParallel(__isl_keep isl_ast_node *Node) {
}
bool IslAstInfo::isExecutedInParallel(__isl_keep isl_ast_node *Node) {
return PollyParallel && isOutermostParallel(Node) &&
!isReductionParallel(Node);
if (!PollyParallel)
return false;
// Do not parallelize innermost loops.
//
// Parallelizing innermost loops is often not profitable, especially if
// they have a low number of iterations.
//
// TODO: Decide this based on the number of loop iterations that will be
// executed. This can possibly require run-time checks, which again
// raises the question of both run-time check overhead and code size
// costs.
if (!PollyParallelForce && isInnermost(Node))
return false;
return isOutermostParallel(Node) && !isReductionParallel(Node);
}
isl_union_map *IslAstInfo::getSchedule(__isl_keep isl_ast_node *Node) {

2
polly/test/Isl/Ast/OpenMP/multiple_loops_outer_parallel.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-ast -polly-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-ast -polly-parallel -polly-parallel-force -analyze < %s | FileCheck %s
;
; void jd(int *A) {
; CHECK: #pragma omp parallel for

2
polly/test/Isl/Ast/OpenMP/nested_loop_both_parallel_parametric.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-ast -polly-parallel -analyze -polly-delinearize < %s | FileCheck %s
; RUN: opt %loadPolly -polly-ast -polly-parallel -polly-parallel-force -analyze -polly-delinearize < %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-pc-linux-gnu"
; int A[1024][1024];

2
polly/test/Isl/Ast/OpenMP/nested_loop_inner_parallel.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-ast -polly-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-ast -polly-parallel -polly-parallel-force -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"
target triple = "x86_64-pc-linux-gnu"

2
polly/test/Isl/Ast/OpenMP/single_loop_param_parallel.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-ast -polly-parallel -analyze < %s | FileCheck %s
; RUN: opt %loadPolly -polly-ast -polly-parallel -polly-parallel-force -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"
target triple = "x86_64-pc-linux-gnu"

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

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; This code has failed the scev based code generation as the scev in the scop
; contains an AddRecExpr of an outer loop. When generating code, we did not

6
polly/test/Isl/CodeGen/OpenMP/loop-body-references-outer-values-2.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR-SCEV
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR-SCEV
; AST: #pragma simd
; AST: #pragma omp parallel for

6
polly/test/Isl/CodeGen/OpenMP/loop-body-references-outer-values-3.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-parallel-force -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -basicaa -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -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**

6
polly/test/Isl/CodeGen/OpenMP/loop-body-references-outer-values.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev < %s | FileCheck %s -check-prefix=IR
; Make sure we correctly forward the reference to 'A' to the OpenMP subfunction.
;

2
polly/test/Isl/CodeGen/OpenMP/reference-other-bb.ll
View File

@ -1,4 +1,4 @@
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; IR: @foo.polly.subfn
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

4
polly/test/Isl/CodeGen/OpenMP/reference-preceeding-loop.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze -polly-codegen-scev < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze -polly-codegen-scev < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; - Test the case where scalar evolution references a loop that is outside

12
polly/test/Isl/CodeGen/OpenMP/single_loop.ll
View File

@ -1,10 +1,10 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-import-jscop -polly-import-jscop-dir=%S -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST-STRIDE4
; RUN: opt %loadPolly -polly-parallel -polly-import-jscop -polly-import-jscop-dir=%S -polly-codegen-isl -S < %s | FileCheck %s -check-prefix=IR-STRIDE4
; RUN: opt %loadPolly -polly-parallel -polly-import-jscop -polly-import-jscop-dir=%S -polly-codegen-isl -polly-codegen-scev -S < %s | FileCheck %s -check-prefix=IR-STRIDE4
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-import-jscop -polly-import-jscop-dir=%S -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST-STRIDE4
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-import-jscop -polly-import-jscop-dir=%S -polly-codegen-isl -S < %s | FileCheck %s -check-prefix=IR-STRIDE4
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-import-jscop -polly-import-jscop-dir=%S -polly-codegen-isl -polly-codegen-scev -S < %s | FileCheck %s -check-prefix=IR-STRIDE4
; This extensive test case tests the creation of the full set of OpenMP calls
; as well as the subfunction creation using a trivial loop as example.

6
polly/test/Isl/CodeGen/OpenMP/single_loop_with_loop_invariant_baseptr.ll
View File

@ -1,6 +1,6 @@
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-parallel-force -polly-parallel-force -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-parallel-force -polly-parallel-force -polly-codegen-isl -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -tbaa -polly-parallel -polly-parallel-force -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; #define N 1024
; float A[N];

4
polly/test/Isl/CodeGen/OpenMP/two-parallel-loops-reference-outer-indvar.ll
View File

@ -1,5 +1,5 @@
; RUN: opt %loadPolly -polly-parallel -polly-ast -analyze -polly-codegen-scev < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-ast -analyze -polly-codegen-scev < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -polly-parallel -polly-parallel-force -polly-codegen-isl -S -polly-codegen-scev -verify-dom-info < %s | FileCheck %s -check-prefix=IR
; This test case verifies that we create correct code even if two OpenMP loops
; share common outer variables.