forked from OSchip/llvm-project
Add option to limit the maximal number of parallel threads.
Differential Revision: http://reviews.llvm.org/D5581 llvm-svn: 219004
This commit is contained in:
parent
12b355a2ce
commit
990cd4c2e2
|
@ -18,10 +18,16 @@
|
|||
#include "llvm/IR/Dominators.h"
|
||||
#include "llvm/IR/Module.h"
|
||||
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
|
||||
#include "llvm/Support/CommandLine.h"
|
||||
|
||||
using namespace llvm;
|
||||
using namespace polly;
|
||||
|
||||
static cl::opt<int>
|
||||
PollyNumThreads("polly-num-threads",
|
||||
cl::desc("Number of threads to use (0 = auto)"), cl::Hidden,
|
||||
cl::init(0));
|
||||
|
||||
// We generate a loop of either of the following structures:
|
||||
//
|
||||
// BeforeBB BeforeBB
|
||||
|
@ -185,7 +191,7 @@ void ParallelLoopGenerator::createCallSpawnThreads(Value *SubFn,
|
|||
F = Function::Create(Ty, Linkage, Name, M);
|
||||
}
|
||||
|
||||
Value *NumberOfThreads = ConstantInt::get(LongType, 0);
|
||||
Value *NumberOfThreads = ConstantInt::get(LongType, PollyNumThreads);
|
||||
Value *Args[] = {SubFn, SubFnParam, NumberOfThreads, LB, UB, Stride};
|
||||
|
||||
Builder.CreateCall(F, Args);
|
||||
|
|
|
@ -0,0 +1,36 @@
|
|||
; RUN: opt %loadPolly -polly-codegen -enable-polly-openmp -S < %s | FileCheck %s --check-prefix=AUTO
|
||||
; RUN: opt %loadPolly -polly-codegen -enable-polly-openmp -polly-num-threads=1 -S < %s | FileCheck %s --check-prefix=ONE
|
||||
; RUN: opt %loadPolly -polly-codegen -enable-polly-openmp -polly-num-threads=4 -S < %s | FileCheck %s --check-prefix=FOUR
|
||||
;
|
||||
; AUTO: call void @GOMP_parallel_loop_runtime_start(void (i8*)* @jd.polly.subfn, i8* %polly.par.userContext{{[0-9]*}}, i64 0, i64 0, i64 1024, i64 1)
|
||||
; ONE: call void @GOMP_parallel_loop_runtime_start(void (i8*)* @jd.polly.subfn, i8* %polly.par.userContext{{[0-9]*}}, i64 1, i64 0, i64 1024, i64 1)
|
||||
; FOUR: call void @GOMP_parallel_loop_runtime_start(void (i8*)* @jd.polly.subfn, i8* %polly.par.userContext{{[0-9]*}}, i64 4, i64 0, i64 1024, i64 1)
|
||||
;
|
||||
; void jd(int *A) {
|
||||
; for (int i = 0; i < 1024; i++)
|
||||
; A[i] = 0;
|
||||
; }
|
||||
;
|
||||
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
||||
|
||||
define void @jd(i32* %A) {
|
||||
entry:
|
||||
br label %for.cond
|
||||
|
||||
for.cond: ; preds = %for.inc, %entry
|
||||
%indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
|
||||
%exitcond = icmp ne i64 %indvars.iv, 1024
|
||||
br i1 %exitcond, label %for.body, label %for.end
|
||||
|
||||
for.body: ; preds = %for.cond
|
||||
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
|
||||
store i32 0, i32* %arrayidx, align 4
|
||||
br label %for.inc
|
||||
|
||||
for.inc: ; preds = %for.body
|
||||
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
||||
br label %for.cond
|
||||
|
||||
for.end: ; preds = %for.cond
|
||||
ret void
|
||||
}
|
Loading…
Reference in New Issue