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

[LoopVectorizer] Count dependencies of consecutive pointers as uniforms 

For the purpose of calculating the cost of the loop at various vectorization
factors, we need to count dependencies of consecutive pointers as uniforms
(which means that the VF = 1 cost is used for all overall VF values).

For example, the TSVC benchmark function s173 has:
  ...
  %3 = add nsw i64 %indvars.iv, 16000
  %arrayidx8 = getelementptr inbounds %struct.GlobalData* @global_data, i64 0, i32 0, i64 %3
  ...
and we must realize that the add will be a scalar in order to correctly deduce
it to be profitable to vectorize this on PowerPC with VSX enabled. In fact, all
dependencies of a consecutive pointer must be a scalar (uniform), and so we
simply need to add all consecutive pointers to the worklist that currently
detects collects uniforms.

Fixes PR19296.

llvm-svn: 205387
This commit is contained in:
Hal Finkel 2014-04-02 02:34:49 +00:00
parent 326e1fa13b
commit b0ebdc0f43
3 changed files with 65 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -3656,6 +3656,16 @@ void LoopVectorizationLegality::collectLoopUniforms() {
// Start with the conditional branch and walk up the block.
Worklist.push_back(Latch->getTerminator()->getOperand(0));
// Also add all consecutive pointer values; these values will be uniform
// after vectorization (and subsequent cleanup) and, until revectorization is
// supported, all dependencies must also be uniform.
for (Loop::block_iterator B = TheLoop->block_begin(),
BE = TheLoop->block_end(); B != BE; ++B)
for (BasicBlock::iterator I = (*B)->begin(), IE = (*B)->end();
I != IE; ++I)
if (I->getType()->isPointerTy() && isConsecutivePtr(I))
Worklist.insert(Worklist.end(), I->op_begin(), I->op_end());
while (Worklist.size()) {
Instruction *I = dyn_cast<Instruction>(Worklist.back());
Worklist.pop_back();

4
llvm/test/Transforms/LoopVectorize/PowerPC/lit.local.cfg Normal file
View File

@ -0,0 +1,4 @@
targets = set(config.root.targets_to_build.split())
if not 'PowerPC' in targets:
config.unsupported = True

51
llvm/test/Transforms/LoopVectorize/PowerPC/vsx-tsvc-s173.ll Normal file
View File

@ -0,0 +1,51 @@
; RUN: opt < %s -mcpu=pwr7 -mattr=+vsx -loop-vectorize -instcombine -S | FileCheck %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
%struct.GlobalData = type { [32000 x float], [3 x i32], [4 x i8], [32000 x float], [5 x i32], [12 x i8], [32000 x float], [7 x i32], [4 x i8], [32000 x float], [11 x i32], [4 x i8], [32000 x float], [13 x i32], [12 x i8], [256 x [256 x float]], [17 x i32], [12 x i8], [256 x [256 x float]], [19 x i32], [4 x i8], [256 x [256 x float]], [23 x i32], [4 x i8], [256 x [256 x float]] }
@global_data = external global %struct.GlobalData, align 16
@ntimes = external hidden unnamed_addr global i32, align 4
define signext i32 @s173() #0 {
entry:
%0 = load i32* @ntimes, align 4
%cmp21 = icmp sgt i32 %0, 0
br i1 %cmp21, label %for.cond1.preheader, label %for.end12
for.cond1.preheader: ; preds = %for.end, %entry
%nl.022 = phi i32 [ %inc11, %for.end ], [ 0, %entry ]
br label %for.body3
for.body3: ; preds = %for.body3, %for.cond1.preheader
%indvars.iv = phi i64 [ 0, %for.cond1.preheader ], [ %indvars.iv.next, %for.body3 ]
%arrayidx = getelementptr inbounds %struct.GlobalData* @global_data, i64 0, i32 0, i64 %indvars.iv
%1 = load float* %arrayidx, align 4
%arrayidx5 = getelementptr inbounds %struct.GlobalData* @global_data, i64 0, i32 3, i64 %indvars.iv
%2 = load float* %arrayidx5, align 4
%add = fadd float %1, %2
%3 = add nsw i64 %indvars.iv, 16000
%arrayidx8 = getelementptr inbounds %struct.GlobalData* @global_data, i64 0, i32 0, i64 %3
store float %add, float* %arrayidx8, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 16000
br i1 %exitcond, label %for.end, label %for.body3
for.end: ; preds = %for.body3
%inc11 = add nsw i32 %nl.022, 1
%4 = load i32* @ntimes, align 4
%mul = mul nsw i32 %4, 10
%cmp = icmp slt i32 %inc11, %mul
br i1 %cmp, label %for.cond1.preheader, label %for.end12
for.end12: ; preds = %for.end, %entry
ret i32 0
; CHECK-LABEL: @s173
; CHECK: load <4 x float>*
; CHECK: add i64 %index, 16000
; CHECK: ret i32 0
}
attributes #0 = { nounwind }