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

[NVPTX] declare no vector registers 

Summary:
Without this patch, LoopVectorizer in certain cases (see loop-vectorize.ll)
produces code with complex control flow which hurts later optimizations. Since
NVPTX doesn't have vector registers in LLVM's sense
(NVPTXTTI::getRegisterBitWidth(true) == 32), we for now declare no vector
registers to effectively disable loop vectorization.

Reviewers: jholewinski

Subscribers: jingyue, llvm-commits, jholewinski

Differential Revision: http://reviews.llvm.org/D11089

llvm-svn: 241884
This commit is contained in:
Jingyue Wu 2015-07-10 04:31:56 +00:00
parent c851ccc3bd
commit ad85c8c204
3 changed files with 47 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.cpp
View File

@ -117,3 +117,9 @@ unsigned NVPTXTTIImpl::getArithmeticInstrCost(
Opd1PropInfo, Opd2PropInfo); Opd1PropInfo, Opd2PropInfo);
} }
} }
unsigned NVPTXTTIImpl::getNumberOfRegisters(bool Vector) {
if (Vector)
return 0;
return BaseT::getNumberOfRegisters(Vector);
}

2
llvm/lib/Target/NVPTX/NVPTXTargetTransformInfo.h
View File

@ -58,6 +58,8 @@ public:
TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue, TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None, TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None); TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None);
unsigned getNumberOfRegisters(bool Vector);
}; };
} // end namespace llvm } // end namespace llvm

39
llvm/test/CodeGen/NVPTX/loop-vectorize.ll Normal file
View File

@ -0,0 +1,39 @@
; RUN: opt < %s -O3 -S | FileCheck %s
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
target triple = "nvptx64-nvidia-cuda"
define void @no_vectorization(i32 %n, i32 %a, i32 %b) {
; CHECK-LABEL: no_vectorization(
; CHECK-NOT: <4 x i32>
; CHECK-NOT: <4 x i1>
entry:
%cmp.5 = icmp sgt i32 %n, 0
br i1 %cmp.5, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
br label %for.body
for.cond.cleanup.loopexit: ; preds = %for.body
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%i.06 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
%add = add nsw i32 %i.06, %a
%mul = mul nsw i32 %add, %b
%cmp1 = icmp sgt i32 %mul, -1
tail call void @llvm.assume(i1 %cmp1)
%inc = add nuw nsw i32 %i.06, 1
%exitcond = icmp eq i32 %inc, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
}
declare void @llvm.assume(i1) #0
attributes #0 = { nounwind }
!nvvm.annotations = !{!0}
!0 = !{void (i32, i32, i32)* @no_vectorization, !"kernel", i32 1}